Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Genetic Drift03:33

Genetic Drift

41.2K
Natural selection—probably the most well-known evolutionary mechanism—increases the prevalence of traits that enhance survival and reproduction. However, evolution does not merely propagate favorable traits, nor does it always benefit populations.
41.2K
Bias in Epidemiological Studies01:29

Bias in Epidemiological Studies

748
Biases can arise at various stages of research, from study design and data collection to analysis and interpretation. Recognizing and addressing these biases is essential to ensure the validity and reliability of epidemiological findings.Broadly speaking, biases in epidemiology fall into three main categories: selection bias, information bias, and confounding. A more detailed description of possible biases is:  
748
Steps in Outbreak Investigation01:18

Steps in Outbreak Investigation

241
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
241
Parametric Survival Analysis: Weibull and Exponential Methods01:14

Parametric Survival Analysis: Weibull and Exponential Methods

684
Parametric survival analysis models survival data by assuming a specific probability distribution for the time until an event occurs. The Weibull and exponential distributions are two of the most commonly used methods in this context, due to their versatility and relatively straightforward application.
Weibull Distribution
The Weibull distribution is a flexible model used in parametric survival analysis. It can handle both increasing and decreasing hazard rates, depending on its shape parameter...
684
Actuarial Approach01:20

Actuarial Approach

142
The actuarial approach, a statistical method originally developed for life insurance risk assessment, is widely used to calculate survival rates in clinical and population studies. This method accounts for participants lost to follow-up or those who die from causes unrelated to the study, ensuring a more accurate representation of survival probabilities.
Consider the example of a high-risk surgical procedure with significant early-stage mortality. A two-year clinical study is conducted,...
142
Cancer Survival Analysis01:21

Cancer Survival Analysis

472
Cancer survival analysis focuses on quantifying and interpreting the time from a key starting point, such as diagnosis or the initiation of treatment, to a specific endpoint, such as remission or death. This analysis provides critical insights into treatment effectiveness and factors that influence patient outcomes, helping to shape clinical decisions and guide prognostic evaluations. A cornerstone of oncology research, survival analysis tackles the challenges of skewed, non-normally...
472

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Participants in Medicare's New Mandatory Bundled Payment Program.

Population health management·2026
Same author

Bundled Payments-Looking Beyond the Episode.

JAMA internal medicine·2026
Same author

Comparison of Alternative Policy Definitions for Safety-Net Ambulatory Practices.

JAMA health forum·2026
Same author

A Machine Learning Model to Improve Risk Adjustment Accuracy in Medicare.

Health services research·2026
Same author

Transplantation in Mandatory Kidney Payment Models: Understanding the Potential Influence of the ESRD Treatment Choices Model on the Increasing Organ Transplant Access Model.

Kidney medicine·2026
Same author

Nudges to Clinicians and Patients for Influenza Vaccines During Visits: The BE IMMUNE Randomized Clinical Trial.

JAMA internal medicine·2026

Related Experiment Video

Updated: Oct 1, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.2K

Performance Drift in a Mortality Prediction Algorithm during the SARS-CoV-2 Pandemic.

Ravi B Parikh1,2, Yichen Zhang1, Corey Chivers1

  • 1Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA.

Medrxiv : the Preprint Server for Health Sciences
|March 9, 2022
PubMed
Summary

The performance of a machine learning prognostic algorithm declined during the SARS-CoV-2 pandemic due to increased telemedicine and decreased laboratory use. This algorithm drift highlights the need to reassess clinical predictive tools during public health crises.

More Related Videos

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
10:46

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

10.8K
Establishing a Competing Risk Regression Nomogram Model for Survival Data
04:57

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Published on: October 23, 2020

10.4K

Related Experiment Videos

Last Updated: Oct 1, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
07:31

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack

Published on: May 15, 2020

7.2K
A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
10:46

A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data

Published on: December 9, 2015

10.8K
Establishing a Competing Risk Regression Nomogram Model for Survival Data
04:57

Establishing a Competing Risk Regression Nomogram Model for Survival Data

Published on: October 23, 2020

10.4K

Area of Science:

  • Health Informatics
  • Machine Learning in Healthcare
  • Clinical Decision Support

Background:

  • Clinical predictive algorithms are vital for resource allocation to high-risk patients.
  • These algorithms can experience performance degradation ('drift') due to changes in clinical practice or patient populations.
  • The SARS-CoV-2 pandemic introduced significant shifts in healthcare utilization, necessitating an evaluation of its impact on predictive algorithm performance.

Approach:

  • The study examined the performance drift of the Conversation Connect prognostic algorithm, which predicts 180-day mortality in cancer outpatients.
  • Performance was assessed across pre-pandemic, early-pandemic, and later-pandemic periods using electronic health record (EHR) data from 237,336 encounters.
  • Interrupted time series analyses quantified changes in high-risk encounters and evaluated the false negative rate (FNR) as the primary drift metric.

Key Points:

  • The later-pandemic period saw a decrease in high-risk encounters and a significant increase in the algorithm's FNR, indicating reduced accuracy.
  • Increased telemedicine utilization and decreased laboratory test ordering were observed during the pandemic.
  • Lower mortality risk scores were associated with telemedicine encounters and those without preceding laboratory draws.

Conclusions:

  • The SARS-CoV-2 pandemic led to a substantial decline in the performance of the Conversation Connect prognostic algorithm.
  • Shifts towards telemedicine and reduced laboratory utilization were key contributors to this performance drift.
  • Findings suggest that other EHR-based clinical predictive algorithms may be similarly affected, requiring regular assessment and potential retraining.