• Skip to main content
  • Skip to secondary menu
  • Skip to primary sidebar
  • Skip to secondary sidebar
  • Skip to footer

  • Opinion
  • Health IT
    • Behavioral Health
    • Care Coordination
    • EMR/EHR
    • Interoperability
    • Patient Engagement
    • Population Health Management
    • Revenue Cycle Management
    • Social Determinants of Health
  • Digital Health
    • AI
    • Blockchain
    • Precision Medicine
    • Telehealth
    • Wearables
  • Life Sciences
  • Investments
  • M&A
  • Value-based Care
    • Accountable Care (ACOs)
    • Medicare Advantage

Mount Sinai Develop Machine Learning Models to Predict Critical Illness and Mortality in COVID-19 Patients

by Fred Pennic 11/11/2020 Leave a Comment

  • LinkedIn
  • Twitter
  • Facebook
  • Email
  • Print
Mount Sinai Develop Machine Learning Models to Predict Critical Illness and Mortality in COVID-19 Patients Mount Sinai to Deploy Lumeris Value-Based Services to Optimize Population Health Outcomes

What You Should Know:

– Mount Sinai researchers have developed machine learning models that predict the likelihood of critical events and mortality in COVID-19 patients within clinically relevant time windows.

– The new machine learning models were outlined in a recent study published in the Journal of Medical Internet Research—could aid clinical practitioners at Mount Sinai and across the world in the care and management of COVID-19 patients.


Research Protocols

– In the retrospective study using EHRs from more than 4,000 adult patients admitted to five Mount Sinai Health System hospitals from March to May, researchers and clinicians from the MSCIC analyzed characteristics of COVID-19 patients, including past medical history, comorbidities, vital signs, and laboratory test results at admission, to predict critical events such as intubation and mortality within various clinically relevant time windows that can forecast short and medium-term risks of patients over the hospitalization.

–  Researchers used the machine learning models to predict a critical event or mortality at time windows of 3, 5, 7, and 10 days from admission.

Results/Outcomes

– At the one-week mark—which performed best overall, correctly flagging the most critical events while returning the fewest false positives—acute kidney injury, fast breathing, high blood sugar, and elevated lactate dehydrogenase (LDH) indicating tissue damage or disease were the strongest drivers in predicting critical illness. Older age, blood level imbalance, and C-reactive protein levels indicating inflammation, were the strongest drivers in predicting mortality.

“From the initial outburst of COVID-19 in New York City, we saw that COVID-19 presentation and disease course are heterogeneous and we have built machine learning models using patient data to predict outcomes,” said Benjamin Glicksberg, PhD, Assistant Professor of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai, member of the Hasso Plattner Institute for Digital Health at Mount Sinai and Mount Sinai Clinical Intelligence Center (MSCIC), and one of the study’s principal investigators. “Now in the early stages of a second wave, we are much better prepared than before. We are currently assessing how these models can aid clinical practitioners in managing care of their patients in practice.”

  • LinkedIn
  • Twitter
  • Facebook
  • Email
  • Print

Tagged With: Clinical Intelligence, Coronavirus (COVID-19), digital health, Machine Learning, Mount Sinai, PhD, Vital

Tap Native

Get in-depth healthcare technology analysis and commentary delivered straight to your email weekly

Reader Interactions

Primary Sidebar

Subscribe to HIT Consultant

Latest insightful articles delivered straight to your inbox weekly.

Submit a Tip or Pitch

Featured Interview

Reach7 Diabetes Studios Founder Chun Yong on Reimagining Chronic Care with a Concierge Medical Model

Most-Read

HHS Finalizes HTI-4 Rule: Prior Authorization & E-Prescribing Interoperability

HHS Finalizes HTI-4 Rule: Prior Authorization & E-Prescribing Interoperability

Meaningful Use Penalties_Meaningful Use_Partial Code Free_Senators Urge CMS to Establish Clear Metrics for ICD-10 Testing

CMS Finalizes TEAM Model: A New Era of Value-Based Surgical Care

White House Event Unveils CMS Health Tech Ecosystem Initiative

White House Event Unveils CMS Health Tech Ecosystem Initiative

Digital Health Faces Q2'25 Pullback: Funding Falls to 5-Year Low, But AI Dominates and $1B+ IPOs Emerge

Healthcare Investment Shifts in 1H 2025: AI Remains a Bright Spot Amidst Fundraising Decline

Digital Health Faces Q2'25 Pullback: Funding Falls to 5-Year Low

Digital Health Faces Q2’25 Pullback: Funding Falls to 5-Year Low

Beyond the Hype: Building AI Systems in Healthcare Where Hallucinations Are Not an Option

Beyond the Hype: Building AI Systems in Healthcare Where Hallucinations Are Not an Option

Health IT Sector Navigates Policy Turbulence with Resilient M&A

Health IT’s New Chapter: IPOs Return, Resilient M&A, Valuations Rise in 1H 2025

PwC Report: US Medical Cost Trend to Remain Elevated at 8.5% in 2026

PwC Report: US Medical Cost Trend to Remain Elevated at 8.5% in 2026

Philips Launches ECG AI Marketplace, Partnering with Anumana to Enhance Cardiac Care with AI-Powered Diagnostics

Philips Launches ECG AI Marketplace, Partnering with Anumana to Enhance Cardiac Care with AI-Powered Diagnostics

WeightWatchers Emerges from Bankruptcy, Launches New Menopause Program

WeightWatchers Emerges from Bankruptcy, Launches New Menopause Program

Secondary Sidebar

Footer

Company

  • About Us
  • Advertise with Us
  • Reprints and Permissions
  • Submit An Op-Ed
  • Contact
  • Subscribe

Editorial Coverage

  • Opinion
  • Health IT
    • Care Coordination
    • EMR/EHR
    • Interoperability
    • Population Health Management
    • Revenue Cycle Management
  • Digital Health
    • Artificial Intelligence
    • Blockchain Tech
    • Precision Medicine
    • Telehealth
    • Wearables
  • Startups
  • Value-Based Care
    • Accountable Care
    • Medicare Advantage

Connect

Subscribe to HIT Consultant Media

Latest insightful articles delivered straight to your inbox weekly

Copyright © 2025. HIT Consultant Media. All Rights Reserved. Privacy Policy |