Publications by authors named "Joseph Finkelstein"

138 Publications

Identification of Liver Cancer Stem Cell Stemness Markers Using a Comparative Analysis of Public Data Sets.

Stem Cells Cloning 2021 16;14:9-17. Epub 2021 Jun 16.

Center for Biomedical and Population Health Informatics, Icahn School of Medicine at Mount Sinai, New York, NY, 10029, USA.

Purpose: Comparative reanalysis of single-cell transcriptomics data to gain useful novel insights into cancer stem cells (CSCs), which are a rare subset of cells within tumors, characterized by their capability to self-renew and differentiate, and their role in tumorigenicity.

Patients And Methods: This project utilized publically available liver single-cell RNA-seq datasets of liver cancer and liver progenitor cell types to demonstrate how shared large amounts of data can generate new and valuable information. The data were analyzed using EdgeR differential expression analysis, with focus on a set of 34 known stemness markers.

Results: We showed that the expression of stemness markers SOX9, KRT19, KRT7, and CD24, and Yamanaka factors Oct4 and SOX2 in CSCs was significantly elevated relative to progenitor cell types, potentially explaining their increased differentiation and replication potential.

Conclusion: These results help to further document the complementary expression changes that give CSCs their distinct phenotypic profile. Our findings have potential significance to advance our knowledge of the important genes relevant to CSCs.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2147/SCCAA.S307043DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8216768PMC
June 2021

ReMeDy: a platform for integrating and sharing published stem cell research data with a focus on iPSC trials.

Database (Oxford) 2021 Jun;2021

Center for Biomedical and Population Health Informatics, Icahn School of Medicine at Mount Sinai, 1425 Madison Avenue, Icahn L2-36, New York, NY 10029, USA.

Abstract: Recent regenerative medicine studies have emphasized the need for increased standardization, harmonization and sharing of information related to stem cell product characterization, to help drive these innovative interventions toward public availability and to increase collaboration in the scientific community. Although numerous attempts and numerous databases have been made to manage these data, a platform that incorporates all the heterogeneous data collected from stem cell projects into a harmonized project-based framework is still lacking. The aim of the database, which is described in this study, is to provide an intelligent informatics solution that integrates comprehensive characterization of diverse stem cell product characteristics with research subject and project outcome information. In the resulting platform, heterogeneous data are validated using predefined ontologies and stored in a relational database, to ensure data quality and ease of access. Testing was performed using 51 published, publically available induced pluripotent stem cell projects conducted in clinical, preclinical and in-vitro evaluations. Future aims of this project include further increasing the database size to include all published stem cell trials and develop additional data visualization tools to improve usability. Our testing demonstrated the robustness of the proposed platform, by seamlessly harmonizing diverse common data elements, and the potential of this platform for driving knowledge generation from the aggregation and harmonization of these diverse data.

Database Url: https://remedy.mssm.edu/.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1093/database/baab038DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8218701PMC
June 2021

Impact of COVID-19 Pandemic on Use of Telemedicine Services in an Academic Medical Center.

Stud Health Technol Inform 2021 May;281:407-411

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

The COVID-19 pandemic changed the landscape of telehealth services. The goal of this paper was to identify demographic groups of patients who have used telemedicine services before and after the start of the pandemic, and to analyze how different demographic groups' telehealth usage patterns change throughout the course of the pandemic. A de-identified study dataset was generated by querying electronic health records at the Mount Sinai Health System to identify all patients. 129,625 patients were analyzed. Demographic shifts in patients seeking telemedicine service were identified. There was significant increase in the middle age and older population using telehealth services. During the pandemic use of telemedicine services was increased among male patients and racial minority patients. Furthermore, telehealth services had expanded to a broader spectrum of medical specialties.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI210190DOI Listing
May 2021

Introducing a Platform for Integrating and Sharing Stem Cell Research Data.

Stud Health Technol Inform 2021 May;281:387-391

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

Advancements in regenerative medicine have highlighted the need for increased standardization and sharing of stem cell products to help drive these innovative interventions toward public availability and to increase collaboration in the scientific community. Although numerous attempts and numerous databases have been made to store this data, there is still a lack of a platform that incorporates heterogeneous stem cell information into a harmonized project-based framework. The aim of the platform described in this study, ReMeDy, is to provide an intelligent informatics solution which integrates diverse stem cell product characteristics with study subject and omics information. In the resulting platform, heterogeneous data is validated using predefined ontologies and stored in a relational database. In this initial feasibility study, testing of the ReMeDy functionality was performed using published, publically-available induced pluripotent stem cell projects conducted in in vitro, preclinical and intervention evaluations. It demonstrated the robustness of ReMeDy for storing diverse iPSC data, by seamlessly harmonizing diverse common data elements, and the potential utility of this platform for driving knowledge generation from the aggregation of this shared data. Next steps include increasing the number of curated projects by developing a crowdsourcing framework for data upload and an automated pipeline for metadata abstraction. The database is publically accessible at https://remedy.mssm.edu/.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI210186DOI Listing
May 2021

Entity Extraction for Clinical Notes, a Comparison Between MetaMap and Amazon Comprehend Medical.

Stud Health Technol Inform 2021 May;281:258-262

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

Extracting meaningful information from clinical notes is challenging due to their semi- or unstructured format. Clinical notes such as discharge summaries contain information about diseases, their risk factors, and treatment approaches associated to them. As such, it is critical for healthcare quality as well as for clinical research to extract those information and make them accessible to other computerized applications that rely on coded data. In this context, the goal of this paper is to compare the automatic medical entity extraction capacity of two available entity extraction tools: MetaMap (MM) and Amazon Comprehend Medical (ACM). Recall, precision and F-score have been used to evaluate the performance of the tools. The results show that ACM achieves higher average recall, average precision, and average F-score in comparison with MM.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI210160DOI Listing
May 2021

Comparative Analysis of Public Data Sets to Identify Stemness Markers That Differentiate Liver Cancer Stem Cells.

Stud Health Technol Inform 2021 May;281:818-819

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

Cancer stem cells (CSCs) represent an important field in translational medicine for generating novel cancer treatments. To identify important stemness markers in liver CSCs that potentially explain their resistance to treatment, we analyzed 10865 single-cell RNA-seq samples across 42684 coding and non-coding genes. Our results show that CSCs have significantly increased expression of two Yamanaka factors (Oct4, 2.14X and SOX2, 1.13X) and three stemness factors (CD44, 3.25X; KRT7, 2.2X; SOX9, 1.71X), relative to liver progenitor cells. Our study demonstrates the potential power of harnessing shared big data for driving translational medicine for novel hypothesis generation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI210290DOI Listing
May 2021

Identifying Core Outcome Sets in COVID-19 Clinical Trials Using ClinicalTrials.gov.

Stud Health Technol Inform 2021 May;281:514-515

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

Introduction of core outcome sets (COS) facilitates evidence synthesis, transparency in outcome reporting, and standardization in clinical research. However, development of COS may be a time consuming and expensive process. Publicly available repositories, such as ClinicalTrials.gov (CTG), provide access to a vast collection of clinical trial characteristics including primary and secondary outcomes, which can be analyzed using a comprehensive set of tools. With growing number of COVID-19 clinical trials, COS development may provide crucial means to standardize, aggregate, share, and analyze diverse research results in a harmonized way. This study was aimed at initial assessment of utility of CTG analytics for identifying COVID-19 COS. At the time of this study, January, 2021, we analyzed 120 ongoing NIH-funded COVID-19 clinical trials initiated in 2020 to inform COVID-19 COS development by evaluating and ranking clinical trial outcomes based on their structured representation in CTG. Using this approach, COS comprised of 25 major clinical outcomes has been identified with mortality, mental health status, and COVID-19 antibodies at the top of the list. We concluded that CTG analytics can be instrumental for COVID-19 COS development and that further analysis is warranted including broader number of international trials combined with more granular approach and ontology-driven pipelines for outcome extraction and curation.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI210221DOI Listing
May 2021

Automated Identification of Common Disease-Specific Outcomes for Comparative Effectiveness Research Using ClinicalTrials.gov: Algorithm Development and Validation Study.

JMIR Med Inform 2021 Feb 8;9(2):e18298. Epub 2021 Feb 8.

Center for Biomedical and Population Health Informatics, Icahn School of Medicine at Mount Sinai, New York, NY, United States.

Background: Common disease-specific outcomes are vital for ensuring comparability of clinical trial data and enabling meta analyses and interstudy comparisons. Traditionally, the process of deciding which outcomes should be recommended as common for a particular disease relied on assembling and surveying panels of subject-matter experts. This is usually a time-consuming and laborious process.

Objective: The objectives of this work were to develop and evaluate a generalized pipeline that can automatically identify common outcomes specific to any given disease by finding, downloading, and analyzing data of previous clinical trials relevant to that disease.

Methods: An automated pipeline to interface with ClinicalTrials.gov's application programming interface and download the relevant trials for the input condition was designed. The primary and secondary outcomes of those trials were parsed and grouped based on text similarity and ranked based on frequency. The quality and usefulness of the pipeline's output were assessed by comparing the top outcomes identified by it for chronic obstructive pulmonary disease (COPD) to a list of 80 outcomes manually abstracted from the most frequently cited and comprehensive reviews delineating clinical outcomes for COPD.

Results: The common disease-specific outcome pipeline successfully downloaded and processed 3876 studies related to COPD. Manual verification indicated that the pipeline was downloading and processing the same number of trials as were obtained from the self-service ClinicalTrials.gov portal. Evaluating the automatically identified outcomes against the manually abstracted ones showed that the pipeline achieved a recall of 92% and precision of 79%. The precision number indicated that the pipeline was identifying many outcomes that were not covered in the literature reviews. Assessment of those outcomes indicated that they are relevant to COPD and could be considered in future research.

Conclusions: An automated evidence-based pipeline can identify common clinical trial outcomes of comparable breadth and quality as the outcomes identified in comprehensive literature reviews. Moreover, such an approach can highlight relevant outcomes for further consideration.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2196/18298DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7899806PMC
February 2021

Retrospective cohort study of clinical characteristics of 2199 hospitalised patients with COVID-19 in New York City.

BMJ Open 2020 11 27;10(11):e040736. Epub 2020 Nov 27.

The Zena and Michael A. Wiener Cardiovascular Institute, New York, New York, USA.

Objective: The COVID-19 pandemic is a global public health crisis, with over 33 million cases and 999 000 deaths worldwide. Data are needed regarding the clinical course of hospitalised patients, particularly in the USA. We aimed to compare clinical characteristic of patients with COVID-19 who had in-hospital mortality with those who were discharged alive.

Design: Demographic, clinical and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed COVID-19 between 27 February and 2 April 2020 were identified through institutional electronic health records. We performed a retrospective comparative analysis of patients who had in-hospital mortality or were discharged alive.

Setting: All patients were admitted to the Mount Sinai Health System, a large quaternary care urban hospital system.

Participants: Participants over the age of 18 years were included.

Primary Outcomes: We investigated in-hospital mortality during the study period.

Results: A total of 2199 patients with COVID-19 were hospitalised during the study period. As of 2 April, 1121 (51%) patients remained hospitalised, and 1078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 μg/mL, C reactive protein was 162 mg/L and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 μg/mL, C reactive protein was 79 mg/L and procalcitonin was 0.09 ng/mL.

Conclusions: In our cohort of hospitalised patients, requirement of intensive care and mortality were high. Patients who died typically had more pre-existing conditions and greater perturbations in inflammatory markers as compared with those who were discharged.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1136/bmjopen-2020-040736DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7702220PMC
November 2020

Usability of Remote Assessment of Exercise Capacity for Pulmonary Telerehabilitation Program.

Stud Health Technol Inform 2020 Nov;275:72-76

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

Pulmonary rehabilitation [PR] has been successfully carried out via telemedicine however initial patient assessment has been traditionally conducted in PR centers. The first step in PR is assessment of patient's exercise capacity which allows individualized prescription of safe and effective exercise program. With COVID-19 pandemics assessment of patients in PR centers has been limited resulting in significant reduction of patients undergoing life-saving PR. The goal of this pilot study was to introduce approaches for remote assessment of exercise capacity using videoconferencing platforms and provide initial usability assessment of this approach by conducing cognitive walkthrough testing. We developed a remote assessment system that supports comprehensive physical therapy assessment necessary for prescription of a personalized exercise program tailored to individual fitness level and limitations in gait and balance of the patient under evaluation. Usability was assessed by conducting cognitive walkthrough and system usability surveys. The usability inspection of the remote exercise assessment demonstrated overall high acceptance by all study participants. Our next steps in developing user-centered interface should include usability evaluation in different subgroups of patients with varying socio-economic background, different age groups, computer skills, literacy and numeracy.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200697DOI Listing
November 2020

Latent COVID-19 Clusters in Patients with Chronic Respiratory Conditions.

Stud Health Technol Inform 2020 Nov;275:32-36

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

The goal of this paper was to apply unsupervised machine learning techniques towards the discovery of latent COVID-19 clusters in patients with chronic lower respiratory diseases (CLRD). Patients who underwent testing for SARS-CoV-2 were identified from electronic medical records. The analytical dataset comprised 2,328 CLRD patients of whom 1,029 were tested COVID-19 positive. We used the factor analysis for mixed data method for preprocessing. It performed principle component analysis on numeric values and multiple correspondence analysis on categorical values which helped convert categorical data into numeric. Cluster analysis was an effective means to both distinguish subgroups of CLRD patients with COVID-19 as well as identify patient clusters which were adversely affected by the infection. Age, comorbidity index and race were important factors for cluster separations. Furthermore, diseases of the circulatory system, the nervous system and sense organs, digestive system, genitourinary system, metabolic diseases and immunity disorders were also important criteria in the resulting cluster analyses.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200689DOI Listing
November 2020

Increasing Use of Cardiac and Pulmonary Rehabilitation in Traditional and Community Settings: OPPORTUNITIES TO REDUCE HEALTH CARE DISPARITIES.

J Cardiopulm Rehabil Prev 2020 11;40(6):350-355

National Heart Lung and Blood Institute, Bethesda, Maryland (Drs Fleg, Cooper, and Punturieri and Ms Shero); Henry Ford Hospital, Detroit, Michigan (Dr Keteyian); Denver Health Medical Center, Denver, and University of Colorado Anschutz Medical Center, Aurora, Colorado (Dr Peterson); Mayo Clinic, Rochester, Minnesota (Dr Benzo); Icahn School of Medicine at Mount Sinai, New York (Dr Finkelstein); University of Pittsburgh, Pittsburgh, Pennsylvania (Dr Forman); University of Vermont, Burlington (Dr Gaalema); and National Institute on Aging, Bethesda, Maryland (Drs Joseph and Zieman).

Although both cardiac rehabilitation (CR) and pulmonary rehabilitation (PR) are recommended by clinical practice guidelines and covered by most insurers, they remain severely underutilized. To address this problem, the National Heart, Lung, and Blood Institute (NHLBI), in collaboration with the National Institute on Aging (NIA), developed Funding Opportunity Announcements (FOAs) in late 2017 to support phase II clinical trials to increase the uptake of CR and PR in traditional and community settings. The objectives of these FOAs were to (1) test strategies that will lead to increased use of CR and PR in the US population who are eligible based on clinical guidelines; (2) test strategies to reduce disparities in the use of CR and PR based on age, gender, race/ethnicity, and socioeconomic status; and (3) test whether increased use of CR and PR, whether by traditional center-based or new models, is accompanied by improvements in relevant clinical and patient-centered outcomes, including exercise capacity, cardiovascular and pulmonary risk factors, and quality of life. Five NHLBI grants and a single NIA grant were funded in the summer of 2018 for this CR/PR collaborative initiative. A brief description of the research to be developed in each grant is provided.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1097/HCR.0000000000000527DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7644593PMC
November 2020

Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation.

J Med Internet Res 2020 11 6;22(11):e24018. Epub 2020 Nov 6.

Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, United States.

Background: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking.

Objective: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points.

Methods: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions.

Results: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction.

Conclusions: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2196/24018DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7652593PMC
November 2020

From Many to One: Designing a Unified Flowsheet in the EMR to Replace Multiple Disparate Devices.

Stud Health Technol Inform 2020 Jun;272:407-410

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

This study represents a post-implementation qualitative inquiry for a maturing flowsheet design that aims to replace multiple disparate devices used for data entry. The flowsheet has already experienced multiple iterative development cycles based on formal feedback from formative and summative usability studies. This next phase focused on a semi-structured qualitative interview to provide new feedback that will be used to further refine the product. Results of the 9-item interview were both actionable and provocative, revealing multiple avenues of improvement and a new usability map that can inform future studies and design plans.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200581DOI Listing
June 2020

Introducing an Ontology-Driven Pipeline for the Identification of Common Data Elements.

Stud Health Technol Inform 2020 Jun;272:379-382

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

Common Data Elements (CDEs) are necessary for ensuring data sharing across studies, providing comparability, and enabling aggregation and meta-analyses. The process of developing a set of CDEs for a given clinical research area has typically been arduous and time-consuming. In this work we introduce an automated pipeline that can greatly aid the process by identifying, aggregating, and ranking relevant CDEs from the outcomes of studies registered on clinicaltrials.gov (CTG). The pipeline uses the Medical Subject Headings (MeSH) ontology to group and rank candidate CDEs by specific diseases. The initial CDE pipeline has been tested using an emerging research domain. The resulting CDEs output was aligned with the current recommendations in the corresponding subject area. Further development of automated means for CDE generation based on structured information from CTG and MeSH is warranted.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200574DOI Listing
June 2020

Using Big Data to Predict Outcomes of Opioid Treatment Programs.

Stud Health Technol Inform 2020 Jun;272:366-369

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

Potential of big data analytics in analyzing outcomes of opioid treatment programs (OTP) has not been fully explored. The goal of this study was to assess potential of big data in predicting OTP outcomes based on the initial intake forms which includes demographics, social and health history. The analytical sample comprised over 30,000 people admitted in OTP. Around 66% of patients reported improvements after completing OTP. We compared the results of Logistics Regression, Random Forest, and XGBoost for predictive modeling. XGBoost with sampling and threshold tuning performed the best (44% F1 score) with over 60% accuracy. Further big data exploration of OTP is warranted.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200571DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7847309PMC
June 2020

Disparities in Racial and Ethnic Representation in Stem Cell Clinical Trials.

Stud Health Technol Inform 2020 Jun;272:358-361

Icahn School of Medicine at Mount Sinai, NY, USA.

ClinicalTrials.gov (CTG) provides integrated access to structured records of thousands of randomized clinical trials (RCT). CTG functionality allows download of the entire dataset in XML format for further knowledge discovery and analytics. This study represents an instructive use case of utilizing this functionality for identifying patient representation disparities in stem cell RCTs. The goal of this study was to determine the racial and ethnic composition of stem cell clinical trials and to identify potential disparities in minority representation. The clinical trial registration portal ClinicalTrials.gov was queried to identify stem cell trials and to compare their racial and ethnic composition to the US population data. Based on our analysis of 248 available trials, we have concluded that not all races and ethnicities are adequately represented in US stem cell trials; thus, concerted efforts are warranted for more inclusive representation of minorities in future stem cell trials.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200569DOI Listing
June 2020

Association Between System Usage Pattern and Impact of Web-Based Telerehabilitation in Patients with Multiple Sclerosis.

Stud Health Technol Inform 2020 Jun;272:346-349

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

Patients with multiple sclerosis (PwMS) increasingly use online services for managing their healthcare. The objective of this study was to investigate web log data (weblogs) generated by PwMS in the process of web-based telerehabilitation and correlate them with rehabilitation progress. The weblogs from 17 patients (female: 15, male 2; mean age: 60.1±11.4 years) were tracked for an average period of 153.6±38.3 days with the total number of log events and page visit records of 1,457 and 37,030, respectively. The time and frequency of patients' web visits were investigated as well as their adherence to prescribed exercise regimen. Rehabilitation progress was gauged by changes in quality of life, mobility, and sleep ascertained by measuring MSQOL, 2MWT and PSQI respectively. The changes in these metrics were correlated with system usage patterns. On average, PwMS visited 30 pages a day for 26.5 minutes, with a single login amounting for 27 pages in duration of 22.0 minutes. The average exercise program comprised 6.9 sets and 29.1 repetitions with average set and repetition completion rates of 46.5% and 72.6% respectively. A statistically significant association has been found between time spent in the online exercise mode and clinical improvements. The results of the study demonstrate that the patients had more pronounced outcome improvements when they increased the time of using the telerehabilitation system for home-based exercise. The results of this study could contribute to the development of more efficient home-based telerehabilitation systems.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200566DOI Listing
June 2020

Towards Intelligent Integration and Sharing of Stem Cell Research Data.

Stud Health Technol Inform 2020 Jun;272:334-337

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

Advancements in regenerative medicine have brought to the fore the need for increased standardization and sharing of stem cell product characterization to help drive these innovative interventions toward public availability. Although numerous attempts have been made to store this data, there is still a lack of a platform that incorporates heterogeneous stem cell information into a harmonized project-based framework. The aim of this project was to introduce and pilot-test an intelligent informatics solution which integrates diverse stem cell product characteristics with study subject and omics information. In the resulting platform, heterogeneous data is validated using predefined ontologies and stored in a NoSQL repository. Pilot-testing was performed on nine sponsored stem cell projects conducting preclinical and intervention evaluations. The pilot-testing demonstrated the robustness of the proposed platform, by seamlessly harmonizing diverse common data elements, and the potential of this platform for driving knowledge generation from the aggregation of this shared data.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200563DOI Listing
June 2020

Fitbit Accuracy Depends on Activity Pace and Placement Location.

Stud Health Technol Inform 2020 Jun;272:310-313

Icahn School of Medicine at Mount Sinai, NY, USA.

This study is designed to measure the concordance of step counts recorded by Fitbit activity trackers when the devices are placed on multiple locations of the body and while subjects climb stairs at fast, slow, and medium paces. Nine participants wore 5 Fitbit trackers concurrently while performing the stair-climbing activity. The level of concordance was characterized by variability metrics derived from five step counts obtained for each study participant at each climbing pace. Results of one-way ANOVA analysis revealed statistically significant difference between mean variance, standard deviation (SD) and range of step count measurements depending on location of tracker and pace of movement. Stair climbing at a 'medium pace' produced the least variance (25.9±24.5) with smallest SD (4.0±2.3), whereas the 'slow pace' trial produced the greatest variance (1770.9±3307.5) and SD (27.6±27.1). Discordance between Fitbit step count measurements obtained at different activity levels may affect overall accuracy of step count reporting.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200557DOI Listing
June 2020

Association Between Number of Actionable Pharmacogenetic Variants and Length of Hospital Stay.

Stud Health Technol Inform 2020 Jun;272:195-198

Columbia University Irving Medical Center, USA.

The goal of this study was to evaluate association between number of pharmacogenetic variants and length of hospital stay. Electronic medical records were combined with exome sequencing results in 450 hospitalized patients. De-identified data set was used to characterize urgent care utilization and to identify presence of 44 actionable pharmacogenetic variants according to the guidelines of the Clinical Pharmacogenetics Implementation Consortium. The average age was 58.03 ± 16.47 ranging from 20 to 91 years old, average number of pharmacogenetic variants was 61.22 ± 26.52 ranging from 20 to 169, and mean length of hospital stay was 6.50 ± 4.29 ranging between 1 and 42 days. After adjusting for patient socio-demographics and overall disease severity reflected by the Charlson comorbidity index, a significant association between mean length of stay and number of pharmacogenetic variants was found using generalized linear regression (p-value < 2.2e-16).
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200527DOI Listing
June 2020

Unsupervised Machine Learning for the Discovery of Latent Clusters in COVID-19 Patients Using Electronic Health Records.

Stud Health Technol Inform 2020 Jun;272:1-4

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

The goal of this paper was to apply unsupervised machine learning techniques towards the discovery of latent clusters in COVID-19 patients. Over 6,000 adult patients tested positive for the SARS-CoV-2 infection at the Mount Sinai Health System in New York, USA met the inclusion criteria for analysis. Patients' diagnoses were mapped onto chronicity and one of the 18 body systems, and the optimal number of clusters was determined using K-means algorithm and the elbow method. 4 clusters were identified; the most frequently associated comorbidities involved infectious, respiratory, cardiovascular, endocrine, and genitourinary disorders, as well as socioeconomic factors that influence health status and contact with health services. These results offer a strong direction for future research and more granular analysis.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200478DOI Listing
June 2020

Data Integration Approaches for Representing Stem Cell Studies.

Stud Health Technol Inform 2020 Jun;270:1235-1236

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

The aim of this study was to examine existing methods for sharing results of stem cell research via online data repositories. To identify the relevant repositories, a PubMed search was conducted using standard MeSH terms which was followed by a web-based search of relevant databases. The search yielded 16 databases created between 2010 and 2019. The review of databases identified 35 major rubrics and their sub-rubrics organized in a five-module system. Data integration approaches were characterized by three domains (common data elements, data visualization and analysis tools, and ontology mapping) which varied widely across the databases. Current state of stem cell data integration lacks reproducibility and standardization. Standardization of data integration approaches for representing stem cell studies is necessary to facilitate data sharing.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200379DOI Listing
June 2020

Towards a Highly Usable, Mobile Electronic Platform for Patient Recruitment and Consent Management.

Stud Health Technol Inform 2020 Jun;270:1066-1070

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

This study seeks to assess usability and acceptance of E-Consent on mobile devices such as tablet computers for collecting universal biobank consents. Usability inspection occurred via cognitive walkthroughs and heuristics evaluations, supplemented by surveys to capture health literacy, patient engagement, and other metrics. 17 patients of varied ages, backgrounds, and occupations participated in the study. The System Usability Scale (SUS) provided a standardized reference for usability and satisfaction, and the mean result of 84.4 placed this mobile iteration in the top 10th percentile. A semi-structured qualitative interview provided copious actionable feedback, which will inform the next iteration of this project. Overall, this implementation of the E-Consent framework on mobile devices was considered easy-to-use, satisfying, and engaging, allowing users to progress through the consent materials at their own pace. The platform has once again demonstrated high usability and high levels of user acceptance, this time in a novel setting.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200325DOI Listing
June 2020

Relationship Between Exercise Duration in Multimodal Telerehabilitation and Quality of Sleep in Patients with Multiple Sclerosis.

Stud Health Technol Inform 2020 Jun;270:658-662

Icahn School of Medicine at Mount Sinai.

The purpose of this study was to investigate the effect of a telerehabilitation system on the quality of sleep in patients with multiple sclerosis (PwMS). Fifteen females and two males (60.1 ± 11.4 years) who used the system for three months completed the Pittsburg Sleep Quality Index (PSQI) at the baseline and end of follow-up. Total System Usage (TSU) and Total Exercise Time (TET) were elucidated from the system web logs for each PwMS. A significant association (p<0.05) was found between PSQI sleep efficiency (SE) and TSU (0.76) and between SE and TET (0.81). The association between PSQI total score (TS) and TSU and between TS and TET were -0.507 and -0.702 respectively (p<0.05). Our results uncovered an association between amount of exercise time spent by PwMS and positive effects on both the efficiency and quality of sleep. Thus, further development of approaches promoting continuous participation of PwMS in telerehabilitation is warranted.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200242DOI Listing
June 2020

Using Big Data Analytics to Identify Dentists with Frequent Future Malpractice Claims.

Stud Health Technol Inform 2020 Jun;270:489-493

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

Healthcare spending has been growing at an increasing rate in the US, due in part to medical malpractice costs. Dental malpractice is an area that has not been studied in depth. Using National Practitioner Data Bank (NPDB), we explored the extent of dental malpractice claims and sought to construct a predictive model that can help us identify dental practitioners at risk of performing medical malpractice. Over 1,500 dental malpractice claims were reported annually, and over $1.7 billion being paid out by medical malpractice insurers over the past 15 years. Majority of claims resulted in minor injuries, and the number of major injury claims increased over years. In prediction, we randomly split the data into train (75%) and test (25%) datasets. We trained and tuned models using 5-fold cross validation on the training set. Then, we fitted the model on the test data for performance measures. We used Logistic Regression, Random Forest (RF) and XGBoost and tuned the hypermeters of models accordingly through grid search and cross validation. XGBoost was the best machine learning model to predict the risk of dentists having several malpractice reports. The best performing model had an accuracy of 72.8% with 30.6% F1 score. The NPDB database is a valuable dataset to study dental malpractice claims. Further analysis of information extracted from this dataset is warranted.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.3233/SHTI200208DOI Listing
June 2020

Clinical Characteristics of Hospitalized Covid-19 Patients in New York City.

medRxiv 2020 Apr 23. Epub 2020 Apr 23.

Background: The coronavirus 2019 (Covid-19) pandemic is a global public health crisis, with over 1.6 million cases and 95,000 deaths worldwide. Data are needed regarding the clinical course of hospitalized patients, particularly in the United States. Methods Demographic, clinical, and outcomes data for patients admitted to five Mount Sinai Health System hospitals with confirmed Covid-19 between February 27 and April 2, 2020 were identified through institutional electronic health records. We conducted a descriptive study of patients who had in-hospital mortality or were discharged alive. Results A total of 2,199 patients with Covid-19 were hospitalized during the study period. As of April 2nd, 1,121 (51%) patients remained hospitalized, and 1,078 (49%) completed their hospital course. Of the latter, the overall mortality was 29%, and 36% required intensive care. The median age was 65 years overall and 75 years in those who died. Pre-existing conditions were present in 65% of those who died and 46% of those discharged. In those who died, the admission median lymphocyte percentage was 11.7%, D-dimer was 2.4 ug/ml, C-reactive protein was 162 mg/L, and procalcitonin was 0.44 ng/mL. In those discharged, the admission median lymphocyte percentage was 16.6%, D-dimer was 0.93 ug/ml, C-reactive protein was 79 mg/L, and procalcitonin was 0.09 ng/mL. Conclusions This is the largest and most diverse case series of hospitalized patients with Covid-19 in the United States to date. Requirement of intensive care and mortality were high. Patients who died typically had pre-existing conditions and severe perturbations in inflammatory markers.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1101/2020.04.19.20062117DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7277011PMC
April 2020

Utilizing User-Centered EHR Design for Systematic Deep Brain Stimulation Data Collection.

AMIA Jt Summits Transl Sci Proc 2020 30;2020:527-532. Epub 2020 May 30.

Icahn School of Medicine at Mount Sinai, New York, New York.

This project aims to assess usability and acceptance of a customized Epic-based flowsheet designed to streamline the complex workflows associated with care of patients with implanted Deep Brain Stimulators (DBS). DBS patient care workflows are markedly fragmented, requiring providers to switch between multiple disparate systems. This is the first attempt to systematically evaluate usability of a unified solution built as a flowsheet in Epic. Iterative development processes were applied, collecting formal feedback throughout. Evaluation consisted of cognitive walkthroughs, heuristic analysis, and 'think-aloud' technique. Participants completed 3 tasks and multiple questionnaires with Likert-like questions and long-form written feedback. Results demonstrate that the strengths of the flowsheet are its consistency, mapping, and affordance. System Usability Scale scores place this first version of the flowsheet above the 70th percentile with an 'above average' usability rating. Most importantly, a copious amount of actionable feedback was captured to inform the next iteration of this build.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC7233084PMC
May 2020

Informatics Approaches for Harmonized Intelligent Integration of Stem Cell Research.

Stem Cells Cloning 2020 28;13:1-20. Epub 2020 Jan 28.

Center for Bioinformatics and Data Analytics, Columbia University, New York, NY, USA.

As biomedical data integration and analytics play an increasing role in the field of stem cell research, it becomes important to develop ways to standardize, aggregate, and share data among researchers. For this reason, many databases have been developed in recent years in an attempt to systematically warehouse data from different stem cell projects and experiments at the same time. However, these databases vary widely in their implementation and structure. The aim of this scoping review is to characterize the main features of available stem cell databases in order to identify specifications useful for implementation in future stem cell databases. We conducted a scoping review of peer-reviewed literature and online resources to identify and review available stem cell databases. To identify the relevant databases, we performed a PubMed search using relevant MeSH terms followed by a web search for databases which may not have an associated journal article. In total, we identified 16 databases to include in this review. The data elements reported in these databases represented a broad spectrum of parameters from basic socio-demographic variables to various cells characteristics, cell surface markers expression, and clinical trial results. Three broad sets of functional features that provide utility for future stem cell research and facilitate bioinformatics workflows were identified. These features consisted of the following: common data elements, data visualization and analysis tools, and biomedical ontologies for data integration. Stem cell bioinformatics is a quickly evolving field that generates a growing number of heterogeneous data sets. Further progress in the stem cell research may be greatly facilitated by development of applications for intelligent stem cell data aggregation, sharing and collaboration process.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.2147/SCCAA.S237361DOI Listing
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC6996484PMC
January 2020

Implant Failure Prediction Using Discriminant Analysis.

Annu Int Conf IEEE Eng Med Biol Soc 2019 Jul;2019:3433-3437

Electronic dental records (EDR) provide access to a vast repository of clinical information which may be used for analyzing dental care delivery. The goal of this study was identification of determinants of implant survival and development of implant failure prediction model using large data set of intact and failed implant parameters extracted from EDR. A retrospective analysis of 19 variables reflecting patient, surgeon and dental treatment characteristics of 800 dental implants was performed using discriminant analysis to develop a predictive model identifying potential implant failure based on characteristics routinely available in a clinical care setting. The intact and failed implant characteristics were compared using the Goodman and Kruskal's lambda test, the point-biserial test, the chi-square test, and ANOVA test. A stepwise discriminant analysis reduced model dimensionality from 19 to 4 features. The final discriminant analysis model included the following variables: non-temporary implant, pre-op antibiotics, immunocompromised status, and gender. Overall, 72% of implant failure cases and 62% of intact implants were correctly identified by the resulting discriminant function. As the final predictive feature set is readily available in EDR, the resulting algorithm may be implemented as a clinical decision support module embedded into EDR to promote personalized approach in dental implant patients.
View Article and Find Full Text PDF

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC.2019.8856783DOI Listing
July 2019
-->