Search

Amyotrophic lateral sclerosis (ALS) is known to represent a collection of overlapping syndromes. Various classification systems based on empirical observations have been proposed, but it is unclear to what extent they reflect ALS population substructures. We aimed to use machine-learning techniques to identify the number and nature of ALS subtypes to obtain a better understanding of this heterogeneity, enhance our understanding of the disease, and improve clinical care.In this retrospective study, we applied unsupervised Uniform Manifold Approximation and Projection [UMAP]) modelling, semi-supervised (neural network UMAP) modelling, and supervised (ensemble learning based on LightGBM) modelling to a population-based discovery cohort of patients who were diagnosed with ALS while living in the Piedmont and Valle d'Aosta regions of Italy, for whom detailed clinical data, such as age at symptom onset, were available. We excluded patients with missing Revised ALS Functional Rating Scale (ALSFRS-R) feature values from the unsupervised and semi-supervised steps. We replicated our findings in an independent population-based cohort of patients who were diagnosed with ALS while living in the Emilia Romagna region of Italy.Between Jan 1, 1995, and Dec 31, 2015, 2858 patients were entered in the discovery cohort. After excluding 497 (17%) patients with missing ALSFRS-R feature values, data for 42 clinical features across 2361 (83%) patients were available for the unsupervised and semi-supervised analysis. We found that semi-supervised machine learning produced the optimum clustering of the patients with ALS. These clusters roughly corresponded to the six clinical subtypes defined by the Chiò classification system (ie, bulbar, respiratory, flail arm, classical, pyramidal, and flail leg ALS). Between Jan 1, 2009, and March 1, 2018, 1097 patients were entered in the replication cohort. After excluding 108 (10%) patients with missing ALSFRS-R feature values, data for 42 clinical features across 989 patients were available for the unsupervised and semi-supervised analysis. All 1097 patients were included in the supervised analysis. The same clusters were identified in the replication cohort. By contrast, other ALS classification schemes, such as the El Escorial categories, Milano-Torino clinical staging, and King's clinical stages, did not adequately label the clusters. Supervised learning identified 11 clinical parameters that predicted ALS clinical subtypes with high accuracy (area under the curve 0·982 [95% CI 0·980-0·983]).Our data-driven study provides insight into the ALS population substructure and confirms that the Chiò classification system successfully identifies ALS subtypes. Additional validation is required to determine the accuracy and clinical use of these algorithms in assigning clinical subtypes. Nevertheless, our algorithms offer a broad insight into the clinical heterogeneity of ALS and help to determine the actual subtypes of disease that exist within this fatal neurodegenerative syndrome. The systematic identification of ALS subtypes will improve clinical care and clinical trial design.US National Institute on Aging, US National Institutes of Health, Italian Ministry of Health, European Commission, University of Torino Rita Levi Montalcini Department of Neurosciences, Emilia Romagna Regional Health Authority, and Italian Ministry of Education, University, and Research.For the Italian and German translations of the abstract see Supplementary Materials section.

Objective To compare the incidence and clinical features of individuals presenting in emergency rooms (ER) with facial palsy during the Italian COVID‐19 outbreak and in the same period of 2019. Methods We retrospectively reviewed the medical records for all accesses to the six ER in the province of Reggio Emilia, Italy, during the first phase of the COVID‐19 pandemic (27 February‐3 May 2020) to identify all cases of diagnosed facial palsy. Clinical information was retrieved for each patient and compared with that of facial palsy cases presenting in 2019. Result Between 27 February and 3 May 2020, 38 patients presented to provincial ERs for facial palsy; in 2019, there were 22 cases, for an incidence rate ratio of 1.73 (95% CI 1.02–2.92) for the 2020 cohort. Of the 2020 cohort, eight patients (21%) presented with active or recent symptoms consistent with COVID‐19 infection, compared with 2 (9%) in 2019 (p = .299); one was tested and resulted positive for SARS‐CoV‐2. Moreover, patients were younger (−11 years, p = .037) than those of the previous year and manifested a longer lag (+1.1 days, p = .001) between symptoms onset and ER presentation. Conclusion We observed a higher occurrence of facial palsy during the COVID‐19 outbreak compared to the same period of the previous year; 21% of patients presenting with facial palsy had active or recent symptoms consistent with SARS‐CoV‐2 infection, suggesting an excess risk of facial palsy during or after COVID‐19. These patients searched for medical attention later, probably because of the fear of contracting COVID‐19 during assistance., The objective of this study is to describe the clinical features of individuals presenting with facial palsy during the Italian COVID‐19 outbreak. We retrospectively reviewed the medical records for all accesses to the emergency departments in the province of Reggio Emilia, Italy, during the first phase of the COVID‐19 pandemic (27 February‐3 May 2020) to identify all cases of diagnosed facial palsy. We observed a higher occurrence of facial palsy during the COVID‐19 outbreak compared to the same period of the previous year; 21% of patients presenting with facial palsy had active or recent symptoms consistent with SARS‐CoV‐2 infection, suggesting a potential correlation.

Background: Acute respiratory failure can be triggered by several causes, either of pulmonary or extra-pulmonary origin. Pompe disease, or type II glycogen storage disease, is a serious and often fatal disorder, due to a pathological accumulation of glycogen caused by a defective activiy of acid α-glucosidase (acid maltase), a lysosomal enzyme involved in glycogen degradation. The prevalence of the disease is estimated between 1 in 40,000 to 1 in 300,000 subjects. Case presentation: This case report describes a difficult diagnosis of late-onset Pompe disease (LOPD) in a 52 year old Caucasian woman with acute respiratory failure requiring orotracheal intubation and subsequent tracheostomy for long-term mechanical ventilation 24 h/day. Despite a complex diagnostic process including several blood tests, bronchoscopy with BAL, chest CT, brain NMR, electromyographies, only a muscle biopsy allowed to reach the correct diagnosis. Discussion: The most frequent presentation of myopathies, including LOPD, is proximal limb muscle weakness. Respiratory related symptoms (dyspnea on effort, reduced physical capacity, recurrent infections, etc.) and respiratory failure are often evident in the later stages of the diseases, but they have been rarely described as the onset symptoms in LOPD. In our case, a third stage LOPD, the cooperation between pulmonologists and neurologists was crucial in reaching a correct diagnosis despite a very complex clinical scenario due to different confounding co-morbidities as potential causes of respiratory failure and an atypical presentation. In this patient, enzyme replacement therapy with infusion of alglucosidase alfa was associated with progressive reduction of ventilatory support to night hours, and recovery of autonomous walking.

We investigated structural brain differences between a group of early-mild PD patients at different phases of the disease and healthy subjects using voxel-based morphometry (VBM). 20 mild PD patients compared to 15 healthy at baseline and after 2 years of follow-up. VBM is a fully automated technique, which allows the identification of regional differences in the gray matter enabling an objective analysis of the whole brain between groups of subjects. With respect to controls, PD patients exhibited decreased GM volumes in right putamen and right parietal cortex. After 2 years of disease, the same patients confirmed GM loss in the putamen and parietal cortex; a significant difference was also observed in the area of pedunculopontine nucleus (PPN) and in the mesencephalic locomotor region (MLR). PD is associated with brain morphological changes in cortical and subcortical structures. The first regions to be affected in PD seem to be the parietal cortex and the putamen. A third structure that undergoes atrophy is the part of the inferior-posterior midbrain, attributable to the PPN and MLR. Our findings provide new insight into the brain involvement in PD and could contribute to a better understanding of the sequence of events occurring in these patients.

Paroxysmal dysarthria is an unusual condition characterised by brief episodes of dysarthria with the sudden onset and frequent recurrence. It has been mainly reported in multiple sclerosis and an association with midbrain lesions has been claimed; however, most of the reported patients had multiple brain alterations so it was difficult to associate this symptom with a specific lesion site. We illustrate the cases of two patients with an isolated demyelinating midbrain lesion presenting paroxysmal dysarthria as the only symptom; both participants had oligoclonal bands in the cerebrospinal fluid and an unremarkable follow-up. Both patients had benefit from carbamazepine treatment, similarly to previously reported cases. Our report confirms that a demyelinating midbrain lesion is sufficient to provoke paroxysmal dysarthria. It is noteworthy that an erroneous diagnosis of psychogenic disorders was initially made in both cases, highlighting the importance not to underestimate isolated paroxysmal symptoms in clinical practice.