This paper proposes a method for evaluating and scoring the activities of rehabilitation service users in order to pinpoint the problems with the health service of this kind and set the adequate targets for each user. Sincs the Nursing Care Insurance System was introduced in Japan in 2000, it has been argued that home-visit rehabilitation services should be excluded from home-nursing care services. However, the methods of certifing that nursing care is required are not fully established yet for setting the rehabilitation targets for service users. As things stand, it is recommended that such a method as the Functional Independence Measure (FIM) or the Barthel Index (BI) should be utilized. However, these methods only evaluate “performing activities” (the activities that a user usually performs). In order to set the users' targets, we thought it necessary to establish a method for evaluating “possible activities” (the activities that a user is able to perform at his/her full capacity). We have established a method called Functional Scoring (FS) which evaluates and scores the both performing and possible activities based on the same evaluation items. We conducted experimental evaluations on the home-visit rehabilitation users for one year from October 2005 to September 2006. When the first evaluations in 2005 were compared with the second evaluations in 2006, the total score of the performing activities significantly increased from 44.1±13.7 to 47.8±14.2 (P<0.05). Although the total score of the possible activities did not significantly increase, it demonstrated an upward trend from 49.6±13.2 to 51.6±13.5. The result suggests that our method is useful for distinguishing between the performing and possible activities. The proposed method enables us to adequately recognize the problems each user has, and to set the rehabilitation target for each user, which can be shared between the user, care personnel, and care service provider.
Rehabilitation aspects ; Functional ; FS ; Care given by nurses ; Published Comment

Rehabilitative intervention led to some improvement in bodily function in a patient with amyotrophic lateral sclerosis (ALS) and aspiration pneumonia. By alleviating dyspnea and providing successful supportive care, he improved his sitting position in a wheelchair and reacquired transfer skills. Achieving this reduced burden on his primary caregiver. During rehabilitation, our multidisciplinary team considered the necessary support and care required for the patient to live at home in a sparsely populated area. As a result, we plan to improve his home life after discharge. This stimulated hope and motivation in both the patient and his caregiver to improve his home life, and their increased motivation led them to participate in ALS group meetings. Ultimately, the patient was discharged home.

Objective: Currently, limited information is available on the milk transfer properties of drugs when consumed by lactating women. Therefore, we aim to construct a prediction model of milk transfer of drugs using machine learning methods.Methods: We obtained data from Hale’s Medications & Mothers’ Milk (MMM) and SciFinder®, and then constructed the datasets. The physicochemical and pharmacokinetic data were used as feature variables with M/P ratio ≥ 1 and M/P ratio < 1 as the objective variables, classified into two groups as the classification of milk transferability. In this study, analyses were conducted using machine learning methods: logistic regression, linear support vector machine (linear SVM), kernel method support vector machine (kernel SVM), random forest, and k-nearest neighbor classification. The results were compared to those obtained with the linear regression equation of Yamauchi et al. from a previous study. The analysis was performed using scikit-learn (version 0.24.2) with python (version 3.8.10).Results: Model construction and validation were performed on the training data comprising 159 drugs. The results revealed that the random forest had the highest accuracy, area under the receiver operating characteristic curve (AUC), and F value. Additionally, the results with test data A and B (n = 36, 31), which were not used for training, showed that both F value and accuracy for the random forest and the kernel method SVM exceeded those with the linear regression equation of Yamauchi et al. Conclusion: We were able to construct a predictive model of milk transferability with relatively high performance using a machine learning method capable of nonlinear separation. The predictive model in this study can be applied to drugs with unknown M/P ratios for providing a new source of information on milk transfer.