Massive Transfusion Prediction in Lung Transplant Patients, 2020-2023

390 adult patients who underwent lung transplantation at the Second Affiliated Hospital of the Zhejiang University School of Medicine between 2020 and 2023. The dataset was used to build a predictive model for massive intraoperative blood transfusion, achieving an AUC of 0.830 in the training cohort. The model was created by Xinchen Tao and published on figshare in 2026.

Use Cases

• Building a predictive model for massive blood transfusion based on clinical factors like hemoglobin and APTT.
• Analyzing risk factors for primary graft dysfunction based on transfusion requirements.
• Developing personalized transfusion strategies for lung transplant patients based on a seven-factor nomogram.

Strengths

• Includes 390 patient records with a defined massive transfusion incidence of approximately 25%.
• Model performance was validated with an AUC of 0.830 in the training set and 0.759 in the test set.
• Data is shared under a permissive CC-BY-4.0 license.

Limitations

• The dataset is very small at 26.5 KB, indicating limited scope.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data may reflect geographic and institutional bias from a single hospital in China.

Provenance

Source

figshare

Collection Method

Retrospective cohort study of medical records.

Time Range

2020-2023

Freshness

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

Geography

Second Affiliated Hospital of the Zhejiang University School of Medicine, China