Development and validation of a machine learning-based vocal predictive model for major depressive disorder.

BACKGROUND: Variations in speech intonation are known to be associated with changes in mental state over time. Behavioral vocal analysis is an algorithmic method of determining individuals' behavioral and emotional characteristics from their vocal patterns. It can provide biomarkers for use in psychiatric assessment and monitoring, especially when remote assessment is needed, such as in the COVID-19 pandemic. The objective of this study was to design and validate an effective prototype of automatic speech analysis based on algorithms for classifying the speech features related to MDD using a remote assessment system combining a mobile app for speech recording and central cloud processing for the prosodic vocal patterns. METHODS: Machine learning compared the vocal patterns of 40 patients diagnosed with MDD to the patterns of 104 non-clinical participants. The vocal patterns of 40 patients in the acute phase were also compared to 14 of these patients in the remission phase of MDD. RESULTS: A vocal depression predictive model was successfully generated. The vocal depression scores of MDD patients were significantly higher than the scores of the non-patient participants (p < 0.0001). The vocal depression scores of the MDD patients in the acute phase were significantly higher than in remission (p < 0.02). LIMITATIONS: The main limitation of this study is its relatively small sample size, since machine learning validity improves with big data. CONCLUSIONS: The computerized analysis of prosodic changes may be used to generate biomarkers for the early detection of MDD, remote monitoring, and the evaluation of responses to treatment.

Methods for detecting probable COVID-19 cases from large-scale survey data also reveal probable sex differences in symptom profiles.

Background: Daily symptom reporting collected via web-based symptom survey tools holds the potential to improve disease monitoring. Such screening tools might be able to not only discriminate between states of acute illness and non-illness, but also make use of additional demographic information so as to identify how illnesses may differ across groups, such as biological sex. These capabilities may play an important role in the context of future disease outbreaks. Objective: Use data collected via a daily web-based symptom survey tool to develop a Bayesian model that could differentiate between COVID-19 and other illnesses and refine this model to identify illness profiles that differ by biological sex. Methods: We used daily symptom profiles to plot symptom progressions for COVID-19, influenza (flu), and the common cold. We then built a Bayesian network to discriminate between these three illnesses based on daily symptom reports. We further separated out the COVID-19 cohort into self-reported female and male subgroups to observe any differences in symptoms relating to sex. We identified key symptoms that contributed to a COVID-19 prediction in both males and females using a logistic regression model. Results: Although the Bayesian model performed only moderately well in identifying a COVID-19 diagnosis (71.6% true positive rate), the model showed promise in being able to differentiate between COVID-19, flu, and the common cold, as well as periods of acute illness vs. non-illness. Additionally, COVID-19 symptoms differed between the biological sexes; specifically, fever was a more important symptom in identifying subsequent COVID-19 infection among males than among females. Conclusion: Web-based symptom survey tools hold promise as tools to identify illness and may help with coordinated disease outbreak responses. Incorporating demographic factors such as biological sex into predictive models may elucidate important differences in symptom profiles that hold implications for disease detection.

Detection of COVID-19 using multimodal data from a wearable device: results from the first TemPredict Study.

Early detection of diseases such as COVID-19 could be a critical tool in reducing disease transmission by helping individuals recognize when they should self-isolate, seek testing, and obtain early medical intervention. Consumer wearable devices that continuously measure physiological metrics hold promise as tools for early illness detection. We gathered daily questionnaire data and physiological data using a consumer wearable (Oura Ring) from 63,153 participants, of whom 704 self-reported possible COVID-19 disease. We selected 73 of these 704 participants with reliable confirmation of COVID-19 by PCR testing and high-quality physiological data for algorithm training to identify onset of COVID-19 using machine learning classification. The algorithm identified COVID-19 an average of 2.75 days before participants sought diagnostic testing with a sensitivity of 82% and specificity of 63%. The receiving operating characteristic (ROC) area under the curve (AUC) was 0.819 (95% CI [0.809, 0.830]). Including continuous temperature yielded an AUC 4.9% higher than without this feature. For further validation, we obtained SARS CoV-2 antibody in a subset of participants and identified 10 additional participants who self-reported COVID-19 disease with antibody confirmation. The algorithm had an overall ROC AUC of 0.819 (95% CI [0.809, 0.830]), with a sensitivity of 90% and specificity of 80% in these additional participants. Finally, we observed substantial variation in accuracy based on age and biological sex. Findings highlight the importance of including temperature assessment, using continuous physiological features for alignment, and including diverse populations in algorithm development to optimize accuracy in COVID-19 detection from wearables.