FindTrial
Sign In

Machine learning algorithm to predict mortality in patients based on MIMIC-IV database

Machine learning algorithm to predict mortality in patients based on MIMIC-IV database: ensemble machine-learning methods perform better than logistic regression

Status
Recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2200055703
Enrollment
Unknown
Registered
2022-01-16
Start date
2022-02-01
Completion date
Unknown
Last updated
2023-06-26

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

hospitalized death

Interventions

Gold Standard:Clinical outcome
Index test:ensemble machine-learning methods

Sponsors

the Third Xiangya Hospital of Central South University
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: Eligible patients with LODS and APACHE III scores in MIMIC-IV database.

Exclusion criteria

Exclusion criteria: Patients with two or more times admission into ICU.

Design outcomes

Primary

MeasureTime frame
receiver operating characteristic curve, ROC;Sensitivity;specificity;predicted positive rate;predictive negative rate;—

Countries

China

Contacts

Public ContactTang Yongzhong

the Third Xiangya Hospital of Central South University

tangyongzhong@csu.edu.cn+86 13467572241

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026