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.

Related Publications

Reducing perioperative red blood cell unit issue orders, returns, and waste using failure modes and effects analysis
Sunny S. Lou, et al.

Surgical transfusion has an outsized impact on hospital-based transfusion services, leading to blood product waste and unnecessary costs. The study authors sought to implement a streamlined, reliable process for perioperative blood issue ordering and delivery to reduce waste. The authors developed a failure modes and effects analysis to systematically examine perioperative blood management practices. Based on identified failure modes (e.g., miscommunication, knowledge gaps), a multi-component action plan was devised involving process changes, education, electronic clinical decision support, audit, and feedback. Changes in RBC unit issue requests, returns, waste, labor, and cost were measured pre- and post-intervention.  Findings show that the number of perioperative RBC unit issue requests decreased from 358 per month (SD 24) pre-intervention to 282 per month (SD 16) post-intervention (p < .001), resulting in an estimated savings of 8.9 h per month in blood bank staff labor. The issue-to-transfusion ratio decreased from 2.7 to 2.1 (p < .001). Perioperative RBC unit waste decreased from 4.5% of units issued pre-intervention to 0.8% of units issued post-intervention (p < .001), saving an estimated $148,543 in RBC unit acquisition costs and $546,093 in overhead costs per year.  The intervention successfully achieved sustained reductions in perioperative RBC unit issue orders, returns, and waste, with associated benefits for blood conservation and transfusion program costs.

National Multi-Institutional Validation of a Surgical Transfusion Risk Prediction Model.
Sunny Lou, et al.

Accurate estimation of surgical transfusion risk is important for many aspects of surgical planning, yet few methods are available for estimating such risk. This study uses the 2019 American College of Surgeons NSQIP data file in an effort to reliably validate methods for transfusion risk stratification and to support effective perioperative planning and resource stewardship.  S-PATH performance was evaluated in 1,000,927 surgical cases from 414 hospitals and was found to demonstrate excellent discriminative performance, although with variation across hospitals that was not well-explained by hospital-level characteristics. Initial results highlight the S-PATH’s viability as a generalizable surgical transfusion risk prediction tool.

Challenges in reliable preoperative blood ordering: A qualitative interview study
Phillip Yang, Emma P. Zijlstra, Bruce L. Hall, Stephen H. Gregory, Ronald Jackups Jr, Jing Li, Joanna Abraham, Sunny S. Lou

Presurgical blood orders are important for patient safety during surgery, but excess orders can be costly to patients and the healthcare system. For this study, the researchers aimed to assess clinician perceptions on the presurgical blood ordering process and perceived barriers to reliable decision-making. Semi-structured interviews were undertaken with 23 clinicians, including surgeons, anesthesiologists, nurse anesthetists, nurse practitioners working in preoperative assessment clinics, and transfusion medicine physicians to assess perceptions of current blood ordering processes. Clinicians felt that the current blood ordering process was frequently inconsistent, contributing factors include lack of information on risk, lack of experience, insufficient communication between stakeholders and high turnover in academic settings. The authors conclude that several barriers to reliable decision-making for presurgical blood orders exist. Future efforts to improve ordering consistency may benefit from improved information sharing between stakeholders and education on safe transfusion practices.