Skip to main content

Using sequence clustering to identify clinically relevant subphenotypes in patients with COVID-19 admitted to the intensive care unit 

Lead author Wonsuk Oh discusses this month's JAMIA Journal Club selection:

Oh W, Jayaraman P, Sawant AS, Chan L, Levin MA, Charney AW, Kovatch P, Glicksberg BS, Nadkarni GN. Using sequence clustering to identify clinically relevant subphenotypes in patients with COVID-19 admitted to the intensive care unit. 2021 Nov 23. J Am Med Inform Assoc. 2021;ocab252. doi: 10.1093/jamia/ocab252 

Read the article

Watch the Recording

Author

Wonsuk Oh, PhD
Postdoctoral Fellow
Glicksberg and Nadkarni Labs
Icahn School of Medicine at Mount Sinai - New York, NY

Wonsuk Oh is a postdoctoral fellow in the Department of Genetics and Genomic Sciences at the Icahn School of Medicine at Mount Sinai. He holds a doctorate degree in Health Informatics and a master’s degree in Computer Science from the University of Minnesota – Twin Cities. His research focuses on the application of statistical modeling and machine learning in the field of medicine.

His research investigates the development of machine learning methods to extract clinically meaningful patterns from a large cohort of patients. These patterns detail how patients progress through comorbid conditions, presenting the temporal sequences of these conditions, timing information, and the risk of the complications that these patterns confer on patients. His goal is to discover clinically meaningful patterns from patients’ medical records and develop optimal intervention strategies for higher quality and cost-effective patient care. 

Manager and Moderator

Harry Reyes Nieva, PhD (c), MAS, MA
Biomedical Informatics
Columbia University
New York, NY

Statement of Purpose

COVID-19 is a novel respiratory infection, leading to over 33 million confirmed cases with 0.6 million deaths in the United States by May 2021. While COVID-19 shows heterogeneous clinical courses, indicating there might be distinct subphenotypes in critically ill patients, many studies have been limited to identify subphenotypes using features available at the baseline. In turn, many of these studies overlook the temporal patterns of the clinical features.

In this study, we conducted a sequence cluster analysis to derive novel COVID-19 temporal subphenotypes from biomarkers and treatments on the first 24 hours of intensive care unit admission medical history. We demonstrated that subphenotypes we identified had distinct temporal patterns and clinical outcomes, even though some subphenotypes shared similar baseline features.

Target Audience

The target audience for this activity is professionals and students interested in health informatics.

Learning Objectives

After participating in this webinar, the listener should be better able to:

  • Consider the use of temporal cluster analysis to derive novel subphenotypes
  • Recognize the temporal subphenotypes, which can be potentially beneficial to elucidate underlying pathophysiology, and discover subphenotype-specific treatment approaches

Format

  • 35-minute presentation by article author(s) considering salient features of the published study and its potential impact on practice
  • 25-minute discussion of questions submitted by listeners via the webinar tools and moderated by JAMIA Student Editorial Board members

 Accreditation Statement

The American Medical Informatics Association is accredited by the Accreditation Council for Continuing Medical Education to provide continuing medical education for physicians.

Commercial Support

No commercial support was received for this activity.

Disclosures for this Activity

The following planners and staff who are in a position to control the content of this activity disclose that they have no financial relationships with commercial interests/ineligible entities:

  • Presenter: Wonsuk Oh
  • JAMIA Journal Club Planners: Harry Reyes Nieva, Kirk E. Roberts
  • AMIA Staff: Susanne Arnold, Pesha Rubinstein
Dates and Times: -
Type: Webinar
Course Format(s): Live Virtual
Price: Free
Share