Optimizing Platelet Transfusion through a Personalized Deep Learning Risk Assessment System for Demand Management
Abstract
Platelet demand management (PDM) is a resource-consuming task for physicians and transfusion managers of large hospitals. Inpatient numbers and institutional standards play significant roles in PDM. However, reliance on these factors alone commonly results in platelet shortages. Using data from multiple sources, we developed, validated, tested, and implemented a patient-specific approach to support PDM that uses a deep learning-based risk score to forecast platelet transfusions for each hospitalized patient in the next 24 hours. The models were developed using retrospective electronic health record data of 34,809 patients treated between 2017 and 2022. Static and time-dependent features included demographics, diagnoses, procedures, blood counts, past transfusions, hematotoxic medications, and hospitalization duration. Using an expanding window approach, we created a training and live-prediction pipeline with a 30-day input and 24-hour forecast. Hyperparameter tuning determined the best validation Area Under the Precision-Recall Curve (AUC-PR) score for Long Short-Term Memory (LSTM) deep learning models, which were then tested on independent datasets from the same hospital. The highest performance was achieved with a model specific for hemato-oncology patients (AUC-PR: 0.84, ROC-AUC 0.98), followed by a multi-specialty model covering all other patients (AUC-PR: 0.73). The model specific to cardiothoracic surgery had the lowest performance (AUC-PR: 0.42), likely due to unexpected intra-surgery bleedings. This is the first deep learning-based platelet transfusion predictor enabling individualized 24-hour risk assessments at high AUC-PR. Implemented as a decision-support system, deep-learning forecasts might improve patient care by detecting platelet demand earlier and preventing critical transfusion shortages.
Merlin Engelke
Data Science
My research interests include machine learning, digitalization, and automation.
René Hosch
Team Lead
My research interests include distributed Computer Vision, Generative Adversarial Networks and Image-to-Image translation.
Katarzyna Borys
Data Science
My research interests include Deep Learning, Computer Vision, Radiomics, and Explainable AI.
Johannes Haubold
Medical Lead
My research interests include virtual sequencing, non-invasive tumor decoding and clinical AI integration.
