Search

Isolated mitochondrial complex II deficiency is a rare cause of mitochondrial respiratory chain disease. To date biallelic variants in three genes encoding mitochondrial complex II molecular components have been unequivocally associated with mitochondrial disease (SDHA/SDHB/SDHAF1). Additionally, variants in one further complex II component (SDHD) have been identified as a candidate cause of isolated mitochondrial complex II deficiency in just two unrelated affected individuals with clinical features consistent with mitochondrial disease, including progressive encephalomyopathy and lethal infantile cardiomyopathy. We present clinical and genomic investigations in four individuals from an extended Palestinian family with clinical features consistent with an autosomal recessive mitochondrial complex II deficiency, in which our genomic studies identified a homozygous NM_003002.3:c.[205 G > A];[205 G > A];p.[(Glu69Lys)];[(Glu69Lys)] SDHDvariant as the likely cause. Reviewing previously published cases, these findings consolidate disruption of SDHD function as a cause of mitochondrial complex II deficiency and further define the phenotypic spectrum associated with SDHDgene variants.

Biallelic INPP4Avariants have recently been associated with severe neurodevelopmental disease in single-case reports. Here, we expand and elucidate the clinical-genetic spectrum and provide a pathomechanistic explanation for genotype-phenotype correlations.

BackgroundThere is a need for diagnostic tests of early PD diagnosis. A subset of AI known as deep learning (DL) has shown great promise in diagnostic medical imaging, sometimes outperforming radiolo- gists by detecting patterns invisible to the human eye. Using DL, we explored whether such changes are detectable on routine PD MRI scans.MethodsWe trained a convolutional neural network to classify 138 PD and 60 control brain MRI images acquired from the Parkinson’s Progression Marker Initiative (PPMI) database. Models were assessed using k-fold cross-validation. We used Deep SHapley Additive exPlanations (DeepSHAP) to visualise the contri- bution of individual pixels to the model’s prediction.ResultsA combined dataset of axial T2 and proton density MRI images was classified with 79% accuracy and an area under the curve (AUC) of 0.86. Respectively T2 and proton density models classified cases with 81/84% accuracy and AUC of 0.83/0.88. DeepSHAP heat maps demonstrated predominant interest in midbrain slices.ConclusionOur models exhibited good diagnostic performance and demonstrated interest in PD relevant brain regions. We will validate this model in a large dataset of routinely collected NHS MRI scans, many of which predate onset of motor symptoms.

Bohning DE, Shastri A, McGavin L, et al. Motor cortex brain activity induced by 1-Hz transcranial magnetic stimulation is similar in location and level to that for volitional movement. Invest Radiol 2000;35676–683.