Testing an ICU time-series model to predict mortality at a major hospital

Is this trial a fit for you?

A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.

What this trial studies

This observational study validates how well the Time-Series Electronic Health Record Foundation Model generalizes to and performs in the ICU at Peking University People’s Hospital. The design combines retrospective data and forward-looking data to assess predictive performance for critical-care mortality, including dynamic prognostic outputs. Eligible adults with at least 24 hours in the ICU and complete EHRs are analyzed, with outcomes like 28-day mortality followed up as needed. Data quality and completeness are strictly checked to ensure reliable model inputs and results.

Why it matters

Who can join: the full rules

Inclusion Criteria:

* Age ≥ 18 years, no gender restriction;
* ICU length of stay ≥ 24 hours (to ensure sufficient time-series monitoring data for model generation);
* Complete electronic health record data, including baseline demographic characteristics and at least one complete laboratory test record after ICU admission.

Exclusion Criteria:

* Patients who are transferred out or die within 24 hours of ICU admission;
* Duplicate admission records for non-initial ICU admissions (only the initial ICU admission record is retained to ensure independence);
* Severe deficiency in core data (e.g., absence of major vital sign recordings or \> 50% missing key laboratory test results);
* Patients with abandonment of treatment or discharge against medical advice, leading to inability to ascertain the definitive clinical outcome.

Where it's running

• Peking University People's Hospital
  Beijing, Beijing Municipality, China Recruiting

Study contacts

• Study coordinator: Huiying Zhao, PhD
• Email: zhaohuiying@pku.edu.cn
• Phone: +86 13811088270

Similar studies

Other studies for the same condition or treatment. Recruiting studies are listed first.

• Can blood and physical tests before transplant predict non-relapse mortality

  This study tests whether pre-transplant blood markers and physical tests can predict non-relapse mortality in adults undergoing stem cell therapy.

  Recruiting Henry Ford Health System · Detroit, Michigan · NCT07769151

• Prediction score for death or lung transplant in emphysema caused by alpha-1 antitrypsin deficiency

  This study tests a new prediction tool to identify people with emphysema due to alpha-1-antitrypsin deficiency who are at high risk of death or needing a lung transplant.

  Recruiting at 4 sites University Hospital, Bordeaux · Bron and 3 other locations · NCT07715617

• Deciphering why some patients stay a long time in the ICU using detailed clinical profiling

  This study will try to identify clinical patterns in adults who stay in the ICU five days or longer to better understand persistent critical illness.

  Recruiting at 6 sites Lisbon Academic Medical Center - Centro Académico de Medicina de Lisboa · Lisbon, Lisbon District and 6 other locations · NCT07510776

• Lung ultrasound and lactate at discharge to predict 30-day outcomes after acute heart failure

  We’re testing whether a combination of lung ultrasound and blood lactate at discharge can help predict who will be readmitted or die within 30 days after leaving the hospital for acute heart failure.

  Recruiting University of Monastir · Monastir, Monastir Governorate · NCT07345156

• What predicts death in the ICU? Analyzing APACHE II in Colombian patients

  This study tests how well the APACHE II score predicts ICU mortality in adults treated at a Colombian hospital.

  Recruiting Hospital Departamental de Villavicencio · Villavicencio, Meta Department · NCT07249749

• Pediatric intensive care transport registry in Germany

  This project collects nationwide data to see how critically ill children are transported between hospitals in Germany and who needs these specialized transfers.

  Recruiting at 2 sites Philipps University Marburg · Dresden and 1 other locations · NCT07070258

How to take part

1. Review the eligibility criteria above with your treating physician.
2. Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
3. Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.