Patient Blood Management

Multicenter Validation of a Machine Learning Model for Surgical Transfusion Risk at 45 US Hospitals

We previously developed a personalized AI model to predict surgical transfusion risk. Here we simulated using it for preop T&S decisions at 45 US hospitals. Our model (S-PATH) did better than the standard of care approach (MSBOS). We also measured performance using a clinically meaningful benchmark, the number of T&S ordered. S-PATH needed ~ 1/3 fewer while maintaining 96% sensitivity for finding patients who need blood. Importantly, we used S-PATH out of the box. No retraining or fine tuning on individual hospitals. Nonetheless, it still performed well. This kind of robustness is rare among AI models, and suggests S-PATH could be immediately useful for many hospital systems.

Challenges in reliable preoperative blood ordering - a qualitative interview study

Presurgical blood orders are important for patient safety during surgery, but excess orders can be costly to patients and the healthcare system. We assessed clinician perceptions on the presurgical blood ordering process and perceived barriers to reliable decision-making, including lack of information on surgical transfusion risk, lack of experience in ordering clinicians, and poor communication between stakeholders.

National Multi-Institutional Validation of a Surgical Transfusion Risk Prediction Model

Preparation for transfusion is important, but excessive preparation is common, costly, and contributes to blood waste. This tool helps doctors identify patients at risk for transfusion so they can get the care they need. We evaluated the tool's performance at 414 NSQIP-contributing hospitals, and found that it showed promising generalizability and could potentially be used across a diverse range of hospitals to assist with perioperative planning.

Reducing perioperative red blood cell unit issue orders, returns, and waste using failure modes and effects analysis

Surgical transfusion has an outsized impact on hospital-based transfusion services, leading to blood product waste and unnecessary costs. In this paper, we describe the design and implementation of a streamlined reliable process for perioperative blood ordering and delivery to reduce red cell waste.

Personalized Surgical Transfusion Risk Prediction Using Machine Learning to Guide Preoperative Type and Screen Orders

20 million patients have surgery in the US every year, and ~ 1 million of those patients require life-saving blood transfusion. Presurgical preparation for transfusion is important to allow for safe and timely transfusion during surgery, but excessive preparation is unfortunately common, costly, and contributes to blood waste. In this paper, we develop a personalized surgical transfusion risk prediction model using a database of 3 million surgical patients, and show that using such a model to guide presurgical type and screen orders can potentially improve patient safety while reducing the number of unnecessary orders. Reproducible code is provided to make predictions for new patients.