Penn’s researcher has awarded $ 8 million to advance mental health diagnostics using AI

How can artificial intelligence (AI) and automatic learning (ML) be used to develop more precise psychiatric phenotypes for diagnostics and treatment of mental health care? This objective is what the Senior FELLOW and Penn Medicine Professor Yong Chen, Phdwill work for the next five years in a project that has the potential to revolutionize the way in which mental health disorders are studied and treated.

Chen, who directs both Penn Computer, inference and learning lab (Penncil) and the Center for Health IA and synthesis of evidence (Chase) received a subsidy of $ 8 million from the National Institute of Mental Health, as well as the University of Yale and Mayo Clinic. He will run the data coordination center for a multidisciplinary collaborative research project – the most $ 150 million Phenotypes measured individually to advance the translation of calculation in mental health (Impact-MH) Initiative. Eight teams will use behavioral measures and calculation methods to define new profiles of clinical patients to support clinical decision -making in mental health care.

New integrated data type

“The Impact-MH project is very unique because it seeks to apply concepts of precision medicine in the field of mental health, where heterogeneity is particularly difficult,” said Chen, professor of biostatistics, epidemiology and computer science at the Perelman School of Medicine. “The integration of multimodal data, including behavioral, clinical and biological information, in IT phenotyping is a revolutionary approach that promises to revolutionize patient care by making diagnostics and mental health and more personalized, precise and focused on data. This level of integration is not yet current in mental health research. ”

“The project is distinct from our other work in its ambitious scale and concentration,” continued Chen. “While Penncil has a vast experience of calculation methods, automatic learning and AI in various clinical fields, this project is unusual in its application to the complexities of mental disorders. It also distinguishes itself from its multi-institutional collaboration, aimed at establishing new standards for the collection of mental health data, its representation and its analysis. ”

Beyond the observable

Currently, mental health clinicians are faced with major obstacles due to too large diagnostic categories and a lack of profiles of patients clearly defined, making treatment decisions more difficult. They may find it difficult to capture the complete image using standard tools such as control lists or interviews, based strongly on the observable, but two patients with the same diagnosis can have different symptoms and respond differently to treatment.

A phenotype is the set of characteristics or features of an individual. In mental health, this may include symptoms and behaviors, cognitive performance, organic markers such as the results of brain imaging and hormone levels and responses to treatment. A clinical phenotype is a detailed profile of how a person’s condition is presented – not only in symptoms but in these different biological, psychological and behavioral fields.

Tailor -made treatment approaches

“In a clinical situation, the finished Impact-MH product could be used to improve the diagnosis, prognosis and personalization of treatment,” said Chen. “For example, clinicians could use these signatures to predict how individual patients could react to specific treatments, follow their progress more effectively and make more informed decisions concerning the evolution of treatment. The objective is to promote personalized care, reduce the heterogeneity of mental health diagnostics and improve patient results by adapting processing approaches according to new types of clinical signatures. “