Publications by authors named "Paul Dexter"

58 Publications

An Automated Line-of-Therapy Algorithm for Adults With Metastatic Non-Small Cell Lung Cancer: Validation Study Using Blinded Manual Chart Review.

JMIR Med Inform 2021 Oct 12;9(10):e29017. Epub 2021 Oct 12.

Regenstrief Institute, Inc, Indianapolis, IN, United States.

Background: Extraction of line-of-therapy (LOT) information from electronic health record and claims data is essential for determining longitudinal changes in systemic anticancer therapy in real-world clinical settings.

Objective: The aim of this retrospective cohort analysis is to validate and refine our previously described open-source LOT algorithm by comparing the output of the algorithm with results obtained through blinded manual chart review.

Methods: We used structured electronic health record data and clinical documents to identify 500 adult patients treated for metastatic non-small cell lung cancer with systemic anticancer therapy from 2011 to mid-2018; we assigned patients to training (n=350) and test (n=150) cohorts, randomly divided proportional to the overall ratio of simple:complex cases (n=254:246). Simple cases were patients who received one LOT and no maintenance therapy; complex cases were patients who received more than one LOT and/or maintenance therapy. Algorithmic changes were performed using the training cohort data, after which the refined algorithm was evaluated against the test cohort.

Results: For simple cases, 16 instances of discordance between the LOT algorithm and chart review prerefinement were reduced to 8 instances postrefinement; in the test cohort, there was no discordance between algorithm and chart review. For complex cases, algorithm refinement reduced the discordance from 68 to 62 instances, with 37 instances in the test cohort. The percentage agreement between LOT algorithm output and chart review for patients who received one LOT was 89% prerefinement, 93% postrefinement, and 93% for the test cohort, whereas the likelihood of precise matching between algorithm output and chart review decreased with an increasing number of unique regimens. Several areas of discordance that arose from differing definitions of LOTs and maintenance therapy could not be objectively resolved because of a lack of precise definitions in the medical literature.

Conclusions: Our findings identify common sources of discordance between the LOT algorithm and clinician documentation, providing the possibility of targeted algorithm refinement.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2196/29017DOI Listing
October 2021

Applying interpretable deep learning models to identify chronic cough patients using EHR data.

Comput Methods Programs Biomed 2021 Oct 4;210:106395. Epub 2021 Sep 4.

Indiana University School of Medicine, 340W 10th St #6200, Indianapolis, IN 46202, United States; Regenstrief Institute, 1101W 10th Street, Indianapolis, IN, 46202, United States. Electronic address:

Background And Objective: Chronic cough (CC) affects approximately 10% of adults. Many disease states are associated with chronic cough, such as asthma, upper airway cough syndrome, bronchitis, and gastroesophageal reflux disease. The lack of an ICD code specific for chronic cough makes it challenging to identify such patients from electronic health records (EHRs). For clinical and research purposes, computational methods using EHR data are urgently needed to identify chronic cough cases. This research aims to investigate the data representations and deep learning algorithms for chronic cough prediction.

Methods: Utilizing real-world EHR data from a large academic healthcare system from October 2005 to September 2015, we investigated Natural Language Representation of the EHR data and systematically evaluated deep learning and traditional machine learning models to predict chronic cough patients. We built these machine learning models using structured data (medication and diagnosis) and unstructured data (clinical notes).

Results: The sensitivity and specificity of a transformer-based deep learning algorithm, specifically BERT with attention model, was 0.856 and 0.866, respectively, using structured data (medication and diagnosis). Sensitivity and specificity improved to 0.952 and 0.930 when we combined structured data with symptoms extracted from clinical notes. We further found that the attention mechanism of deep learning models can be used to extract important features that drive the prediction decisions. Compared with our previously published rule-based algorithm, the deep learning algorithm can identify more chronic cough patients with structured data.

Conclusions: By applying deep learning models, chronic cough patients can be reliably identified for prospective or retrospective research through medication and diagnosis data, widely available in EHR and electronic claims data, thus improving the generalizability of the patient identification algorithm. Deep learning models can identify chronic cough patients with even higher sensitivity and specificity when structured and unstructured EHR data are utilized. We anticipate language-based data representation and deep learning models developed in this research could also be productively used for other disease prediction and case identification.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.cmpb.2021.106395DOI Listing
October 2021

Strategies to Integrate Genomic Medicine into Clinical Care: Evidence from the IGNITE Network.

J Pers Med 2021 Jul 8;11(7). Epub 2021 Jul 8.

Center for Applied Genomics & Precision Medicine, Duke University School of Medicine, Durham, NC 27708, USA.

The complexity of genomic medicine can be streamlined by implementing some form of clinical decision support (CDS) to guide clinicians in how to use and interpret personalized data; however, it is not yet clear which strategies are best suited for this purpose. In this study, we used implementation science to identify common strategies for applying provider-based CDS interventions across six genomic medicine clinical research projects funded by an NIH consortium. Each project's strategies were elicited via a structured survey derived from a typology of implementation strategies, the Expert Recommendations for Implementing Change (ERIC), and follow-up interviews guided by both implementation strategy reporting criteria and a planning framework, RE-AIM, to obtain more detail about implementation strategies and desired outcomes. We found that, on average, the three pharmacogenomics implementation projects used more strategies than the disease-focused projects. Overall, projects had four implementation strategies in common; however, operationalization of each differed in accordance with each study's implementation outcomes. These four common strategies may be important for precision medicine program implementation, and pharmacogenomics may require more integration into clinical care. Understanding how and why these strategies were successfully employed could be useful for others implementing genomic or precision medicine programs in different contexts.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/jpm11070647DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8306482PMC
July 2021

Multi-Institutional Implementation of Clinical Decision Support for and Genotyping in Antihypertensive Management.

J Pers Med 2021 May 27;11(6). Epub 2021 May 27.

Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY 10029, USA.

(1) Background: Clinical decision support (CDS) is a vitally important adjunct to the implementation of pharmacogenomic-guided prescribing in clinical practice. A novel CDS was sought for the , , and genes to guide optimal selection of antihypertensive medications among the African American population cared for at multiple participating institutions in a clinical trial. (2) Methods: The CDS committee, made up of clinical content and CDS experts, developed a framework and contributed to the creation of the CDS using the following guiding principles: 1. medical algorithm consensus; 2. actionability; 3. context-sensitive triggers; 4. workflow integration; 5. feasibility; 6. interpretability; 7. portability; and 8. discrete reporting of lab results. (3) Results: Utilizing the principle of discrete patient laboratory and vital information, a novel CDS for , , and was created for use in a multi-institutional trial based on a medical algorithm consensus. The alerts are actionable and easily interpretable, clearly displaying the purpose and recommendations with pertinent laboratory results, vitals and links to ordersets with suggested antihypertensive dosages. Alerts were either triggered immediately once a provider starts to order relevant antihypertensive agents or strategically placed in workflow-appropriate general CDS sections in the electronic health record (EHR). Detailed implementation instructions were shared across institutions to achieve maximum portability. (4) Conclusions: Using sound principles, the created genetic algorithms were applied across multiple institutions. The framework outlined in this study should apply to other disease-gene and pharmacogenomic projects employing CDS.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3390/jpm11060480DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8226809PMC
May 2021

Transforming primary medical research knowledge into clinical decision.

AMIA Annu Symp Proc 2020 25;2020:358-362. Epub 2021 Jan 25.

Regenstrief Institute, Inc., Indianapolis, IN.

While the utility of computerized clinical decision support (CCDS) for multiple select clinical domains has been clearly demonstrated, much less is known about the full breadth of domains to which CCDS approaches could be productively applied. To explore the applicability of CCDS to general medical knowledge, we sampled a total of 500 primary research articles from 4 high-impact medical journals. Employing rule-based templates, we created high-level CCDS rules for 72% (361/500) of primary medical research articles. We subsequently identified data sources needed to implement those rules. Ourfindings suggest that CCDS approaches, perhaps in the form of non-interruptive infobuttons, could be much more broadly applied. In addition, our analytic methods appear to provide a means of prioritizing and quantitating the relative utility of available data sources for purposes of CCDS.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8075430PMC
June 2021

Establishing the value of genomics in medicine: the IGNITE Pragmatic Trials Network.

Genet Med 2021 07 29;23(7):1185-1191. Epub 2021 Mar 29.

Division of Genomic Medicine, National Human Genome Research Institute, NIH, Bethesda, MD, USA.

Purpose: A critical gap in the adoption of genomic medicine into medical practice is the need for the rigorous evaluation of the utility of genomic medicine interventions.

Methods: The Implementing Genomics in Practice Pragmatic Trials Network (IGNITE PTN) was formed in 2018 to measure the clinical utility and cost-effectiveness of genomic medicine interventions, to assess approaches for real-world application of genomic medicine in diverse clinical settings, and to produce generalizable knowledge on clinical trials using genomic interventions. Five clinical sites and a coordinating center evaluated trial proposals and developed working groups to enable their implementation.

Results: Two pragmatic clinical trials (PCTs) have been initiated, one evaluating genetic risk APOL1 variants in African Americans in the management of their hypertension, and the other to evaluate the use of pharmacogenetic testing for medications to manage acute and chronic pain as well as depression.

Conclusion: IGNITE PTN is a network that carries out PCTs in genomic medicine; it is focused on diversity and inclusion of underrepresented minority trial participants; it uses electronic health records and clinical decision support to deliver the interventions. IGNITE PTN will develop the evidence to support (or oppose) the adoption of genomic medicine interventions by patients, providers, and payers.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41436-021-01118-9DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8263480PMC
July 2021

Identifying and Characterizing a Chronic Cough Cohort Through Electronic Health Records.

Chest 2021 06 17;159(6):2346-2355. Epub 2020 Dec 17.

Merck & Co., Inc., Kenilworth, NJ.

Background: Chronic cough (CC) of 8 weeks or more affects about 10% of adults and may lead to expensive treatments and reduced quality of life. Incomplete diagnostic coding complicates identifying CC in electronic health records (EHRs). Natural language processing (NLP) of EHR text could improve detection.

Research Question: Can NLP be used to identify cough in EHRs, and to characterize adults and encounters with CC?

Study Design And Methods: A Midwestern EHR system identified patients aged 18 to 85 years during 2005 to 2015. NLP was used to evaluate text notes, except prescriptions and instructions, for mentions of cough. Two physicians and a biostatistician reviewed 12 sets of 50 encounters each, with iterative refinements, until the positive predictive value for cough encounters exceeded 90%. NLP, International Classification of Diseases, 10th revision, or medication was used to identify cough. Three encounters spanning 56 to 120 days defined CC. Descriptive statistics summarized patients and encounters, including referrals.

Results: Optimizing NLP required identifying and eliminating cough denials, instructions, and historical references. Of 235,457 cough encounters, 23% had a relevant diagnostic code or medication. Applying chronicity to cough encounters identified 23,371 patients (61% women) with CC. NLP alone identified 74% of these patients; diagnoses or medications alone identified 15%. The positive predictive value of NLP in the reviewed sample was 97%. Referrals for cough occurred for 3.0% of patients; pulmonary medicine was most common initially (64% of referrals).

Limitations: Some patients with diagnosis codes for cough, encounters at intervals greater than 4 months, or multiple acute cough episodes may have been misclassified.

Interpretation: NLP successfully identified a large cohort with CC. Most patients were identified through NLP alone, rather than diagnoses or medications. NLP improved detection of patients nearly sevenfold, addressing the gap in ability to identify and characterize CC disease burden. Nearly all cases appeared to be managed in primary care. Identifying these patients is important for characterizing treatment and unmet needs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.chest.2020.12.011DOI Listing
June 2021

Enrollment of Diverse Populations in the INGENIOUS Pharmacogenetics Clinical Trial.

Front Genet 2020 25;11:571. Epub 2020 Jun 25.

Department of Medicine, Indiana University, Indianapolis, IN, United States.

Recruitment of diverse populations and subjects living in Medically Underserved Areas and Populations (MUA/P's) into clinical trials is a considerable challenge. Likewise, representation of African-Americans in pharmacogenetic trials is often inadequate, but critical for identifying genetic variation within and between populations. To identify enrollment patterns and variables that predict enrollment in a diverse underserved population, we analyzed data from the INGENIOUS (Indiana GENomics Implementation and Opportunity for the UnderServed), pharmacogenomics implementation clinical trial conducted at a community hospital for underserved subjects (Safety net hospital), and a statewide healthcare system (Academic hospital). We used a logistic regression model to identify patient variables that predicted successful enrollment after subjects were contacted and evaluated the reasons that clinical trial eligible subjects refused enrollment. In both healthcare systems, African-Americans were less likely to refuse the study than non-Hispanic Whites (Safety net, OR = 0.68, and < 0.002; Academic hospital, OR = 0.64, and < 0.001). At the Safety net hospital, other minorities were more likely to refuse the study than non-Hispanic Whites (OR = 1.58, < 0.04). The odds of refusing the study once contacted increased with patient age (Safety net hospital, OR = 1.02, < 0.001, Academic hospital, OR = 1.02, and < 0.001). At the Academic hospital, females were less likely to refuse the study than males (OR = 0.81, = 0.01) and those not living in MUA/P's were less likely to refuse the study than those living in MUA/P's (OR = 0.81, = 0.007). The most frequent barriers to enrollment included not being interested, being too busy, transportation, and illness. A lack of trust was reported less frequently. In conclusion, African-Americans can be readily recruited to pharmacogenetic clinical trials once contact has been successfully initiated. However, health care initiatives and increased recruitment efforts of subjects living in MUA/Ps are needed. Enrollment could be further enhanced by improving research awareness and knowledge of clinical trials, reducing time needed for participation, and compensating for travel.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3389/fgene.2020.00571DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7330082PMC
June 2020

Development of a Genomic Data Flow Framework: Results of a Survey Administered to NIH-NHGRI IGNITE and eMERGE Consortia Participants.

AMIA Annu Symp Proc 2019 4;2019:363-370. Epub 2020 Mar 4.

Vanderbilt University Medical Center, Nashville, TN.

Precision health's more individualized molecular approach will enrich our understanding of disease etiology and patient outcomes. Universal implementation of precision health will not be feasible, however, until there is much greater automation of processes related to genomic data transmission, transformation, and interpretation. In this paper, we describe a framework for genomic data flow developed by the Clinical Informatics Work Group of the NIH National Human Genome Research Institute (NHGRI) IGNITE Network consortium. We subsequently report the results of a genomic data flow survey administered to sites funded by NIH-NHGRI for large scale genomic medicine implementations. Finally, we discuss insights and challenges identified through these survey results as they relate to both the current and a desirable future state of genomic data flow.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7153090PMC
July 2020

Survival, Chemotherapy Treatments, and Health Care Utilization Among Patients with Advanced Small Cell Lung Cancer: An Observational Study.

Adv Ther 2020 01 11;37(1):552-565. Epub 2019 Dec 11.

Merck & Co., Kenilworth, NJ, USA.

Introduction: Most cases of small cell lung cancer (SCLC) are diagnosed at an advanced stage. The objective of this study was to investigate patient characteristics, survival, chemotherapy treatments, and health care use after a diagnosis of advanced SCLC in subjects enrolled in a health system network.

Methods: This was a retrospective cohort study of patients aged ≥ 18 years who either were diagnosed with stage III/IV SCLC or who progressed to advanced SCLC during the study period (2005-2015). Patients identified from the Indiana State Cancer Registry and the Indiana Network for Patient Care were followed from their advanced diagnosis index date until the earliest date of the last visit, death, or the end of the study period. Patient characteristics, survival, chemotherapy regimens, associated health care visits, and durations of treatment were reported. Time-to-event analyses were performed using the Kaplan-Meier method.

Results: A total of 498 patients with advanced SCLC were identified, of whom 429 were newly diagnosed with advanced disease and 69 progressed to advanced disease during the study period. Median survival from the index diagnosis date was 13.2 months. First-line (1L) chemotherapy was received by 464 (93.2%) patients, most commonly carboplatin/etoposide, received by 213 (45.9%) patients, followed by cisplatin/etoposide (20.7%). Ninety-five (20.5%) patients progressed to second-line (2L) chemotherapy, where topotecan monotherapy (20.0%) was the most common regimen, followed by carboplatin/etoposide (14.7%). Median survival was 10.1 months from 1L initiation and 7.7 months from 2L initiation.

Conclusion: Patients in a regional health system network diagnosed with advanced SCLC were treated with chemotherapy regimens similar to those in earlier reports based on SEER-Medicare data. Survival of patients with advanced SCLC was poor, illustrating the lack of progress over several decades in the treatment of this lethal disease and highlighting the need for improved treatments.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1007/s12325-019-01161-8DOI Listing
January 2020

Passive Digital Signature for Early Identification of Alzheimer's Disease and Related Dementia.

J Am Geriatr Soc 2020 03 29;68(3):511-518. Epub 2019 Nov 29.

Department of Biostatistics, Indiana University School of Medicine and School of Public Health, Indianapolis, Indiana.

Objectives: Developing scalable strategies for the early identification of Alzheimer's disease and related dementia (ADRD) is important. We aimed to develop a passive digital signature for early identification of ADRD using electronic medical record (EMR) data.

Design: A case-control study.

Setting: The Indiana Network for Patient Care (INPC), a regional health information exchange in Indiana.

Participants: Patients identified with ADRD and matched controls.

Measurements: We used data from the INPC that includes structured and unstructured (visit notes, progress notes, medication notes) EMR data. Cases and controls were matched on age, race, and sex. The derivation sample consisted of 10 504 cases and 39 510 controls; the validation sample included 4500 cases and 16 952 controls. We constructed models to identify early 1- to 10-year, 3- to 10-year, and 5- to 10-year ADRD signatures. The analyses included 14 diagnostic risk variables and 10 drug classes in addition to new variables produced from unstructured data (eg, disorientation, confusion, wandering, apraxia, etc). The area under the receiver operating characteristics (AUROC) curve was used to determine the best models.

Results: The AUROC curves for the validation samples for the 1- to 10-year, 3- to 10-year, and 5- to 10-year models that used only structured data were .689, .649, and .633, respectively. For the same samples and years, models that used both structured and unstructured data produced AUROC curves of .798, .748, and .704, respectively. Using a cutoff to maximize sensitivity and specificity, the 1- to 10-year, 3- to 10-year, and 5- to 10-year models had sensitivity that ranged from 51% to 62% and specificity that ranged from 80% to 89%.

Conclusion: EMR-based data provide a targeted and scalable process for early identification of risk of ADRD as an alternative to traditional population screening. J Am Geriatr Soc 68:511-518, 2020.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/jgs.16218DOI Listing
March 2020

Identifying dominant inpatient trends leveraging electronic physician orders:The Medical Gopher 1993-2016.

AMIA Annu Symp Proc 2018 5;2018:377-384. Epub 2018 Dec 5.

Indiana University School of Medicine, Indianapolis IN.

The Medical Gopher was one of the first examples of a computerized physician order entry system. For decades, it captured the "best thoughts" of thousands of physicians at their particular moments in medical history. We hypothesized and found that electronic physician orders can identify important overarching trends in medicine through simple graphs, which can prompt both informed reflection and potentially action if redirection is needed.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6371382PMC
October 2019

Drug-gene and drug-drug interactions associated with tramadol and codeine therapy in the INGENIOUS trial.

Pharmacogenomics 2019 04 20;20(6):397-408. Epub 2019 Feb 20.

Department of Medicine, Indiana University School of Medicine, Indianapolis, IN 46202, USA.

Tramadol and codeine are metabolized by CYP2D6 and are subject to drug-gene and drug-drug interactions. This interim analysis examined prescribing behavior and efficacy in 102 individuals prescribed tramadol or codeine while receiving pharmaco-genotyping as part of the INGENIOUS trial (NCT02297126). Within 60 days of receiving tramadol or codeine, clinicians more frequently prescribed an alternative opioid in ultrarapid and poor metabolizers (odds ratio: 19.0; 95% CI: 2.8-160.4) as compared with normal or indeterminate metabolizers (p = 0.01). After adjusting the CYP2D6 activity score for drug-drug interactions, uncontrolled pain was reported more frequently in individuals with reduced CYP2D6 activity (odds ratio: 0.50; 95% CI: 0.25-0.94). Phenoconversion for drug-drug and drug-gene interactions is an important consideration in pharmacogenomic implementation; drug-drug interactions may obscure the potential benefits of genotyping.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2217/pgs-2018-0205DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6562829PMC
April 2019

Qualitative study of system-level factors related to genomic implementation.

Genet Med 2019 07 23;21(7):1534-1540. Epub 2018 Nov 23.

Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania, Philadelphia, PA, USA.

Purpose: Research on genomic medicine integration has focused on applications at the individual level, with less attention paid to implementation within clinical settings. Therefore, we conducted a qualitative study using the Consolidated Framework for Implementation Research (CFIR) to identify system-level factors that played a role in implementation of genomic medicine within Implementing GeNomics In PracTicE (IGNITE) Network projects.

Methods: Up to four study personnel, including principal investigators and study coordinators from each of six IGNITE projects, were interviewed using a semistructured interview guide that asked interviewees to describe study site(s), progress at each site, and factors facilitating or impeding project implementation. Interviews were coded following CFIR inner-setting constructs.

Results: Key barriers included (1) limitations in integrating genomic data and clinical decision support tools into electronic health records, (2) physician reluctance toward genomic research participation and clinical implementation due to a limited evidence base, (3) inadequate reimbursement for genomic medicine, (4) communication among and between investigators and clinicians, and (5) lack of clinical and leadership engagement.

Conclusion: Implementation of genomic medicine is hindered by several system-level barriers to both research and practice. Addressing these barriers may serve as important facilitators for studying and implementing genomics in practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1038/s41436-018-0378-9DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6533158PMC
July 2019

A comparison between physicians and computer algorithms for form CMS-2728 data reporting.

Hemodial Int 2017 01 29;21(1):117-124. Epub 2016 Jun 29.

Department of Medicine, Indiana University School of Medicine, Indianapolis, Indiana, USA.

Introduction: CMS-2728 form (Medical Evidence Report) assesses 23 comorbidities chosen to reflect poor outcomes and increased mortality risk. Previous studies questioned the validity of physician reporting on forms CMS-2728. We hypothesize that reporting of comorbidities by computer algorithms identifies more comorbidities than physician completion, and, therefore, is more reflective of underlying disease burden.

Methods: We collected data from CMS-2728 forms for all 296 patients who had incident ESRD diagnosis and received chronic dialysis from 2005 through 2014 at Indiana University outpatient dialysis centers. We analyzed patients' data from electronic medical records systems that collated information from multiple health care sources. Previously utilized algorithms or natural language processing was used to extract data on 10 comorbidities for a period of up to 10 years prior to ESRD incidence. These algorithms incorporate billing codes, prescriptions, and other relevant elements. We compared the presence or unchecked status of these comorbidities on the forms to the presence or absence according to the algorithms.

Findings: Computer algorithms had higher reporting of comorbidities compared to forms completion by physicians. This remained true when decreasing data span to one year and using only a single health center source. The algorithms determination was well accepted by a physician panel. Importantly, algorithms use significantly increased the expected deaths and lowered the standardized mortality ratios.

Discussion: Using computer algorithms showed superior identification of comorbidities for form CMS-2728 and altered standardized mortality ratios. Adapting similar algorithms in available EMR systems may offer more thorough evaluation of comorbidities and improve quality reporting.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/hdi.12445DOI Listing
January 2017

The IGNITE network: a model for genomic medicine implementation and research.

BMC Med Genomics 2016 Jan 5;9. Epub 2016 Jan 5.

Duke Center for Applied Genomics and Precision Medicine, Duke University Medical Center, 101 Science Dr, Rm 2111, CIEMAS Bldg, Durham, NC, 27708, USA.

Background: Patients, clinicians, researchers and payers are seeking to understand the value of using genomic information (as reflected by genotyping, sequencing, family history or other data) to inform clinical decision-making. However, challenges exist to widespread clinical implementation of genomic medicine, a prerequisite for developing evidence of its real-world utility.

Methods: To address these challenges, the National Institutes of Health-funded IGNITE (Implementing GeNomics In pracTicE; www.ignite-genomics.org ) Network, comprised of six projects and a coordinating center, was established in 2013 to support the development, investigation and dissemination of genomic medicine practice models that seamlessly integrate genomic data into the electronic health record and that deploy tools for point of care decision making. IGNITE site projects are aligned in their purpose of testing these models, but individual projects vary in scope and design, including exploring genetic markers for disease risk prediction and prevention, developing tools for using family history data, incorporating pharmacogenomic data into clinical care, refining disease diagnosis using sequence-based mutation discovery, and creating novel educational approaches.

Results: This paper describes the IGNITE Network and member projects, including network structure, collaborative initiatives, clinical decision support strategies, methods for return of genomic test results, and educational initiatives for patients and providers. Clinical and outcomes data from individual sites and network-wide projects are anticipated to begin being published over the next few years.

Conclusions: The IGNITE Network is an innovative series of projects and pilot demonstrations aiming to enhance translation of validated actionable genomic information into clinical settings and develop and use measures of outcome in response to genome-based clinical interventions using a pragmatic framework to provide early data and proofs of concept on the utility of these interventions. Through these efforts and collaboration with other stakeholders, IGNITE is poised to have a significant impact on the acceleration of genomic information into medical practice.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/s12920-015-0162-5DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4700677PMC
January 2016

Linkage of Indiana State Cancer Registry and Indiana Network for Patient Care Data.

J Registry Manag 2016 ;43(4):174-8

BACKGROUND: Large automated electronic health records (EHRs), if brought together in a federated data model, have the potential to serve as valuable population-based tools in studying the patterns and effectiveness of treatment. The Indiana Network for Patient Care (INPC) is a unique federated EHR data repository that contains data collected from a large population across various health care settings throughout the state of Indiana. The INPC clinical data environment allows quick access and extraction of information from medical charts. The purpose of this project was to evaluate 2 different methods of record linkage between the Indiana State Cancer Registry (ISCR) and INPC, determine the match rate for linkage between the ISCR and INPC data for patients diagnosed with cancer, and to assess the completeness of the ISCR based on additional validated cancer cases identified in the INPC EHRs. METHODS: Deterministic and probabilistic algorithms were applied to link ISCR cases to the INPC. The linkage results were validated by manual review and the accuracy assessed with positive predictive value (PPV). Medical charts of melanoma and lung cancer cases identified in INPC but not linked to ISCR were manually reviewed to identify true incidence cancers missed by the ISCR, from which the completeness of the ISCR was estimated for each cancer. RESULTS: Both deterministic and probabilistic approaches to linking ISCR and INPC had extremely high PPV (>99%) for identifying true matches for the overall cohort and each subcohort. The combined match rate for melanoma and lung cancer cases identified in the ISCR that matched to any patient occurrence in INPC (not by disease) was 85.5% for the complete cohort, 94.4% for melanoma, and 84.4% for lung cancer. The estimated completeness of capture by the ISCR was 84% for melanoma and 98% for lung cancer. Conclusion: Cancer registries can be successfully linked to patients’ EHR data from institutions participating in a regional health information organization (RHIO) with a high match rate. A pragmatic approach to data linkage may apply both deterministic and probabilistic approaches together for the diverse purposes of cancer control research. The RHIO has the potential to add value to the state cancer registry through the identification of additional true incident cases, but more advanced approaches, such as natural language processing, are needed.
View Article and Find Full Text PDF

Download full-text PDF

Source
April 2018

Identification of Patients with Family History of Pancreatic Cancer--Investigation of an NLP System Portability.

Stud Health Technol Inform 2015 ;216:604-8

Department of Health Sciences Research, Mayo Clinic, Rochester, MN.

In this study we have developed a rule-based natural language processing (NLP) system to identify patients with family history of pancreatic cancer. The algorithm was developed in a Unstructured Information Management Architecture (UIMA) framework and consisted of section segmentation, relation discovery, and negation detection. The system was evaluated on data from two institutions. The family history identification precision was consistent across the institutions shifting from 88.9% on Indiana University (IU) dataset to 87.8% on Mayo Clinic dataset. Customizing the algorithm on the the Mayo Clinic data, increased its precision to 88.1%. The family member relation discovery achieved precision, recall, and F-measure of 75.3%, 91.6% and 82.6% respectively. Negation detection resulted in precision of 99.1%. The results show that rule-based NLP approaches for specific information extraction tasks are portable across institutions; however customization of the algorithm on the new dataset improves its performance.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5863760PMC
December 2016

DEEPEN: A negation detection system for clinical text incorporating dependency relation into NegEx.

J Biomed Inform 2015 Apr 16;54:213-9. Epub 2015 Mar 16.

School of Informatics and Computing, Indiana University, Indianapolis, IN, USA. Electronic address:

In Electronic Health Records (EHRs), much of valuable information regarding patients' conditions is embedded in free text format. Natural language processing (NLP) techniques have been developed to extract clinical information from free text. One challenge faced in clinical NLP is that the meaning of clinical entities is heavily affected by modifiers such as negation. A negation detection algorithm, NegEx, applies a simplistic approach that has been shown to be powerful in clinical NLP. However, due to the failure to consider the contextual relationship between words within a sentence, NegEx fails to correctly capture the negation status of concepts in complex sentences. Incorrect negation assignment could cause inaccurate diagnosis of patients' condition or contaminated study cohorts. We developed a negation algorithm called DEEPEN to decrease NegEx's false positives by taking into account the dependency relationship between negation words and concepts within a sentence using Stanford dependency parser. The system was developed and tested using EHR data from Indiana University (IU) and it was further evaluated on Mayo Clinic dataset to assess its generalizability. The evaluation results demonstrate DEEPEN, which incorporates dependency parsing into NegEx, can reduce the number of incorrect negation assignment for patients with positive findings, and therefore improve the identification of patients with the target clinical findings in EHRs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.jbi.2015.02.010DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5863758PMC
April 2015

Automated pancreatic cyst screening using natural language processing: a new tool in the early detection of pancreatic cancer.

HPB (Oxford) 2015 May 24;17(5):447-53. Epub 2014 Dec 24.

Department of Surgery, Indiana University School of Medicine, Indianapolis, IN, USA.

Introduction: As many as 3% of computed tomography (CT) scans detect pancreatic cysts. Because pancreatic cysts are incidental, ubiquitous and poorly understood, follow-up is often not performed. Pancreatic cysts may have a significant malignant potential and their identification represents a 'window of opportunity' for the early detection of pancreatic cancer. The purpose of this study was to implement an automated Natural Language Processing (NLP)-based pancreatic cyst identification system.

Method: A multidisciplinary team was assembled. NLP-based identification algorithms were developed based on key words commonly used by physicians to describe pancreatic cysts and programmed for automated search of electronic medical records. A pilot study was conducted prospectively in a single institution.

Results: From March to September 2013, 566,233 reports belonging to 50,669 patients were analysed. The mean number of patients reported with a pancreatic cyst was 88/month (range 78-98). The mean sensitivity and specificity were 99.9% and 98.8%, respectively.

Conclusion: NLP is an effective tool to automatically identify patients with pancreatic cysts based on electronic medical records (EMR). This highly accurate system can help capture patients 'at-risk' of pancreatic cancer in a registry.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1111/hpb.12375DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4402056PMC
May 2015

Regenstrief Institute's Medical Gopher: a next-generation homegrown electronic medical record system.

Int J Med Inform 2014 Mar 14;83(3):170-9. Epub 2013 Dec 14.

Regenstrief Institute Inc., Indianapolis, IN, USA; Indiana University School of Medicine, Indianapolis, IN, USA; Wishard/Eskenazi Health Services, Indianapolis, IN, USA.

Objective: Regenstrief Institute developed one of the seminal computerized order entry systems, the Medical Gopher, for implementation at Wishard Hospital nearly three decades ago. Wishard Hospital and Regenstrief remain committed to homegrown software development, and over the past 4 years we have fully rebuilt Gopher with an emphasis on usability, safety, leveraging open source technologies, and the advancement of biomedical informatics research. Our objective in this paper is to summarize the functionality of this new system and highlight its novel features.

Materials And Methods: Applying a user-centered design process, the new Gopher was built upon a rich-internet application framework using an agile development process. The system incorporates order entry, clinical documentation, result viewing, decision support, and clinical workflow. We have customized its use for the outpatient, inpatient, and emergency department settings.

Results: The new Gopher is now in use by over 1100 users a day, including an average of 433 physicians caring for over 3600 patients daily. The system includes a wizard-like clinical workflow, dynamic multimedia alerts, and a familiar 'e-commerce'-based interface for order entry. Clinical documentation is enhanced by real-time natural language processing and data review is supported by a rapid chart search feature.

Discussion: As one of the few remaining academically developed order entry systems, the Gopher has been designed both to improve patient care and to support next-generation informatics research. It has achieved rapid adoption within our health system and suggests continued viability for homegrown systems in settings of close collaboration between developers and providers.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.ijmedinf.2013.11.004DOI Listing
March 2014

An efficient pancreatic cyst identification methodology using natural language processing.

Stud Health Technol Inform 2013 ;192:822-6

School of Informatics, Indiana University, Indianapolis, IN, USA.

Pancreatic cancer is one of the deadliest cancers, mostly diagnosed at late stages. Patients with pancreatic cysts are at higher risk of developing cancer and their surveillance can help to diagnose the disease in earlier stages. In this retrospective study we collected a corpus of 1064 records from 44 patients at Indiana University Hospital from 1990 to 2012. A Natural Language Processing (NLP) system was developed and used to identify patients with pancreatic cysts. NegEx algorithm was used initially to identify the negation status of concepts that resulted in precision and recall of 98.9% and 89% respectively. Stanford Dependency parser (SDP) was then used to improve the NegEx performance resulting in precision of 98.9% and recall of 95.7%. Features related to pancreatic cysts were also extracted from patient medical records using regex and NegEx algorithm with 98.5% precision and 97.43% recall. SDP improved the NegEx algorithm by increasing the recall to 98.12%.
View Article and Find Full Text PDF

Download full-text PDF

Source
April 2015

Medication adherence and tolerability of Alzheimer's disease medications: study protocol for a randomized controlled trial.

Trials 2013 May 4;14:125. Epub 2013 May 4.

Department of Pharmacy Practice, Purdue University School of Pharmacy, 410 West 10th Street, West Lafayette, IN, USA.

Background: The class of acetylcholinesterase inhibitors (ChEI), including donepezil, rivastigmine, and galantamine, have similar efficacy profiles in patients with mild to moderate Alzheimer's disease (AD). However, few studies have evaluated adherence to these agents. We sought to prospectively capture the rates and reasons for nonadherence to ChEI and determine factors influencing tolerability and adherence.

Methods/design: We designed a pragmatic randomized clinical trial to evaluate the adherence to ChEIs among older adults with AD. Participants include AD patients receiving care within memory care practices in the greater Indianapolis area. Participants will be followed at 6-week intervals up to 18 weeks to measure the primary outcome of ChEI discontinuation and adherence rates and secondary outcomes of behavioral and psychological symptoms of dementia. The primary outcome will be assessed through two methods, a telephone interview of an informal caregiver and electronic medical record data captured from each healthcare system through a regional health information exchange. The secondary outcome will be measured by the Healthy Aging Brain Care Monitor and the Neuropsychiatric Inventory. In addition, the trial will conduct an exploratory evaluation of the pharmacogenomic signatures for the efficacy and the adverse effect responses to ChEIs. We hypothesized that patient-specific factors, including pharmacogenomics and pharmacokinetic characteristics, may influence the study outcomes.

Discussion: This pragmatic trial will engage a diverse population from multiple memory care practices to evaluate the adherence to and tolerability of ChEIs in a real world setting. Engaging participants from multiple healthcare systems connected through a health information exchange will capture valuable clinical and non-clinical influences on the patterns of utilization and tolerability of a class of medications with a high rate of discontinuation.

Trial Registration: Clinicaltrials.gov: NCT01362686.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1186/1745-6215-14-125DOI Listing
May 2013

A regional informatics platform for coordinated antibiotic-resistant infection tracking, alerting, and prevention.

Clin Infect Dis 2013 Jul 10;57(2):254-62. Epub 2013 Apr 10.

Department of Medicine, Northwestern University, Chicago, IL 60611, USA.

Background: We developed and assessed the impact of a patient registry and electronic admission notification system relating to regional antimicrobial resistance (AMR) on regional AMR infection rates over time. We conducted an observational cohort study of all patients identified as infected or colonized with methicillin-resistant Staphylococcus aureus (MRSA) and/or vancomycin-resistant enterococci (VRE) on at least 1 occasion by any of 5 healthcare systems between 2003 and 2010. The 5 healthcare systems included 17 hospitals and associated clinics in the Indianapolis, Indiana, region.

Methods: We developed and standardized a registry of MRSA and VRE patients and created Web forms that infection preventionists (IPs) used to maintain the lists. We sent e-mail alerts to IPs whenever a patient previously infected or colonized with MRSA or VRE registered for admission to a study hospital from June 2007 through June 2010.

Results: Over a 3-year period, we delivered 12 748 e-mail alerts on 6270 unique patients to 24 IPs covering 17 hospitals. One in 5 (22%-23%) of all admission alerts was based on data from a healthcare system that was different from the admitting hospital; a few hospitals accounted for most of this crossover among facilities and systems.

Conclusions: Regional patient registries identify an important patient cohort with relevant prior antibiotic-resistant infection data from different healthcare institutions. Regional registries can identify trends and interinstitutional movement not otherwise apparent from single institution data. Importantly, electronic alerts can notify of the need to isolate early and to institute other measures to prevent transmission.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/cid/cit229DOI Listing
July 2013

Development and Implementation of an Electronic Decision Support to Manage the Health of a High-Risk Population: The enhanced Electronic Medical Record Aging Brain Care Software (eMR-ABC).

EGEMS (Wash DC) 2013 11;1(1):1009. Epub 2013 Mar 11.

Indiana University ; Regenstrief Institute.

Introduction: Health care systems in the United States are transitioning from volume-based purchasing models to value-based purchasing models that demand both delivery of personalized care for each patient and cost-effective population health management. The enhanced medical record for aging brain care (eMR-ABC) software is an electronic decision support system that facilitates the management of a high-risk population suffering from aging brain disorders such as dementia.

Methods: Using the lenses of the Complex Adaptive System and the Reflective Adaptive Process, we assembled an interdisciplinary team of clinicians, health services researchers, and software developers who designed, implemented, evaluated, and continuously modified the eMR-ABC to meet the needs of care coordinators who manage the health of a targeted high-risk population.

Results: The eMR-ABC captures and monitors the cognitive, functional, behavioral, and psychological symptoms of a registry of patients suffering from dementia or depression as well as the burden of patients' family caregivers. It provides decision support to care coordinators to create a personalized care plan that includes evidence-based nonpharmacological protocols, self-management handouts, and alerts of medications with potentially adverse cognitive effects. The software's built-in engine tracks patient visits and on-demand functionality to generate population reports for specified indicators.

Discussion: Population health programs depend on data collection and information systems with the ability to provide valuable and timely feedback on an ongoing basis. Following these guidelines, the eMR-ABC was designed specifically to meet the management needs of a high-risk population.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.13063/2327-9214.1009DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC4371521PMC
April 2015

Connecting research discovery with care delivery in dementia: the development of the Indianapolis Discovery Network for Dementia.

Clin Interv Aging 2012 16;7:509-16. Epub 2012 Nov 16.

Indiana University Center for Aging Research, Indianapolis, IN, USA.

Background: The US Institute of Medicine has recommended an integrated, locally sensitive collaboration among the various members of the community, health care systems, and research organizations to improve dementia care and dementia research.

Methods: Using complex adaptive system theory and reflective adaptive process, we developed a professional network called the "Indianapolis Discovery Network for Dementia" (IDND). The IDND facilitates effective and sustainable interactions among a local and diverse group of dementia researchers, clinical providers, and community advocates interested in improving care for dementia patients in Indianapolis, Indiana.

Results: The IDND was established in February 2006 and now includes more than 250 members from more than 30 local (central Indiana) organizations representing 20 disciplines. The network uses two types of communication to connect its members. The first is a 2-hour face-to-face bimonthly meeting open to all members. The second is a web-based resource center (http://www.indydiscoverynetwork.org ). To date, the network has: (1) accomplished the development of a network website with an annual average of 12,711 hits per day; (2) produced clinical tools such as the Healthy Aging Brain Care Monitor and the Anticholinergic Cognitive Burden Scale; (3) translated and implemented the collaborative dementia care model into two local health care systems; (4) created web-based tracking software, the Enhanced Medical Record for Aging Brain Care (eMR-ABC), to support care coordination for patients with dementia; (5) received more than USD$24 million in funding for members for dementia-related research studies; and (6) adopted a new group-based problem-solving process called the "IDND consultancy round."

Conclusion: A local interdisciplinary "think-tank" network focused on dementia that promotes collaboration in research projects, educational initiatives, and quality improvement efforts that meet the local research, clinical, and community needs relevant to dementia care has been built.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2147/CIA.S36078DOI Listing
May 2013

Adherence to drug-drug interaction alerts in high-risk patients: a trial of context-enhanced alerting.

J Am Med Inform Assoc 2013 May 17;20(3):494-8. Epub 2012 Nov 17.

Department of Medical Informatics, Regenstrief Institute, Indianapolis, IN 46202, USA.

Objective: Drug-drug interaction (DDI) alerting is an important form of clinical decision support, yet physicians often fail to attend to critical DDI warnings due to alert fatigue. We previously described a model for highlighting patients at high risk of a DDI by enhancing alerts with relevant laboratory data. We sought to evaluate the effect of this model on alert adherence in high-risk patients.

Methods: A 6-month randomized controlled trial involving 1029 outpatient physicians was performed. The target interactions were all DDIs known to cause hyperkalemia. Alerts in the intervention group were enhanced with the patient's most recent potassium and creatinine levels. The control group received unmodified alerts. High -risk patients were those with baseline potassium >5.0 mEq/l and/or creatinine ≥1.5 mg/dl (132 μmol/l).

Results: We found no significant difference in alert adherence in high-risk patients between the intervention group (15.3%) and the control group (16.8%) (p=0.71). Adherence in normal risk patients was significantly lower in the intervention group (14.6%) than in the control group (18.6%) (p<0.01). In neither group did physicians increase adherence in patients at high risk.

Conclusions: Physicians adhere poorly to hyperkalemia-associated DDI alerts even in patients with risk factors for a clinically significant interaction, and the display of relevant laboratory data in these alerts did not improve adherence levels in the outpatient setting. Further research is necessary to determine optimal strategies for conveying patient-specific DDI risk.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1136/amiajnl-2012-001073DOI Listing
May 2013

Concept and development of a discharge alert filter for abnormal laboratory values coupled with computerized provider order entry: a tool for quality improvement and hospital risk management.

J Patient Saf 2012 Jun;8(2):69-75

Division of General Medicine, Department of Neurosurgery, Emory University School of Medicine, Atlanta, Georgia 30303, USA.

Purpose: To develop a clinical decision support system activated at the time of discharge to reduce potentially inappropriate discharges from unidentified or unaddressed abnormal laboratory values.

Methods: We identified 106 laboratory tests for possible inclusion in the discharge alert filter. We selected 7 labs as widely available, commonly obtained, and associated with high risk for potential morbidity or mortality within abnormal ranges. We identified trigger thresholds at levels that would capture significant laboratory abnormalities while avoiding excessive flag generation because of laboratory results that minimally deviate outside the normal reference range.

Results: We selected sodium (>155 or <125 mmol/L), potassium (<2.5 or >6 mEq/dL) phosphorous (<1.6 mg/dL), magnesium (<1.2 mg/dL), creatinine greater than 1.1 with a rise of 20% or more between the 2 most recent results, white blood cell count (>11,000 cells/mm with a rise of 20% or more between the 2 most recent results), and international normalized ratio greater than 4.

Conclusions: A discharge alert filter that reliably and effectively identifies patients that may be discharged in unsafe situations because of unaddressed critical laboratory values can improve patient safety at discharge and potentially reduce the incidence of costly litigation. Further research is needed to validate whether the proposed discharge alert filter is effective at improving patient safety at discharge.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/PTS.0b013e31824aba75DOI Listing
June 2012

Preparing for an aging population and improving chronic disease management.

AMIA Annu Symp Proc 2010 Nov 13;2010:162-6. Epub 2010 Nov 13.

Regenstrief Institute, Indianapolis, IN;

New models of health care delivery are inevitable. There is likely to be increasing emphasis on patient self-monitoring, health care delivery at patient homes, interdisciplinary treatment plans, a greater percentage of medical care delivered by non-physician health professionals, targeted health educational materials, and greater involvement and training of informal caregivers. The Information Technologies (IT) infrastructure of health systems will need to adapt. We have begun sorting out the implications of this future within a County public hospital system: defining the desirable features, relevant technologies, necessary modifications to the network, and additional data elements to be captured. We seek to build an infrastructure that will support new patient-focused technologies designed to more efficiently and effectively support older individuals. We hypothesize utility to further exploring the impact that new health care delivery models will have on health systems' IT infrastructures.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3041380PMC
November 2010
-->