Research and application of machine learning models based on multimodal big data for precise transfusion management in acute myeloid leukaemia.
Machine learning models combining blood counts and clinical data could optimize blood transfusions in leukemia patients, reducing unnecessary or harmful transfusions.
This review of machine learning applications for precise transfusion management in AML synthesizes approaches using multimodal big data (CBC parameters, laboratory values, clinical variables, genomics) to optimize transfusion decisions. Ensemble models demonstrated best predictive performance, and the review bridges the T1 (hematologic malignancies) and T2 (CBC/ML in hematology) watchlist topics, partially filling the vacant T2 slot for this run.
What the study was
- Study design
- Systematic/narrative review of ML applications for transfusion decision support
- Population
- Patients with acute myeloid leukemia requiring transfusion support
- Category
- Diagnostics
- Maturity
- Exploratory
- Journal
- Transfusion medicine (Oxford, England)
Why it surfaced
Review of ML for transfusion management in AML; bridges T1 and T2 watchlist topics. T2 was vacant today; this review partially fills the gap. Transfus Med. Li Y corresponding author.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.