Advanced search
Start date
Betweenand
Related content
(Reference retrieved automatically from Web of Science through information on FAPESP grant and its corresponding number as mentioned in the publication by the authors.)

Overachieving Municipalities in Public Health: A Machine-learning Approach

Full text
Author(s):
Porto Chiavegatto Filho, Alexandre Dias [1, 2] ; dos Santos, Hellen Geremias [2] ; do Nascimento, Carla Ferreira [2] ; Massa, Kaio [2] ; Kawachi, Ichiro [1]
Total Authors: 5
Affiliation:
[1] Harvard TH Chan Sch Publ Hlth, Dept Social & Behav Sci, Boston, MA - USA
[2] Univ Sao Paulo, Sch Publ Hlth, Dept Epidemiol, 715 Av Dr Arnaldo, BR-01246904 Sao Paulo, SP - Brazil
Total Affiliations: 2
Document type: Journal article
Source: EPIDEMIOLOGY; v. 29, n. 6, p. 836-840, NOV 2018.
Web of Science Citations: 1
Abstract

Background: Identifying successful public health ideas and practices is a difficult challenge towing to the presence of complex baseline characteristics that can affect health outcomes. We propose the use of machine learning algorithms to predict life expectancy at birth, and then compare health-related characteristics of the under- and overachievers (i.e., municipalities that have a worse and better outcome than predicted, respectively). Methods: Our outcome was life expectancy at birth for Brazilian municipalities, and we used as predictors 60 local characteristics that are not directly controlled by public health officials (e.g., socioeconomic factors). Results: The highest predictive performance was achieved by an ensemble of machine learning algorithms (cross-validated mean squared error of 0.168), including a 35% gain in comparison with standard decision trees. Overachievers presented better results regarding primary health care, such as higher coverage of the massive multidisciplinary program Family Health Strategy. On the other hand, underachievers performed more cesarean deliveries and mammographies and had more life-support health equipment. Conclusions: The findings suggest that analyzing the predicted value of a health outcome may bring insights about good public health practices. (AU)

FAPESP's process: 17/09369-8 - Cause-specific mortality prediction with machine learning on a longitudinal sample of 502,632 individuals
Grantee:Alexandre Dias Porto Chiavegatto Filho
Support Opportunities: Regular Research Grants