This is a Posture Activity Model that predicts out the likely number of patients who will be suffering from posture related diseases.
Hospitals and Payors (Insurance companies) are trying to setup targeted disease management & patient engagement programs and one among the interests is finding out the likely number of patients who will be suffering from posture related related diseases. Model is able to predict the posture the patient has been exposed to for longer time. It can be used to predict posture related diseases at early stage by actively monitoring the sitting / standing /walking posture among the patients. Market Impact: Healthcare costs reduced by 13% in patients with regular physical activity. This is on an average – 700$ per person It leverages various AzureML Studio components as well as custom R code for data cleansing and feature engineering. Identifying variables for Classification model Filter based Feature Selection, linear Correlation, Multi Collinearity, Statistical test. Input: We propose a dataset with 5 classes (sitting-down, standing-up, standing, walking, and sitting) collected on 8 hours of activities of 4 healthy subjects. Data has been collected from http://groupware.les.inf.puc-rio.br, having 165,633 number of records with 19 feature variables (Columns) with the help of accelerometer placed on different parts of the body. Output: The output of the model is the type of posture that a patient has been exposed to for longer time at any part of the day. Author: Shubham Gupta & Ajaykarthick S. are a Data Science Learner @ Cognizant Technology Solutions