The primary research focus of Feichen Shen, Ph.D., is to develop innovative methodologies and applications for artificial intelligence (AI), machine and deep learning, graph and data mining, ontologies, and semantic web. The goal of his research is to apply these techniques to improve health care delivery and facilitate translational studies.
- AI-driven, rare disease differential diagnosis. Due to the uncommon nature of rare diseases, clinical evidence and empirical knowledge remain largely undiscovered, which often contributes to diagnostic odysseys. Dr. Shen aims to develop generic AI and machine learning techniques based on large numbers of biomedical knowledge bases, literature reviews and electronic health records to accelerate early differential diagnosis for rare diseases.
- Precision oncology. Cancer is responsible for millions of deaths worldwide every year. Although significant progress has been achieved in cancer medicine, many issues remain to be addressed for improving cancer therapy. Drug repurposing provides ways to identify new uses for approved drugs that are outside the scope of the original medical indication. However, drug repurposing is challenging to implement, as patients with cancer are of known heterogeneous genetic makeups and phenotypic differences. Dr. Shen's team aims to develop a precision drug repurposing framework leveraging AI and biomedical informatics.
- Deep phenotyping for precision medicine. It is challenging to make accurate phenotypic characterizations for patients and detect proper associations between genotype and phenotype because the amount of data contained in electronic health records is overwhelming. By developing state-of-the-art graph mining techniques, Dr. Shen aims to incorporate knowledge-driven insights from heterogeneous knowledge resources into clinical data to precisely characterize patients for optimized health care delivery.
Significance to patient care
Dr. Shen's work uncovers biomedical and clinical information buried in heterogeneous data sources and establishes semantic interoperability between public biomedical knowledge and clinical data. His work has potential to improve clinical diagnostic decision-making.
- Recipient, Gerstner Family Career Development Award, Mayo Clinic Center for Individualized Medicine, 2020