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.

Impact of simulated MitraClip on forward flow obstruction in the setting of mitral leaflet tethering: An in vitro investigation.

OBJECTIVES: We aimed to evaluate diastolic leaflet tethering as a factor that may cause mitral stenosis (MS) after simulated MitraClip implantation, using an in vitro left heart simulator. BACKGROUND: Leaflet tethering commonly seen in functional mitral regurgitation may be a significant factor affecting the severity of MS after MitraClip implantation. METHODS: A left heart simulator with excised ovine mitral valves (N = 6), and custom edge-to-edge clip devices (GTclip) was used to mimic implantation of MitraClip in a variety of positions. Anterior mitral leaflet (AML) tethering severity was varied for each case (leaflet excursion of 75°, 60°, and 45°, consistent with mild, moderate and severe tethering), and the baseline mitral annular area (MAA) was varied across samples (3.6-4.8 cm2 ). The resulting mitral valve area (MVA), and peak/mean mitral valve gradient (MVG) were measured in each case. RESULTS: AML tethering severity was a highly significant factor increasing MVG and decreasing MVA (P < 0.001). When GTclip placement was simulated with severe AML tethering, mean MVG >5 mmHg resulted more frequently than with GTclip placement alone (46% vs. 4%, respectively). However, severe AML tethering alone significantly reduced baseline MVA to 3.6 ± 0.2 cm2 , and increased baseline MVG to 3.0 ± 0.4 mmHg. At MAA above 4.7 cm2 , severe AML tethering did not cause moderate MS, even with placement of two GTclips (95% confidence). CONCLUSIONS: Our results show that diastolic AML tethering may predispose to MS after clip placement, however, MS was not observed when baseline MVA was above 4.0 cm2 . Severity of AML tethering may be an important criterion in selecting patients for edge-to-edge repair.