AI-driven Automated Biomedical Research

Not Applicable

Not yet recruiting

• Conditions: Biomedical Research; Artificial Intelligence (AI)

• Registration Number: NCT06962423
• Lead Sponsor: Tsinghua University

Brief Summary

This study will evaluate the effects of the AI system developed by our team on biomedical research.

Detailed Description

It i a randomized-controlled study. Participants will be randomly assigned to the Intervention Group using our AI system and the Control Group. Both groups will perform the same biomedical research tasks and submit reports. At the end of the study, the research performance of the two groups will be evaluated.

Study Timeline

• Status Verified: 2025-04
• Study First Submitted: 2025-04-15
• Study First Submitted QC: 2025-04-29
• Last Update Submitted: 2025-04-29
• Study First Posted: 2025-05-08
• Last Update Posted: 2025-05-08
• Study Start: 2025-05-15
• Primary Completion: 2026-05-15
• Study Completion: 2026-05-15

Recruitment & Eligibility

• Status: NOT_YET_RECRUITING
• Sex: All
• Target Recruitment: 40

Inclusion Criteria

• (1) Age ≥ 18 years old;
• (2) Agree to sign consent form and invest time in this study;
• (3) Able to understand and complete research tasks.

Exclusion Criteria

• (1) Currently participating in other projects that may interfere with this research and unable to ensure participation time;
• (2) Have a history of major diseases or poor physical condition in the past three months that may affect research participation;
• (3) Unwilling or unable to understand and complete the research tasks.

Study & Design

• Study Type: INTERVENTIONAL
• Study Design: PARALLEL

Primary Outcome Measures

Name	Time	Method
Research quality evaluation scale	Through study completion, an average of 1 week	Independent senior experts will evaluate the research reports from the Intervention Group and the Control Group using a standardized 100-point Research Quality Evaluation Scale. A higher score indicates better research quality.

Secondary Outcome Measures

Name	Time	Method
Research time cost	Through study completion, an average of 1 week	The time spent by the Intervention Group and the Control Group to complete tasks will be compared.
Model resource consumption	Through study completion, an average of 1 week	GPU usage rate and time and model size will be tracked and compared to evaluate the computational resource consumption of the Intervention Group and Control Group.
User evaluation	Through study completion, an average of 1 week	User evaluation on the study will be assessed by Likert Scales.
Model performance	Through study completion, an average of 1 week	The diagnostic accuracy, sensitivity, specificity, and area under the receiver-operating characteristic curve (AUC-ROC) will be reported to compare the performance of models generated by the Intervention Group and the Control Group.

Trial Locations

Locations (1)

Tsinghua University; 🇨🇳 Beijing, Beijing, China