Search

PURPOSE Low-attenuation muscle (LAM) area at mid-thigh, a computed tomography (CT)-derived index of intramuscular lipids, is associated with insulin resistance, obesity, and type 2 diabetes. The present study aimed at testing the hypothesis that changes in LAM area in trunk muscles from a single abdominal scan could provide relevant information to evaluate the effects of a lifestyle intervention without the use of a mid-thigh CT scan. METHODS Cardiometabolic risk variables, including waist circumference, lipoprotein-lipid profile, glucose tolerance, and cardiorespiratory fitness, were assessed in a sample of 102 dyslipidemic viscerally obese men at baseline and after a 1-yr lifestyle intervention. Abdominal (L4-L5) and mid-thigh CT scans were performed and abdominal muscles classified as psoas and core muscles. Scans were segmented to calculate muscle areas, LAM areas, and mean attenuation values. RESULTS All muscle groups showed a decrease in LAM areas (P < 0.0001) in response to the lifestyle intervention. Changes in LAM areas were significantly associated with changes in triglycerides, high-density lipoprotein (HDL) cholesterol, cholesterol/HDL cholesterol ratio and log triglycerides/HDL cholesterol ratio (mid-thigh, 0.20 ≤ |r| ≤ 0.29; psoas, 0.28 ≤ |r| ≤ 0.38; core, 0.29 ≤ |r| ≤ 0.34, P < 0.05). Changes in core LAM area were significantly associated with changes in 2-h glucose levels, glucose area measured during the oral glucose tolerance test and homeostasis model assessment of insulin resistance (0.21 ≤ r ≤ 0.34, P < 0.05). Stepwise regression analyses showed that changes in LAM psoas area were associated with changes in HDL cholesterol and the cholesterol/HDL cholesterol ratio independently from changes in visceral adiposity. CONCLUSIONS Changes in trunk LAM areas are useful indices of changes in mid-thigh LAM area observed with a 1-yr lifestyle intervention. Thus, an additional mid-thigh scan is not necessary to evaluate muscle lipid content by CT when an abdominal CT scan is available.

Concussion prevalence in sport is well recognized, so too is the challenge of clinical and return-to-play management for an injury with an inherent indeterminant time course of resolve. A clear, valid insight into the anticipated resolution time could assist in planning treatment intervention.This study implemented a supervised machine learning-based approach in modeling estimated symptom resolve time in high school athletes who incurred a concussion during sport activity.We examined the efficacy of 10 classification algorithms using machine learning for the prediction of symptom resolution time (within 7, 14, or 28 d), with a data set representing 3 yr of concussions suffered by high school student-athletes in football (most concussion incidents) and other contact sports.The most prevalent sport-related concussion reported symptom was headache (94.9%), followed by dizziness (74.3%) and difficulty concentrating (61.1%). For all three category thresholds of predicted symptom resolution time, single-factor ANOVA revealed statistically significant performance differences across the 10 classification models for all learners at a 95% confidence interval (P = 0.000). Naïve Bayes and Random Forest with either 100 or 500 trees were the top-performing learners with an area under the receiver operating characteristic curve performance ranging between 0.656 and 0.742 (0.0-1.0 scale).Considering the limitations of these data specific to symptom presentation and resolve, supervised machine learning demonstrated efficacy, while warranting further exploration, in developing symptom-based prediction models for practical estimation of sport-related concussion recovery in enhancing clinical decision support.