Deepak Gupta, M.B.B.S., associate professor of neurological sciences at the Larner College of Medicine, is quoted in NR Times discussing the Clinical Decision Support platform for Parkinson’s Disease, or CDS-PD, which uses machine learning, a form of AI that spots patterns in data, to support a physician’s clinical decision-making in real time during a patient’s visit with a Parkinson’s specialist.
CDS-PD combines information collected during the visit with standard clinical diagnostic criteria to classify a patient’s diagnosis at the point of care. It also uses machine learning to perform disease subtyping and compute prognosis measures based on commonly collected clinical scales.
The multicenter research project was led by Dr. Gupta, who also is director of clinical informatics for neurology at UVM Health and a movement disorders neurologist at the UVM Medical Center.
“Artificial intelligence-driven clinical informatics tools like CDS-PD have the potential to bridge the gap between availability of diagnostic criteria and clinical practice guidelines to improve the accuracy of diagnoses,” Gupta says.
Using CDS-PD, Gupta and his colleagues showed for the first time in a prospective study of US veterans that Parkinson’s patients with exposure to Agent Orange might have lower cognitive performance and greater patient-reported motor disability compared with patients without such exposure.
The researchers are now expanding CDS-PD to investigate AI-based methods of studying cognitive decline in Parkinson’s disease and to implement a practical diagnostic algorithm to help general neurologists distinguish between Parkinson’s disease and related atypical parkinsonian disorders.
In future, they plan to make the platform interoperable with electronic health record systems and integrate it with Ambient AI in clinical practice.