AI-Driven Prediction of Biological Age With EHR

NCT06791486 | Recruiting

• 1 other identifier: Biological Age
• Study Type: observational
• Target: 1,000,000
• Locations: 1 country
• Sites: 4

Brief Summary

This is a multi-center, retrospective clinical study designed to evaluate the application and effectiveness of an AI-assisted predictive model for predicting biological age using electronic health records (EHR). The study will analyze various health data points, including medical history, laboratory results, and clinical observations, to estimate the biological age of patients. By comparing biological age with chronological age, the study aims to assess the accuracy of the model and its potential in identifying age-related health risks and improving patient care.

Conditions

Biological Age

Keywords

Biological Age; electronic health records; AI prediction; aging

Outcome Measures

Primary Outcomes (1)

• Biological Age Prediction Accuracy

  The accuracy of the AI model in predicting biological age compared to chronological age. This will be evaluated using the Pearson Correlation Coefficient (PCC) to assess the strength of the correlation between predicted biological age and chronological age. Additionally, R-squared (R²) will be used to evaluate the proportion of variance in biological age explained by the model.

  1 year

Secondary Outcomes (1)

• Health Risk Correlation

  1 year

Study Arms (2)

Biologically Younger Group

Participants whose biological age is predicted to be younger than their chronological age.

Other: AI-assisted predictive model

Biologically Older Group

Participants whose biological age is predicted to be older than their chronological age.

Other: AI-assisted predictive model

Interventions

AI-assisted predictive model OTHER

This study utilizes an AI-assisted predictive model that analyzes multimodal data from electronic health records, including medical history, laboratory results, imaging data, and lifestyle factors, to estimate biological age. The model employs deep learning algorithms to predict biological age, compare it to chronological age, and identify early signs of age-related health risks. The intervention is not a direct treatment or procedure but aims to develop a tool for predicting biological age to help personalize care and improve long-term health outcomes.

Biologically Older Group; Biologically Younger Group

Eligibility Criteria

• Age: 0 Years - 100 Years
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population consists of individuals who have received care at participating hospitals or healthcare centers with accessible electronic health records (EHR). Participants will include those with complete EHR data, including medical history, laboratory test results, imaging data, and lifestyle factors such as diet, physical activity, and smoking habits. The cohort will comprise both individuals who are healthy and those with chronic conditions or comorbidities to analyze biological age prediction across different health statuses. The study will be conducted across multiple healthcare facilities to ensure a diverse patient population representing a wide range of age groups, health conditions, and demographics.

You may qualify if:

• Patients with comprehensive and accessible EHR data, including medical history, laboratory results, treatment data, imaging data (if available), and lifestyle factors (e.g., smoking, physical activity, diet).
• Patients with no significant cognitive impairments that would prevent them from providing informed consent or participating in the study.
• All participants must provide informed consent for the use of their medical data for research purposes.

You may not qualify if:

• Patients with incomplete or missing critical EHR data such as medical history, laboratory results, or treatment data that are necessary for predicting biological age.
• atients with severe cognitive disorders (e.g., dementia, significant mental disabilities) who are unable to provide informed consent or participate meaningfully in the study.
• Patients with terminal illnesses or those with limited life expectancy where biological age predictions may not be relevant for the purposes of the study.

Sponsors & Collaborators

• The Eye Hospital of Wenzhou Medical University: lead

Study Sites (4)

Nanfang Hospital

Guangzhou, Guangdong, China

RECRUITING

First Affiliated Hospital of Wenzhou Medical University

Wenzhou, Zhejiang, China

RECRUITING

Second Affiliated Hospital of Wenzhou Medical University

Wenzhou, Zhejiang, China

RECRUITING

The Eye Hospital of Wenzhou Medical University

Wenzhou, Zhejiang, China

RECRUITING

Central Study Contacts

Fei Liu, MD

CONTACT

+86 13810512704; liufei_2359@163.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Chief Scientist

Study Record Dates

• First Submitted: January 19, 2025
• First Posted: January 24, 2025
• Study Start: March 1, 2023
• Primary Completion: April 2, 2025
• Study Completion: April 2, 2025
• Last Updated: April 2, 2025

Record last verified: 2025-04

Data Sharing

• IPD Sharing: Will not share

Locations

CN (4)