Basal ganglia involvement in ARX patients: The reason for ARX patients very specific grasping?

The ARX (Aristaless Related homeoboX) gene was identified in 2002 as responsible for XLAG syndrome, a lissencephaly characterized by an almost complete absence of cortical GABAergic interneurons, and for milder forms of X-linked Intellectual Disability (ID) without apparent brain abnormalities. The most frequent mutation found in the ARX gene, a duplication of 24 base pairs (c.429_452dup24) in exon 2, results in a recognizable syndrome in which patients present ID without primary motor impairment, but with a very specific upper limb distal motor apraxia associated with a pathognomonic hand-grip, described as developmental Limb Kinetic Apraxia (LKA). In this study, we first present ARX expression during human fetal brain development showing that it is strongly expressed in GABAergic neuronal progenitors during the second and third trimester of pregnancy. We show that although ARX expression strongly decreases towards the end of gestation, it is still present after birth in some neurons of the basal ganglia, thalamus and cerebral cortex, suggesting that ARX also plays a role in more mature neuron functioning. Then, using morphometric brain MRI in 13 ARX patients carrying c.429_452dup24 mutation and in 13 sex- and age-matched healthy controls, we show that ARX patients have a significantly decreased volume of several brain structures including the striatum (and more specifically the caudate nucleus), hippocampus and thalamus as well as decreased precentral gyrus cortical thickness. We observe a significant correlation between caudate nucleus volume reduction and motor impairment severity quantified by kinematic parameter of precision grip. As basal ganglia are known to regulate sensorimotor processing and are involved in the control of precision gripping, the combined decrease in cortical thickness of primary motor cortex and basal ganglia volume in ARX dup24 patients is very likely the anatomical substrate of this developmental form of LKA.

Transforming Clinical Data into Actionable Prognosis Models: Machine-Learning Framework and Field-Deployable App to Predict Outcome of Ebola Patients.

BACKGROUND: Assessment of the response to the 2014-15 Ebola outbreak indicates the need for innovations in data collection, sharing, and use to improve case detection and treatment. Here we introduce a Machine Learning pipeline for Ebola Virus Disease (EVD) prognosis prediction, which packages the best models into a mobile app to be available in clinical care settings. The pipeline was trained on a public EVD clinical dataset, from 106 patients in Sierra Leone. METHODS/PRINCIPAL FINDINGS: We used a new tool for exploratory analysis, Mirador, to identify the most informative clinical factors that correlate with EVD outcome. The small sample size and high prevalence of missing records were significant challenges. We applied multiple imputation and bootstrap sampling to address missing data and quantify overfitting. We trained several predictors over all combinations of covariates, which resulted in an ensemble of predictors, with and without viral load information, with an area under the receiver operator characteristic curve of 0.8 or more, after correcting for optimistic bias. We ranked the predictors by their F1-score, and those above a set threshold were compiled into a mobile app, Ebola CARE (Computational Assignment of Risk Estimates). CONCLUSIONS/SIGNIFICANCE: This method demonstrates how to address small sample sizes and missing data, while creating predictive models that can be readily deployed to assist treatment in future outbreaks of EVD and other infectious diseases. By generating an ensemble of predictors instead of relying on a single model, we are able to handle situations where patient data is partially available. The prognosis app can be updated as new data become available, and we made all the computational protocols fully documented and open-sourced to encourage timely data sharing, independent validation, and development of better prediction models in outbreak response.