Michael Simonov
Michael Simonov has a total of 108 co-authors. Here are the top co-authors by number of shared publications:
- Francis Perry Wilson
Clinical and Translational Research Accelerator, Department of Medicine, Yale School of Medicine, New Haven, CT
7 shared publications - Yu Yamamoto
Yale University School of Medicine, New Haven, Connecticut
6 shared publications - Dennis Legen Shung
Division of Gastroenterology and Hepatology, Department of Medicine, Mayo Clinic, Rochester, MN, USA; Department of Artificial Intelligence and Informatics, Mayo Clinic, Rochester, MN, USA
5 shared publications - Smita Krishnaswamy
Department of Computer Science, Yale University, New Haven, USA
4 shared publications - Aditya Biswas
Clinical and Translational Research Accelerator, Yale School of Medicine, Yale University, New Haven, CT, United States
3 shared publications - Allen Hsiao
Department of Pediatrics, Yale University School of Medicine, New Haven, CT, United States
3 shared publications
Latest Publications
- Open Access
- 3 September 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8  (1) , e52120
Promoting Collaborative Scholarship During the COVID-19 Pandemic Through an Innovative COVID-19 Data Explorer and Repository at Yale School of Medicine: Development and Usability Study
Background: The COVID-19 pandemic sparked a surge of research publications spanning epidemiology, basic science, and clinical science. Thanks to the digital revolution, large data sets are now accessible, which also enables real-time epidemic tracking. However, despite this, academic faculty and their trainees have been struggling to access comprehensive clinical data. To tackle this issue, we have devised a clinical data repository that streamlines research processes and promotes interdisciplinary collaboration. Objective: This study aimed to present an easily accessible up-to-date database that promotes access to local COVID-19 clinical data, thereby increasing efficiency, streamlining, and democratizing the research enterprise. By providing a robust database, a broad range of researchers (faculty and trainees) and clinicians from different areas of medicine are encouraged to explore and collaborate on novel clinically relevant research questions. Methods: A research platform, called the Yale Department of Medicine COVID-19 Explorer and Repository (DOM-CovX), was constructed to house cleaned, highly granular, deidentified, and continually updated data from over 18,000 patients hospitalized with COVID-19 from January 2020 to January 2023, across the Yale New Haven Health System. Data across several key domains were extracted including demographics, past medical history, laboratory values during hospitalization, vital signs, medications, imaging, procedures, and outcomes. Given the time-varying nature of several data domains, summary statistics were constructed to limit the computational size of the database and provide a reasonable data file that the broader research community could use for basic statistical analyses. The initiative also included a front-end user interface, the DOM-CovX Explorer, for simple data visualization of aggregate data. The detailed clinical data sets were made available for researchers after a review board process. Results: As of January 2023, the DOM-CovX Explorer has received 38 requests from different groups of scientists at Yale and the repository has expanded research capability to a diverse group of stakeholders including clinical and research-based faculty and trainees within 15 different surgical and nonsurgical specialties. A dedicated DOM-CovX team guides access and use of the database, which has enhanced interdepartmental collaborations, resulting in the publication of 16 peer-reviewed papers, 2 projects available in preprint servers, and 8 presentations in scientific conferences. Currently, the DOM-CovX Explorer continues to expand and improve its interface. The repository includes up to 3997 variables across 7 different clinical domains, with continued growth in response to researchers’ requests and data availability. Conclusions: The DOM-CovX Data Explorer and Repository is a user-friendly tool for analyzing data and accessing a consistently updated, standardized, and large-scale database. Its innovative approach fosters collaboration, diversity of scholarly pursuits, and expands medical education. In addition, it can be applied to other diseases beyond COVID-19.
- 3 September 2024
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 8  (1) , e52120
Open AccessPromoting Collaborative Scholarship During the COVID-19 Pandemic Through an Innovative COVID-19 Data Explorer and Repository at Yale School of Medicine: Development and Usability Study
Background: The COVID-19 pandemic sparked a surge of research publications spanning epidemiology, basic science, and clinical science. Thanks to the digital revolution, large data sets are now accessible, which also enables real-time epidemic tracking. However, despite this, academic faculty and their trainees have been struggling to access comprehensive clinical data. To tackle this issue, we have devised a clinical data repository that streamlines research processes and promotes interdisciplinary collaboration. Objective: This study aimed to present an easily accessible up-to-date database that promotes access to local COVID-19 clinical data, thereby increasing efficiency, streamlining, and democratizing the research enterprise. By providing a robust database, a broad range of researchers (faculty and trainees) and clinicians from different areas of medicine are encouraged to explore and collaborate on novel clinically relevant research questions. Methods: A research platform, called the Yale Department of Medicine COVID-19 Explorer and Repository (DOM-CovX), was constructed to house cleaned, highly granular, deidentified, and continually updated data from over 18,000 patients hospitalized with COVID-19 from January 2020 to January 2023, across the Yale New Haven Health System. Data across several key domains were extracted including demographics, past medical history, laboratory values during hospitalization, vital signs, medications, imaging, procedures, and outcomes. Given the time-varying nature of several data domains, summary statistics were constructed to limit the computational size of the database and provide a reasonable data file that the broader research community could use for basic statistical analyses. The initiative also included a front-end user interface, the DOM-CovX Explorer, for simple data visualization of aggregate data. The detailed clinical data sets were made available for researchers after a review board process. Results: As of January 2023, the DOM-CovX Explorer has received 38 requests from different groups of scientists at Yale and the repository has expanded research capability to a diverse group of stakeholders including clinical and research-based faculty and trainees within 15 different surgical and nonsurgical specialties. A dedicated DOM-CovX team guides access and use of the database, which has enhanced interdepartmental collaborations, resulting in the publication of 16 peer-reviewed papers, 2 projects available in preprint servers, and 8 presentations in scientific conferences. Currently, the DOM-CovX Explorer continues to expand and improve its interface. The repository includes up to 3997 variables across 7 different clinical domains, with continued growth in response to researchers’ requests and data availability. Conclusions: The DOM-CovX Data Explorer and Repository is a user-friendly tool for analyzing data and accessing a consistently updated, standardized, and large-scale database. Its innovative approach fosters collaboration, diversity of scholarly pursuits, and expands medical education. In addition, it can be applied to other diseases beyond COVID-19.
- Open Access
Time to Hyperkalemia and Other Outcomes Post-Implementation of the 2021 CKD-EPI Creatinine Equation: An Observational Cohort Study
Background Timely diagnosis can delay progression to poor clinical outcomes and biomarker endpoints in CKD. Our objective was to analyze how the implementation of the 2021 CKD-EPI Creatinine Equation (CKD-EPI 2021) affected time to the doubling of serum creatinine, prescription or dispense of potassium-lowering drugs, hyperkalemia, and creation of arteriovenous graft fistula for dialysis within one year of CKD diagnosis. Methods We used retrospective EHR data to create two cohorts of adult patients based on date of diagnosis. We followed patients from their CKD diagnosis to the occurrence of each outcome, their last medical encounter, or 1-year post diagnosis, whichever occurred first. The first cohort was diagnosed in 2021 when the CKD-EPI 2009 Creatinine Equation (pre-update cohort) was recommended. The second cohort was diagnosed in 2022 when CKD-EPI 2021 (post-update cohort) was recommended. Multivariable models for the time relationship between cohort and each outcome were adjusted for demographics, social determinants of health, and comorbidities. As CKD-EPI 2021 was race-free, we also considered the interaction between cohort and race. Results We found 261,774 patients with a first-time CKD diagnosis. After implementation of CKD-EPI 2021, patients were less likely to have a diagnosis of hyperkalemia, potassium-lowering drug prescription, a doubling of serum creatinine, or an arteriovenous graft fistula placement within a year of CKD diagnosis. Black patients in the post-update cohort were less likely to be diagnosed with hyperkalemia compared to Black patients in the pre-update cohort (AHR 0.83; CI 0.80, 0.86), but Black patients overall were significantly more likely than non-Black patients to have hyperkalemia. Conclusions Time to poor clinical outcomes and biomarkers differs by the date of CKD diagnosis. Future work should elucidate the mechanisms driving these differences, whether there have been significant changes in treatment practices since the CKD-EPI 2021 recommendation, and long-term effects of each outcome.
Open AccessTime to Hyperkalemia and Other Outcomes Post-Implementation of the 2021 CKD-EPI Creatinine Equation: An Observational Cohort Study
Background Timely diagnosis can delay progression to poor clinical outcomes and biomarker endpoints in CKD. Our objective was to analyze how the implementation of the 2021 CKD-EPI Creatinine Equation (CKD-EPI 2021) affected time to the doubling of serum creatinine, prescription or dispense of potassium-lowering drugs, hyperkalemia, and creation of arteriovenous graft fistula for dialysis within one year of CKD diagnosis. Methods We used retrospective EHR data to create two cohorts of adult patients based on date of diagnosis. We followed patients from their CKD diagnosis to the occurrence of each outcome, their last medical encounter, or 1-year post diagnosis, whichever occurred first. The first cohort was diagnosed in 2021 when the CKD-EPI 2009 Creatinine Equation (pre-update cohort) was recommended. The second cohort was diagnosed in 2022 when CKD-EPI 2021 (post-update cohort) was recommended. Multivariable models for the time relationship between cohort and each outcome were adjusted for demographics, social determinants of health, and comorbidities. As CKD-EPI 2021 was race-free, we also considered the interaction between cohort and race. Results We found 261,774 patients with a first-time CKD diagnosis. After implementation of CKD-EPI 2021, patients were less likely to have a diagnosis of hyperkalemia, potassium-lowering drug prescription, a doubling of serum creatinine, or an arteriovenous graft fistula placement within a year of CKD diagnosis. Black patients in the post-update cohort were less likely to be diagnosed with hyperkalemia compared to Black patients in the pre-update cohort (AHR 0.83; CI 0.80, 0.86), but Black patients overall were significantly more likely than non-Black patients to have hyperkalemia. Conclusions Time to poor clinical outcomes and biomarkers differs by the date of CKD diagnosis. Future work should elucidate the mechanisms driving these differences, whether there have been significant changes in treatment practices since the CKD-EPI 2021 recommendation, and long-term effects of each outcome.
- Open Access
Effects of changes in calculating GFR using KDIGO standards: Discordance in the Staging and Timing of Diagnosis of Chronic Kidney Disease
Introduction Chronic kidney disease (CKD) is a highly prevalent disease with disparities in diagnosis and treatment. Until recently, primary diagnosis for CKD was based on equations that incorporated race and have demonstrated racial bias. This study had two aims comparing outcomes for Black patients and their counterparts: 1) whether using the new 2021 CKD-EPI equation led to decreased disparity with time to diagnosis; and 2) whether there was discordance in the staging between the two equations at potential diagnosis point. Methods We evaluated patients aged 18 and over with non-hospitalization related serum creatinine laboratory results between January 1, 2016 and September 30, 2023. We estimated the GFR for each patient using the 2009 and 2021 CKD-EPI creatinine equations. We assessed stage discordance for stages 3a, 3b, 4, and 5 using chi-square tests and the Cochran-Mantel-Haenszel. We used multivariate logistic regression to assess a change in staging based on the equation used. Results 15.5% of the 8,080,889 patients included in this study were Black. The median age was 57 years and 15.3% of patients met the criteria for stage 3a CKD or higher using either equation. Discordance in staging by equation and by race existed, especially for Black patients at stages 3a and 3b. 40% of Black patients identified as stage 4 using the 2021 equation were 3b or lower using the 2009 equation. Discussion Well established medical algorithms with race components are being re-examined. We found more disparity with the initial staging of the disease. The disconnect in the timing of staging by equation for Black patients means a number of these patients may not have received the appropriate treatment. Future work should elucidate the impact of the change in CKD staging with the 2021 CKD-EPI creatinine equation on treatment. Conclusion Significant disparity exists in the timing and staging of CKD by CKD-EPI equation and by race.
Open AccessEffects of changes in calculating GFR using KDIGO standards: Discordance in the Staging and Timing of Diagnosis of Chronic Kidney Disease
Introduction Chronic kidney disease (CKD) is a highly prevalent disease with disparities in diagnosis and treatment. Until recently, primary diagnosis for CKD was based on equations that incorporated race and have demonstrated racial bias. This study had two aims comparing outcomes for Black patients and their counterparts: 1) whether using the new 2021 CKD-EPI equation led to decreased disparity with time to diagnosis; and 2) whether there was discordance in the staging between the two equations at potential diagnosis point. Methods We evaluated patients aged 18 and over with non-hospitalization related serum creatinine laboratory results between January 1, 2016 and September 30, 2023. We estimated the GFR for each patient using the 2009 and 2021 CKD-EPI creatinine equations. We assessed stage discordance for stages 3a, 3b, 4, and 5 using chi-square tests and the Cochran-Mantel-Haenszel. We used multivariate logistic regression to assess a change in staging based on the equation used. Results 15.5% of the 8,080,889 patients included in this study were Black. The median age was 57 years and 15.3% of patients met the criteria for stage 3a CKD or higher using either equation. Discordance in staging by equation and by race existed, especially for Black patients at stages 3a and 3b. 40% of Black patients identified as stage 4 using the 2021 equation were 3b or lower using the 2009 equation. Discussion Well established medical algorithms with race components are being re-examined. We found more disparity with the initial staging of the disease. The disconnect in the timing of staging by equation for Black patients means a number of these patients may not have received the appropriate treatment. Future work should elucidate the impact of the change in CKD staging with the 2021 CKD-EPI creatinine equation on treatment. Conclusion Significant disparity exists in the timing and staging of CKD by CKD-EPI equation and by race.
- Open Access
- 29 August 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Promoting Collaborative Scholarship During the COVID-19 Pandemic Through an Innovative COVID-19 Data Explorer and Repository at Yale School of Medicine: Development and Usability Study (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The COVID-19 pandemic sparked a surge of research publications spanning epidemiology, basic science, and clinical science. Thanks to the digital revolution, large data sets are now accessible, which also enables real-time epidemic tracking. However, despite this, academic faculty and their trainees have been struggling to access comprehensive clinical data. To tackle this issue, we have devised a clinical data repository that streamlines research processes and promotes interdisciplinary collaboration. Objective: This study aimed to present an easily accessible up-to-date database that promotes access to local COVID-19 clinical data, thereby increasing efficiency, streamlining, and democratizing the research enterprise. By providing a robust database, a broad range of researchers (faculty and trainees) and clinicians from different areas of medicine are encouraged to explore and collaborate on novel clinically relevant research questions. Methods: A research platform, called the Yale Department of Medicine COVID-19 Explorer and Repository (DOM-CovX), was constructed to house cleaned, highly granular, deidentified, and continually updated data from over 18,000 patients hospitalized with COVID-19 from January 2020 to January 2023, across the Yale New Haven Health System. Data across several key domains were extracted including demographics, past medical history, laboratory values during hospitalization, vital signs, medications, imaging, procedures, and outcomes. Given the time-varying nature of several data domains, summary statistics were constructed to limit the computational size of the database and provide a reasonable data file that the broader research community could use for basic statistical analyses. The initiative also included a front-end user interface, the DOM-CovX Explorer, for simple data visualization of aggregate data. The detailed clinical data sets were made available for researchers after a review board process. Results: As of January 2023, the DOM-CovX Explorer has received 38 requests from different groups of scientists at Yale and the repository has expanded research capability to a diverse group of stakeholders including clinical and research-based faculty and trainees within 15 different surgical and nonsurgical specialties. A dedicated DOM-CovX team guides access and use of the database, which has enhanced interdepartmental collaborations, resulting in the publication of 16 peer-reviewed papers, 2 projects available in preprint servers, and 8 presentations in scientific conferences. Currently, the DOM-CovX Explorer continues to expand and improve its interface. The repository includes up to 3997 variables across 7 different clinical domains, with continued growth in response to researchers’ requests and data availability. Conclusions: The DOM-CovX Data Explorer and Repository is a user-friendly tool for analyzing data and accessing a consistently updated, standardized, and large-scale database. Its innovative approach fosters collaboration, diversity of scholarly pursuits, and expands medical education. In addition, it can be applied to other diseases beyond COVID-19. Trial Registration:
- 29 August 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessPromoting Collaborative Scholarship During the COVID-19 Pandemic Through an Innovative COVID-19 Data Explorer and Repository at Yale School of Medicine: Development and Usability Study (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: The COVID-19 pandemic sparked a surge of research publications spanning epidemiology, basic science, and clinical science. Thanks to the digital revolution, large data sets are now accessible, which also enables real-time epidemic tracking. However, despite this, academic faculty and their trainees have been struggling to access comprehensive clinical data. To tackle this issue, we have devised a clinical data repository that streamlines research processes and promotes interdisciplinary collaboration. Objective: This study aimed to present an easily accessible up-to-date database that promotes access to local COVID-19 clinical data, thereby increasing efficiency, streamlining, and democratizing the research enterprise. By providing a robust database, a broad range of researchers (faculty and trainees) and clinicians from different areas of medicine are encouraged to explore and collaborate on novel clinically relevant research questions. Methods: A research platform, called the Yale Department of Medicine COVID-19 Explorer and Repository (DOM-CovX), was constructed to house cleaned, highly granular, deidentified, and continually updated data from over 18,000 patients hospitalized with COVID-19 from January 2020 to January 2023, across the Yale New Haven Health System. Data across several key domains were extracted including demographics, past medical history, laboratory values during hospitalization, vital signs, medications, imaging, procedures, and outcomes. Given the time-varying nature of several data domains, summary statistics were constructed to limit the computational size of the database and provide a reasonable data file that the broader research community could use for basic statistical analyses. The initiative also included a front-end user interface, the DOM-CovX Explorer, for simple data visualization of aggregate data. The detailed clinical data sets were made available for researchers after a review board process. Results: As of January 2023, the DOM-CovX Explorer has received 38 requests from different groups of scientists at Yale and the repository has expanded research capability to a diverse group of stakeholders including clinical and research-based faculty and trainees within 15 different surgical and nonsurgical specialties. A dedicated DOM-CovX team guides access and use of the database, which has enhanced interdepartmental collaborations, resulting in the publication of 16 peer-reviewed papers, 2 projects available in preprint servers, and 8 presentations in scientific conferences. Currently, the DOM-CovX Explorer continues to expand and improve its interface. The repository includes up to 3997 variables across 7 different clinical domains, with continued growth in response to researchers’ requests and data availability. Conclusions: The DOM-CovX Data Explorer and Repository is a user-friendly tool for analyzing data and accessing a consistently updated, standardized, and large-scale database. Its innovative approach fosters collaboration, diversity of scholarly pursuits, and expands medical education. In addition, it can be applied to other diseases beyond COVID-19. Trial Registration:
- Open Access
Risk of COVID-19 breakthrough infection and hospitalization in individuals with comorbidities
Background Studies have shown that those with certain high-risk comorbidities such as diabetes, chronic kidney disease (CKD), chronic lung disease, or those with immunocompromising conditions have increased risk of hospitalization from COVID-19. Here we estimate the elevated risks of breakthrough infection and hospitalization in fully vaccinated individuals with comorbidities. Methods Using a population of fully-vaccinated patients in the de-identified Truveta Platform of electronic health records from January 1, 2019, to January 10, 2022, we used logistic regression to estimate risk of 1) a patient experiencing a breakthrough COVID-19 infection after being fully vaccinated, and 2) rate of hospitalization in those experiencing breakthrough infection. Potential confounding was adjusted with inverse probability weighting for each comorbidity by age, race, ethnicity, and sex. We present ORs and percentages of breakthrough infections by comorbidity status. Results Of 3,424,965 fully vaccinated patients, 2.79%, 2.63%, 2.38%, 1.83% with CKD, chronic lung disease, diabetes, and those in an immunocompromised state experienced breakthrough infection, respectively, compared to 1.95% in the overall population. All cormorbidities were associated with significantly increased odds of breakthrough infections and subsequent hospitalizations. Breakthrough infection hospitalizations in populations with comorbidities ranged from 26.43% for CKD to 10.23% for chronic lung disease, with corresponding ORs of 2.22 (95% CI: 1.88 - 2.63) and 1.37 (95% CI: 1.21 - 1.55), respectively. Conclusions Fully-vaccinated individuals with certain comorbidities experienced increased risk of breakthrough COVID-19 infection and subsequent hospitalizations compared to the general population. Individuals with comorbidities should remain vigilant against infection even if vaccinated. Highlights COVID-19 infection has greater severity in those with comorbidities. Here we investigate the risk of breakthrough infections and hospitalizations in fully-vaccinated individuals with and without comorbidities. We find increased rates of breakthrough infections with all comorbidities, with CKD having the greatest risk. Individuals with chronic lung disease had the highest rate of breakthrough infection, but the lowest subsequent risk of hospitalization. Individuals with comorbidities should remain vigilant against infection even if vaccinated.
Open AccessRisk of COVID-19 breakthrough infection and hospitalization in individuals with comorbidities
Background Studies have shown that those with certain high-risk comorbidities such as diabetes, chronic kidney disease (CKD), chronic lung disease, or those with immunocompromising conditions have increased risk of hospitalization from COVID-19. Here we estimate the elevated risks of breakthrough infection and hospitalization in fully vaccinated individuals with comorbidities. Methods Using a population of fully-vaccinated patients in the de-identified Truveta Platform of electronic health records from January 1, 2019, to January 10, 2022, we used logistic regression to estimate risk of 1) a patient experiencing a breakthrough COVID-19 infection after being fully vaccinated, and 2) rate of hospitalization in those experiencing breakthrough infection. Potential confounding was adjusted with inverse probability weighting for each comorbidity by age, race, ethnicity, and sex. We present ORs and percentages of breakthrough infections by comorbidity status. Results Of 3,424,965 fully vaccinated patients, 2.79%, 2.63%, 2.38%, 1.83% with CKD, chronic lung disease, diabetes, and those in an immunocompromised state experienced breakthrough infection, respectively, compared to 1.95% in the overall population. All cormorbidities were associated with significantly increased odds of breakthrough infections and subsequent hospitalizations. Breakthrough infection hospitalizations in populations with comorbidities ranged from 26.43% for CKD to 10.23% for chronic lung disease, with corresponding ORs of 2.22 (95% CI: 1.88 - 2.63) and 1.37 (95% CI: 1.21 - 1.55), respectively. Conclusions Fully-vaccinated individuals with certain comorbidities experienced increased risk of breakthrough COVID-19 infection and subsequent hospitalizations compared to the general population. Individuals with comorbidities should remain vigilant against infection even if vaccinated. Highlights COVID-19 infection has greater severity in those with comorbidities. Here we investigate the risk of breakthrough infections and hospitalizations in fully-vaccinated individuals with and without comorbidities. We find increased rates of breakthrough infections with all comorbidities, with CKD having the greatest risk. Individuals with chronic lung disease had the highest rate of breakthrough infection, but the lowest subsequent risk of hospitalization. Individuals with comorbidities should remain vigilant against infection even if vaccinated.
- Open Access
- 12 May 2021
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16  (5) , e0251376
Predicting patients with false negative SARS-CoV-2 testing at hospital admission: A retrospective multi-center study
Importance: False negative SARS-CoV-2 tests can lead to spread of infection in the inpatient setting to other patients and healthcare workers. However, the population of patients with COVID who are admitted with false negative testing is unstudied. Objective: To characterize and develop a model to predict true SARS-CoV-2 infection among patients who initially test negative for COVID by PCR. Design: Retrospective cohort study. Setting: Five hospitals within the Yale New Haven Health System between 3/10/2020 and 9/1/2020. Participants: Adult patients who received diagnostic testing for SARS-CoV-2 virus within the first 96 hours of hospitalization. Exposure: We developed a logistic regression model from readily available electronic health record data to predict SARS-CoV-2 positivity in patients who were positive for COVID and those who were negative and never retested. Main outcomes and measures: This model was applied to patients testing negative for SARS-CoV-2 who were retested within the first 96 hours of hospitalization. We evaluated the ability of the model to discriminate between patients who would subsequently retest negative and those who would subsequently retest positive. Results: We included 31,459 hospitalized adult patients; 2,666 of these patients tested positive for COVID and 3,511 initially tested negative for COVID and were retested. Of the patients who were retested, 61 (1.7%) had a subsequent positive COVID test. The model showed that higher age, vital sign abnormalities, and lower white blood cell count served as strong predictors for COVID positivity in these patients. The model had moderate performance to predict which patients would retest positive with a test set area under the receiver-operator characteristic (ROC) of 0.76 (95% CI 0.70–0.83). Using a cutpoint for our risk prediction model at the 90th percentile for probability, we were able to capture 35/61 (57%) of the patients who would retest positive. This cutpoint amounts to a number-needed-to-retest range between 15 and 77 patients. Conclusion and relevance: We show that a pragmatic model can predict which patients should be retested for COVID. Further research is required to determine if this risk model can be applied prospectively in hospitalized patients to prevent the spread of SARS-CoV-2 infections.
- 12 May 2021
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 16  (5) , e0251376
Open AccessPredicting patients with false negative SARS-CoV-2 testing at hospital admission: A retrospective multi-center study
Importance: False negative SARS-CoV-2 tests can lead to spread of infection in the inpatient setting to other patients and healthcare workers. However, the population of patients with COVID who are admitted with false negative testing is unstudied. Objective: To characterize and develop a model to predict true SARS-CoV-2 infection among patients who initially test negative for COVID by PCR. Design: Retrospective cohort study. Setting: Five hospitals within the Yale New Haven Health System between 3/10/2020 and 9/1/2020. Participants: Adult patients who received diagnostic testing for SARS-CoV-2 virus within the first 96 hours of hospitalization. Exposure: We developed a logistic regression model from readily available electronic health record data to predict SARS-CoV-2 positivity in patients who were positive for COVID and those who were negative and never retested. Main outcomes and measures: This model was applied to patients testing negative for SARS-CoV-2 who were retested within the first 96 hours of hospitalization. We evaluated the ability of the model to discriminate between patients who would subsequently retest negative and those who would subsequently retest positive. Results: We included 31,459 hospitalized adult patients; 2,666 of these patients tested positive for COVID and 3,511 initially tested negative for COVID and were retested. Of the patients who were retested, 61 (1.7%) had a subsequent positive COVID test. The model showed that higher age, vital sign abnormalities, and lower white blood cell count served as strong predictors for COVID positivity in these patients. The model had moderate performance to predict which patients would retest positive with a test set area under the receiver-operator characteristic (ROC) of 0.76 (95% CI 0.70–0.83). Using a cutpoint for our risk prediction model at the 90th percentile for probability, we were able to capture 35/61 (57%) of the patients who would retest positive. This cutpoint amounts to a number-needed-to-retest range between 15 and 77 patients. Conclusion and relevance: We show that a pragmatic model can predict which patients should be retested for COVID. Further research is required to determine if this risk model can be applied prospectively in hospitalized patients to prevent the spread of SARS-CoV-2 infections.
- Open Access
- 23 April 2021
- Published by Springer Nature in Scientific Reports
- Vol. 11  (1) , 1-12
Neural network predicts need for red blood cell transfusion for patients with acute gastrointestinal bleeding admitted to the intensive care unit
Acute gastrointestinal bleeding is the most common gastrointestinal cause for hospitalization. For high-risk patients requiring intensive care unit stay, predicting transfusion needs during the first 24 h using dynamic risk assessment may improve resuscitation with red blood cell transfusion in admitted patients with severe acute gastrointestinal bleeding. A patient cohort admitted for acute gastrointestinal bleeding (N = 2,524) was identified from the Medical Information Mart for Intensive Care III (MIMIC-III) critical care database and separated into training (N = 2,032) and internal validation (N = 492) sets. The external validation patient cohort was identified from the eICU collaborative database of patients admitted for acute gastrointestinal bleeding presenting to large urban hospitals (N = 1,526). 62 demographic, clinical, and laboratory test features were consolidated into 4-h time intervals over the first 24 h from admission. The outcome measure was the transfusion of red blood cells during each 4-h time interval. A long short-term memory (LSTM) model, a type of Recurrent Neural Network, was compared to a regression-based models on time-updated data. The LSTM model performed better than discrete time regression-based models for both internal validation (AUROC 0.81 vs 0.75 vs 0.75;P < 0.001)and external validation (AUROC 0.65 vs 0.56 vs 0.56;P < 0.001). A LSTM model can be used to predict the need for transfusion of packed red blood cells over the first 24 h from admission to help personalize the care of high-risk patients with acute gastrointestinal bleeding.
- 23 April 2021
- Published by Springer Nature in Scientific Reports
- Vol. 11  (1) , 1-12
Open AccessNeural network predicts need for red blood cell transfusion for patients with acute gastrointestinal bleeding admitted to the intensive care unit
Acute gastrointestinal bleeding is the most common gastrointestinal cause for hospitalization. For high-risk patients requiring intensive care unit stay, predicting transfusion needs during the first 24 h using dynamic risk assessment may improve resuscitation with red blood cell transfusion in admitted patients with severe acute gastrointestinal bleeding. A patient cohort admitted for acute gastrointestinal bleeding (N = 2,524) was identified from the Medical Information Mart for Intensive Care III (MIMIC-III) critical care database and separated into training (N = 2,032) and internal validation (N = 492) sets. The external validation patient cohort was identified from the eICU collaborative database of patients admitted for acute gastrointestinal bleeding presenting to large urban hospitals (N = 1,526). 62 demographic, clinical, and laboratory test features were consolidated into 4-h time intervals over the first 24 h from admission. The outcome measure was the transfusion of red blood cells during each 4-h time interval. A long short-term memory (LSTM) model, a type of Recurrent Neural Network, was compared to a regression-based models on time-updated data. The LSTM model performed better than discrete time regression-based models for both internal validation (AUROC 0.81 vs 0.75 vs 0.75;P < 0.001)and external validation (AUROC 0.65 vs 0.56 vs 0.56;P < 0.001). A LSTM model can be used to predict the need for transfusion of packed red blood cells over the first 24 h from admission to help personalize the care of high-risk patients with acute gastrointestinal bleeding.
- 1 January 2021
- Published by Elsevier in Clinical Gastroenterology and Hepatology
- Vol. 19  (1) , 72-79.e21
Use of Proton Pump Inhibitors Increases Risk of Incident Kidney Stones
- 1 January 2021
- Published by Elsevier in Clinical Gastroenterology and Hepatology
- Vol. 19  (1) , 72-79.e21
Use of Proton Pump Inhibitors Increases Risk of Incident Kidney Stones