Machine Learning in Neurosurgery: Toward Complex Inputs, Actionable Predictions, and Generalizable Translations.

Machine learning can predict neurosurgical diagnosis and outcomes, power imaging analysis, and perform robotic navigation and tumor labeling. State-of-the-art models can reconstruct and generate images, predict surgical events from video, and assist in intraoperative decision-making. In this review, we will detail the neurosurgical applications of machine learning, ranging from simple to advanced models, and their potential to transform patient care. As machine learning techniques, outputs, and methods become increasingly complex, their performance is often more impactful yet increasingly difficult to evaluate. We aim to introduce these advancements to the neurosurgical audience while suggesting major potential roadblocks to their safe and effective translation. Unlike the previous generation of machine learning in neurosurgery, the safe translation of recent advancements will be contingent on neurosurgeons' involvement in model development and validation.

Examining the Process and Impact of Social Problem Solving in Autistic Children.

Social problem solving (SPS) represents a social cognitive reasoning process that gives way to behavior when individuals are navigating challenging social situations. Autistic individuals have been shown to struggle with specific aspects of SPS, which, in turn, has been related to social difficulties in children. However, no previous work has measured how SPS components not only relate to one another but also discretely and conjointly predict autism-related symptoms and social difficulties in autistic children, specifically. Fifty-eight autistic children (44 male; 6-10 years old, Mage=8.67, SDage=1.31) completed a self-administered, computerized assessment of SPS. To elucidate how SPS components discretely, and combined, contribute to autism-related symptoms and social difficulties, commonality analyses were conducted for each measure assessing autism-related symptoms and social difficulties. Socially normative problem identification, goal preference, and solution preference were related to fewer parent-reported autism-related social difficulties. Measures related to autism symptomatology, social perspective taking, and emotion recognition were not significantly associated with discrete SPS components in this sample. The problem identification aspect of SPS contributed the most unique variance to parent-reported autism-related social difficulties, while shared variance across all SPS components accounted for substantial variance in both parent-reported autism-related social difficulties models. Results suggest that SPS components are interrelated, but distinct, constructs in the autistic population. These findings not only further clarify the impact of SPS components on autism-related symptoms and social difficulties, but also have implications for refining SPS-focused interventions in the autistic population.