Post-Transplant Pulmonary Infection Risk Factors and mNGS Pathogen Detection, 2020-2023

Hanshui Jiang's dataset contains clinical data from patients who developed pulmonary infections after liver or kidney transplantation between January 2020 and December 2023. It includes demographic characteristics, transplant parameters, laboratory results, and metagenomic next-generation sequencing (mNGS) pathogen detection outcomes. The data was used to develop and test a machine learning model for prognostic prediction.

Use Cases

• Training prognostic models for post-transplant pulmonary infection based on mNGS pathogen detection and clinical variables.
• Analyzing the correlation between laboratory markers like procalcitonin (PCT) and C-reactive protein (CRP) with infection outcomes.
• Validating feature importance for clinical risk stratification using methods like LASSO regression and SHAP analysis.
• Comparing pathogen detection rates between mNGS and conventional diagnostic methods in an immunocompromised cohort.

Strengths

• Includes mNGS pathogen detection results with a reported positive detection rate of 84.76%.
• Dataset was split into a training set (n=262) and a test set (n=66) with confirmed statistical similarity in baseline characteristics.
• The derived prediction model achieved a high ROC-AUC of 0.9206 in the test set.
• Identifies 14 key predictive variables, including mNGS bacterial/fungal/viral detection and specific lab markers.

Limitations

• Row count 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 and a specific time range, which may limit generalizability.

Provenance

Source

Hanshui Jiang via figshare.

Collection Method

Retrospective collection of clinical data from patients at a single hospital.

Time Range

January 2020 to December 2023

Freshness

Last updated 2026-05-28 04:49:38; freshness should be verified.