Lung Transplant Patient Data for Predicting Massive Intraoperative Blood Transfusion

390 adult patients who underwent lung transplantation at a single hospital between 2020 and 2023. The dataset was used to develop a predictive model for massive intraoperative blood transfusion, achieving an AUC of 0.830 in the training cohort. It was authored by Xinchen Tao and published on figshare in 2026.

Use Cases

• Developing a risk prediction model for massive transfusion based on features like primary diagnosis and hemoglobin level.
• Analyzing the relationship between surgical factors (e.g., cold ischemia time, surgical type) and intraoperative blood loss.
• Validating a clinical nomogram for personalized transfusion strategy optimization in lung transplant patients.

Strengths

• Includes 390 patient records from a defined cohort (2020-2023).
• Model development followed a structured methodology with a 70/30 train-test split and bootstrap validation.
• The predictive model achieved an AUC of 0.830 in the training set, indicating strong discriminative performance.

Limitations

• Row count for the underlying data table is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data is from a single hospital center, which may limit generalizability to other populations.

Provenance

Source

Retrospective cohort from the Second Affiliated Hospital of the Zhejiang University School of Medicine.

Collection Method

Retrospective clinical data collection for model development.

Time Range

2020 to 2023

Freshness

Last updated 2026-05-18 05:35:43; freshness should be verified.

Geography

China (likely Zhejiang province)