Predictive Approaches for Low-cost Preventive Medicine Program in Developing Countries

Reviewed, Featured
Yukino Baba, Hisashi Kashima, Yasunobu Nohara, Eiko Kai, Partha Ghosh, Rafiqul Islam Maruf, Ashir Ahmed, Masahiro Kuroda, Sozo Inoue, Tatsuo Hiramatsu, Michio Kimura, Shuji Shimizu, Kunihisa Kobayashi, Koji Tsuda, Masashi Sugiyama, Mathieu Blondel, Naonori Ueda, Masaru Kitsuregawa, Naoki Nakashima,
The 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)
(Not Available)
(Not Available)
Sydney, Australia
Non-communicable diseases (NCDs) are no longer just a
problem for high-income countries, but they are also a problem
that affects developing countries. Preventive medicine is
definitely the key to combat NCDs; however, the cost of preventive
programs is a critical issue affecting the popularization
of these medicine programs in developing countries. In
this study, we investigate predictive modeling for providing a
low-cost preventive medicine program. In our two-year-long
field study in Bangladesh, we collected the health checkup
results of 15,075 subjects, the data of 6,607 prescriptions,
and the follow-up examination results of 2,109 subjects. We
address three prediction problems, namely subject risk prediction,
drug recommendation, and future risk prediction, by
using machine learning techniques; our multiple-classifier
approach successfully reduce the costs of health checkups,
a multi-task learning method provide accurate recommendation
for specific types of drugs, and an active learning
method achieve an efficient assignment of healthcare workers
for the follow-up care of subjects.

Data Files