Novel Approach to Onco-Nephrology through Combining Machine-Learning and Prospective Clinical Study

This onco-nephrology research project has the potential to make significant contributions to society, the economy, and academic development: • Society: Integrating artificial intelligence (AI), including deep learning (DL), into onco-nephrology will enable the development of personalized risk prediction models for acute kidney injury (AKI) and acute kidney disease (AKD). These models will enhance early detection and prevention of kidney complications, improving patient outcomes and quality of life. By leveraging wearable devices and multimodal data, the project aims to address unmet medical needs, reduce the burden of kidney-related diseases in cancer patients, and promote better health management. • Economy: Improved predictive models will help optimize healthcare resource allocation by reducing hospital readmissions, dialysis, and unnecessary treatments. Personalized treatment plans tailored to individual risk profiles will lead to more efficient and cost-effective cancer care, benefiting both healthcare systems and patients. This approach supports better utilization of resources and reduces overall healthcare costs. • Academic Development: The project will contribute to the generation of diverse and comprehensive clinical datasets, advancing research in onco-nephrology and precision medicine. Cutting-edge AI-based prediction models will drive innovation in machine learning, nephrology, and oncology. Collaboration with international partners (e.g., Vietnam, Taiwan) will establish a global research network, enabling validation and application of these models in multi-center, multi-country settings. • Innovation: By conducting pre-clinical studies (i.e., a silent testing approach, this project will create new frameworks for integrating AI into healthcare research, setting a precedent for future studies in other medical fields. This effort represents a step toward transforming onco-nephrology into a more precise and globally applicable discipline.