Extracting the latent needs of dementia patients and caregivers from transcribed interviews in japanese: an initial assessment of the availability of morpheme selection as input data with Z-scores in machine learning.

BACKGROUND: Given the increasing number of dementia patients worldwide, a new method was developed for machine learning models to identify the 'latent needs' of patients and caregivers to facilitate patient/public involvement in societal decision making. METHODS: Japanese transcribed interviews with 53 dementia patients and caregivers were used. A new morpheme selection method using Z-scores was developed to identify trends in describing the latent needs. F-measures with and without the new method were compared using three machine learning models. RESULTS: The F-measures with the new method were higher for the support vector machine (SVM) (F-measure of 0.81 with the new method and F-measure of 0.79 without the new method for patients) and Naive Bayes (F-measure of 0.69 with the new method and F-measure of 0.67 without the new method for caregivers and F-measure of 0.75 with the new method and F-measure of 0.73 without the new method for patients). CONCLUSION: A new scheme based on Z-score adaptation for machine learning models was developed to predict the latent needs of dementia patients and their caregivers by extracting data from interviews in Japanese. However, this study alone cannot be used to assign significance to the adaptation of the new method because of no enough size of sample dataset. Such pre-selection with Z-score adaptation from text data in machine learning models should be considered with more modified suitable methods in the near future.

The Role of miR-217-5p in the Puromycin Aminonucleoside-Induced Morphological Change of Podocytes.

Podocytes, alternatively called glomerular epithelial cells, are terminally differentiated cells that wrap around glomerular capillaries and function as a part of the glomerular filtration barrier in the kidney. Therefore, podocyte injury with morphological alteration and detachment from glomerular capillaries leads to severe proteinuria and subsequent renal failure through glomerulosclerosis. Previous RNA sequencing analysis of primary rat podocytes exposed to puromycin aminonucleoside (PAN), a well-known experimental model of injured podocytes, identified several transcripts as being aberrantly expressed. However, how the expression of these transcripts is regulated remains unclear. MicroRNAs (miRNAs) are small noncoding RNAs that posttranscriptionally inhibit the expression of their target transcripts. In this study, using small RNA sequencing analysis, miR-217-5p was identified as the most upregulated transcript in PAN-treated rat podocytes. MiR-217-5p overexpression in E11 podocyte cells led to shrunken cells with abnormal actin cytoskeletons. Consistent with these changes in cell morphology, gene ontology (GO) enrichment analysis showed that interactive GO terms related to cell morphogenesis were enriched with the predicted targets of miR-217-5p. Of the predicted targets highly downregulated by PAN, Myosin 1d (Myo1d) is a nonmuscle myosin predicted to be involved in actin filament organization and thought to play a role in podocyte morphogenesis and injury. We demonstrated that miR-217-5p targets Myo1d by luciferase assays, qRT-PCR, and Western blotting. Furthermore, we showed that miR-217-5p was present in urine from PAN- but not saline-administrated rats. Taken together, our data suggest that miR-217-5p may serve as a therapeutic target and a biomarker for podocyte injury.