Regression
JADBio includes many types of regression models. The key indicator that JADBio will perform a regression analysis is found in your data; the predicted outcome is a continuous run of numbers. The example use case we provide for regression is based on a dataset published as part of a study in the progression of Parkinson’s disease. JADBio is able to produce accurate predictive models regardless of your expertise in advanced machine learning techniques.
Monitoring Parkinson’s Progression from Home
Physicians treating patients with Parkinson’s disease (PD) monitor progression via the Unified Parkinson Disease Rating Scale (UPDRS). These methods are costly and hinder recruitment for future large-scale clinical trials. Clinical information and twenty different speech signals from 5785 individuals with varying severities of progression were uploaded onto the JADBio platform to measure the relevance and accuracy of an at-home speech test. Read more: Accurate Telemonitoring of Parkinson’s
The analysis qualified two out of 90 predictive models that were trained and tested within 18 minutes. The Best Performing Model, based on Regression Random Forrest (R2 =.802) far outperformed the Best Interpretable Model, which was based on Ridge Linear Regression (R2 = .136). While age and sex are still strong predictors of outcome, five attributes of the speech test also have significant predictive value.
#predictiveanalytics #Parkinson’s #speech #VoiceAI #patientcare
OTHER
Do you have questions?
JADBio can meet your needs. Ask one of our experts for an interactive demo.
Stay connected to get our news first!
Do you have questions?
JADBio can meet your needs. Ask one of our experts for an interactive demo.
Join the JADai Community!
Sign up with a FREE Basic plan! Be part of a growing community of AutoML enthusiasts
GET STARTED
