Your browser doesn't support javascript.
Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation.
Vaid, Akhil; Somani, Sulaiman; Russak, Adam J; De Freitas, Jessica K; Chaudhry, Fayzan F; Paranjpe, Ishan; Johnson, Kipp W; Lee, Samuel J; Miotto, Riccardo; Richter, Felix; Zhao, Shan; Beckmann, Noam D; Naik, Nidhi; Kia, Arash; Timsina, Prem; Lala, Anuradha; Paranjpe, Manish; Golden, Eddye; Danieletto, Matteo; Singh, Manbir; Meyer, Dara; O'Reilly, Paul F; Huckins, Laura; Kovatch, Patricia; Finkelstein, Joseph; Freeman, Robert M; Argulian, Edgar; Kasarskis, Andrew; Percha, Bethany; Aberg, Judith A; Bagiella, Emilia; Horowitz, Carol R; Murphy, Barbara; Nestler, Eric J; Schadt, Eric E; Cho, Judy H; Cordon-Cardo, Carlos; Fuster, Valentin; Charney, Dennis S; Reich, David L; Bottinger, Erwin P; Levin, Matthew A; Narula, Jagat; Fayad, Zahi A; Just, Allan C; Charney, Alexander W; Nadkarni, Girish N; Glicksberg, Benjamin S.
  • Vaid A; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Somani S; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Russak AJ; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • De Freitas JK; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Chaudhry FF; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Paranjpe I; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Johnson KW; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Lee SJ; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Miotto R; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Richter F; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Zhao S; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Beckmann ND; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Naik N; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Kia A; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Timsina P; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Lala A; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Paranjpe M; Department of Anesthesiology, Perioperative and Pain Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Golden E; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Danieletto M; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Singh M; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Meyer D; Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • O'Reilly PF; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Huckins L; Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Kovatch P; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Finkelstein J; The Zena and Michael A. Wiener Cardiovascular Institute, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Freeman RM; Harvard Medical School, Boston, MA, United States.
  • Argulian E; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Kasarskis A; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Percha B; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Aberg JA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Bagiella E; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Horowitz CR; The Pamela Sklar Division of Psychiatric Genomics, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Murphy B; The Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Nestler EJ; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Schadt EE; The Pamela Sklar Division of Psychiatric Genomics, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Cho JH; The Department of Psychiatry, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Cordon-Cardo C; Mount Sinai Data Warehouse, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Fuster V; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Charney DS; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Reich DL; Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Bottinger EP; Mount Sinai Heart, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Levin MA; Department of Cardiology, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Narula J; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Fayad ZA; Department of Population Health Science and Policy, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Just AC; Icahn Institute for Data Science and Genomic Technology, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Charney AW; Mount Sinai Data Office, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Nadkarni GN; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
  • Glicksberg BS; Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, United States.
J Med Internet Res ; 22(11): e24018, 2020 11 06.
Article in English | MEDLINE | ID: covidwho-979821
ABSTRACT

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.
Subject(s)
Keywords

Full text: Available Collection: International databases Database: MEDLINE Main subject: Pneumonia, Viral / Coronavirus Infections / Machine Learning Type of study: Cohort study / Diagnostic study / Observational study / Prognostic study / Randomized controlled trials Limits: Adolescent / Adult / Aged / Female / Humans / Male / Middle aged / Young adult Country/Region as subject: North America Language: English Journal: J Med Internet Res Journal subject: Medical Informatics Year: 2020 Document Type: Article Affiliation country: 24018

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Pneumonia, Viral / Coronavirus Infections / Machine Learning Type of study: Cohort study / Diagnostic study / Observational study / Prognostic study / Randomized controlled trials Limits: Adolescent / Adult / Aged / Female / Humans / Male / Middle aged / Young adult Country/Region as subject: North America Language: English Journal: J Med Internet Res Journal subject: Medical Informatics Year: 2020 Document Type: Article Affiliation country: 24018