A Supervised Text-Embedded Transformer Matching Model to Detect Fall Injuries in Medicare Data
Year: 2026
Type: preprint
Abstract: Objective: To develop and validate a supervised text-embedded transformer matching model to identify fall injuries in Medicare data, and evaluate the model's performance -- alongside a validated rule-based algorithm-- against "ground truth" from an external reference standard (self-reported fall injuries leading to medical attention). Materials and Methods: Text embeddings of ICD-10-CM and CPT codes in Medicare claims/encounters from participants in the Strategies to Reduce Injuries and Develop Confidence in Elders (STRIDE) trial served as model inputs. Trained on annotated claims/encounters occurring within +/- one month of self-reported fall injuries leading to medical attention, the transformer model generated a continuous 0-1 probability that each claim/encounter was for a fall injury. The model was then applied to all claims/encounters in STRIDE and compared alongside the rule-based algorithm to the external reference standard. Results: The model achieved an area under the curve (AUC) of > 0.96 against annotated claims/encounters in 9 out of 10 holdout folds and 0.85 in the remaining fold. In the full STRIDE dataset, the model achieved a peak AUC of 0.86 (95% CI, 0.84-0.87) against the external reference standard, with results comparable to the rule-based algorithm. Discussion: Relative to rule-based approaches, which typically generate binary outcomes, the continuous event probability generated by the transformer model could support clinical endpoint adjudication, with high-probability predictions treated as events, moderate-probability predictions being adjudicated, and low-probability predictions treated as non-events. Conclusion: A text-embedded transformer model identified fall injuries with comparable accuracy to a rule-based algorithm, demonstrating "proof of concept" for use in endpoint adjudication.
Source: medRxiv
Institutions: The University of Texas MD Anderson Cancer Center, Yale University, Brigham and Women's Hospital, Harvard University, University of Michigan, Michigan Medicine, VA Center for Clinical Management Research, Ann Arbor VA Medical Center, RAND Corporation, University of California, Los Angeles, VA Greater Los Angeles Healthcare System
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Awards: Randomized Trial of a Multifactorial Fall Injury Prevention Strategy, G4166874930, G6881567127, Los Angeles Claude D. Pepper Older Americans Independence Center, Enhancing the Efficiency of Pragmatic Clinical Trials Using Administrative Data: Analysis of the STRIDE Study, Yale Clinical and Translational Science Award, Claude D. Pepper Older Americans Independence Center at Yale
OpenAlex ID: W7172013416