In the lush May, the 6th Tianfu Health Management Discipline Construction Academic Conference grandly opened in Chengdu. This conference brings together academicians of the Chinese Academy of Sciences and Chinese Academy of Engineering, leading talents and senior scholars in the field of health management to deeply interpret national health policies, actively explore new paths for scientific health management, and provide new ideas for chronic disease prevention and control strategies and precise health interventions.

At the sub forum on "Construction and Operation Management of Grassroots Health Examination and Management Specialty" held on the afternoon of May 10th, Professor Luo Rong, Director of the Health Management Center of the First Affiliated Hospital of Chongqing Medical University, presented a wonderful report entitled "New 'Healthy' Solution for Early Screening and Diagnosis of Liver Cancer: Exploration and Practice of miRNA7 and Multimodal Fusion Model". Focusing on the core issues of early screening and diagnosis of liver cancer, the innovative achievements of miRNA7 multimodal fusion model and clinical application were vividly demonstrated through typical cases and detailed data, and were highly praised by the attending experts.

Regarding the current situation of chronic liver disease and liver cancer in China, Director Luo introduced that there are nearly 400,000 new cases of liver cancer in China every year, accounting for nearly 50% of the global total. Meanwhile, metabolic dysfunction associated fatty liver disease (MASLD) has become one of the most common chronic liver diseases worldwide. In recent years, a large number of studies have found that MASLD has become the fastest-growing cause of hepatocellular carcinoma (HCC) cases. In response to the severe situation of liver cancer prevention and control in China, Director Luo pointed out that it is imperative to carry out or expand screening for high-risk groups of liver cancer and detect early patients as soon as possible. Precise early screening and stratified health management are economically effective health strategies for preventing liver cancer, which have been included in the national public health strategy and have received multiple policy supports.

Director Luo further introduced the relevant methods for early screening and diagnosis of liver cancer. MiRNA7, as a new peripheral blood nucleic acid detection technology for liver cancer, has a detection rate of 86.1% for extremely early liver cancer, which is 30% higher than the traditional biomarker AFP, demonstrating excellent diagnostic performance; Meanwhile, miRNA7 can accurately identify AFP negative liver cancer patients, with sensitivity and specificity of 77.7% and 84.5%, respectively, significantly better than traditional biomarker detection. With its outstanding performance and powerful early warning capability, miRNA7 has been included in authoritative guidelines such as the "Diagnosis and Treatment Guidelines for Primary Liver Cancer (2024 Edition)".

Subsequently, Director Luo vividly demonstrated the wide application scenarios of miRNA7 in the field of health management through two typical cases. In Case 1, miRNA7 issued a liver cancer risk warning 18 months earlier than imaging, buying valuable time for early treatment. In Case 2, when traditional liver cancer markers (AFP/AFP-L3/DCP) were negative, miRNA7 was still able to accurately indicate tumor risk, successfully assisting in the diagnosis of a 1.5cm small liver cancer, fully demonstrating the unique advantages and important value of miRNA7 in early liver cancer screening.

Nowadays, the multimodal data fusion empowered by artificial intelligence has broken through the barriers of traditional medical data, promoting the evolution of clinical diagnosis and treatment from a single dimension to the "intelligent decision-making" of multi-source data collaboration, helping clinical doctors to more accurately evaluate patients' conditions and significantly improve diagnostic accuracy.

Director Luo pointed out that previous multimodal models, such as GALAD, GAAD, ASAP, lack large-scale Chinese population data and markers at the gene molecular level. The miRNA7 multimodal fusion model, as an innovative solution for early screening and diagnosis of liver cancer, is based on the integration and exploration of large laboratory data in hospitals, covering patient basic information, traditional serological markers, and 7 plasma miRNAs. By constructing a multimodal fusion algorithm for analysis, accurate diagnosis can be achieved. The research results show that the GALADM model is superior to single indicator, single combination of previous indicators, and GALAD model in distinguishing HCC and non-HCC populations in the extremely early and early stages of liver cancer. This model overcomes the limitations of single detection and embodies core values such as multi-dimensional data complementarity and improved accuracy. Its application prospects are very broad.

Finally, Director Luo emphasized that AI driven multimodal models are the core of early screening and management in the future, and have important social value. She hopes that in the future, with the continuous iteration and upgrading of technology, more breakthroughs and innovations can be brought to the prevention and treatment of liver cancer.

This conference continues to promote the transformation from "disease treatment as the center" to "people's health as the center", strengthen the role of "advancing the gateway and extending the service", promote technological innovation and transformation applications, and inject new momentum into the high-quality development of health management disciplines.

Through the successful implementation of the miRNA7 multimodal fusion model, we look forward to collaborating with more health management experts to effectively advance the early detection of cancer in China and contribute to the early realization of the "Healthy China 2030" cancer prevention and control goals!