We analyzed Activities of Daily Living (ADLs) of 296,051 residents in the US Veterans Affairs nursing homes called Community Living Centers (CLCs) between 1/1/2000 and 9/10/2012. Data were used to classify patients as having feeding (F), bathing (B), grooming (G), dressing (D), bowel continence (L), bladder continence (U), toilet use (T), transfers (S), and walking disabilities (W). In the data, total patients’ visits resulted in 1,820,714 assessments which were used for predictions after excluding the cases with one assessment.
For our predictions, we have used several advanced Machine Learning (ML) algorithms with the above dataset. The technical details of the algorithms will be accessible soon through the scientific articles we are putting forward for publications.