Congratulations to Dr. Parisa Rashidi, associate professor and J. Crayton Pruitt Term Fellow, and her team for receiving a $2.4 million RO1 grant from the NIH National Institute of Biomedical Imaging and Bioengineering (NIBIB) for a collaborative project (Co-PI: Dr. Azra Bihorac) on “Intelligent Intensive Care Unit (I2CU): Pervasive Sensing and Artificial Intelligence for Augmented Clinical Decision-making.”
In the United States, 5.7 million patients are admitted annually to intensive care units (ICU), with costs exceeding $82 billion. Although close monitoring and dynamic assessment of patient acuity are key aspects of ICU care, both are limited by the time constraints imposed on healthcare providers. Many important details related to the visual assessment of patients, such as facial expressions like pain, head and extremity movements, posture, and mobility, are captured sporadically by overburdened nurses or are not captured at all.
The existing computable ICU acuity scores are poorly accepted in clinical practice, as they are mainly static models of moderate accuracy, often requiring manual calculations and providing limited interpretability. As a result, assessing patient acuity in the ICU relies almost exclusively on physicians’ clinical judgment and vigilance.
Consequently, these critical visual cues associated with critical indices often cannot be incorporated into a physicians’ clinical status assessment. There is an urgent unmet need for real-time interpretable, dynamic, autonomous, and precise acuity prediction in the ICU that integrates the patient’s visual assessment with continuous physiologic measurement and clinical data.
The proposed intelligent ICU (I2CU) concept is based on the long-term goal of sensing, quantifying, and communicating a patient’s condition in an autonomous, precise, and interpretable manner. The overall objective is to develop novel tools for sensing, quantifying, and communicating any patient’s condition in an autonomous, precise, and interpretable manner. The overall objective will be achieved by pursuing three specific aims. (1) Developing and validating an interpretable deep learning algorithm for precise and dynamic prediction of the patient’s clinical status to determine if it is more accurate in predicting daily care transition outcomes while providing interpretable information to the physician. (2) Developing a pervasive sensing system for autonomous visual assessment of critically ill patients to determine if it can provide an accurate visual assessment of a patient compared to human experts and if it can enrich acuity prediction when combined with clinical data. (3) Implementing and evaluating an intelligent platform for real-time integration of autonomous visual assessment and acuity prediction in the clinical workflow to determine accuracy in real-time prospective evaluation and determine physicians’ risk perception and satisfaction.
The proposed research is significant since it will address several key problems and critical barriers in critical care, including (1) lack of precise and real-time prediction of clinical trajectory, (2) manual repetitive ICU assessments, and (3) uncaptured patient aspects. Ultimately, the results are expected to improve patient outcomes and decrease hospitalization costs, as well as lifelong complications.
The proposed research is relevant to public health because it can enhance critical care workflow and early critical care intervention, ultimately improving patient outcomes and decreasing hospitalization costs.
UF team members:
- Parisa Rashidi, Ph.D., (Contact PI), Associate Professor, Biomedical Engineering, College of Engineering
- Azra Bihorac, M.D., (Co-PI) Professor of Medicine, Surgery, and Anesthesiology, College of Medicine
- Martin Heesacker, Ph.D., (Co-I) Professor, Department of Psychology
- Tezcan Ozrazgat Baslanti, Ph.D., (Co-I) Research Assistant Professor, Department of Anesthesiology
- Marko Suvajdzic, Ph.D., (Co-I) Associate Professor, UF College of the Arts
- Patrick Tighe, M.D., (Co-I) Associate Professor, Department of Anesthesiology