Anatomic Interpretability in Neuroimage Deep Learning: Saliency Approaches for Typical Aging and Traumatic Brain Injury.

The black box nature of deep neural networks (DNNs) makes researchers and clinicians hesitant to rely on their findings. Saliency maps can enhance DNN explainability by suggesting the anatomic localization of relevant brain features. This study compares seven popular attribution-based saliency approaches to assign neuroanatomic interpretability to DNNs that estimate biological brain age (BA) from magnetic resonance imaging (MRI).

Frailty and associated prognosis among older emergency department patients with suspected infection: A prospective, observational cohort study.

Background: Prognosis and disposition among older emergency department (ED) patients with suspected infection remains challenging. Frailty is increasingly recognized as a predictor of poor prognosis among critically ill patients; however, its association with clinical outcomes among older ED patients with suspected infection is unknown.

Methods: We conducted a multicenter prospective cohort study at two tertiary care EDs.

The Mitochondrial Basis for Adaptive Variation in Aerobic Performance in High-Altitude Deer Mice.

Mitochondria play a central role in aerobic performance. Studies aimed at elucidating how evolved variation in mitochondrial physiology contributes to adaptive variation in aerobic performance can therefore provide a unique and powerful lens to understanding the evolution of complex physiological traits. Here, we review our ongoing work on the importance of changes in mitochondrial quantity and quality to adaptive variation in aerobic performance in high-altitude deer mice.