Data Sheet 1_Development of a machine learning-based mortality prediction model for patien

439 hospitalized patients with mental disorders and COVID-19 were retrospectively collected from 10 hospitals in Henan Province, China. The dataset was used to develop and validate machine-learning models for predicting 31-day mortality. It was created by Yi Zhang and last updated on 2026-05-26.

Use Cases

• Training mortality prediction models based on routine clinical and laboratory variables.
• Analyzing feature importance for mortality risk based on SHAP analysis results.
• Comparing performance of different machine-learning algorithms (e.g., neural networks) on imbalanced clinical data.
• Studying the association between specific predictors like concomitant hormone therapy and COVID-19 outcomes in a specialized cohort.

Strengths

• Data from 439 patients across 10 hospitals provides a multicenter perspective.
• Model development used an independent test cohort of 131 patients for validation.
• The best-performing model achieved an AUC of 0.911 in the test cohort.
• Includes demographic details such as a patient cohort that is 63.1% female.

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 bias inherent to its collection from hospitals in Henan Province, China.

Provenance

Source

figshare, author Yi Zhang

Collection Method

Retrospectively collected from hospital records.

Freshness

Last updated 2026-05-26 06:03:47; freshness should be verified

Geography

Henan Province, China