Key result
Probabilistic Lasso algorithm outperforms rule-based ICD methods for identifying PTSD in veterans, achieving ~80% agreement.
Why the study?
A valid electronic medical record-based phenotype was needed to identify PTSD cases and controls among U.S. veterans for a genome-wide association study.
Does a Lasso regression-based EMR algorithm improve the identification of PTSD in U.S. veterans compared to an ICD-based algorithm?
Observational (n=500)
Does a Lasso regression-based EMR algorithm improve the identification of PTSD in U.S. veterans compared to an ICD-based algorithm?
Absolute Event Rate: 80% vs 75%
A Lasso regression-based EMR algorithm demonstrated high sensitivity and accuracy for identifying PTSD in U.S. veterans, outperforming a standard ICD-based approach.
May improve veteran PTSD phenotyping in EMRs; hypothesis-generating until validated in independent cohorts.
We developed an algorithm for identifying U.S. veterans with a history of posttraumatic stress disorder (PTSD), using the Department of Veterans Affairs (VA) electronic medical record (EMR) system. This work was motivated by the need to create a valid EMR-based phenotype to identify thousands of cases and controls for a genome-wide association study of PTSD in veterans. We used manual chart review (n = 500) as the gold standard. For both the algorithm and chart review, three classifications were possible: likely PTSD, possible PTSD, and likely not PTSD. We used Lasso regression with cross-validation to select statistically significant predictors of PTSD from the EMR and then generate a predicted probability score of being a PTSD case for every participant in the study population (range: 0-1.00). Comparing the performance of our probabilistic approach (Lasso algorithm) to a rule-based approach (International Classification of Diseases [ICD] algorithm), the Lasso algorithm showed modestly higher overall percent agreement with chart review than the ICD algorithm (80% vs. 75%), higher sensitivity (0.95 vs. 0.84), and higher accuracy (AUC = 0.95 vs. 0.90). We applied a 0.7 probability cut-point to the Lasso results to determine final PTSD case-control status for the VA population. The final algorithm had a 0.99 sensitivity, 0.99 specificity, 0.95 positive predictive value, and 1.00 negative predictive value for PTSD classification (grouping possible PTSD and likely not PTSD) as determined by chart review. This algorithm may be useful for other research and quality improvement endeavors within the VA.
No takes yet. Share an insight, caveat, or question.
Harrington et al. (2019) conducted an observational in Posttraumatic stress disorder (PTSD) (n=500). Lasso algorithm (probabilistic approach) vs. ICD algorithm (rule-based approach) was evaluated on Overall percent agreement with chart review for PTSD classification. A probabilistic Lasso algorithm demonstrated higher overall agreement (80% vs. 75%) and accuracy (AUC 0.95 vs. 0.90) for identifying PTSD in veterans compared to a rule-based ICD algorithm.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: