Kim Submits NIH R01 Application

Kudos to Hyeoneui Kim, associate professor, and her entire team for the submission of their NIH R01 application entitled "Assessing Pain in Patients Who are Unable to Express Pain Experience Using Routinely Collected Clinical Data." This proposal requests funding for a four-year period with a start date of April 1, 2020.  

Pain is a common yet most under-treated condition. Unmanaged pain causes a wide spectrum of adverse consequences to patients and seriously alters their quality of life. Hospitals put pain management as a high priority area of care. An accurate assessment of pain is a prerequisite for effective pain management.

However, assessing pain is not always straightforward, especially in critically ill patients who cannot make reliable verbal reports or behavioral signs of pain. These patients are at a high risk of receiving suboptimal treatment of pain and suffering adverse consequences. To address these challenges, we propose to develop personalized algorithms that assess pain based on the routinely collected clinical data. Patient data collected from Intensive Care Units (ICUs) of two large academic centers will be used in this project. High-quality data produce a high-quality prediction.

We will develop pain prediction algorithms using the pain levels reported by patients or rated by nurses based on patient behavior as gold standards. For patients who cannot express pain experience, we will use the incidence of painful procedures and analgesic administration schedules as a proxy to gold standards of pain presence. We will develop an advanced machine learning architecture with semi-supervised machine learning. This will enable us to make the best use of the vast amount of clinical data that are high dimensional and temporally dependent. This study aims to address the challenging clinical and ethical problem in pain management with non-invasive and relatively inexpensive approaches. When incorporated into clinical workflow the pain prediction method developed in this study will make a measurable impact on the outcomes of critically ill patients by facilitating more accurate, timely, and complete pain assessment.