Regional medical inter-institutional cooperation in medical provider network constructed using patient claims data from Japan

TL;DR

This study constructs and analyzes medical provider networks from patient claims data in Japan to evaluate how cooperation among providers impacts healthcare quality, especially hospital stay duration, using advanced network features and machine learning.

Contribution

The paper introduces a novel approach to quantify medical cooperation's impact on healthcare quality by incorporating provider usage patterns and advanced network features like node2vec.

Findings

Stronger medical provider cooperation reduces hospital stay duration.

Node2vec features explain about 20% of the variation in hospital stay.

Advanced network features outperform simple strength measures in explaining healthcare outcomes.

Abstract

The aging world population requires a sustainable and high-quality healthcare system. To examine the efficiency of medical cooperation, medical provider and physician networks were constructed using patient claims data. Previous studies have shown that these networks contain information on medical cooperation. However, the usage patterns of multiple medical providers in a series of medical services have not been considered. In addition, these studies used only general network features to represent medical cooperation, but their expressive ability was low. To overcome these limitations, we analyzed the medical provider network to examine its overall contribution to the quality of healthcare provided by cooperation between medical providers in a series of medical services. This study focused on: i) the method of feature extraction from the network, ii) incorporation of the usage pattern of medical providers, and iii) expressive ability of the statistical model. Femoral neck fractures were selected as the target disease. To build the medical provider networks, we analyzed the patient claims data from a single prefecture in Japan between January 1, 2014 and December 31, 2019. We considered four types of models: a model using node strength and linear regression to a model using feature representation by node2vec and regression tree ensemble, which is a machine learning method. The results showed that a stronger medical provider reduces the duration of hospital stay. The overall contribution of the medical cooperation to the duration of hospital stay extracted from the medical provider network using node2vec is approximately 20%, which is approximately 20 times higher than the model using strength.