Objective and Rationale: Currently, two of the most important challenges faced by clinicians and researchers in the field of Parkinson's disease (PD) are forecasting of accurate diagnosis and likely course of the disease in an individual patient. With respect to PD in Veterans, several studies have shown that exposure to neurotoxins, such as Agent Orange, is associated with increased risk of PD. To this end, PD is a presumptive condition for Veterans who served in a certain place (Vietnam, Korean Demilitarized Zone, and Camp Lejeune) during a certain time period, under the assumptions that they might have been exposed to toxins (such as Agent Orange). However, there have been limited or no research on whether there are differences in PD associated with Agent Orange exposure in Veterans versus PD not associated with Agent Orange exposure in non-Veterans, especially with respect to the accuracy of diagnosis. PD is diagnosed by primary care physicians, neurologists, and movement disorders neurologists based on the presence of key movement symptoms and signs, such as slowness of movement with rest tremor and/or increase in muscle tone. However, such clinical diagnosis can be inaccurate as these symptoms can also be present in other conditions related to PD, such as Lewy body dementia and atypical Parkinsonian syndromes. The Movement Disorders Society, a leading organization of PD specialists, has created criteria for diagnosis for PD with high accuracy. However, these criteria are significantly complex and impractical in clinic, especially in primary care and general neurology clinics. Beyond the diagnosis, the most important question faced by PD patients and their clinicians is that of prognosis, that is, how will the patient's disease progress in the future? Currently, there are no tools available to clinicians to forecast such prognosis for an individual patient. The proposed study aims to develop a tool, the Ontology-based, Real-time, Machine learning Informatics System for Parkinson's Disease (ORMIS-PD) platform, to address these unmet needs.

Applicability and Impact: This proposal addresses the "Innovative data analytic methods" section of the Focus Area "Clinical and research application of digital health technology leading to development of new treatments for Parkinson's disease in those individuals exposed to neurotoxins." As part of Aim 1, development of ORMIS-PD platform will occur. It will be designed to enable capturing of the patient's clinical information (symptoms and signs) collected institutively via a touch-screen interface in a clinician-friendly manner. Then, ORMIS-PD will automatically reconcile the collected information with the Movement Disorders Society criteria for computer-aided diagnosis of the patient. Furthermore, the ORMIS-PD platform will automatically calculate the prognosis score from the collected information, and then apply the artificial intelligence method, driven by data of a large PD database, Parkinson Progression Marker Initiative, for forecasting future changes in the prognosis score. As part of Aim 2, clinical information of PD patients will be collected using ORMIS-PD for two groups, one group with Agent Orange exposure and another group without Agent Orange exposure, at two sites, namely, University of Vermont Medical Center and Oregon Health & Science University/Portland Veterans Affairs Medical Center. Afterwards, the two groups will be compared with respect to their ORMIS-PD generated diagnosis and prognosis score. Ultimately, the proposed research project will lay the groundwork for application of artificial intelligence approaches for improving PD diagnosis and predicting progression.

Principal Investigator Career Goals: Driven by a deep personal connection with PD, Dr. Gupta, the Principal Investigator in this proposal, has devoted his career to PD since the very beginning of his medical career. Dr. Gupta did his neurology residency training with dedicated research track focused in PD at Case Western Reserve University, one of the collaborating institutions on this project, and fellowship training in Movement Disorders (PD) at Columbia University, during which he successfully carried out several small but novel research projects in PD. Since he started as faculty at University of Vermont, Dr. Gupta has committed to developing a niche in the application of clinical informatics to advance PD research, and the proposed project is a further reflection of that commitment. Dr. Gupta is currently enrolled in a clinical informatics graduate program at Oregon Health and Science University, another collaborating institution on this project. This graduate program will equip him with the knowledge and skills in informatics to develop and conduct this project, as it is outlined in his Researcher Development Plan. Dr. Gupta will also undertake additional coursework as part of this project to expand his expertise in clinical and translational research. The research plan outlined in this proposal will allow Dr. Gupta to develop and conduct a multi-institution clinical informatics and research project in the field of PD, one of the fastest growing sub-disciplines in medical research. His two mentors, Dr. Boyd, a clinician-investigator mentor, and Dr. Sahoo, an informatics mentor, each fill a knowledge niche in Dr. Gupta's training as a translational physician-scientist in neurology.