Related Experiment Video
Updated: May 16, 2026

Implementation of a Real-Time Psychosis Risk Detection and Alerting System Based on Electronic Health Records using CogStack
Published on: May 15, 2020
Development and evaluation of a Naïve Bayesian model for coding causation of workers' compensation claims
S J Bertke1, A R Meyers, S J Wurzelbacher
1National Institute for Occupational Safety and Health, Division of Surveillance, Hazard Evaluations, and Field Studies, Industrywide Studies Branch, 4676 Columbia Parkway, Cincinnati, OH 45226, USA. inh4@cdc.gov
A new computer algorithm accurately codes millions of workers' compensation claims for musculoskeletal disorders (MSDs) and slips, trips, or falls (STFs) in minutes. This automated method significantly reduces manual data entry burdens for researchers and practitioners.
Area of Science:
- Occupational Health
- Data Science
- Public Health
Background:
- Tracking musculoskeletal disorders (MSDs) and slips, trips, or falls (STFs) is crucial for workplace safety research.
- Manual coding of large workers' compensation datasets is time-consuming and resource-intensive.
Purpose of the Study:
- To develop and evaluate a computer auto-coding algorithm for classifying injury causation in workers' compensation claims.
- To automate the identification of MSDs and STFs from unstructured accident narratives.
Main Methods:
- An algorithm was trained on a dataset of manually coded workers' compensation claims.
- The algorithm was evaluated for its speed and accuracy in coding millions of claims.
Main Results:
- The auto-coding program achieved approximately 90% accuracy in classifying claims as MSD, STF, or other.
- The algorithm processed thousands of claims in minutes, demonstrating high efficiency.
Conclusions:
- The developed program offers an accurate and efficient method for identifying MSD and STF causation in large claim databases.
- This automated approach can be generalized to classify other types of unstructured text narratives in various fields.
Related Concept Videos
Causality in Epidemiology
Criteria for Causality: Bradford Hill Criteria - II
Correlation and Causation
Correlation versus Causation
If the dependent variable increases or decreases when the independent variable increases, there is a positive or negative...
Criteria for Causality: Bradford Hill Criteria - I
Theory of Attribution II: Kelley's Covariation Theory
Compensation Mechanisms
Respiratory Compensation
This mechanism addresses metabolic-induced pH imbalances by adjusting breathing rates. Respiratory compensation begins within minutes of detecting a pH...
