AI-Agent for Automated Diagnosis and Predicting Using EHR and Multimodal Data

AI-Agent Assisted Automation for Diagnosing and Predicting Patients Using Electronic Health Records and Multimodal Data

The goal of this clinical study is to evaluate the effectiveness of an AI agent in diagnosing and predicting diseases using electronic health records (EHR) and multimodal imaging data. The AI agent leverages advanced machine learning algorithms to process and analyze diverse health data sources, aiming to assist healthcare providers in making more accurate diagnoses and predictions.

Study Overview

• Status: Recruiting
• Conditions: AI Agent

Detailed Description

This multi-center, retrospective clinical study is designed to evaluate the application and effectiveness of an AI agent in the medical decision-making process. The AI agent integrates and analyzes multimodal data, including electronic health records (EHR) and various imaging data (e.g., X-rays, MRIs, CT scans, ultrasounds) to predict and diagnose a range of diseases. By leveraging the power of machine learning and data fusion techniques, the AI agent can identify patterns in large and complex datasets, offering insights that may not be immediately apparent through traditional diagnostic methods.The study will compare the AI agent's diagnostic accuracy and disease prediction capabilities with traditional diagnostic practices to assess its potential benefits in clinical settings. Key questions include whether the AI agent can assist in early diagnosis, predict disease progression, and support healthcare professionals in making personalized treatment decisions. Participants will not be required to undergo any additional interventions; they will only provide historical health data, including EHR and relevant imaging data, which will be analyzed by the AI agent. The AI system will then use this data to assist healthcare providers by offering predictions and diagnostic suggestions based on the analysis of the multimodal information. The ultimate goal is to determine whether this AI-driven approach can improve diagnostic accuracy, optimize treatment strategies, and enhance patient outcomes in clinical practice.

• Study Type: Observational
• Enrollment (Estimated): 2000000

Contacts and Locations

• Study Contact: Name: Fei Liu, MD; Phone Number: +86 13810512704; Email: liufei_2359@163.com

Study Locations

• China
  • Guangdong
    • Guangzhou, Guangdong, China
      • Recruiting
      • Sun Yat-Sen Memorial Hospital
      • Contact: Yunfang Yu; Phone Number: +86 020-81332199; Email: yuyf9@mail.sysu.edu.cn
    • Guangzhou, Guangdong, China
      • Recruiting
      • Nanfang Hospital
      • Contact: Zhuomin Li; Phone Number: +86-0577-85397527; Email: chetneyli.1001@gmail.com
    • Guangzhou, Guangdong, China
      • Recruiting
      • Sun Yat-sen University Cancer Hospital
      • Contact: Yuxing Lu; Phone Number: +86 13161233730; Email: yxlu0613@gmail.com
  • Sichuan
    • Chengdu, Sichuan, China
      • Recruiting
      • West China Hospital
      • Contact: Kai Wang; Phone Number: +86 028-85422114; Email: wkai@stu.pku.edu.cn
  • Zhejiang
    • Wenzhou, Zhejiang, China
      • Recruiting
      • First Affiliated Hospital of Wenzhou Medical University
      • Contact: Cheng Tang; Email: c249325687@163.com
    • Wenzhou, Zhejiang, China
      • Recruiting
      • Second Affiliated Hospital of Wenzhou Medical University
      • Contact: Sian Liu; Phone Number: +86-0577-88002888; Email: liusan@mail3.sysu.edu.cn

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

• Sampling Method: Non-Probability Sample

Study Population

The participants for this study will be selected from multiple healthcare centers and hospitals that maintain comprehensive electronic health records (EHR) and multimodal imaging data. The study population will include patients who have a variety of diseases or health conditions, with data available for diagnosis and disease progression. Participants will have confirmed diagnoses based on clinical records or imaging data, including but not limited to conditions captured by X-rays, CT scans, MRIs, and ultrasounds. Both those with complex health conditions and those with more common illnesses will be included to evaluate the AI system's diagnostic and predictive capabilities across a broad spectrum of cases.Participants from these centers will provide historical health data, and there will be no active intervention beyond the use of their existing clinical and imaging data for training and testing the AI system.

Description

Inclusion Criteria:

1. Participants must have comprehensive electronic health records (EHR) available, including demographic information, medical history, and laboratory results.
2. Participants must have available multimodal imaging data (e.g., X-rays, CT scans, MRIs, ultrasounds) relevant to their health condition.
3. Participants must have a confirmed diagnosis of one or more diseases or health conditions based on clinical records or imaging data.
4. Patients must provide consent for the use of their historical health data for research purposes.

Exclusion Criteria:

1. Participants with ambiguous or unverifiable diagnoses that cannot be accurately categorized.
2. Duplicate or redundant patient data (e.g., repeated records of the same patient without clear differentiation).

Study Plan

How is the study designed?

Number of groups / cohorts

1

Cohorts and Interventions

Group / Cohort

AI-Assisted Disease Prediction Using EHR and Imaging Data; This cohort consists of patients whose historical health data, including electronic health records (EHR) and multimodal imaging data (e.g., X-rays, MRIs, CT scans, ultrasounds), will be analyzed by an AI agent. The AI system will assist in diagnosing and predicting diseases by processing and integrating these diverse data sources. The primary focus is to evaluate the ability of the AI agent to identify patterns and predict disease progression with high accuracy. Participants will not be required to take any additional actions beyond providing their medical history and imaging data. The aim is to assess how well the AI system can support clinical decision-making and improve diagnostic outcomes based on the provided data.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Area Under the Curve (AUC)	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).	1 year
F1 Score	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.	1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Sensitivity (True Positive Rate)	Sensitivity measures how well the AI model identifies true positive cases, such as correctly diagnosing pregnant women with complications or identifying neonatal disorders.	1 year
Specificity (True Negative Rate)	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.	1 year

Collaborators and Investigators

• Sponsor: The Eye Hospital of Wenzhou Medical University

Study record dates

Study Major Dates

• Study Start (Actual): July 1, 2023
• Primary Completion (Estimated): July 1, 2025
• Study Completion (Estimated): July 1, 2025

Study Registration Dates

• First Submitted: January 19, 2025
• First Submitted That Met QC Criteria: January 19, 2025
• First Posted (Actual): January 24, 2025

Study Record Updates

• Last Update Posted (Actual): April 17, 2025
• Last Update Submitted That Met QC Criteria: April 16, 2025
• Last Verified: April 1, 2025

More Information

Terms related to this study

• Keywords: AI agent
• Other Study ID Numbers: AI-agent

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No