Healthcare Expenditure Prediction with Neighbourhood Variables – A Random Forest Model
Datos Bibliográficos
| ID | 8021028 |
|---|---|
| Autores | Sigrid M Mohnen (0000-0002-1537-8706, National Institute for Public Health and the Environment), Adriënne H Rotteveel (0000-0002-3395-0147, Erasmus University Rotterdam, autor de correspondencia), G Doornbos (National Institute for Public Health and the Environment), Johan Polder (0000-0002-3231-2178, National Institute for Public Health and the Environment) |
| Año | 2020 |
| Volumen | 11 |
| Número | 2 |
| Páginas | 111-138 |
| Fecha de publicación | 2020-09-30 |
| Peer Reviewed | Sí |
| Open Access | Sí |
| Tipo | ARTICLE |
| Revista | Statistics Politics and Policy (JOURNAL) |
| Identificadores de la revista | ISSN: 2151-7509 • E-ISSN: 2194-6299 |
| Editorial | De Gruyter (PUBLISHER • DE) |
| DOI | 10.1515/spp-2019-0010 |
| OpenAlex | W3090966930 |
| Idioma | EN |
| Citas recibidas | 1 |
| Referencias citadas | 57 |
We investigated the additional predictive value of an individual’s neighbourhood (quality and location), and of changes therein on his/her healthcare costs. To this end, we combined several Dutch nationwide data sources from 2003 to 2014, and selected inhabitants who moved in 2010. We used random forest models to predict the area under the curve of the regular healthcare costs of individuals in the years 2011–2014. In our analyses, the quality of the neighbourhood before the move appeared to be quite important in predicting healthcare costs (i.e. importance rank 11 out of 126 socio-demographic and neighbourhood variables; rank 73 out of 261 in the full model with prior expenditure and medication). The predictive performance of the models was evaluated in terms of R 2 (or proportion of explained variance) and MAE (mean absolute (prediction) error). The model containing only socio-demographic information improved marginally when neighbourhood was added ( R 2 +0.8%, MAE −€5). The full model remained the same for the study population ( R 2 = 48.8%, MAE of €1556) and for subpopulations. These results indicate that only in prediction models in which prior expenditure and utilization cannot or ought not to be used neighbourhood might be an interesting source of information to improve predictive performance
Econometrics · Economics · Geography · Health care · Neighbourhood (mathematics · Sociology · Statistics · Variance (accounting · Demography · Global Health Care Issues · Health disparities and outcomes · Mathematics · Medicine · Urban Transport and Accessibility
Neighborhood Effects on the Long-Term Well-Being of Low-Income Adults
Health benefits of green spaces in the living environment
Sources of Geographic Variation in Health Care
Physical activity level and health-related quality of life in the general adult population
Physical Activity and Public Health
Ranger
Ecological Approaches
An Ecological Approach to Creating Active Living Communities
Random Forests
Neighborhoods and health
Matching Methods for Causal Inference
Nature and Health
Moving to Opportunity in Boston
The Effects of Exposure to Better Neighborhoods on Children
Is socioeconomic status associated with utilization of health care services in a single-payer universal health care system
Incorporating machine learning and social determinants of health indicators into prospective risk adjustment for health plan payments
The Association between Neighborhood Social Capital and Cancer Screening
Does living by the coast improve health and wellbeing
Neighborhood Effects on Health
Using natural experiments to evaluate population health interventions
Mother-Perceived Social Capital and Children’s Oral Health and Use of Dental Care in the United States
Diagnosis-based Cost Groups in the Dutch Risk-equalization Model
Towards a capitation formula for competing health insurers. An empirical analysis
From social integration to health
Mandatory pooling as a supplement to risk-adjusted capitation payments in a competitive health insurance market
Assessing 'Neighborhood Effects
| Obras citantes distintas | 1 |
|---|---|
| Citas por año | 0,2 |
| Intervalo de citas | 2021 - 2021 (1) |
| Velocidad de citación | historical |
| Altamente citado | No |
| Tipos de cita | Neutras: 1 |