Dr. Lou’s Research

Intelligent Clinical Decision Support for Perioperative Blood Management

Preoperative testing and preparation for intraoperative transfusion is essential for patient safety during surgery. However, excessive preparation is costly and contributes to blood product waste. Approximately $10 billion dollars are spent each year on presurgical blood orders, yet < 20% of patients with such orders require transfusion. Anesthesiologists should place presurgical blood orders only for patients who need it; there is an acute public health need for tools that accurately estimate the risk of transfusion to guide clinical decision-making. The PI developed a personalized machine learning (ML) model, named S-PATH, to estimate surgical transfusion risk based on patient- and procedure-specific characteristics, and demonstrated its validity across local and national datasets. Compared to standard-of-care Maximum Surgical Blood Ordering Schedule methods, S-PATH had improved accuracy and discrimination. The research objective is to design, implement, and evaluate S-PATH as a clinical decision support (CDS) system embedded within the Electronic Health Record (EHR). Aim 1 designs and assesses the usability of the S-PATH system using a user-centered design process involving interviews for needs analysis, iterative prototyping, and a usability study. Aim 2 evaluates the functionality and safety of the S-PATH system with a 6-month prospective cohort study where S-PATH recommendations will be silently recorded for all presurgical patients and compared with usual clinical care. The expected outcome of this research is a generalizable personalized CDS system to guide presurgical blood orders that is usable and safe to deploy within preoperative workflow, facilitating a future clinical trial with potential benefit for patient safety, blood conservation, and cost.