AI model predicts outcomes for dialysis patients

Predicting Clinical Outcomes in Dialysis Patients Using Electronic Health Records: An AI-Based Approach

This study is testing if an AI tool can help doctors predict health outcomes for dialysis patients, like their risk of dying or developing anemia, to provide better care.

Quick facts

• Study type: Observational
• Enrollment: 1000000 (estimated)
• Ages: 20 Years to 100 Years
• Sex: All
• Sponsor: The Eye Hospital of Wenzhou Medical University (other)
• Locations: 1 site (Beijing, Beijing Municipality)
• Trial ID: NCT06791447 on ClinicalTrials.gov

What this trial studies

This observational study evaluates the effectiveness of an AI-assisted predictive model designed to forecast clinical outcomes in dialysis patients. By analyzing multimodal health data from electronic health records (EHR), the study focuses on predicting both primary outcomes, such as mortality, and intermediate outcomes like anemia and blood pressure. The aim is to enhance early identification of at-risk patients, thereby facilitating improved clinical decision-making and personalized care strategies. The study will involve multiple centers to gather a diverse patient population and robust data.

Who should consider this trial

Good fit: Ideal candidates are patients who have been undergoing dialysis for at least 3 months and have complete EHR data.

Not a fit: Patients with incomplete EHR data or those who have been on dialysis for less than 3 months may not benefit from this study.

Why it matters

Potential benefit: If successful, this approach could lead to better management and outcomes for dialysis patients through early identification of risks.

How similar studies have performed: Other studies utilizing AI for predictive modeling in healthcare have shown promising results, indicating potential success for this approach.

Eligibility criteria

Inclusion Criteria:

1. Patients who have been undergoing dialysis (either hemodialysis or peritoneal dialysis) for at least 3 months.
2. Complete and accessible EHR data, including medical history, laboratory test results, dialysis treatment details, and clinical observations.
3. Participants must provide informed consent for the use of their health data for research purposes.

Exclusion Criteria:

1. Patients with incomplete or missing critical EHR data, including medical history, laboratory results, dialysis data, or treatment details necessary for the study.
2. Patients who have been on dialysis for less than 3 months, to ensure stable data for outcome prediction.

Where this trial is running

Beijing, Beijing Municipality

• General Hospital of PLA — Beijing, Beijing Municipality, China (RECRUITING)

Study contacts

• Study coordinator: Fei Liu, MD

Conditions: Dialysis Patients, AI-Assisted Prediction