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 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.

Predicting Individual Patient Platelet Demand in a Large Tertiary Care Hospital Using Machine Learning.

Introduction: An increasing shortage of donor blood is expected, considering the demographic change in Germany. Due to the short shelf life and varying daily fluctuations in consumption, the storage of platelet concentrates (PCs) becomes challenging. This emphasizes the need for reliable prediction of needed PCs for the blood bank inventories. Therefore, the objective of this study was to evaluate multimodal data from multiple source systems within a hospital to predict the number of platelet transfusions in 3 days on a per-patient level. Methods: Data were collected from 25,190 (42% female and 58% male) patients between 2017 and 2021. For each patient, the number of received PCs, platelet count blood tests, drugs causing thrombocytopenia, acute platelet diseases, procedures, age, gender, and the period of a patient's hospital stay were collected. Two models were trained on samples using a sliding window of 7 days as input and a day 3 target. The model predicts whether a patient will be transfused 3 days in the future. The model was trained with an excessive hyperparameter search using patient-level repeated 5-fold cross-validation to optimize the average macro F2-score. Results: The trained models were tested on 5,022 unique patients. The best-performing model has a specificity of 0.99, a sensitivity of 0.37, an area under the precision-recall curve score of 0.45, an MCC score of 0.43, and an F1-score of 0.43. However, the model does not generalize well for cases when the need for a platelet transfusion is recognized. Conclusion: A patient AI-based platelet forecast could improve logistics management and reduce blood product waste. In this study, we build the first model to predict patient individual platelet demand. To the best of our knowledge, we are the first to introduce this approach. Our model predicts the need for platelet units for 3 days in the future. While sensitivity underperforms, specificity performs reliably. The model may be of clinical use as a pretest for potential patients needing a platelet transfusion within the next 3 days. As sensitivity needs to be improved, further studies should introduce deep learning and wider patient characterization to the methodological multimodal, multisource data approach. Furthermore, a hospital-wide consumption of PCs could be derived from individual predictions.

Clinical assessment of image quality, usability and patient comfort in dedicated spiral breast computed tomography.

OBJECTIVE: To investigate aspects of image quality, feasibility and patient comfort in dedicated spiral breast computed tomography (B-CT) in a large patient cohort. METHODS: This retrospective study was approved by the institutional review board. 2418 B-CT scans from 1222 women examined between 04/16/2019 and 04/13/2022 were analyzed. Patients evaluated their comfort during the examination, radiographers carrying out the scans evaluated the patient's mobility and usability of the B-CT device, whereas radiologists assessed lesion contrast, detectability of calcifications, breast coverage and overall image quality. For semi-quantitative assessment, a Likert-Scale was used and statistical significance and correlations were calculated using ANOVAs and Spearman tests. RESULTS: Comfort, mobility and usability of the B-CT were rated each with either "no" or "negligible" complaints in >99%. Image quality was rated with "no" or "negligible complaints" in 96.7%. Lesion contrast and detectability of calcifications were rated either "optimal" or "good" in 92.6% and 98.4%. "Complete" and "almost complete" breast coverage were reported in 41.9%, while the pectoral muscle was found not to be covered in 56.0%. Major parts of the breast were not covered in 2.1%. Some variables were significantly correlated, such as age with comfort (ρ = -0.168, p < .001) and mobility (ρ = -0.172, p < .001) as well as patient weight with lesion contrast (ρ = 0.172, p < .001) and breast coverage (ρ = -0.109, p < .001). CONCLUSIONS: B-CT provides high image quality and contrast of soft tissue lesions as well as calcifications, while covering the pre-pectoral areas of the breast remains challenging. B-CT is easy to operate for the radiographer and comfortable for the majority of women.