Machine Learning in Neuro-Oncology, Epilepsy, Alzheimer's Disease, and Schizophrenia.

Applications of machine learning (ML) in translational medicine include therapeutic drug creation, diagnostic development, surgical planning, outcome prediction, and intraoperative assistance. Opportunities in the neurosciences are rich given advancement in our understanding of the brain, expanding indications for intervention, and diagnostic challenges often characterized by multiple clinical and environmental factors. We present a review of ML in neuro-oncology, epilepsy, Alzheimer's disease, and schizophrenia to highlight recent progression in these field, optimizing machine learning capabilities in their current forms. Supervised learning models appear to be the most commonly incorporated algorithm models for machine learning across the reviewed neuroscience disciplines with primary aim of diagnosis. Accuracy ranges are high from 63% to 99% across all algorithms investigated. Machine learning contributions to neurosurgery, neurology, psychiatry, and the clinical and basic science neurosciences may enhance current medical best practices while also broadening our understanding of dynamic neural networks and the brain.

The Role of the Cerebellum in Control of Swallow: Evidence of Inspiratory Activity During Swallow.

Anatomical connections are reported between the cerebellum and brainstem nuclei involved in swallow such as the nucleus tractus solitarius, nucleus ambiguus, and Kölliker-fuse nuclei. Despite these connections, a functional role of the cerebellum during swallow has not been elucidated. Therefore, we examined the effects of cerebellectomy on swallow muscle recruitment and swallow-breathing coordination in anesthetized freely breathing cats. Electromyograms were recorded from upper airway, pharyngeal, laryngeal, diaphragm, and chest wall muscles before and after complete cerebellectomy. Removal of the cerebellum reduced the excitability of swallow (i.e., swallow number), and muscle recruitment of the geniohyoid, thyroarytenoid, parasternal (chestwall), and diaphragm muscles, but did not disrupt swallow-breathing coordination. Additionally, diaphragm and parasternal muscle activity during swallow is reduced after cerebellectomy, while no changes were observed during breathing. These findings suggest the cerebellum modulates muscle excitability during recruitment, but not pattern or coordination of swallow with breathing.

Swallow-breathing coordination during incremental ascent to altitude.

Swallow and breathing are highly coordinated behaviors reliant on shared anatomical space and neural pathways. Incremental ascent to high altitudes results in hypoxia/hypocapnic conditions altering respiratory drive, however it is not known whether these changes also alter swallow. We examined the effect of incremental ascent (1045 m, 3440 m and 4371 m) on swallow motor pattern and swallow-breathing coordination in seven healthy adults. Submental surface electromyograms (sEMG) and spirometry were used to evaluate swallow triggered by saliva and water infusion. Swallow-breathing phase preference was different between swallows initiated by saliva versus water. With ascent, saliva swallows changed to a dominate pattern of occurrence during the transition from inspiration to expiration. Additionally, water swallows demonstrated a significant decrease in submental sEMG duration and a shift in submental activity to earlier in the apnea period, especially at 4371 m. Our results suggest that there are changes in swallow-breathing coordination and swallow production that likely increase airway protection with incremental ascent to high altitude. The adaptive changes in swallow were likely due to the exposure to hypoxia and hypocapnia, along with airway irritation.