TBM vs VM Diagnosis: Laboratory Data for 558 Patients from 2000-2024

Clinical and laboratory data from 558 participants, including 190 tuberculous meningitis (TBM) and 368 viral meningitis (VM) patients, treated at Xijing Hospital between 2000 and 2024. The dataset was used to develop machine learning models for differential diagnosis, with ten key laboratory features identified. The study was authored by Xiaoyan Hao and last updated in April 2026.

Use Cases

• Training binary classifiers to differentiate tuberculous from viral meningitis based on ten laboratory indicators.
• Evaluating feature importance for meningitis diagnosis using SHAP analysis on identified clinical markers.
• Developing clinical nomograms for diagnostic support based on routine cerebrospinal fluid and blood tests.

Strengths

• Includes data from 558 patients with a defined class distribution (190 TBM, 368 VM).
• Covers a 24-year time range (2000-2024) from a single hospital, providing longitudinal consistency.
• Identifies ten specific laboratory features for model development, including CSF glucose, protein, and D-Dimer.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Data may reflect geographic and temporal bias inherent to a single hospital source.

Provenance

Source

Xiaoyan Hao via figshare.

Collection Method

Clinical and laboratory data collected from patients at Xijing Hospital.

Time Range

2000 to 2024

Freshness

Last updated 2026-04-15 05:45:33; freshness should be verified.

Geography

Likely China (Xijing Hospital).