Prediction of perioperative transfusions using an artificial neural network

Abstract

Background Accurate prediction of operative transfusions is essential for resource allocation and identifying patients at risk of postoperative adverse events. This research examines the efficacy of using artificial neural networks (ANNs) to predict transfusions for all inpatient operations. Methods Over 1.6 million surgical cases over a two year period from the NSQIP-PUF database are used. Data from 2014 (750937 records) are used for model development and data from 2015 (885502 records) are used for model validation. ANN and regression models are developed to predict perioperative transfusions for surgical patients. Results Various ANN models and logistic regression, using four variable sets, are compared. The best performing ANN models with respect to both sensitivity and area under the receiver operator characteristic curve outperformed all of the regression models (p < .001) and achieved a performance of 70-80% specificity with a corresponding 75-62% sensitivity. Conclusion ANNs can predict >75% of the patients who will require transfusion and 70% of those who will not. Increasing specificity to 80% still enables a sensitivity of almost 67%. The unique contribution of this research is the utilization of a single ANN model to predict transfusions across a broad range of surgical procedures.

Transfusion Medicine: From AB0 to AI (Artificial Intelligence)

“…Factually, there is a growing evidence of AI application in TM, largely machine learning (equipment) but also deep learning applications (donor mobilization, stock management, cross matching, transfusion prediction in surgical interventions and prescription). In the advanced world, machine learning has been introduced in the clinical decision-making for transfusion, using data sets and stochastic dynamic programming (30,31) to predict the need (32)(33)(34).…”

From demand forecasting to inventory ordering decisions for red blood cells through integrating machine learning, statistical modeling, and inventory optimization

“…As this study was aimed at RBC inventory management, the biological plausibility of key predictors was not directly addressed. Recent publications on the prediction of perioperative RBC transfusions 46,47 and the prediction of RBC transfusion for patients with acute gastrointestinal bleeding 48 using patient level data also showed that laboratory test results (e.g., INR, creatinine, RDW, etc.) were important predictors for RBC transfusions.…”

Classification of abnormal location in medium voltage switchgears using hybrid gravitational search algorithm-artificial intelligence

“…Data without label are grouped based on similarity between the input data. The data are then classified after the dataset are labelled to train [25,26]. ANN is able to perform non-linear statistical modeling and can be an alternative to logistic regression [27].…”