Prospective Real-World Study of Multimodal AI

Nanfang Hospital, Southern Medical University

Status: Invitation-only

Conditions: Pancancer

Study type: Observational

Funder types: Other

Identifiers

NCT07269236

NFEC-2025-602

Details and patient eligibility

About

This project proposes to collect prospective multimodal data-such as pathology, imaging, and clinical information-and to perform integrative analyses. AI technologies can offer novel solutions for disease classification, tumor grading, histological subtyping, molecular subtyping, selection of chemotherapy regimens, risk stratification, treatment response prediction, report generation, and intelligent question-answering. This research provides important support for precision medicine and individualized treatment and has significant theoretical and practical implications. Conducting a prospective randomized controlled study better aligns with clinical application requirements and can accelerate the comprehensive deployment of AI systems.

Enrollment: 2,000 estimated patients

Sex: All

Ages: 18+ years old

Volunteers: No Healthy Volunteers

Inclusion criteria

1. Age 18 years or older.
2. Patients with available digitized pathology slides, radiological imaging, and corresponding clinical data.

Exclusion criteria

1.Patients with missing data or specimens not meeting quality control requirements for analysis.

Trial design

2,000 participants in 3 patient groups

ZSCPH validation dataset

Description:

Approximately 1,000 prospective patients across various disease types will have digitized scanned images, imaging information, and clinicopathological data provided, collected from Zhongshan People's Hospital (Zhongshan, Guangdong, China) between October 2025 and September 2030.

NFHSMU validation dataset

Description:

We conducted a prospective validation study to compare the diagnostic performance among pathologists, our multimodal artificial intelligence model . This study was initiated on October 1, 2025 at Nanfang Hospital, Southern Medical University (NFHSMU).

Randomized controlled trial

Description:

We conducted a prospective randomized controlled trial to compare the diagnostic performance among pathologists, the multimodal artificial intelligence model, and pathologist-with-model-assisted diagnosis at Nanfang Hospital of Southern Medical University (NFHSMU).The trial commenced data collection on October 1, 2025 to establish the NFHSMU randomized controlled trial dataset. Following quality control, the slides were randomly allocated (1:1:1 ratio) into three groups:Model-only group/Pathologist-only group/Model-assisted pathologist group.