Related Experiment Video
Updated: Jun 27, 2025

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Application of a data continuity prediction algorithm to an electronic health record-based pharmacoepidemiology study
James H Flory1, Yongkang Zhang2, Samprit Banerjee2
1Endocrinology Service, Department of Subspecialty Medicine, Memorial Sloan Kettering Cancer Center, New York City, New York, USA.
A simple algorithm effectively identifies patients with high electronic health record data continuity, improving study validity. This method enhances the accuracy of pharmacoepidemiologic research, particularly for COVID-19 outcomes.
Area of Science:
- Health Informatics
- Pharmacoepidemiology
- Biostatistics
Background:
- Electronic Health Records (EHRs) are crucial for research.
- Ensuring data continuity in EHRs is vital for study validity.
- Practical applications of data continuity algorithms are limited.
Purpose of the Study:
- To develop and validate algorithms for identifying high data continuity patients in EHRs.
- To assess the impact of data continuity on study validity.
- To apply these algorithms in a pharmacoepidemiologic study of COVID-19 hospitalization.
Main Methods:
- Developed and validated four algorithms to assess EHR data continuity.
- Utilized a simplified model with five EHR-derived variables.
- Applied the algorithms to a pharmacoepidemiologic study comparing antidiabetic drug effects on COVID-19 hospitalization.
Main Results:
- A concise algorithm performed comparably to complex models in identifying high data continuity.
- Higher data continuity correlated with more accurate variable ascertainment.
- In the pharmacoepidemiologic study, higher data continuity revealed higher COVID-19 hospitalization rates and adjusted associations.
Conclusions:
- A simple, portable algorithm effectively predicts data continuity.
- The algorithm enhances the validity of empirical studies.
- Improved data continuity leads to more reliable research findings.
More Related Videos
Related Concept Videos
Analysis of Population Pharmacokinetic Data
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
Model-Independent Approaches for Pharmacokinetic Data: Noncompartmental Analysis
One important characteristic of noncompartmental analyses is that drug exposure increases proportionally with increasing doses. This...
Analysis Methods of Pharmacokinetic Data: Model and Model-Independent Approaches
The model approach uses mathematical models to describe changes in drug concentration over time. Pharmacokinetic models help characterize drug behavior in patients, predict drug concentration in the body fluids, calculate optimum dosage regimens, and evaluate the risk of toxicity. However, ensuring that the model fits the experimental data accurately...
Mechanistic Models: Compartment Models in Individual and Population Analysis
Steps in Outbreak Investigation

