Acuity Score
Acuity scores quantify the severity of a patient's condition, primarily in critical care, to guide resource allocation and treatment decisions. Current research focuses on improving accuracy and timeliness through the integration of wearable sensor data (e.g., accelerometry) and electronic health records with machine learning models, including deep neural networks (like convolutional and recurrent architectures) and state-space models. These advancements aim to provide more precise, real-time assessments of patient stability, predict transitions to instability, and anticipate the need for life-sustaining therapies, ultimately leading to improved patient outcomes and more efficient healthcare resource management.
Papers
The Potential of Wearable Sensors for Assessing Patient Acuity in Intensive Care Unit (ICU)
Jessica Sena, Mohammad Tahsin Mostafiz, Jiaqing Zhang, Andrea Davidson, Sabyasachi Bandyopadhyay, Ren Yuanfang, Tezcan Ozrazgat-Baslanti, Benjamin Shickel, Tyler Loftus, William Robson Schwartz, Azra Bihorac, Parisa Rashidi
APRICOT-Mamba: Acuity Prediction in Intensive Care Unit (ICU): Development and Validation of a Stability, Transitions, and Life-Sustaining Therapies Prediction Model
Miguel Contreras, Brandon Silva, Benjamin Shickel, Tezcan Ozrazgat-Baslanti, Yuanfang Ren, Ziyuan Guan, Jeremy Balch, Jiaqing Zhang, Sabyasachi Bandyopadhyay, Kia Khezeli, Azra Bihorac, Parisa Rashidi