"How are you?" Estimation of anxiety, sleep quality, and mood using computational voice analysis.

We developed a method of estimating impactors of cognitive function (ICF) - such as anxiety, sleep quality, and mood - using computational voice analysis. Clinically validated questionnaires (VQs) were used to score anxiety, sleep and mood while salient voice features were extracted to train regression models with deep neural networks. Experiments with 203 subjects showed promising results with significant concordance correlation coefficients (CCC) between actual VQ scores and the predicted scores (0.46 = anxiety, 0.50 = sleep quality, 0.45 = mood).

The clinical utility of a hand-held computerized optical imaging system at assessing skin discoloration.

BACKGROUND: A hand-held computerized optical device (HCOD) that can be used by a layperson has been developed which is capable of imaging facial skin and assessing multiple skin attributes, including discoloration. OBJECTIVES: The aim of this study was to assess the HCOD's ability to measure changes in discoloration induced over an 8-week course of treatment by comparing data obtained from the HCOD with the assessments of a trained research dermatologist. METHODS: Ten female Caucasian subjects, aged between 41 and 79 years, exhibiting moderate facial dyspigmentation used a combination 0.01% fluocinolone acetonide, 4% hydroquinone, and 0.05% tretinoin cream twice daily for 8 weeks. Subjects were evaluated at weeks 0, 4, and 8 by a dermatologist. Images were also taken with high resolution digital photography and with the HCOD. Human testing was directed by a dermatologist, used approved consent forms, and products approved by the FDA. RESULTS: Facial dyspigmentation as scored by a clinician significantly decreased from 4.10 to 2.70 by week 8. HCOD discoloration area scores also significantly decreased from 100,989 to 87,276 by week 8. Assessment of pigmented area by the HCOD proved to be the most reliable in terms of correlating to a clinician's score. Limitations The study had a small sample size and was not placebo controlled because the effectiveness of the HCOD was being evaluated, not the skin lightening product. CONCLUSIONS: The HCOD's discoloration area count statistically correlated with the clinician dyspigmentation scores when evaluating the effect of a prescription skin lightening cream on subjects with moderate facial discolorations.