The latest research result of Digital Phenotyping-based Depression Detection in the Presence of Comorbidity: An Uncertainty Reasoning, a key international (regional) cooperative research project led by Professor Yan Zhijun Recently published in Journal of Management Information Systems, the international top journal of Information System. The study presents an uncertainty inference method exploring the number-phenotype-based detection of depression in complication cases. The research results were completed by Professor Yan Zhijun team in collaboration with Professor Dongsong Zhang from the University of North Carolina at Charlotte.
Depression is an growing health and social problem, causes significant economic and health losses. Detection and diagnosis of depression has been very challenging, especially for patients with concurrent other complications. Digital phenotyping is a technique to detect mental illness, which has become a very promising tool in the field of automatic detection of depression. However, existing digital phenotype-based tests for depression do not account for diagnostic uncertainty caused by similar symptoms shared between depression and other complications, which may negatively affect detection accuracy. This paper presents a novel deep learning model that processes and incorporates data from multiple sensors and addresses the problem of diagnostic uncertainty based on evidence theory. Experimental results show that the proposed model has better performance than existing models. This work proposes a new AI-based treatment method for uncertainty problems, which improves the accuracy of depression detection under complications, and makes an important contribution to the design of scientific and mental health research.
The Journal of Management Information Systems is one of the 50 top business school journals rated by the Financial Times (Financial Times 50 Journals, FT50). FT50 is used to evaluate the research ability of business schools, which is highly recognized internationally. It is an important basis for the Financial Times to rank business schools. Its journals cover many fields such as economics, strategic management, organization and human resources, operational management, information management, financial accounting, finance and other fields.
Reference: Fei Peng, Dongsong Zhang, Zhijun Yan (2024) Digital Phenotyping-based Depression Detection in the Presence of Comorbidity: An Uncertainty Reasoning Approach, Journal of Management Information Systems, 41:4, 931-957, DOI: 10.1080/07421222.2024.2415770
