Biological Age
Conditions
Keywords
Biological Age, electronic health records, AI prediction, aging
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.
Detailed description
Biological age prediction is crucial for assessing overall health, determining the risk of age-related diseases, and providing personalized healthcare. While chronological age is a key factor, it does not always reflect an individual's true biological aging process. Early identification of accelerated biological aging and associated health risks can significantly impact early interventions and long-term health outcomes. In clinical practice, healthcare providers integrate a wide range of patient data, including medical history, laboratory test results, and clinical observations, to understand an individual's health status and predict potential future risks. As precision medicine becomes more important, the ability to predict biological age and personalize care plans is essential. Recent advancements in artificial intelligence and data analysis techniques have shown promise in enhancing the accuracy of biological age predictions. This study aims to develop an AI-assisted decision-making system by integrating multimodal data from electronic health records, laboratory results, clinical observations, and patient demographics. The objective is to improve diagnostic accuracy, optimize clinical workflows, and provide more personalized healthcare for patients by predicting biological age, identifying at-risk individuals, and improving health outcomes.
Interventions
OTHERAI-assisted predictive model
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.
Sponsors
The Eye Hospital of Wenzhou Medical University
Study design
Observational model
COHORT
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
0 Years to 100 Years
Healthy volunteers
Yes
Inclusion criteria
1. 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). 2. Patients with no significant cognitive impairments that would prevent them from providing informed consent or participating in the study. 3. All participants must provide informed consent for the use of their medical data for research purposes.
Exclusion criteria
1. Patients with incomplete or missing critical EHR data such as medical history, laboratory results, or treatment data that are necessary for predicting biological age. 2. atients with severe cognitive disorders (e.g., dementia, significant mental disabilities) who are unable to provide informed consent or participate meaningfully in the study. 3. Patients with terminal illnesses or those with limited life expectancy where biological age predictions may not be relevant for the purposes of the study.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Biological Age Prediction Accuracy | 1 year | 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. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Health Risk Correlation | 1 year | The correlation between predicted biological age and various health risks, such as the development of chronic diseases (e.g., cardiovascular disease, diabetes), using PCC to evaluate the relationship between biological age predictions and health outcomes. |
Countries
China
Contacts
Primary ContactFei Liu, MD
Outcome results
None listed