Search for: All records

Sepsis is a dysregulated host response to infection with high mortality and morbidity. Early detection and intervention have been shown to improve patient outcomes, but existing computational models relying on structured electronic health record data often miss contextual information from unstructured clinical notes. This study introduces COMPOSER-LLM, an open-source large language model (LLM) integrated with the COMPOSER model to enhance early sepsis prediction. For high-uncertainty predictions, the LLM extracts additional context to assess sepsis-mimics, improving accuracy. Evaluated on 2500 patient encounters, COMPOSER-LLM achieved a sensitivity of 72.1%, positive predictive value of 52.9%, F-1 score of 61.0%, and 0.0087 false alarms per patient hour, outperforming the standalone COMPOSER model. Prospective validation yielded similar results. Manual chart review found 62% of false positives had bacterial infections, demonstrating potential clinical utility. Our findings suggest that integrating LLMs with traditional models can enhance predictive performance by leveraging unstructured data, representing a significant advance in healthcare analytics. 

One of the common hydrotherapeutic exercises is walking in water because buoyancy reduces joint loading and increases mobility for a patient. The fluid drag forces (the forces that act on the person from the fluid in the direction opposing the direction of motion) cause changes in muscle activations, as walking in water changes the forces that act on the leg compared with overground walking. Here, through a series of numerical simulations, we quantify how the flow forces that act on the leg due to its motion in water change over a walking gait cycle. We show that besides drag forces that act on the walking legs and peak when the leg is accelerated forward, relatively large lateral forces (in the direction perpendicular to the direction of motion) also act on the leg. These forces are caused by the rapid acceleration of the opposite leg when the two legs are close, creating an asymmetric pressure distribution around the leg. These results are unexpected and could have significant implications for designing hydrotherapeutic plans for patients by considering the lateral forces besides the drag forces that act on the body while walking in water.