Optimizing platelet transfusion through a personalized deep learning risk assessment system for demand management.

Autor:	Engelke M; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Schmidt CS; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute for Transfusion Medicine, University Medicine Essen, Essen, Germany., Baldini G; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Parmar V; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Hosch R; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Borys K; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Koitka S; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Turki AT; Computational Hematology Laboratory, Department of Hematology and Stem Cell Transplantation, West-German Cancer Center, University Medicine Essen, Essen, Germany.; Department of Hematology and Oncology, Marienhospital University Hospital, Ruhr University Bochum, Bochum, Germany., Haubold J; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany., Horn PA; Institute for Transfusion Medicine, University Medicine Essen, Essen, Germany., Nensa F; Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.; Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany.
Jazyk:	angličtina
Zdroj:	Blood [Blood] 2023 Dec 28; Vol. 142 (26), pp. 2315-2326.
DOI:	10.1182/blood.2023021172
Abstrakt:	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 deep learning models, which were then tested on independent data sets from the same hospital. The model tailored for hematology and oncology patients exhibited the best performance (AUC-PR, 0.84; area under the receiver operating characteristic curve [ROC-AUC], 0.98), followed by a multispecialty model covering all other patients (AUC-PR, 0.73). The model specific to cardiothoracic surgery had the lowest performance (AUC-PR, 0.42), likely because of unexpected intrasurgery bleedings. To our knowledge, 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. (© 2023 by The American Society of Hematology.)
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu