Automated voice biomarkers for depression symptoms using an online cross-sectional data collection initiative.

IMPORTANCE: Depression is an illness affecting a large percentage of the world's population throughout the lifetime. To date, there is no available biomarker for depression detection and tracking of symptoms relies on patient self-report. OBJECTIVE: To explore and validate features extracted from recorded voice samples of depressed subjects as digital biomarkers for suicidality, psychomotor disturbance, and depression severity. DESIGN: We conducted a cross-sectional study over the course of 12 months using a frequently visited web form version of the PHQ9 hosted by Mental Health America (MHA) to ask subjects for anonymous voice samples via a separate web form hosted by NeuroLex Laboratories. Subjects were asked to provide demographics, answers to the PHQ9, and two voice samples. SETTING: Online only. PARTICIPANTS: Users of the MHA website. MAIN OUTCOMES AND MEASURES: Performance of statistical models using extracted voice features to predict psychomotor disturbance, suicidality, and depression severity as indicated by the PHQ9. RESULTS: Voice features extracted from recorded audio of depressed subjects were able to predict PHQ9 question 9 and total scores with an area under the curve of 0.821 and a mean absolute error of 4.7, respectively. Psychomotor Disturbance prediction was less powerful with an area under the curve of 0.61. CONCLUSION AND RELEVANCE: Automated voice analysis using short recordings of patient speech may be used to augment depression screen and symptom management.

Lower leg muscle involvement in Duchenne muscular dystrophy: an MR imaging and spectroscopy study.

OBJECTIVE: To describe the involvement of lower leg muscles in boys with Duchenne muscular dystrophy (DMD) by using MR imaging (MRI) and spectroscopy (MRS) correlated to indices of functional status. SUBJECTS AND METHODS: Nine boys with DMD (mean age, 11 years) and eight healthy age- and BMI-matched boys (mean age, 13 years) prospectively underwent lower leg MRI, 1H-MRS of tibialis anterior (TA) and soleus (SOL) for lipid fraction measures, and 31P-MRS for pH and high-energy phosphate measures. DMD subjects were evaluated using the Vignos lower extremity functional rating, and tests including 6 min walk test (6MWT) and 10 m walk. RESULTS: DMD subjects had highest fatty infiltration scores in peroneal muscles, followed by medial gastrocnemius and soleus. Compared to controls, DMD boys showed higher intramuscular fat (P = 0.04), lipid fractions of TA and SOL (P = 0.02 and 0.003, respectively), pH of anterior compartment (P = 0.0003), and lower phosphocreatine/inorganic phosphorus ratio of posterior compartment (P = 0.02). The Vignos rating correlated with TA (r = 0.79, P = 0.01) and SOL (r = 0.71, P = 0.03) lipid fractions. The 6MWT correlated with fatty infiltration scores of SOL (r = -0.76, P = 0.046), medial (r = -0.80, P = 0.03) and lateral (r = -0.84, P = 0.02) gastrocnemius, intramuscular fat (r = -0.80, P = 0.03), and SOL lipid fraction (r = -0.89, P = 0.007). Time to walk 10 m correlated with anterior compartment pH (r = 0.78, P = 0.04). CONCLUSION: Lower leg muscles of boys with DMD show a distinct involvement pattern and increased adiposity that correlates with functional status. Lower leg MRI and 1H-MRS studies may help to noninvasively demonstrate the severity of muscle involvement.

Adiponectin is inversely associated with intramyocellular and intrahepatic lipids in obese premenopausal women.

Adiponectin, an adipokine secreted by adipocytes, exerts beneficial effects on glucose and lipid metabolism and has been found to improve insulin resistance by decreasing triglyceride content in muscle and liver in obese mice. Adiponectin is found in several isoforms and the high-molecular weight (HMW) form has been linked most strongly to the insulin-sensitizing effects. Fat content in skeletal muscle (intramyocellular lipids, IMCL) and liver (intrahepatic lipids, IHL) can be quantified noninvasively using proton magnetic resonance spectroscopy ((1)H-MRS). The purpose of our study was to assess the relationship between HMW adiponectin and measures of glucose homeostasis, IMCL and IHL, and to determine predictors of adiponectin levels. We studied 66 premenopausal women (mean BMI 31.0 ± 6.6 kg/m(2)) who underwent (1)H-MRS of calf muscles and liver for IMCL and IHL, computed tomography (CT) of the abdomen for abdominal fat depots, dual-energy X-ray absorptiometry (DXA) for fat and lean mass assessments, HMW and total adiponectin, fasting lipid profile and an oral glucose tolerance test (homeostasis model assessment of insulin resistance (HOMA(IR)), glucose and insulin area under the curve). There were strong inverse associations between HMW adiponectin and measures of insulin resistance, IMCL and IHL, independent of visceral adipose tissue (VAT) and total body fat. IHL was the strongest predictor of adiponectin and adiponectin was a predictor of HOMA(IR). Our study showed that in premenopausal obese women HMW adiponectin is inversely associated with IMCL and IHL content. This suggests that adiponectin exerts positive effects on insulin sensitivity in obesity by decreasing intracellular triglyceride content in skeletal muscle and liver; it is also possible that our results reflect effects of insulin on adiponectin.