Age-related effects on the anterior and posterior hippocampal volumes in 6-21 year olds: A model selection approach.

Although recent studies support significant differences in intrinsic structure, function, and connectivity along the longitudinal axis of the hippocampus, few studies have investigated the normative development of this dimension. In addition, factors known to influence hippocampal structure, such as sex or puberty, have yet to be characterized when assessing age-related effects on its subregions. This study addresses this gap by investigating the relationship of the anterior (antHC) and posterior (postHC) hippocampus volumes with age, and how these are moderated by sex or puberty, in structural magnetic resonance imaging scans from 183 typically developing participants aged 6-21 years. Based on previous literature, we first anticipated that non-linear models would best represent the relationship between age and the antHC and postHC volumes. We found that age-related effects are region-specific, such that the antHC volume remains stable with increasing age, while the postHC shows a cubic function characterized by overall volume increase with age but a slower rate during adolescence. Second, we hypothesized that models, which include biological sex or pubertal status would best describe these relationships. Contrary to expectation, models comprising either biological sex or pubertal status did not significantly improve model performance. Further longitudinal research is needed to evaluate their effects on the antHC and postHC development.

Artificial Intelligence Algorithms in Health Care: Is the Current Food and Drug Administration Regulation Sufficient?

Given the growing use of machine learning (ML) technologies in health care, regulatory bodies face unique challenges in governing their clinical use. Under the regulatory framework of the Food and Drug Administration, approved ML algorithms are practically locked, preventing their adaptation in the ever-changing clinical environment, defeating the unique adaptive trait of ML technology in learning from real-world feedback. At the same time, regulations must enforce a strict level of patient safety to mitigate risk at a systemic level. Given that ML algorithms often support, or at times replace, the role of medical professionals, we have proposed a novel regulatory pathway analogous to the regulation of medical professionals, encompassing the life cycle of an algorithm from inception, development to clinical implementation, and continual clinical adaptation. We then discuss in-depth technical and nontechnical challenges to its implementation and offer potential solutions to unleash the full potential of ML technology in health care while ensuring quality, equity, and safety. References for this article were identified through searches of PubMed with the search terms "Artificial intelligence," "Machine learning," and "regulation" from June 25, 2017, until June 25, 2022. Articles were also identified through searches of the reference list of the articles. Only papers published in English were reviewed. The final reference list was generated based on originality and relevance to the broad scope of this paper.