👤 Giuseppe Noce

We evaluated the accuracy of standard machine learning (ML) algorithms in predicting 1-year cognitive decline in Alzheimer's disease patients with mild cognitive impairment (ADMCI) using resting-state electroencephalographic (rsEEG) biomarkers enriched with APOE genotype, sex, age, and educational attainment data. The study analyzed datasets from 63 ADMCI patients obtained from an international archive. The ML algorithms included Simple Logistic Regression, Model Trees, Logistic Regression, K-nearest neighbor, and Support Vector Machine. Input features comprised lobar rsEEG source activities across delta (<4 Hz) to alpha (≈10-12 Hz) bands, cerebrospinal fluid (CSF Aβ1-42/p-tau), and structural magnetic resonance imaging (sMRI) biomarkers. Cognitive decline was assessed over a 1-year follow-up ("stable" vs. "decliner") based on Mini-Mental State Examination (MMSE) scores. The four independent ML algorithms accurately predicted changes in the MMSE score over a 1-year follow-up, with accuracies of 77-78% in ADMCI participants aged ≥ 70 years and 74-77% in those aged < 70 years. These findings suggest that rsEEG biomarkers in ADMCI patients may not only reveal underlying pathophysiological mechanisms affecting cortical arousal and vigilance but also hold predictive value for cognitive outcomes. Show less

Jmjd1C is one of the Jmjd1 family genes that encode putative demethylases against histone H3K9 and non-histone proteins and has been proven to play an indispensable role in mouse spermatogenesis. Here, we analyzed a newly-bred transgenic mouse strain carrying a Jmjd1C loss-of-function allele in which a β-geo cassette was integrated into the intron of the Jmjd1C locus. Jmjd1C gene-trap homozygous testes exhibited malformations in postmeiotic processes and a deficiency in the long-term maintenance of undifferentiated spermatogonia. Some groups of spermatids in the homozygous testis showed abnormal organization and incomplete elongation from the first wave of spermatogenesis onwards. Moreover, histone H4K16 acetylation, which is required for the onset of chromatin remodeling, appeared to be remarkably decreased. These effects may not have been a result of the drastic decrease in gene expression related to the events but instead may have been due to the lack of interaction between JMJD1C and its partner proteins, such as MDC1 and HSP90. Additionally, significant decreases in Oct4 expression and NANOG- and OCT4-expressing spermatogonia were found in the Jmjd1C homozygous mature testis, suggesting that JMJD1C may participate in the maintenance of spermatogonial stem cell self-renewal by up-regulating Oct4 expression. These results indicate that JMJD1C has multiple functions during spermatogenesis through interactions with different partners during the spermatogenic stages. Show less