Autosomal Recessive Spastic Ataxia of Charlevoix-Saguenay due to Novel Mutations in the SACS Gene.

Autosomal recessive spastic ataxia of Charlevoix-Saguenay (ARSACS) is characterized by triad of progressive cerebellar ataxia, progressive spasticity, and axonal/demyelinating peripheral neuropathy. Other manifestations include dysarthria, weakness in lower extremities and distal muscle wasting, foot deformities, retinal striation, prolapse of the mitral valve and rarely intellectual disability, hearing loss, and myoclonic epilepsy. We describe a patient who developed peripheral sensorimotor neuropathy in the absence of spasticity on initial presentation. He had nerve root enhancement on magnetic resonance imaging (MRI) lumbar spine, and nerve conduction studies were suggestive of demyelinating polyneuropathy. Patient had mild cerebellar atrophy on MRI and some delay of motor milestones. Over the course of several months, he developed spasticity, and genetic analysis together with clinical presentation was consistent with ARSACS. He was noted to have a pathogenic mutation c.8108G>A (p. Arg2703His) inherited from mother and a variant of uncertain significance c.7216T>C (p. Ser2406Pro) inherited from his father in SACS gene. Atypical cases may present later in life or in absence of one of the classical features at the time of presentation, which may make diagnosis difficult. Our patient had such an atypical presentation of ARSACS. Young patients with neuropathy and concomitant cerebellar atrophy on MRI should raise suspicion for hereditary spastic ataxia syndrome. Follow-up examination can often reveal additional findings to aid the diagnosis.

Artificial Intelligence, Wearables and Remote Monitoring for Heart Failure: Current and Future Applications.

Substantial milestones have been attained in the field of heart failure (HF) diagnostics and therapeutics in the past several years that have translated into decreased mortality but a paradoxical increase in HF-related hospitalizations. With increasing data digitalization and access, remote monitoring via wearables and implantables have the potential to transform ambulatory care workflow, with a particular focus on reducing HF hospitalizations. Additionally, artificial intelligence and machine learning (AI/ML) have been increasingly employed at multiple stages of healthcare due to their power in assimilating and integrating multidimensional multimodal data and the creation of accurate prediction models. With the ever-increasing troves of data, the implementation of AI/ML algorithms could help improve workflow and outcomes of HF patients, especially time series data collected via remote monitoring. In this review, we sought to describe the basics of AI/ML algorithms with a focus on time series forecasting and the current state of AI/ML within the context of wearable technology in HF, followed by a discussion of the present limitations, including data integration, privacy, and challenges specific to AI/ML application within healthcare.