Background: GNE myopathy is an autosomal recessive adult-onset distal myopathy. While a few case reports have described the progression of GNE myopathy during pregnancy, to our knowledge, none have examined disease progression after delivery or obstetric complications.Objective: This study aimed to reveal maternal complications, newborn complications, and the impact of pregnancy on disease progression in GNE myopathy patients.Methods: We conducted a questionnaire survey on pregnancy, delivery, and newborns involving female GNE myopathy patients who are currently registered in a national registry in Japan.Results: The response rate for the questionnaire survey was 60.0% (72/120). Of the 72 respondents, 44 (61.1%) had pregnancy experience (average, 1.8 pregnancies; 53 pregnancies before onset and 28 after onset). The incidence of threatened abortion was 26.9% among post-onset pregnancies, which was higher compared to those of the general Japanese population (p = 0.03). No other maternal or infant complications were commonly observed. Over 80% were unaware of changes in disease progression during pregnancy (mean age, 32.8 ± 3.5 years) or after delivery (32.9 ± 3.8 years), while 19.0% experienced disease exacerbation within a year after delivery (30.0 ± 1.0 years). Six patients developed myopathy within a year after delivery (29.7 ± 4.6 years), while none developed myopathy during pregnancy.Conclusions: There were no serious maternal or newborn complications, and subjective progression did not differ during or after delivery in the majority of GNE myopathy patients. However, our findings suggest the importance of considering the possibility of threatened abortion and disease progression after delivery.
Histopathologic evaluation is essential for categorizing and studying neuromuscular disorders. However, experienced specialists and pathologists are limited, especially in underserved areas. Although new technologies, such as artificial intelligence, are expected to improve medical reach, their use in rare diseases is challenging because of the limited availability of training datasets. To address this knowledge gap, we developed an algorithm based on deep convolutional neural networks that used data from microscopic images of hematoxylin-and-eosin-stained pathology slides. Our algorithm differentiated idiopathic inflammatory myopathies (mostly treatable) from hereditary muscle diseases (mostly non-treatable) and achieved better sensitivity and specificity than real physicians' diagnoses. Furthermore, it successfully and accurately classified four subtypes of the abovementioned muscular conditions. These results suggest that our algorithm can be safely used in a clinical setting. We established the similarity between the algorithm's and physicians' predictions using visualization technology, and clarified the validity of the predictions.