Sepsis ARDS Mortality Risk Model with 7 Clinical Indicators

A clinical dataset of 635 adult sepsis patients with acute respiratory distress syndrome (ARDS) from Shaanxi Provincial People's Hospital, used to develop a 28-day mortality prediction model. The model integrates seven immune-inflammatory-nutritional indicators and was validated on a separate set of 158 patients. The dataset was uploaded by Qi Xin in March 2026.

Use Cases

• Training mortality prediction models based on immune-inflammatory-nutritional indicators like AAPR and NLR.
• Benchmarking new sepsis risk scores against the described nomogram's performance.
• Analyzing the relationship between nutritional status (e.g., PNI) and sepsis outcomes.
• Developing clinical decision support tools based on the model's threshold probabilities.

Strengths

• Model demonstrated high predictive performance with an AUC of 0.873 in training and 0.837 in validation.
• Data is derived from a specific clinical cohort of 635 patients, providing a defined sample.
• Model integrates seven readily accessible clinical indicators, potentially aiding clinical adoption.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count for the underlying data is unknown, which may limit suitability assessment.
• Data may reflect geographic bias inherent to a single hospital in Shaanxi province.

Provenance

Source

Clinical data from Shaanxi Provincial People's Hospital.

Collection Method

Retrospective clinical data collection and analysis using LASSO and logistic regression.

Time Range

null

Freshness

Last updated 2026-03-17 13:07:23; freshness should be verified.

Geography

Shaanxi province, China.