Hokkaido Information University

Fabry disease (FD) is an X-linked lysosomal storage disorder caused by pathogenic variants in the GLA gene, resulting in deficient or dysfunctional α-galactosidase A (AGAL) activity. Newborn screening (NBS) enables early detection and management; however, ascertaining the pathogenicity of unknown GLA variants remains a diagnostic challenge. This study aimed to evaluate the clinical significance of GLA gene variants detected through NBS in Japan, utilizing biochemical, genetic, and structural analyses. A total of 22 individuals, including newborns and their relatives carrying GLA gene variants, were analyzed. Plasma AGAL activity, plasma globotriaosylsphingosine (Lyso-Gb3), and urinary globotriaosylceramide levels were measured. In silico predictions, structural modeling, and variant classification databases were employed to assess pathogenicity. Significant reductions in AGAL activity and elevated Lyso-Gb3 levels were observed in variants, such as p.R112H and p.K391E, suggesting a high likelihood of being pathogenic variants. Variants like p.W209R, p.I242T, p.M267T, and p.R356Q demonstrated mild biochemical abnormalities, indicating limited pathogenic potential or non-pathogenicity. Variants, such as p.E66Q and c.-10C > T, showed no significant biochemical effects, indicating that they are benign. This study underscores the diverse pathogenicity of GLA gene variants identified through NBS, emphasizing the need for integrated diagnostic strategies, including biomarker analysis, structural assessments, and long-term clinical follow-up. These findings contribute to improving genotype-phenotype correlations and optimizing diagnostic precision for FD.

The purpose of this study is to develop an automatic terminology mapping system for adverse events between Japanese (JFMDA) and English (IMDRF) terminologies. IMDRF terms were analyzed in four versions: untranslated (English), two machine-translated, and officially translated into Japanese. Conceptual similarity was evaluated using SentenceBERT, and mapping accuracy was assessed against a gold standard. Results showed that translating IMDRF terms into Japanese improved mapping accuracy, with official translations performing best. However, the accuracy was not significantly different from that of machine translations. Term names outperformed definitions, achieving approximately 50% accuracy for health effects. This method supports manual mapping and offers potential for further refinement.

Endovascular aneurysm repair (EVAR) has become a preferred method for treating abdominal aortic aneurysms (AAA) due to its minimally invasive approach. However, identifying factors that influence long-term patient outcomes is crucial for improving prognosis. This study investigates whether machine learning (ML)-based decision tree analysis (DTA) can predict long-term survival (over 5 years postoperatively) by uncovering complex patterns in patient data.

We retrospectively analyzed data from 142 patients who underwent elective EVAR for AAA at Tokyo Medical University Hospital between October 2013 and July 2018. The dataset comprised 24 variables, including age, gender, nutritional status, comorbidities, and surgical details. The decision tree classifier was developed and validated using Python 3.7 and the scikit-learn toolkit.

DTA identified poor nutritional status as the most significant predictor, followed by compromised immunity, active cancer, octogenarians, chronic kidney disease, and chronic obstructive pulmonary disease. The decision tree identified 9 terminal nodes with probabilities of long-term survival. Four of these terminal nodes represented groups of patients with a high probability of long-term survival: 100%, 84%, 77%, and 60%, whereas the other 5 terminal nodes represented groups of patients with a low probability of long-term survival: 17%, 25%, 30%, 45%, and 47%. The model achieved a moderately high accuracy of 76.1%, specificity of 72.4%, sensitivity of 81.8%, precision of 65.2%, and area under the receiver operating characteristic curve of 0.84.

ML-based DTA effectively predicts long-term survival after EVAR, highlighting the importance of comprehensive preoperative assessments and personalized management strategies to improve patient outcomes.