Publications by authors named "Gari D Clifford"

141 Publications

Brain-Based Biotypes of Psychiatric Vulnerability in the Acute Aftermath of Trauma.

Am J Psychiatry 2021 Oct 14:appiajp202120101526. Epub 2021 Oct 14.

Department of Psychiatry and Behavioral Sciences, Emory University, Atlanta (Stevens, van Rooij, Ely, Roeckner, Vincent); Division of Depression and Anxiety, McLean Hospital, Belmont, Mass. (Harnett, Lebois, Ressler); Department of Psychiatry, Harvard Medical School, Boston (Harnett, Lebois, Pizzagalli, Ressler); Departments of Emergency Medicine and Health Services, Policy, and Practice, Alpert Medical School of Brown University, Rhode Island Hospital, and the Miriam Hospital, Providence, R.I. (Beaudoin); Department of Anesthesiology, Institute of Trauma Recovery, University of North Carolina, Chapel Hill (An, Linnstaedt, McLean); Department of Biostatistics, Gillings School of Global Public Health, University of North Carolina, Chapel Hill (Zeng); Departments of Psychiatry and Neurology, University of California, San Francisco (Neylan); Department of Biomedical Informatics, Emory University School of Medicine, Atlanta (Clifford); Institute for Technology in Psychiatry (Germine) and Department of Psychiatry (Rauch), McLean Hospital, Belmont, Mass.; Department of Emergency Medicine, Henry Ford Health System, Detroit (Lewandowski); Department of Emergency Medicine, Vanderbilt University Medical Center, Nashville, Tenn. (Storrow); Department of Emergency Medicine, University of Florida College of Medicine, Jacksonville (Hendry, Sheikh); Department of Emergency Medicine, Indiana University School of Medicine, Indianapolis (Musey); Department of Emergency Medicine, University of Massachusetts Medical School, Worcester (Haran); Department of Emergency Medicine, Cooper Medical School of Rowan University, Camden, N.J. (Jones); Department of Emergency Medicine, College of Medicine and College of Nursing, University of Cincinnati, Cincinnati (Punches); Department of Emergency Medicine and Center for Addiction Research, University of Cincinnati College of Medicine, Cincinnati (Lyons); Departments of Emergency Medicine and Surgery, Division of Acute Care Surgery, University of Alabama School of Medicine, Birmingham (Kurz); Center for Injury Science, University of Alabama, Birmingham (Kurz); Department of Emergency Medicine, Boston Medical Center, Boston (McGrath); Departments of Surgery (Pascual) and Neurosurgery (Pascual), Perelman School of Medicine, University of Pennsylvania, Philadelphia; Department of Emergency Medicine, Einstein Health Care Network, Philadelphia (Datner); Department of Emergency Medicine, Jefferson University Hospitals, Philadelphia (Chang); Department of Emergency Medicine, Wayne State University, Detroit (Pearson); Department of Emergency Medicine, Massachusetts General Hospital, Boston (Peak); Department of Emergency Medicine, Saint Joseph Mercy Hospital, Ann Arbor, Mich. (Domeier); Department of Emergency Medicine, Wayne State University School of Medicine, Detroit (O'Neil); Department of Emergency Medicine, University of Massachusetts Medical School-Baystate, Springfield (Rathley); Department of Emergency Medicine, Beth Israel Deaconess Medical Center, Boston (Sanchez); Department of Emergency Medicine, Harvard Medical School, Boston (Sanchez); Department of Psychiatry, Yale School of Medicine, and U.S. Department of Veterans Affairs National Center for Posttraumatic Stress Disorder, Veterans Affairs Connecticut Healthcare System, New Haven, Conn. (Pietrzak); Department of Psychology, Yale University, New Haven, Conn. (Joorman); Department of Psychological and Brain Sciences, Washington University, St. Louis (Barch); Department of Biosciences and Neuroscience and Institute for Behavioral Medicine Research, Ohio State University Wexner Medical Center, Columbus (Sheridan); Department of Psychiatry, University of Pittsburgh, Pittsburgh (Luna); Departments of Anesthesiology and Internal Medicine-Rheumatology, University of Michigan Medical School, Ann Arbor (Harte); the Kolling Institute of Medical Research, Northern Clinical School, University of Sydney, and Faculty of Medicine and Health, University of Sydney, Sydney, Australia (Elliott); Physical Therapy and Human Movement Sciences, Feinberg School of Medicine, Northwestern University, Chicago (Elliott); Department of Psychology, Temple University, Philadelphia (Murty); Department of Psychiatry and Behavioral Neurosciences, Wayne State University, Detroit (Jovanovich); Department of Psychological Sciences, University of Missouri, St. Louis (Bruce); Department of Emergency Medicine, Washington University School of Medicine, St. Louis (House); Department of Health Care Policy, Harvard Medical School, Boston (Kessler); Department of Epidemiology, Harvard T.H. Chan School of Public Health, Boston (Koenen); Department of Emergency Medicine, University of North Carolina, Chapel Hill (McLean).

Objective: Major negative life events, such as trauma exposure, can play a key role in igniting or exacerbating psychopathology. However, few disorders are diagnosed with respect to precipitating events, and the role of these events in the unfolding of new psychopathology is not well understood. The authors conducted a multisite transdiagnostic longitudinal study of trauma exposure and related mental health outcomes to identify neurobiological predictors of risk, resilience, and different symptom presentations.

Methods: A total of 146 participants (discovery cohort: N=69; internal replication cohort: N=77) were recruited from emergency departments within 72 hours of a trauma and followed for the next 6 months with a survey, MRI, and physiological assessments.

Results: Task-based functional MRI 2 weeks after a motor vehicle collision identified four clusters of individuals based on profiles of neural activity reflecting threat reactivity, reward reactivity, and inhibitory engagement. Three clusters were replicated in an independent sample with a variety of trauma types. The clusters showed different longitudinal patterns of posttrauma symptoms.

Conclusions: These findings provide a novel characterization of heterogeneous stress responses shortly after trauma exposure, identifying potential neuroimaging-based biotypes of trauma resilience and psychopathology.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1176/appi.ajp.2021.20101526DOI Listing
October 2021

Deep Learning Model to Predict Serious Infection Among Children With Central Venous Lines.

Front Pediatr 2021 15;9:726870. Epub 2021 Sep 15.

Department of Biomedical Informatics, Emory School of Medicine, Atlanta, GA, United States.

Predict the onset of presumed serious infection, defined as a positive blood culture drawn and new antibiotic course of at least 4 days (PSI), among pediatric patients with Central Venous Lines (CVLs). Retrospective cohort study. Single academic children's hospital. All hospital encounters from January 2013 to December 2018, excluding the ones without a CVL or with a length-of-stay shorter than 24 h. Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train a deep learning model to predict the occurrence of PSI during the next 48 h of hospitalization. The proposed model prediction was compared to prediction of PSI by a marker of illness severity (PELOD-2). The baseline prevalence of line infections was 0.34% over all segmented 48-h time windows. Events were identified among cases using onset time. All data from admission till the onset was used for cases and among controls we used all data from admission till discharge. The benchmarks were aggregated over all 48 h time windows [N=748,380 associated with 27,137 patient encounters]. The model achieved an area under the receiver operating characteristic curve of 0.993 (95% CI = [0.990, 0.996]), the enriched positive predictive value (PPV) was 23 times greater than the base prevalence. Conversely, prediction by PELOD-2 achieved a lower PPV of 1.5% [0.9%, 2.1%] which was 5 times the baseline prevalence. A deep learning model that employs common clinical features in the electronic health record can help predict the onset of CLABSI in hospitalized children with central venous line 48 hours prior to the time of specimen collection.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fped.2021.726870DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8480258PMC
September 2021

eARDS: A multi-center validation of an interpretable machine learning algorithm of early onset Acute Respiratory Distress Syndrome (ARDS) among critically ill adults with COVID-19.

PLoS One 2021 24;16(9):e0257056. Epub 2021 Sep 24.

Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, Georgia, United States of America.

We present an interpretable machine learning algorithm called 'eARDS' for predicting ARDS in an ICU population comprising COVID-19 patients, up to 12-hours before satisfying the Berlin clinical criteria. The analysis was conducted on data collected from the Intensive care units (ICU) at Emory Healthcare, Atlanta, GA and University of Tennessee Health Science Center, Memphis, TN and the Cerner® Health Facts Deidentified Database, a multi-site COVID-19 EMR database. The participants in the analysis consisted of adults over 18 years of age. Clinical data from 35,804 patients who developed ARDS and controls were used to generate predictive models that identify risk for ARDS onset up to 12-hours before satisfying the Berlin criteria. We identified salient features from the electronic medical record that predicted respiratory failure among this population. The machine learning algorithm which provided the best performance exhibited AUROC of 0.89 (95% CI = 0.88-0.90), sensitivity of 0.77 (95% CI = 0.75-0.78), specificity 0.85 (95% CI = 085-0.86). Validation performance across two separate health systems (comprising 899 COVID-19 patients) exhibited AUROC of 0.82 (0.81-0.83) and 0.89 (0.87, 0.90). Important features for prediction of ARDS included minimum oxygen saturation (SpO2), standard deviation of the systolic blood pressure (SBP), O2 flow, and maximum respiratory rate over an observational window of 16-hours. Analyzing the performance of the model across various cohorts indicates that the model performed best among a younger age group (18-40) (AUROC = 0.93 [0.92-0.94]), compared to an older age group (80+) (AUROC = 0.81 [0.81-0.82]). The model performance was comparable on both male and female groups, but performed significantly better on the severe ARDS group compared to the mild and moderate groups. The eARDS system demonstrated robust performance for predicting COVID19 patients who developed ARDS at least 12-hours before the Berlin clinical criteria, across two independent health systems.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://journals.plos.org/plosone/article?id=10.1371/journal.pone.0257056PLOS
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8462682PMC
October 2021

A prospective examination of sex differences in posttraumatic autonomic functioning.

Neurobiol Stress 2021 Nov 21;15:100384. Epub 2021 Aug 21.

Department of Psychology, Temple University, Philadelphia, PA, 19121, USA.

Background: Cross-sectional studies have found that individuals with posttraumatic stress disorder (PTSD) exhibit deficits in autonomic functioning. While PTSD rates are twice as high in women compared to men, sex differences in autonomic functioning are relatively unknown among trauma-exposed populations. The current study used a prospective design to examine sex differences in posttraumatic autonomic functioning.

Methods: 192 participants were recruited from emergency departments following trauma exposure ( age = 35.88, 68.2% female). Skin conductance was measured in the emergency department; fear conditioning was completed two weeks later and included measures of blood pressure (BP), heart rate (HR), and high frequency heart rate variability (HF-HRV). PTSD symptoms were assessed 8 weeks after trauma.

Results: 2-week systolic BP was significantly higher in men, while 2-week HR was significantly higher in women, and a sex by PTSD interaction suggested that women who developed PTSD demonstrated the highest HR levels. Two-week HF-HRV was significantly lower in women, and a sex by PTSD interaction suggested that women with PTSD demonstrated the lowest HF-HRV levels. Skin conductance response in the emergency department was associated with 2-week HR and HF-HRV only among women who developed PTSD.

Conclusions: Our results indicate that there are notable sex differences in autonomic functioning among trauma-exposed individuals. Differences in sympathetic biomarkers (BP and HR) may have implications for cardiovascular disease risk given that sympathetic arousal is a mechanism implicated in this risk among PTSD populations. Future research examining differential pathways between PTSD and cardiovascular risk among men versus women is warranted.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ynstr.2021.100384DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8397921PMC
November 2021

Development and Validation of a Model to Predict Posttraumatic Stress Disorder and Major Depression After a Motor Vehicle Collision.

JAMA Psychiatry 2021 Sep 1. Epub 2021 Sep 1.

Department of Emergency Medicine, University of Florida College of Medicine, Jacksonville.

Importance: A substantial proportion of the 40 million people in the US who present to emergency departments (EDs) each year after traumatic events develop posttraumatic stress disorder (PTSD) or major depressive episode (MDE). Accurately identifying patients at high risk in the ED would facilitate the targeting of preventive interventions.

Objectives: To develop and validate a prediction tool based on ED reports after a motor vehicle collision to predict PTSD or MDE 3 months later.

Design, Setting, And Participants: The Advancing Understanding of Recovery After Trauma (AURORA) study is a longitudinal study that examined adverse posttraumatic neuropsychiatric sequalae among patients who presented to 28 US urban EDs in the immediate aftermath of a traumatic experience. Enrollment began on September 25, 2017. The 1003 patients considered in this diagnostic/prognostic report completed 3-month assessments by January 31, 2020. Each patient received a baseline ED assessment along with follow-up self-report surveys 2 weeks, 8 weeks, and 3 months later. An ensemble machine learning method was used to predict 3-month PTSD or MDE from baseline information. Data analysis was performed from November 1, 2020, to May 31, 2021.

Main Outcomes And Measures: The PTSD Checklist for DSM-5 was used to assess PTSD and the Patient Reported Outcomes Measurement Information System Depression Short-Form 8b to assess MDE.

Results: A total of 1003 patients (median [interquartile range] age, 34.5 [24-43] years; 715 [weighted 67.9%] female; 100 [weighted 10.7%] Hispanic, 537 [weighted 52.7%] non-Hispanic Black, 324 [weighted 32.2%] non-Hispanic White, and 42 [weighted 4.4%] of non-Hispanic other race or ethnicity were included in this study. A total of 274 patients (weighted 26.6%) met criteria for 3-month PTSD or MDE. An ensemble machine learning model restricted to 30 predictors estimated in a training sample (patients from the Northeast or Midwest) had good prediction accuracy (mean [SE] area under the curve [AUC], 0.815 [0.031]) and calibration (mean [SE] integrated calibration index, 0.040 [0.002]; mean [SE] expected calibration error, 0.039 [0.002]) in an independent test sample (patients from the South). Patients in the top 30% of predicted risk accounted for 65% of all 3-month PTSD or MDE, with a mean (SE) positive predictive value of 58.2% (6.4%) among these patients at high risk. The model had good consistency across regions of the country in terms of both AUC (mean [SE], 0.789 [0.025] using the Northeast as the test sample and 0.809 [0.023] using the Midwest as the test sample) and calibration (mean [SE] integrated calibration index, 0.048 [0.003] using the Northeast as the test sample and 0.024 [0.001] using the Midwest as the test sample; mean [SE] expected calibration error, 0.034 [0.003] using the Northeast as the test sample and 0.025 [0.001] using the Midwest as the test sample). The most important predictors in terms of Shapley Additive Explanations values were symptoms of anxiety sensitivity and depressive disposition, psychological distress in the 30 days before motor vehicle collision, and peritraumatic psychosomatic symptoms.

Conclusions And Relevance: The results of this study suggest that a short set of questions feasible to administer in an ED can predict 3-month PTSD or MDE with good AUC, calibration, and geographic consistency. Patients at high risk can be identified in the ED for targeting if cost-effective preventive interventions are developed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1001/jamapsychiatry.2021.2427DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8411364PMC
September 2021

Why do strategies to strengthen primary health care succeed in some places and fail in others? Exploring local variation in the effectiveness of a community health worker managed digital health intervention in rural India.

BMJ Glob Health 2021 07;6(Suppl 5)

The George Institute for Global Health, Newtown, New South Wales, Australia.

Introduction: Digital health interventions (DHIs) have huge potential as support modalities to identify and manage cardiovascular disease (CVD) risk in resource-constrained settings, but studies assessing them show modest effects. This study aims to identify variation in outcomes and implementation of SMARTHealth India, a cluster randomised trial of an ASHA-managed digitally enabled primary healthcare (PHC) service strengthening strategy for CVD risk management, and to explain how and in what contexts the intervention was effective.

Methods: We analysed trial outcome and implementation data for 18 PHC centres and collected qualitative data via focus groups with ASHAs (n=14) and interviews with ASHAs, PHC facility doctors and fieldteam mangers (n=12) Drawing on principles of realist evaluation and an explanatory mixed-methods design we developed mechanism-based explanations for observed outcomes.

Results: There was substantial between-cluster variation in the primary outcome (overall: I=62.4%, p<=0.001). The observed heterogeneity in trial outcomes was not attributable to any single factor. Key mechanisms for intervention effectiveness were community trust and acceptability of doctors' and ASHAs' new roles, and risk awareness. Enabling local contexts were seen to evolve over time and in response to the intervention. These included obtaining legitimacy for ASHAs' new roles from trusted providers of curative care; ASHAs' connections to community and to qualified providers; their responsiveness to community needs; and the accessibility, quality and appropriateness of care provided by higher level medical providers, including those outside of the implementing (public) subsystem.

Conclusion: Local contextual factors were significant influences on the effectiveness of this DHI-enabled PHC service strategy intervention. Local adaptions need to be planned for, monitored and responded to over time. By identifying plausible explanations for variation in outcomes between clusters, we identify potential strategies to strengthen such interventions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1136/bmjgh-2021-005003DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8314716PMC
July 2021

Thalamic volume and fear extinction interact to predict acute posttraumatic stress severity.

J Psychiatr Res 2021 09 14;141:325-332. Epub 2021 Jul 14.

Department of Emergency Medicine, Saint Joseph Mercy Hospital, Ann Arbor, MI, USA.

Posttraumatic stress disorder (PTSD) is associated with lower gray matter volume (GMV) in brain regions critical for extinction of learned threat. However, relationships among volume, extinction learning, and PTSD symptom development remain unclear. We investigated subcortical brain volumes in regions supporting extinction learning and fear-potentiated startle (FPS) to understand brain-behavior interactions that may impact PTSD symptom development in recently traumatized individuals. Participants (N = 99) completed magnetic resonance imaging and threat conditioning two weeks following trauma exposure as part of a multisite observational study to understand the neuropsychiatric effects of trauma (AURORA Study). Participants completed self-assessments of PTSD (PTSD Checklist for DSM-5; PCL-5), dissociation, and depression symptoms two- and eight-weeks post-trauma. We completed multiple regressions to investigate relationships between FPS during late extinction, GMV, and PTSD symptom development. The interaction between thalamic GMV and FPS during late extinction at two weeks post-trauma predicted PCL-5 scores eight weeks (t (75) = 2.49, β = 0.28, p = 0.015) post-trauma. Higher FPS predicted higher PCL-5 scores in the setting of increased thalamic GMV. Meanwhile, lower FPS also predicted higher PCL-5 scores in the setting of decreased thalamic GMV. Thalamic GMV and FPS interactions also predicted posttraumatic dissociative and depressive symptoms. Amygdala and hippocampus GMV by FPS interactions were not associated with posttraumatic symptom development. Taken together, thalamic GMV and FPS during late extinction interact to contribute to adverse posttraumatic neuropsychiatric outcomes. Multimodal assessments soon after trauma have the potential to distinguish key phenotypes vulnerable to posttraumatic neuropsychiatric outcomes.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jpsychires.2021.07.023DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8513112PMC
September 2021

CNN-Based LCD Transcription of Blood Pressure From a Mobile Phone Camera.

Front Artif Intell 2021 21;4:543176. Epub 2021 May 21.

Department of Biomedical Informatics, Emory University, Atlanta, GA, United States.

Routine blood pressure (BP) measurement in pregnancy is commonly performed using automated oscillometric devices. Since no wireless oscillometric BP device has been validated in preeclamptic populations, a simple approach for capturing readings from such devices is needed, especially in low-resource settings where transmission of BP data from the field to central locations is an important mechanism for triage. To this end, a total of 8192 BP readings were captured from the Liquid Crystal Display (LCD) screen of a standard Omron M7 self-inflating BP cuff using a cellphone camera. A cohort of 49 lay midwives captured these data from 1697 pregnant women carrying singletons between 6 weeks and 40 weeks gestational age in rural Guatemala during routine screening. Images exhibited a wide variability in their appearance due to variations in orientation and parallax; environmental factors such as lighting, shadows; and image acquisition factors such as motion blur and problems with focus. Images were independently labeled for readability and quality by three annotators (BP range: 34-203 mm Hg) and disagreements were resolved. Methods to preprocess and automatically segment the LCD images into diastolic BP, systolic BP and heart rate using a contour-based technique were developed. A deep convolutional neural network was then trained to convert the LCD images into numerical values using a multi-digit recognition approach. On readable low- and high-quality images, this proposed approach achieved a 91% classification accuracy and mean absolute error of 3.19 mm Hg for systolic BP and 91% accuracy and mean absolute error of 0.94 mm Hg for diastolic BP. These error values are within the FDA guidelines for BP monitoring when poor quality images are excluded. The performance of the proposed approach was shown to be greatly superior to state-of-the-art open-source tools (Tesseract and the Google Vision API). The algorithm was developed such that it could be deployed on a phone and work without connectivity to a network.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/frai.2021.543176DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8177819PMC
May 2021

Boosting automated sleep staging performance in big datasets using population subgrouping.

Sleep 2021 07;44(7)

Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, USA.

Current approaches to automated sleep staging from the electroencephalogram (EEG) rely on constructing a large labeled training and test corpora by aggregating data from different individuals. However, many of the subjects in the training set may exhibit changes in the EEG that are very different from the subjects in the test set. Training an algorithm on such data without accounting for this diversity can cause underperformance. Moreover, test data may have unexpected sensor misplacement or different instrument noise and spectral responses. This work proposes a novel method to learn relevant individuals based on their similarities effectively. The proposed method embeds all training patients into a shared and robust feature space. Individuals who share strong statistical relationships and are similar based on their EEG signals are clustered in this feature space before being passed to a deep learning framework for classification. Using 994 patient EEGs from the 2018 Physionet Challenge (≈6,561 h of recording), we demonstrate that the clustering approach significantly boosts performance compared to state-of-the-art deep learning approaches. The proposed method improves, on average, a precision score from 0.72 to 0.81, a sensitivity score from 0.74 to 0.82, and a Cohen's Kappa coefficient from 0.64 to 0.75 under 10-fold cross-validation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/sleep/zsab027DOI Listing
July 2021

Transfer learning from ECG to PPG for improved sleep staging from wrist-worn wearables.

Physiol Meas 2021 Mar 24. Epub 2021 Mar 24.

Department of Biomedical Informatics, Emory University, Atlanta, Georgia, UNITED STATES.

Objective: To develop a sleep staging method from wrist-worn accelerometry and the photoplethysmogram (PPG) by leveraging transfer learning from a large electrocardiogram (ECG) database.

Approach: In previous work, we developed a deep convolutional neural network for sleep staging from ECG using the cross-spectrogram of ECG-derived respiration and instantaneous beat intervals, heart rate variability metrics, spectral characteristics, and signal quality measures derived from 5,793 subjects in Sleep Heart Health Study (SHHS). We updated the weights of this model by transfer learning using PPG data derived from the Empatica E4 wristwatch worn by 105 subjects in the `Emory Twin Study Follow-up' (ETSF) database, for whom overnight polysomnographic (PSG) scoring was available. The relative performance of PPG, and actigraphy (Act), plus combinations of these two signals, with and without transfer learning was assessed.

Main Results: The performance of our model with transfer learning showed higher accuracy (1-9 percentage points) and Cohen's Kappa (0.01-0.13) than those without transfer learning for every classification category. Statistically significant, though relatively small, incremental differences in accuracy occurred for every classification category as tested with the McNemar test. The out-of-sample classification performance using features from PPG and actigraphy for four-class classification was Accuracy (Acc)=68.62% and Kappa=0.44. For two-class classification, the performance was Acc=81.49% and Kappa=0.58.

Significance: We proposed a combined PPG and actigraphy-based sleep stage classification approach using transfer learning from a large ECG sleep database. Results demonstrate that the transfer learning approach improves estimates of sleep state. The use of automated beat detectors and quality metrics means human over-reading is not required, and the approach can be scaled for large cross-sectional or longitudinal studies using wrist-worn devices for sleep-staging.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/abf1b0DOI Listing
March 2021

A Proxy for Detecting IUGR Based on Gestational Age Estimation in a Guatemalan Rural Population.

Front Artif Intell 2020 7;3:56. Epub 2020 Aug 7.

Department of Biomedical Informatics, Emory University, Atlanta, GA, United States.

progress of fetal development is normally assessed through manual measurements taken from ultrasound images, requiring relatively expensive equipment and well-trained personnel. Such monitoring is therefore unavailable in low- and middle-income countries (LMICs), where most of the perinatal mortality and morbidity exists. The work presented here attempts to identify a proxy for IUGR, which is a significant contributor to perinatal death in LMICs, by determining gestational age (GA) from data derived from simple-to-use, low-cost one-dimensional Doppler ultrasound (1D-DUS) and blood pressure devices. A total of 114 paired 1D-DUS recordings and maternal blood pressure recordings were selected, based on previously described signal quality measures. The average length of 1D-DUS recording was 10.43 ± 1.41 min. The min/median/max systolic and diastolic maternal blood pressures were 79/102/121 and 50.5/63.5/78.5 mmHg, respectively. GA was estimated using features derived from the 1D-DUS and maternal blood pressure using a support vector regression (SVR) approach and GA based on the last menstrual period as a reference target. A total of 50 trials of 5-fold cross-validation were performed for feature selection. The final SVR model was retrained on the training data and then tested on a held-out set comprising 28 normal weight and 25 low birth weight (LBW) newborns. The mean absolute GA error with respect to the last menstrual period was found to be 0.72 and 1.01 months for the normal and LBW newborns, respectively. The mean error in the GA estimate was shown to be negatively correlated with the birth weight. Thus, if the estimated GA is lower than the (remembered) GA calculated from last menstruation, then this could be interpreted as a potential sign of IUGR associated with LBW, and referral and intervention may be necessary. The assessment system may, therefore, have an immediate impact if coupled with suitable intervention, such as nutritional supplementation. However, a prospective clinical trial is required to show the efficacy of such a metric in the detection of IUGR and the impact of the intervention.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/frai.2020.00056DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7861337PMC
August 2020

Predicting presumed serious infection among hospitalized children on central venous lines with machine learning.

Comput Biol Med 2021 05 20;132:104289. Epub 2021 Feb 20.

Department of Biomedical Informatics, Emory School of Medicine, Atlanta, GA, USA; Department of Biomedical Engineering, Georgia Institute of Technology and Emory School of Medicine, Atlanta, GA, USA.

Background: Presumed serious infection (PSI) is defined as a blood culture drawn and new antibiotic course of at least 4 days among pediatric patients with Central Venous Lines (CVLs). Early PSI prediction and use of medical interventions can prevent adverse outcomes and improve the quality of care.

Methods: Clinical features including demographics, laboratory results, vital signs, characteristics of the CVLs and medications used were extracted retrospectively from electronic medical records. Data were aggregated across all hospitals within a single pediatric health system and used to train machine learning models (XGBoost and ElasticNet) to predict the occurrence of PSI 8 h prior to clinical suspicion. Prediction for PSI was benchmarked against PRISM-III.

Results: Our model achieved an area under the receiver operating characteristic curve of 0.84 (95% CI = [0.82, 0.85]), sensitivity of 0.73 [0.69, 0.74], and positive predictive value (PPV) of 0.36 [0.34, 0.36]. The PRISM-III conversely achieved a lower sensitivity of 0.19 [0.16, 0.22] and PPV of 0.30 [0.26, 0.34] at a cut-off of ≥ 10. The features with the most impact on the PSI prediction were maximum diastolic blood pressure prior to PSI prediction (mean SHAP = 3.4), height (mean SHAP = 3.2), and maximum temperature prior to PSI prediction (mean SHAP = 2.6).

Conclusion: A machine learning model using common features in the electronic medical records can predict the onset of serious infections in children with central venous lines at least 8 h prior to when a clinical team drew a blood culture.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.compbiomed.2021.104289DOI Listing
May 2021

Classification and Prediction of Post-Trauma Outcomes Related to PTSD Using Circadian Rhythm Changes Measured via Wrist-Worn Research Watch in a Large Longitudinal Cohort.

IEEE J Biomed Health Inform 2021 08 6;25(8):2866-2876. Epub 2021 Aug 6.

Post-Traumatic Stress Disorder (PTSD) is a psychiatric condition resulting from threatening or horrifying events. We hypothesized that circadian rhythm changes, measured by a wrist-worn research watch are predictive of post-trauma outcomes.

Approach: 1618 post-trauma patients were enrolled after admission to emergency departments (ED). Three standardized questionnaires were administered at week eight to measure post-trauma outcomes related to PTSD, sleep disturbance, and pain interference with daily life. Pulse activity and movement data were captured from a research watch for eight weeks. Standard and novel movement and cardiovascular metrics that reflect circadian rhythms were derived using this data. These features were used to train different classifiers to predict the three outcomes derived from week-eight surveys. Clinical surveys administered at ED were also used as features in the baseline models.

Results: The highest cross-validated performance of research watch-based features was achieved for classifying participants with pain interference by a logistic regression model, with an area under the receiver operating characteristic curve (AUC) of 0.70. The ED survey-based model achieved an AUC of 0.77, and the fusion of research watch and ED survey metrics improved the AUC to 0.79.

Significance: This work represents the first attempt to predict and classify post-trauma symptoms from passive wearable data using machine learning approaches that leverage the circadian desynchrony in a potential PTSD population.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/JBHI.2021.3053909DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8395207PMC
August 2021

Prognostic neuroimaging biomarkers of trauma-related psychopathology: resting-state fMRI shortly after trauma predicts future PTSD and depression symptoms in the AURORA study.

Neuropsychopharmacology 2021 06 21;46(7):1263-1271. Epub 2021 Jan 21.

Department of Emergency Medicine, Boston Medical Center, Boston, MA, USA.

Neurobiological markers of future susceptibility to posttraumatic stress disorder (PTSD) may facilitate identification of vulnerable individuals in the early aftermath of trauma. Variability in resting-state networks (RSNs), patterns of intrinsic functional connectivity across the brain, has previously been linked to PTSD, and may thus be informative of PTSD susceptibility. The present data are part of an initial analysis from the AURORA study, a longitudinal, multisite study of adverse neuropsychiatric sequalae. Magnetic resonance imaging (MRI) data from 109 recently (i.e., ~2 weeks) traumatized individuals were collected and PTSD and depression symptoms were assessed at 3 months post trauma. We assessed commonly reported RSNs including the default mode network (DMN), central executive network (CEN), and salience network (SN). We also identified a proposed arousal network (AN) composed of a priori brain regions important for PTSD: the amygdala, hippocampus, mamillary bodies, midbrain, and pons. Primary analyses assessed whether variability in functional connectivity at the 2-week imaging timepoint predicted 3-month PTSD symptom severity. Left dorsolateral prefrontal cortex (DLPFC) to AN connectivity at 2 weeks post trauma was negatively related to 3-month PTSD symptoms. Further, right inferior temporal gyrus (ITG) to DMN connectivity was positively related to 3-month PTSD symptoms. Both DLPFC-AN and ITG-DMN connectivity also predicted depression symptoms at 3 months. Our results suggest that, following trauma exposure, acutely assessed variability in RSN connectivity was associated with PTSD symptom severity approximately two and a half months later. However, these patterns may reflect general susceptibility to posttraumatic dysfunction as the imaging patterns were not linked to specific disorder symptoms, at least in the subacute/early chronic phase. The present data suggest that assessment of RSNs in the early aftermath of trauma may be informative of susceptibility to posttraumatic dysfunction, with future work needed to understand neural markers of long-term (e.g., 12 months post trauma) dysfunction. Furthermore, these findings are consistent with neural models suggesting that decreased top-down cortico-limbic regulation and increased network-mediated fear generalization may contribute to ongoing dysfunction in the aftermath of trauma.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41386-020-00946-8DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8134491PMC
June 2021

Editorial on Remote Health Monitoring: from chronic diseases to pandemics.

Physiol Meas 2021 01 4;41(10):100401. Epub 2021 Jan 4.

Faculty of Biomedical Engineering, Technion-IIT, Israel.

View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/abbb6dDOI Listing
January 2021

Breathing rate and heart rate as confounding factors in measuring T wave alternans and morphological variability in ECG.

Physiol Meas 2021 02 6;42(1):015002. Epub 2021 Feb 6.

Department of Electrical & Computer Engineering, Georgia Institute of Technology, Atlanta, GA, United States of America.

Objective: High morphological variability magnitude (MVM) and microvolt T wave alternans (TWA) within an electrocardiogram (ECG) signifies increased electrical instability and risk of sudden cardiac death. However, the influence of breathing rate (BR), heart rate (HR), and signal-to-noise ratio (SNR) is unknown and may inflate measured values.

Approach: We synthesize ECGs with morphologies derived from the Physikalisch-Technische Bundesanstalt Database. We calculate MVM and TWA at varying BRs, HRs and SNRs. We compare the MVM and TWA of signal with versus without breathing at varying HRs and SNRs. We then quantify the percentage of MVM and TWA estimates affected by BR and HR in a healthy population and assess the effect of removing these affected estimates on a method for classifying individuals with and without post-traumatic stress disorder (PTSD).

Main Results: For signals with high SNR (>15 dB), MVM is significantly increased when BRs are > 9 respirations/minute (rpm) and HRs are < 100 beats/minute (bpm). Increased TWAs are detected for HR/BR pairs of 60/15, 60/30 and 120/30 bpm/rpm. For 18 healthy participants, 8.33% of TWA windows and 66.76% of MVM windows are affected by BR and HR. On average, the number of windows with TWA elevations > 47 μV decreases by 23% after excluding regions with significant BR and HR effect. Adding HR and BR to a morphological variability feature increases the classification performance by 6% for individuals with and without PTSD.

Significance: Physiological BR and HR significantly increase MVM and TWA , indicating that BR and HR should be considered separately as confounders. The code for this work has been released as part of an open-source toolbox.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/abd237DOI Listing
February 2021

Classification of 12-lead ECGs: the PhysioNet/Computing in Cardiology Challenge 2020.

Physiol Meas 2021 01 1;41(12):124003. Epub 2021 Jan 1.

Department of Biomedical Informatics, Emory University, Atlanta, GA, United States of America.

Objective: Vast 12-lead ECGs repositories provide opportunities to develop new machine learning approaches for creating accurate and automatic diagnostic systems for cardiac abnormalities. However, most 12-lead ECG classification studies are trained, tested, or developed in single, small, or relatively homogeneous datasets. In addition, most algorithms focus on identifying small numbers of cardiac arrhythmias that do not represent the complexity and difficulty of ECG interpretation. This work addresses these issues by providing a standard, multi-institutional database and a novel scoring metric through a public competition: the PhysioNet/Computing in Cardiology Challenge 2020.

Approach: A total of 66 361 12-lead ECG recordings were sourced from six hospital systems from four countries across three continents; 43 101 recordings were posted publicly with a focus on 27 diagnoses. For the first time in a public competition, we required teams to publish open-source code for both training and testing their algorithms, ensuring full scientific reproducibility.

Main Results: A total of 217 teams submitted 1395 algorithms during the Challenge, representing a diversity of approaches for identifying cardiac abnormalities from both academia and industry. As with previous Challenges, high-performing algorithms exhibited significant drops ([Formula: see text]10%) in performance on the hidden test data.

Significance: Data from diverse institutions allowed us to assess algorithmic generalizability. A novel evaluation metric considered different misclassification errors for different cardiac abnormalities, capturing the outcomes and risks of different diagnoses. Requiring both trained models and code for training models improved the generalizability of submissions, setting a new bar in reproducibility for public data science competitions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/abc960DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8015789PMC
January 2021

A review of fetal cardiac monitoring, with a focus on low- and middle-income countries.

Physiol Meas 2020 12 18;41(11):11TR01. Epub 2020 Dec 18.

Data Intelligence for Health Lab, Cumming School of Medicine, University of Calgary, Calgary, AB, Canada.

There is limited evidence regarding the utility of fetal monitoring during pregnancy, particularly during labor and delivery. Developed countries rely on consensus 'best practices' of obstetrics and gynecology professional societies to guide their protocols and policies. Protocols are often driven by the desire to be as safe as possible and avoid litigation, regardless of the cost of downstream treatment. In high-resource settings, there may be a justification for this approach. In low-resource settings, in particular, interventions can be costly and lead to adverse outcomes in subsequent pregnancies. Therefore, it is essential to consider the evidence and cost of different fetal monitoring approaches, particularly in the context of treatment and care in low-to-middle income countries. This article reviews the standard methods used for fetal monitoring, with particular emphasis on fetal cardiac assessment, which is a reliable indicator of fetal well-being. An overview of fetal monitoring practices in low-to-middle income counties, including perinatal care access challenges, is also presented. Finally, an overview of how mobile technology may help reduce barriers to perinatal care access in low-resource settings is provided.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/abc4c7DOI Listing
December 2020

Remote health diagnosis and monitoring in the time of COVID-19.

Physiol Meas 2020 11 10;41(10):10TR01. Epub 2020 Nov 10.

Faculty of Biomedical Engineering, Technion-IIT, Haifa, Israel.

Coronavirus disease (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is rapidly spreading across the globe. The clinical spectrum of SARS-CoV-2 pneumonia requires early detection and monitoring, within a clinical environment for critical cases and remotely for mild cases, with a large spectrum of symptoms. The fear of contamination in clinical environments has led to a dramatic reduction in on-site referrals for routine care. There has also been a perceived need to continuously monitor non-severe COVID-19 patients, either from their quarantine site at home, or dedicated quarantine locations (e.g. hotels). In particular, facilitating contact tracing with proximity and location tracing apps was adopted in many countries very rapidly. Thus, the pandemic has driven incentives to innovate and enhance or create new routes for providing healthcare services at distance. In particular, this has created a dramatic impetus to find innovative ways to remotely and effectively monitor patient health status. In this paper, we present a review of remote health monitoring initiatives taken in 20 states during the time of the pandemic. We emphasize in the discussion particular aspects that are common ground for the reviewed states, in particular the future impact of the pandemic on remote health monitoring and consideration on data privacy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/abba0aDOI Listing
November 2020

An open-source automated algorithm for removal of noisy beats for accurate impedance cardiogram analysis.

Physiol Meas 2020 08 11;41(7):075002. Epub 2020 Aug 11.

Department of Biomedical Informatics, Emory University, Atlanta, GA, United States of America. School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, United States of America.

Objective: The impedance cardiogram (ICG) is a non-invasive sensing modality for assessing the mechanical aspects of cardiac function, but is sensitive to artifacts from respiration, speaking, motion, and electrode displacement. Electrocardiogram (ECG)-synchronized ensemble averaging of ICG (conventional ensemble averaging method) partially mitigates these disturbances, as artifacts from intra-subject variability (ISVar) of ICG morphology and event latency remain. This paper describes an automated algorithm for removing noisy beats for improved artifact suppression in ensemble-averaged (EA) ICG beats.

Approach: Synchronized ECG and ICG signals from 144 male subjects at rest in different psychological conditions were recorded. A 'three-stage EA ICG beat' was formed by passing 60-seconds non-overlapping ECG-synchronized ICG signals through three filtering stages. The amplitude filtering stage removed spikes/noisy beats with amplitudes outside of normal physiological ranges. Cross-correlation was applied to remove noisy beats in coarse and fine filtering stages. The accuracy of the algorithm-detected artifacts was measured with expert-identified artifacts. Agreement between the expert and the algorithm was assessed using intraclass correlation coefficients (ICC) and Bland-Altman plots. The ISVar of the cardiac parameters was evaluated to quantify improvement in these estimates provided by the proposed method.

Main Results: The proposed algorithm yielded an accuracy of 96.3% and high inter-rater reliability (ICC > 0.997). Bland-Altman plots showed consistently accurate results across values. The ISVar of the cardiac parameters derived using the proposed method was significantly lower than those derived via conventional ensemble averaging method (p < 0.0001). Enhancement in resolution of fiducial points and smoothing of higher-order time derivatives of the EA ICG beats were observed.

Significance: The proposed algorithm provides a robust framework for removal of noisy beats and accurate estimation of ICG-based parameters. Importantly, the methodology reduced the ISVar of cardiac parameters. An open-source toolbox has been provided to enable other researchers to readily reproduce and improve upon this work.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/ab9b71DOI Listing
August 2020

Classifying Major Depressive Disorder and Response to Deep Brain Stimulation Over Time by Analyzing Facial Expressions.

IEEE Trans Biomed Eng 2021 02 21;68(2):664-672. Epub 2021 Jan 21.

Objective: Major depressive disorder (MDD) is a common psychiatric disorder that leads to persistent changes in mood and interest among other signs and symptoms. We hypothesized that convolutional neural network (CNN) based automated facial expression recognition, pre-trained on an enormous auxiliary public dataset, could provide improve generalizable approach to MDD automatic assessment from videos, and classify remission or response to treatment.

Methods: We evaluated a novel deep neural network framework on 365 video interviews (88 hours) from a cohort of 12 depressed patients before and after deep brain stimulation (DBS) treatment. Seven basic emotions were extracted with a Regional CNN detector and an Imagenet pre-trained CNN, both of which were trained on large-scale public datasets (comprising over a million images). Facial action units were also extracted with the Openface toolbox. Statistics of the temporal evolution of these image features over each recording were extracted and used to classify MDD remission and response to DBS treatment.

Results: An Area Under the Curve of 0.72 was achieved using leave-one-subject-out cross-validation for remission classification and 0.75 for response to treatment.

Conclusion: This work demonstrates the potential for the classification of MDD remission and response to DBS treatment from passively acquired video captured during unstructured, unscripted psychiatric interviews.

Significance: This novel MDD evaluation could be used to augment current psychiatric evaluations and allow automatic, low-cost, frequent use when an expert isn't readily available or the patient is unwilling or unable to engage. Potentially, the framework may also be applied to other psychiatric disorders.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TBME.2020.3010472DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7891869PMC
February 2021

Temporal-Framing Adaptive Network for Heart Sound Segmentation Without Prior Knowledge of State Duration.

IEEE Trans Biomed Eng 2021 02 20;68(2):650-663. Epub 2021 Jan 20.

Objective: This paper presents a novel heart sound segmentation algorithm based on Temporal-Framing Adaptive Network (TFAN), including state transition loss and dynamic inference.

Methods: In contrast to previous state-of-the-art approaches, TFAN does not require any prior knowledge of the state duration of heart sounds and is therefore likely to generalize to non sinus rhythm. TFAN was trained on 50 recordings randomly chosen from Training set A of the 2016 PhysioNet/Computer in Cardiology Challenge and tested on the other 12 independent databases (2,099 recordings and 52,180 beats). And further testing of performance was conducted on databases with three levels of increasing difficulty (LEVEL-I, -II and -III).

Results: TFAN achieved a superior F score for all 12 databases except for 'Test-B,' with an average of 96.72%, compared to 94.56% for logistic regression hidden semi-Markov model (LR-HSMM) and 94.18% for bidirectional gated recurrent neural network (BiGRNN). Moreover, TFAN achieved an overall F score of 99.21%, 94.17%, 91.31% on LEVEL-I, -II and -III databases respectively, compared to 98.37%, 87.56%, 78.46% for LR-HSMM and 99.01%, 92.63%, 88.45% for BiGRNN.

Conclusion: TFAN therefore provides a substantial improvement on heart sound segmentation while using less parameters compared to BiGRNN.

Significance: The proposed method is highly flexible and likely to apply to other non-stationary time series. Further work is required to understand to what extent this approach will provide improved diagnostic performance, although it is logical to assume superior segmentation will lead to improved diagnostics.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TBME.2020.3010241DOI Listing
February 2021

Unsupervised hidden semi-Markov model for automatic beat onset detection in 1D Doppler ultrasound.

Physiol Meas 2020 09 18;41(8):085007. Epub 2020 Sep 18.

Department of Biomedical Informatics, Emory University, Atlanta, GA, United States of America.

Objective: One dimensional (1D) Doppler ultrasound (DUS) is commonly used for fetal health assessment, during both regular prenatal visits and labor. It is used in preference to ECG and other modalities because of its simplicity and cost. To date, all analysis of such data has been confined to a smoothed, windowed heart rate estimation derived from the 1D DUS signal, reducing the potential of short-term variability information. A first step in improving the assessment of short-term variability of the fetal heart rate (FHR) is through implementing an accurate beat detector for 1D DUS signals.

Approach: This work presents an unsupervised probabilistic segmentation method enabled by a hidden semi-Markov model (HSMM). The proposed method employs envelope and spectral features for an online segmentation of fetal 1D DUS signal. The beat onsets and fetal cardiac beat-to-beat intervals are then estimated from the segmentations. For this work, two data sets were used, including 1D DUS recordings from five fetuses recorded in Germany, comprising 6521 beats and 45.06 minutes of data (dataset 1). Simultaneous fetal ECG (fECG) was used as the reference for beat timing. Dataset 2, comprising 4044 beats captured from 17 subjects in the UK was hand scored for beat location and was used as an independent held-out test set. Leave-one-out subject cross-validation was used for parameter tuning on dataset 1. No retraining was performed for dataset 2. To assess the performance of the beat onset detection, the root mean square error (RMSE), F1 score, sensitivity, positive predictivity (PPV) and the error in several standard common heart rate variability metrics were used. These metrics were evaluated on three fiducial points: (1) beat onset, (2) beat offset, and (3) middle of beat interval.

Main Results: In dataset 1, the proposed method provided an RMSE of 20 ms, F1 score of 97.5 %, a Se of 97.6%, and a PPV of 97.3%. In dataset 2, the proposed method achieved an RMSE of 26 ms, an F1 score of 98.5 %, a Se of 98.0 % and a PPV of 98.9 %. It was also determined that the best beat-to-beat interval was derived from the onset of each beat. For the dataset 2, significant correlations were found in all short term heart rate variability metrics tested, both in the time and frequency domain. Only the proportion of successive normal-to-normal interval differences greater than 20 ms (pNN20) exhibited a significant absolute difference.

Significance: This work presents the first-ever description of an algorithm to identify cardiac beats with 1D DUS, closely matching the fetal ECG-derived beats, to enable short-term heart rate variability analysis. The novel algorithm proposed requires no human labeling of data, and could have applicability beyond 1D DUS to other similar highly variable time series.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/aba006DOI Listing
September 2020

Using pulse oximetry waveforms to detect coarctation of the aorta.

Biomed Eng Online 2020 May 14;19(1):31. Epub 2020 May 14.

Division of Cardiology, Pediatric Cardiology, Children's Healthcare of Atlanta, 1405 Clifton Rd, Atlanta, GA, 30322, USA.

Background: Coarctation of the aorta is a common form of critical congenital heart disease that remains challenging to diagnose prior to clinical deterioration. Despite current screening methods, infants with coarctation may present with life-threatening cardiogenic shock requiring urgent hospitalization and intervention. We sought to improve critical congenital heart disease screening by using a novel pulse oximetry waveform analysis, specifically focused on detection of coarctation of the aorta.

Methods And Results: Over a 2-year period, we obtained pulse oximetry waveform data on 18 neonates with coarctation of the aorta and 18 age-matched controls hospitalized in the cardiac intensive care unit at Children's Healthcare of Atlanta. Patients with coarctation were receiving prostaglandin E1 and had a patent ductus arteriosus. By analyzing discrete features in the waveforms, we identified statistically significant differences in the maximum rate of fall between patients with and without coarctation. This was accentuated when comparing the difference between the upper and lower extremities, with the lower extremities having a shallow slope angle when a coarctation was present (p-value 0.001). Postoperatively, there were still differences in the maximum rate of fall between the repaired coarctation patients and controls; however, these differences normalized when compared with the same individual's upper vs. lower extremities. Coarctation patients compared to themselves (preoperatively and postoperatively), demonstrated waveform differences between upper and lower extremities that were significantly reduced after successful surgery (p-value 0.028). This screening algorithm had an accuracy of detection of 72% with 0.61 sensitivity and 0.94 specificity.

Conclusions: We were able to identify specific features in pulse oximetry waveforms that were able to accurately identify patients with coarctation and further demonstrated that these changes normalized after surgical repair. Pulse oximetry screening for congenital heart disease in neonates may thus be improved by including waveform analysis, aiming to identify coarctation of the aorta prior to critical illness. Further large-scale testing is required to validate this screening model among patients in a newborn nursery setting who are low risk for having coarctation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s12938-020-00775-2DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7227302PMC
May 2020

Deep Convolutional Neural Networks and Transfer Learning for Measuring Cognitive Impairment Using Eye-Tracking in a Distributed Tablet-Based Environment.

IEEE Trans Biomed Eng 2021 01 21;68(1):11-18. Epub 2020 Dec 21.

Objective: Alzheimer's disease (AD) is a neurodegenerative disorder that initially presents with memory loss in the presence of underlying neurofibrillary tangle and amyloid plaque pathology. Mild cognitive impairment is the initial symptomatic stage, which is an early window for detecting cognitive impairment prior to progressive decline and dementia. We recently developed the Visuospatial Memory Eye-Tracking Test (VisMET), a passive task capable of classifying cognitive impairment in AD in under five minutes. Here we describe the development of a mobile version of VisMET to enable efficient and widespread administration of the task.

Methods: We delivered VisMET on iPad devices and used a transfer learning approach to train a deep neural network to track eye gaze. Eye movements were used to extract memory features to assess cognitive status in a population of 250 individuals.

Results: Mild to severe cognitive impairment was identifiable with a test accuracy of 70%. By enforcing a minimal eye tracking calibration error of 2 cm, we achieved an accuracy of 76% which is equivalent to the accuracy obtained using commercial hardware for eye-tracking.

Conclusion: This work demonstrates a mobile version of VisMET capable of estimating the presence of cognitive impairment.

Significance: Given the ubiquity of tablet devices, our approach has the potential to scale globally.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/TBME.2020.2990734DOI Listing
January 2021

Estimating birth weight from observed postnatal weights in a Guatemalan highland community.

Physiol Meas 2020 03 6;41(2):025008. Epub 2020 Mar 6.

Department of Biomedical Informatics, Emory University, Atlanta, GA, United States of America.

Objective: Low birth weight is one of the leading contributors to global perinatal deaths. Detecting this problem close to birth enables the initiation of early intervention, thus reducing the long-term impact on the fetus. However, in low-and middle-income countries, sometimes newborns are weighted days or months after birth, thus challenging the identification of low birth weight. This study aims to estimate birth weight from observed postnatal weights recorded in a Guatemalan highland community.

Approach: With 918 newborns recorded in postpartum visits at a Guatemalan highland community, we fitted traditional infant weight models (Count's and Reeds models). The model that fitted the observed data best was selected based on typical newborn weight patterns reported in the medical literature and previous longitudinal studies. Then, estimated birth weights were determined using the weight gain percentage derived from the fitted weight curve.

Main Results: The best model for both genders was the Reeds2 model, with a mean square error of 0.30 kg and 0.23 kg for male and female newborns, respectively. The fitted weight curves exhibited similar behavior to those reported in the literature, with a maximum weight loss around three to five days after birth, and birth weight recovery, on average, by day ten. Moreover, the estimated birth weight was consistent with the 2015 Guatemalan National Survey, no having a statistically significant difference between the estimated birth weight and the reported survey birth weights (two-sided Wilcoxon rank-sum test; [Formula: see text]).

Significance: By estimating birth weight at an opportune time, several days after birth, it may be possible to identify low birth weight more accurately, thus providing timely treatment when is required.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1088/1361-6579/ab7350DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7126327PMC
March 2020

An unbiased, efficient sleep-wake detection algorithm for a population with sleep disorders: change point decoder.

Sleep 2020 08;43(8)

Department of Biomedical Informatics, Emory University School of Medicine, Atlanta, GA, USA.

Study Objectives: The usage of wrist-worn wearables to detect sleep-wake states remains a formidable challenge, particularly among individuals with disordered sleep. We developed a novel and unbiased data-driven method for the detection of sleep-wake and compared its performance with the well-established Oakley algorithm (OA) relative to polysomnography (PSG) in elderly men with disordered sleep.

Methods: Overnight in-lab PSG from 102 participants was compared with accelerometry and photoplethysmography simultaneously collected with a wearable device (Empatica E4). A binary segmentation algorithm was used to detect change points in these signals. A model that estimates sleep or wake states given the changes in these signals was established (change point decoder, CPD). The CPD's performance was compared with the performance of the OA in relation to PSG.

Results: On the testing set, OA provided sleep accuracy of 0.85, wake accuracy of 0.54, AUC of 0.67, and Kappa of 0.39. Comparable values for CPD were 0.70, 0.74, 0.78, and 0.40. The CPD method had sleep onset latency error of -22.9 min, sleep efficiency error of 2.09%, and underestimated the number of sleep-wake transitions with an error of 64.4. The OA method's performance was 28.6 min, -0.03%, and -17.2, respectively.

Conclusions: The CPD aggregates information from both cardiac and motion signals for state determination as well as the cross-dimensional influences from these domains. Therefore, CPD classification achieved balanced performance and higher AUC, despite underestimating sleep-wake transitions. The CPD could be used as an alternate framework to investigate sleep-wake dynamics within the conventional time frame of 30-s epochs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/sleep/zsaa011DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7420526PMC
August 2020

Early Prediction of Sepsis From Clinical Data: The PhysioNet/Computing in Cardiology Challenge 2019.

Crit Care Med 2020 02;48(2):210-217

Department of Biomedical Informatics, Emory University, Atlanta, GA.

Objectives: Sepsis is a major public health concern with significant morbidity, mortality, and healthcare expenses. Early detection and antibiotic treatment of sepsis improve outcomes. However, although professional critical care societies have proposed new clinical criteria that aid sepsis recognition, the fundamental need for early detection and treatment remains unmet. In response, researchers have proposed algorithms for early sepsis detection, but directly comparing such methods has not been possible because of different patient cohorts, clinical variables and sepsis criteria, prediction tasks, evaluation metrics, and other differences. To address these issues, the PhysioNet/Computing in Cardiology Challenge 2019 facilitated the development of automated, open-source algorithms for the early detection of sepsis from clinical data.

Design: Participants submitted containerized algorithms to a cloud-based testing environment, where we graded entries for their binary classification performance using a novel clinical utility-based evaluation metric. We designed this scoring function specifically for the Challenge to reward algorithms for early predictions and penalize them for late or missed predictions and for false alarms.

Setting: ICUs in three separate hospital systems. We shared data from two systems publicly and sequestered data from all three systems for scoring.

Patients: We sourced over 60,000 ICU patients with up to 40 clinical variables for each hour of a patient's ICU stay. We applied Sepsis-3 clinical criteria for sepsis onset.

Interventions: None.

Measurements And Main Results: A total of 104 groups from academia and industry participated, contributing 853 submissions. Furthermore, 90 abstracts based on Challenge entries were accepted for presentation at Computing in Cardiology.

Conclusions: Diverse computational approaches predict the onset of sepsis several hours before clinical recognition, but generalizability to different hospital systems remains a challenge.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/CCM.0000000000004145DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6964870PMC
February 2020

The AURORA Study: a longitudinal, multimodal library of brain biology and function after traumatic stress exposure.

Mol Psychiatry 2020 02 19;25(2):283-296. Epub 2019 Nov 19.

Department of Surgery, Perelman School of Medicine at the University of Pennsylvania, Philadelphia, PA, USA.

Adverse posttraumatic neuropsychiatric sequelae (APNS) are common among civilian trauma survivors and military veterans. These APNS, as traditionally classified, include posttraumatic stress, postconcussion syndrome, depression, and regional or widespread pain. Traditional classifications have come to hamper scientific progress because they artificially fragment APNS into siloed, syndromic diagnoses unmoored to discrete components of brain functioning and studied in isolation. These limitations in classification and ontology slow the discovery of pathophysiologic mechanisms, biobehavioral markers, risk prediction tools, and preventive/treatment interventions. Progress in overcoming these limitations has been challenging because such progress would require studies that both evaluate a broad spectrum of posttraumatic sequelae (to overcome fragmentation) and also perform in-depth biobehavioral evaluation (to index sequelae to domains of brain function). This article summarizes the methods of the Advancing Understanding of RecOvery afteR traumA (AURORA) Study. AURORA conducts a large-scale (n = 5000 target sample) in-depth assessment of APNS development using a state-of-the-art battery of self-report, neurocognitive, physiologic, digital phenotyping, psychophysical, neuroimaging, and genomic assessments, beginning in the early aftermath of trauma and continuing for 1 year. The goals of AURORA are to achieve improved phenotypes, prediction tools, and understanding of molecular mechanisms to inform the future development and testing of preventive and treatment interventions.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41380-019-0581-3DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6981025PMC
February 2020
-->