Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network

<i>Objective</i>: This study aims to determine the characteristics of Type 2 diabetic patients who are more likely to cause high-cost medical expenses using the Bayesian network model. <i>Methods</i>: The 2011–2015 receipt data of Iwamizawa city, Japan were collected from the...

Full description

Bibliographic Details
Main Authors: Yuji Sase, Daiki Kumagai, Teppei Suzuki, Hiroko Yamashina, Yuji Tani, Kensuke Fujiwara, Takumi Tanikawa, Hisashi Enomoto, Takeshi Aoyama, Wataru Nagai, Katsuhiko Ogasawara
Format: Article
Language:English
Published: MDPI AG 2020-07-01
Series:International Journal of Environmental Research and Public Health
Subjects:
Online Access:https://www.mdpi.com/1660-4601/17/15/5271
id doaj-a688fd6dfc39430f9d36641229a07740
record_format Article
spelling doaj-a688fd6dfc39430f9d36641229a077402020-11-25T03:02:15ZengMDPI AGInternational Journal of Environmental Research and Public Health1661-78271660-46012020-07-01175271527110.3390/ijerph17155271Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian NetworkYuji Sase0Daiki Kumagai1Teppei Suzuki2Hiroko Yamashina3Yuji Tani4Kensuke Fujiwara5Takumi Tanikawa6Hisashi Enomoto7Takeshi Aoyama8Wataru Nagai9Katsuhiko Ogasawara10Faculty of Medical Informatics, Hokkaido Information University, Hokkaido 069-8585, JapanSchool of Health Sciences, Hokkaido University, Hokkaido 060-0812, JapanArt & Sports Business, Iwamizawa, Hokkaido University of Education, Hokkaido 068-8642, JapanFaculty of Health Sciences, Hokkaido University, Hokkaido 060-0812, JapanDepartment of Medical Informatics and Hospital Management, Asahikawa Medical University, Hokkaido 078-8510, JapanGraduate School of Commerce, Otaru University of Commerce, Hokkaido 047-8501, JapanFaculty of Health Sciences, Hokkaido University of Science, Hokkaido 006-8585, JapanIwamizawa City, Hokkaido 068-0828, JapanIwamizawa City, Hokkaido 068-0828, JapanIwamizawa City, Hokkaido 068-0828, JapanFaculty of Health Sciences, Hokkaido University, Hokkaido 060-0812, Japan<i>Objective</i>: This study aims to determine the characteristics of Type 2 diabetic patients who are more likely to cause high-cost medical expenses using the Bayesian network model. <i>Methods</i>: The 2011–2015 receipt data of Iwamizawa city, Japan were collected from the National Health Insurance Database. From the record, we identified patients with Type 2 diabetes with the following items: age, gender, area, number of days provided medical services, number of diseases, number of medical examinations, annual healthcare expenditures, and the presence or absence of hospitalization. The Bayesian network model was applied to identify the characteristics of the patients, and four observed values were changed using a model for patients who paid at least 3607 USD a year for medical expenses. The changes in the conditional probability of the annual healthcare expenditures and changes in the percentage of patients with high-cost medical expenses were analyzed. <i>Results</i>: After changing the observed value, the percentage of patients with high-cost medical expense reimbursement increased when the following four conditions were applied: the patient “has ever been hospitalized”, “had been provided medical services at least 18 days a year”, “had at least 14 diseases listed on medical insurance receipts”, and “has not had specific health checkups in five years”. <i>Conclusions</i>: To prevent an excessive rise in healthcare expenditures in Type 2 diabetic patients, measures against complications and promoting encouragement for them to undergo specific health checkups are considered as effective.https://www.mdpi.com/1660-4601/17/15/5271health economicsbayesian networkdiabetesNational Health Insurancemedical costsspecific health checkups
collection DOAJ
language English
format Article
sources DOAJ
author Yuji Sase
Daiki Kumagai
Teppei Suzuki
Hiroko Yamashina
Yuji Tani
Kensuke Fujiwara
Takumi Tanikawa
Hisashi Enomoto
Takeshi Aoyama
Wataru Nagai
Katsuhiko Ogasawara
spellingShingle Yuji Sase
Daiki Kumagai
Teppei Suzuki
Hiroko Yamashina
Yuji Tani
Kensuke Fujiwara
Takumi Tanikawa
Hisashi Enomoto
Takeshi Aoyama
Wataru Nagai
Katsuhiko Ogasawara
Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network
International Journal of Environmental Research and Public Health
health economics
bayesian network
diabetes
National Health Insurance
medical costs
specific health checkups
author_facet Yuji Sase
Daiki Kumagai
Teppei Suzuki
Hiroko Yamashina
Yuji Tani
Kensuke Fujiwara
Takumi Tanikawa
Hisashi Enomoto
Takeshi Aoyama
Wataru Nagai
Katsuhiko Ogasawara
author_sort Yuji Sase
title Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network
title_short Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network
title_full Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network
title_fullStr Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network
title_full_unstemmed Characteristics of Type-2 Diabetics Who are Prone to High-Cost Medical Care Expenses by Bayesian Network
title_sort characteristics of type-2 diabetics who are prone to high-cost medical care expenses by bayesian network
publisher MDPI AG
series International Journal of Environmental Research and Public Health
issn 1661-7827
1660-4601
publishDate 2020-07-01
description <i>Objective</i>: This study aims to determine the characteristics of Type 2 diabetic patients who are more likely to cause high-cost medical expenses using the Bayesian network model. <i>Methods</i>: The 2011–2015 receipt data of Iwamizawa city, Japan were collected from the National Health Insurance Database. From the record, we identified patients with Type 2 diabetes with the following items: age, gender, area, number of days provided medical services, number of diseases, number of medical examinations, annual healthcare expenditures, and the presence or absence of hospitalization. The Bayesian network model was applied to identify the characteristics of the patients, and four observed values were changed using a model for patients who paid at least 3607 USD a year for medical expenses. The changes in the conditional probability of the annual healthcare expenditures and changes in the percentage of patients with high-cost medical expenses were analyzed. <i>Results</i>: After changing the observed value, the percentage of patients with high-cost medical expense reimbursement increased when the following four conditions were applied: the patient “has ever been hospitalized”, “had been provided medical services at least 18 days a year”, “had at least 14 diseases listed on medical insurance receipts”, and “has not had specific health checkups in five years”. <i>Conclusions</i>: To prevent an excessive rise in healthcare expenditures in Type 2 diabetic patients, measures against complications and promoting encouragement for them to undergo specific health checkups are considered as effective.
topic health economics
bayesian network
diabetes
National Health Insurance
medical costs
specific health checkups
url https://www.mdpi.com/1660-4601/17/15/5271
work_keys_str_mv AT yujisase characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT daikikumagai characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT teppeisuzuki characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT hirokoyamashina characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT yujitani characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT kensukefujiwara characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT takumitanikawa characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT hisashienomoto characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT takeshiaoyama characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT watarunagai characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
AT katsuhikoogasawara characteristicsoftype2diabeticswhoarepronetohighcostmedicalcareexpensesbybayesiannetwork
_version_ 1724690647467687936