Self-monitoring auto-updating prognostic models of survival for hospitalized COVID-19 patients

Skip to content

ZSOM Data Catalog

Internal Dataset

Self-monitoring auto-updating prognostic models of survival for hospitalized COVID-19 patients

UID: 10415

Author(s): Todd Levy, Kevin Coppa, Jinxuan Cang, Douglas Barnaby, Marc Paradis... See more...

Stuart Cohen, Alexander Makhnevich, David van Klaveren, David Kent, Karina Davidson, Jamie Hirsch, Theodoros Zanos*

* Corresponding Author

Description: We developed a framework for continuously monitoring and updating prognostic models and apply it to predict 28-day survival in COVID-19 patients. We use demographic, laboratory, and clinical data from electronic health records of 34912 hospitalized COVID-19 patients from March 2020 until May 2022 and compare three modeling methods. Model calibration performance drift is immediately detected with minor fluctuations in discrimination. The overall calibration on the prospective validation cohort is significantly improved when comparing the dynamically updated models against their static counterparts.
Local Expert: Theodoros Zanos

Todd Levy

Subject of Study

Subject Domain

Retrospective Studies

Keywords

Access

Restrictions: Free to All

Free to all with registration
Instructions: As one of the NIH Generalist repositories, Zenodo enables researchers, scientists, EU projects and institutions to share the long tail of small research results in a wide variety of formats including text, spreadsheets, audio, video, and images across all fields of science. Zenodo is an open access repository.

Synapse is a generalist data repository and collaboration platform run by Sage Bionetworks. Synapse allows both open and controlled access.; Access via Zenodo
Model code
Accession #: 10.5281/zenodo.7249622

Access via Synapse

Accession #: 10.7303/syn39792658.1

Associated Publications

Levy TJ, Coppa K, Cang J, Barnaby DP, Paradis MD, Cohen SL, Makhnevich A, van Klaveren D, Kent DM, Davidson KW, Hirsch JS, Zanos TP. Development and validation of self-monitoring auto-updating prognostic models of survival for hospitalized COVID-19 patients. Nat Commun. 2022 Nov 10;13(1):6812. doi: 10.1038/s41467-022-34646-2. PMID: 36357420; PMCID: PMC9648888.

Data Type

Electronic Health Record

Software Used

MatLab

R

Sunrise Clinical Manager

Dataset Format(s)

CSV, Microsoft Word, M (MatLab)

Grant Support: R24AG064191/National Institute on Aging

R01LM012836/National Library of Medicine

K23HL145114/National Heart, Lung, and Blood Institute

ME-1606-35555/Patient-Centered Outcomes Research Institute
Other Resources: NOCOS Calculator
Web calculator implementation of model

Do you have or know of a dataset that should be added to the catalog? Let us know!