Genotype
Conditions
Keywords
AI, AI-prediction, Genotype, Multimodal data
Brief summary
The goal of this clinical study is to explore the potential of using electronic health records (EHR) and multimodal data (such as imaging, lab results, and clinical history) to predict a patient's genotype. The study will evaluate whether predictive models based on this non-genetic data can accurately infer genetic information, which traditionally requires direct genetic testing.
Detailed description
This multi-center, retrospective clinical study aims to evaluate the use of electronic health records (EHR) and multimodal data (such as clinical lab results, imaging data, and medical history) in predicting a patient's genotype. The primary objective of the study is to develop an AI-based prediction model that can infer genetic information by analyzing available health data, eliminating the need for direct genetic testing.The AI model will be trained to process and integrate large datasets, including EHR, lab results, and imaging data such as X-rays, MRIs, and ultrasounds, in order to predict genotypic information. The study will compare the AI-based predictions to actual genetic testing results to evaluate the accuracy of the model. If successful, this method could provide a non-invasive, cost-effective tool for genotype prediction, which could be used in personalized medicine, early disease diagnosis, and risk stratification.Participants will not undergo any genetic testing as part of the study. Instead, their historical medical data will be analyzed by the AI system to predict genetic information and associated disease risks. The study will assess the model's ability to predict genetic predispositions to various health conditions based on the available health data. By doing so, the study aims to advance the use of AI in clinical decision-making and genetic diagnostics.
Interventions
OTHERAI-Predictng Model
The intervention in this study involves an AI-based predictive model designed to analyze and integrate patient electronic health records (EHR), clinical lab results, and multimodal imaging data (e.g., X-rays, MRIs, CT scans). The AI model is trained to predict a patient's genotype based on these non-genetic data sources. This model uses machine learning algorithms to detect patterns and infer genetic information that would traditionally require direct genetic testing. There are no active treatments or genetic tests involved in this intervention; rather, the AI system serves as a tool to predict genetic information from available clinical data, offering a non-invasive and potentially more accessible alternative to genetic testing.
Sponsors
The Eye Hospital of Wenzhou Medical University
Study design
Observational model
CASE_ONLY
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Healthy volunteers
Yes
Inclusion criteria
1. Participants must have comprehensive electronic health records (EHR), including medical history, lab results, and relevant imaging data (e.g., X-rays, MRIs, CT scans). 2. Participants must have existing genetic testing data available for comparison, if applicable. 3. Participants must be willing to provide consent for the use of their health data in the study. 4. Participants must have no active intervention related to genetic testing or prediction during the study period. 5. Participants should have complete and verifiable health data to allow for accurate prediction by the AI model.
Exclusion criteria
1. Participants without available EHR, lab results, or imaging data. 2. Participants with ambiguous, inaccurate, or unverifiable genetic testing results that cannot be used for comparison. 3. Patients with significant discrepancies or missing data that would prevent the AI model from making accurate predictions.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Area Under the Curve (AUC) | 1 year | AUC of the ROC curve, used to quantify diagnostic accuracy. No unit (a ratio or percentage, typically expressed as a number between 0 and 1). |
| F1 Score | 1 year | The F1 score is the harmonic mean of precision and sensitivity (recall). It is a good measure of the model's ability to identify both true positives and minimize false positives, especially in cases where the classes are imbalanced (e.g., when the number of healthy cases is much higher than disease cases). The F1 score ranges from 0 to 1, with 1 indicating perfect precision and recall. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Sensitivity (True Positive Rate) | 1 year | Sensitivity measures how well the AI model identifies true positive cases, such as correctly diagnosing pregnant women with complications or identifying neonatal disorders. |
| Specificity (True Negative Rate) | 1 year | Specificity measures the ability of the AI model to correctly identify cases without diseases, ensuring that healthy mothers and infants are correctly identified as negative. |
Countries
China
Contacts
Primary ContactFei Liu, MD
Outcome results
None listed