NSF Award
2124224
According to the World Health Organization and the Global Burden of Disease 2010 studies, mental<br/>health issues are a top contributor to global disease and a leading cause of disability worldwide. It is an<br/>enormous personal and societal toll. Mental illness is a common precursor to suicide, and suicidality is<br/>the second leading cause of death in youth and young adults between 10 and 34 years of age. In<br/>economic terms, mental illness exceeds cardiovascular diseases in the projected 2011-2030 cost of<br/>noncommunicable diseases (USD16.3T worldwide). Complicating this picture further is the fact that<br/>mental healthcare is desperately resource-limited, and clinicians treating people for mental health<br/>problems operate in a vacuum between visits. This project proposes a fundamental shift in how machine<br/>learning is used to approach the problem of mental health detection and monitoring, with a technological<br/>investigation that brings together speech analysis, language analysis, and machine learning research,<br/>informed by deep clinical experience and expertise and fueled by ethically collected data. A tiered multiarmed<br/>bandit framework will be used to provide a highly flexible way to evaluate multiple kinds of<br/>evidence in settings where there can be diverse methods for assessment that vary in cost and the value of<br/>the information they provide. As such, it is an excellent fit for the real-world problem of mental health<br/>assessment in resource-limited settings. Investigations will include simulations of patient monitoring<br/>between clinical visits that will be informed by realistic, real-world assumptions and team members'<br/>clinical experience treating patients with schizophrenia, depression, and risk of suicide.<br/><br/>At the core of this project's technical approach is the recognition that the “multi-armed bandit” problem in<br/>machine learning is a good fit for the real-world scenario that mental health providers face when<br/>monitoring a population of patients in treatment: what is the best way to allocate limited resources among<br/>competing choices, given only limited information? This project develops a tiered multi-armed bandit<br/>formulation, where a succession of stages is applied to a population of patients in order to best allocate<br/>different types of resources, each with different per-patient impact but also cost. Conceptually, tiered<br/>approaches are familiar in current medical practice. For example, patient contact typically progresses<br/>from a receptionist, to a nurse or intake coordinator, perhaps to a certified nurse practitioner, to a primary<br/>care doctor, ultimately to a specialist---each step involving corresponding increases in both the cost of the<br/>professional involved and their degree of expertise. The tiered multi-armed bandit model developed by<br/>this award includes concerns of stochastic and adverse selection, where patients at one tier do not proceed<br/>deterministically to the next, even when explicitly selected. It also incorporates complex (e.g., non-linear<br/>such as monotone submodular) objective functions that better capture within-cohort interactions. One<br/>core strength of the tiered model is that it provides a flexible way to incorporate multiple kinds of<br/>evaluative evidence in settings where there can be diverse methods for assessment that vary in cost and<br/>the value of the information they provide. Toward that end, this project also includes both text analysis<br/>and speech analysis components that make use of ethically collected language and speech data and<br/>clinically validated assessments of mental condition. Techniques developed under this award, while<br/>directly motivated by and tested in the mental health setting, will be useful in other settings in both<br/>healthcare as well as other settings where a "prioritization funnel" is in play, including talent sourcing and<br/>customer acquisition.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
