JMIR formative research · 2026
Non-Physician Areas in Japan: Typological Classification Based on Regional Demographic Characteristics.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Kuwayama Takashi, Kotani Kazuhiko
Аннотация
BACKGROUND: Across Japan, there are "non-physician areas" where medical institutions are not present and health care access is difficult. Although these areas are defined as a single administrative category, they may vary according to regional demographic characteristics. Understanding this possible heterogeneity may be important for developing more context-sensitive strategies to improve health care accessibility.
OBJECTIVE: This study examined whether non-physician areas can be classified based on regional demographic characteristics using an unsupervised machine learning model.
METHODS: A total of 590 non-physician areas were identified from the national survey conducted by the Ministry of Health, Labour and Welfare of Japan (2019). Data on regional demographic characteristics were also obtained. After z score standardization, k-means clustering was used for classification. The optimal number of clusters was determined using silhouette scores. The data on non-physician areas were divided into training (354/590, 60.0% areas) and validation (236/590, 40.0% areas) datasets. The reproducibility of the cluster structure was evaluated using Jensen-Shannon distance and chi-square tests, and principal component analysis (PCA) was used to examine the overall structure of the clusters.
RESULTS: The optimal number of clusters was 3 (silhouette score=0.266), indicating that non-physician areas could be classified into 3 types. The cluster distributions of the training and validation datasets were consistent (Jensen-Shannon distance=0.017; P=.76), supporting the reproducibility of the cluster structure. The PCA suggested that differences among non-physician areas could be interpreted along 2 axes, including population age structure and settlement size. The 3 clusters represented younger, intermediate, and older types, characterized by differences in demographic and settlement characteristics.
CONCLUSIONS: The present study demonstrated that administratively defined non-physician areas in Japan are not uniform and can be classified into 3 demographically distinct types. The typology may provide a framework for understanding differences not captured by the current administrative designation and for considering more context-sensitive health care strategies.
OBJECTIVE: This study examined whether non-physician areas can be classified based on regional demographic characteristics using an unsupervised machine learning model.
METHODS: A total of 590 non-physician areas were identified from the national survey conducted by the Ministry of Health, Labour and Welfare of Japan (2019). Data on regional demographic characteristics were also obtained. After z score standardization, k-means clustering was used for classification. The optimal number of clusters was determined using silhouette scores. The data on non-physician areas were divided into training (354/590, 60.0% areas) and validation (236/590, 40.0% areas) datasets. The reproducibility of the cluster structure was evaluated using Jensen-Shannon distance and chi-square tests, and principal component analysis (PCA) was used to examine the overall structure of the clusters.
RESULTS: The optimal number of clusters was 3 (silhouette score=0.266), indicating that non-physician areas could be classified into 3 types. The cluster distributions of the training and validation datasets were consistent (Jensen-Shannon distance=0.017; P=.76), supporting the reproducibility of the cluster structure. The PCA suggested that differences among non-physician areas could be interpreted along 2 axes, including population age structure and settlement size. The 3 clusters represented younger, intermediate, and older types, characterized by differences in demographic and settlement characteristics.
CONCLUSIONS: The present study demonstrated that administratively defined non-physician areas in Japan are not uniform and can be classified into 3 demographically distinct types. The typology may provide a framework for understanding differences not captured by the current administrative designation and for considering more context-sensitive health care strategies.