EUVIMEDEUVIMED entdecken
Crossref

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

Merlin Engelke iD, Cynthia Sabrina Schmidt iD, Giulia Baldini iD, Vicky Parmar iD, René Hosch iD, Katarzyna Borys iD, Sven Koitka iD, Amin T Turki iD, Johannes Haubold iD, Peter A Horn, Felix Nensa iD

Blood · 28.12.2023 · 142 (26) · 2315-2326

DOI: 10.1182/blood.2023021172 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Blood, erschienen am 28.12.2023. Verfasst von Merlin Engelke und 10 weiteren Autor:innen. Beteiligte Einrichtung: Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 37 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansPlatelet TransfusionRetrospective StudiesMachine LearningRisk Assessment

Autor:innen und Institutionen

  • Institute for Artificial Intelligence in Medicine, University Medicine Essen, Essen, Germany.
  • Institute of Diagnostic and Interventional Radiology and Neuroradiology, University Medicine Essen, Essen, Germany.
  • Institute for Transfusion Medicine, University Medicine Essen, Essen, Germany.
  • 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.

ORCID-Profile: Merlin Engelke, Cynthia Sabrina Schmidt, Giulia Baldini, Vicky Parmar, René Hosch, Katarzyna Borys, Sven Koitka, Amin T Turki, Johannes Haubold, Felix Nensa

Zitieren

APA

Engelke, M., Schmidt, C. S., Baldini, G., Parmar, V., Hosch, R., Borys, K., Koitka, S., Turki, A. T., Haubold, J., Horn, P. A., & Nensa, F. (2023). Optimizing platelet transfusion through a personalized deep learning risk assessment system for demand management. Blood, 142(26), 2315-2326. https://doi.org/10.1182/blood.2023021172

Vancouver

Engelke M, Schmidt CS, Baldini G, Parmar V, Hosch R, Borys K, et al. Optimizing platelet transfusion through a personalized deep learning risk assessment system for demand management. Blood. 2023;142(26):2315-2326. doi:10.1182/blood.2023021172

BibTeX
@article{Engelke2023,
  author = {Engelke, Merlin and Schmidt, Cynthia Sabrina and Baldini, Giulia and Parmar, Vicky and Hosch, René and Borys, Katarzyna and Koitka, Sven and Turki, Amin T and Haubold, Johannes and Horn, Peter A and Nensa, Felix},
  title = {Optimizing platelet transfusion through a personalized deep learning risk assessment system for demand management},
  journal = {Blood},
  year = {2023},
  volume = {142},
  number = {26},
  pages = {2315--2326},
  doi = {10.1182/blood.2023021172}
}
Kostenlos starten →