Medical and health data associated with the use of AI to support a society with longevity is highly sensitive, requiring learning methods through distributed data processing that achieve privacy protection. In well-known secure distributed computation methods, such as Federated Learning, a central server generally plays an important role in aggregating computations. However, for more secure methods, it is desirable to realize machine learning using an autonomous decentralized method that does not use a central server. This paper proposes a learning method with confidentiality by autonomous distributed processing using decomposed data and parameters on multiple server systems uniformly arranged in a ring structure. The advantage of the proposed method is that the data and parameters can always be learned as decomposed data, thus protecting security. In addition, the machine learning method can be implemented using a distributed processing system that is easy to connect and has a uniform structure in which all servers perform the same process, allowing for flexibility in responding to system changes and failures. Based on the proposed method, we propose an algorithm for the Back Propagation method as an example of machine learning application and show its effectiveness.

View full abstract

The purpose of this study is to examine whether ICT education can promote collaborative learning by comparing within and between grade levels using a ready-made questionnaire at College of Physical Therapy. The subjects were 95 first year and 86 second year students at College of Physical Therapy. We actively implemented collaborative learning using tablets in lecture-oriented classes and verified its educational effects using the 10 point scale. The results of the questionnaire showed that almost all of the items were rated seven or higher. Moreover, significant differences were found between some question items for first year and second year students. It has been indicated that our approach may be generally effective in promoting cooperative learning as active learning. In addition, it was considered necessary to consider the differences in curriculum and experience between grades.

View full abstract

Extracorporeal shock wave lithotripsy (ESWL) is a minimally invasive treatment for urinary stones, but optimizing shock wave intensity remains challenging due to its nonlinear effects on treatment outcomes. This study investigates these effects through subgroup analysis of clinical factors to develop a novel framework for enhancing ESWL success. A dataset of 500 cases treated between 2019 and 2022 was analyzed. Patients were divided into subgroups based on clinical factors such as stone size, location, and CT values. Statistical significance was assessed using Welch’s t-tests for subgroup analysis, and multivariate Lasso regression was employed to evaluate independent predictors. For stones ≥ 9 mm, the total energy delivered, calculated as the product of shock wave intensity and the number of shocks, significantly impacted fragmentation success (mean total energy: success group 2.6 ± 0.4 J, failure group 2.1 ± 0.3 J; p < 0.05). In contrast, for stones < 9 mm or across ungrouped data, no significant effects were observed. These findings highlight the importance of subgrouping for understanding nonlinear relationships and suggest that total energy delivered is a more reliable predictor of success for larger stones. The results emphasize the potential to develop individualized ESWL protocols by optimizing total energy delivered, ultimately improving treatment outcomes. This study bridges statistical methods with clinical protocols, providing actionable insights to reduce treatment failure and the burden on patients.

View full abstract