Machine learning-based prediction of intraoperative blood transfusion in major surgery: exploiting clinical variables and systemic inflammatory indices

August 10, 2026Annals of MedicineOpen Access

View Full Paper

Ask AI

Bookmark

Share

Key Points

The aim is to develop and validate a machine learning model to predict the risk of intraoperative blood transfusion during major surgeries.
Analyzed a retrospective dataset of 1858 adult patients who underwent major surgery.
The dataset was split into training (60%), internal validation (18%), and internal test (22%) sets.
Evaluated 33 candidate variables to identify key predictors using the CatBoost algorithm.
The CatBoost model achieved an AUC of 0.88 in training and 0.80 in testing, indicating strong predictive performance.
The model had a high negative predictive value (NPV) of 0.89 in training and 0.87 in testing.
Identified key predictors of transfusion risk included type of surgery, preoperative hemoglobin, age, BMI, MCV RDW, PT, and inflammatory indices.

We only have this paper's title and publication details.

Develops and validates a machine learning model for predicting transfusion risk in major surgery, indicating improved management strategies.

No takes yet. Share an insight, caveat, or question.

Verzellesi et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Share