Designing Social Care Plans by Grouping Services and Patients in Mixed Cohorts: A Study using Regression versus Neural Nets
Sotirios Raptis *
School of Design and Informatics, Abertay University, Dundee (AUD), Bell Street, Dundee DD1 1HG, Scotland, UK and National Health Services (NHS) Scotland, Gyle Square, 1 South Gyle Crescent, Edinburgh, EH12 9EB, Scotland, UK and MacMillan Cancer Support UK, Caledonian Exchange, 19A Canning St, Edinburgh EH3 8EG, UK.
*Author to whom correspondence should be addressed.
Abstract
Aims: Linking social needs to social classes using different criteria may lead to social services misuse. The paper discusses using ML and Neural Nentwoks (NNs) in linking public services in Scotland in the long term and advocates this can result in a reduction of the services cost connecting resources needed in groups for similar servicesters.
Study Design: The work is based on public data from 22 services offered by Public Health Services (PHS) Scotland that break down into 110 years series called factors.
Place and Duration of Study: NHSS and Abertay University, Dundee, from 2018 to 2020
Methodology: The paper discusses using ML and Neural Nentwoks (NNs). The paper combines typical regression models with clustering and cross-correlation as complementary constituents to predict the demand. uses Linear Regression (LR), Autoregression (ARMA) and 3 types of backpropagation (BP) Neural Networks (BPNN) to link them under specific conditions.
Results: Relationships found were between smoking related healthcare provision, mental health related health serices, and epidemilogical weight in Primary 1(Education) Body Mass Index (BMI) in chlildren. Primary component analysis (PCA) found 11 significant factors while C-Means (CM) clustering gave 5 major factors clusters.
Conclusion: Insurance companies and public policymakers can pack linked services such as those offered to the elderly or to low-income people in the longer term.
Keywords: Probability, cohorts, data frames, services, prediction