Related Experiment Video
Updated: Sep 3, 2025
Competing-Risk Nomogram for Predicting Cancer-Specific Survival in Multiple Primary Colorectal Cancer Patients after Surgery
Published on: September 27, 2024
An algorithm to predict data completeness in oncology electronic medical records for comparative effectiveness
David Merola1, Sebastian Schneeweiss1, Deborah Schrag2
1Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA; Department of Epidemiology, Harvard TH Chan School of Public Health, Boston, MA.
Electronic health record (EHR) discontinuity can bias studies. This study developed an algorithm to identify high EHR continuity in oncology patients, significantly reducing misclassification and improving data accuracy for research.
Area of Science:
- Health Informatics
- Oncology Research
- Data Science
Background:
- Electronic health record (EHR) discontinuity, characterized by missing out-of-network encounters, introduces significant information bias in clinical studies.
- Accurate patient data is crucial for reliable research outcomes, especially in complex fields like oncology.
Purpose of the Study:
- To develop and validate an algorithm for identifying high EHR continuity among oncology patients.
- To quantify the impact of EHR data completeness on reducing misclassification bias in cohort studies.
Main Methods:
- Utilized a linked Medicare-EHR database for 79,678 oncology patients.
- Developed a regression model to predict the continuity ratio (CR) of outpatient encounters captured by EHR.
- Evaluated model performance using Spearman correlation and quantified misclassification by decile of CR.
Main Results:
- A high correlation (σSpearman=0.86) was observed between predicted and observed continuity.
- Restricting cohorts to high EHR continuity subjects significantly reduced misclassification (MSD reduced 7-fold) and improved sensitivity (35-fold increase).
Conclusions:
- Implementing high EHR continuity criteria in oncology research can mitigate misclassification bias without substantially affecting cohort representativeness.
- Further research is needed to optimize the application of continuity prediction rules in cohort study designs.
More Related Videos
07:13Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
07:41Performing Data Mining And Integrative Analysis Of Biomarker in Breast Cancer Using Multiple Publicly Accessible Databases
Published on: May 17, 2019
Related Concept Videos
01:24Kaplan-Meier Approach
01:21Cancer Survival Analysis
01:20Comparing the Survival Analysis of Two or More Groups
02:50Combination Therapies and Personalized Medicine
The combination of the drug acetazolamide and sulforaphane is a good example of combination therapy to treat cancer. The cells in the interior of a large tumor often die due to the hypoxic and...
01:23Types of Biopharmaceutical Studies: Controlled and Non-Controlled Approaches
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...