Digital Content-Free Speech Analysis Tool to Measure Affective Distress in Mental Health: Evaluation Study
Bibliographic record
Abstract
BACKGROUND: Mood disorders and depression are pervasive and significant problems worldwide. These represent severe health and emotional impairments for individuals and a considerable economic and social burden. Therefore, fast and reliable diagnosis and appropriate treatment are of great importance. Verbal communication can clarify the speaker's mental state-regardless of the content, via speech melody, intonation, and so on. In both everyday life and clinical conditions, a listener with appropriate previous knowledge or a trained specialist can grasp helpful knowledge about the speaker's psychological state. Using automated speech analysis for the assessment and tracking of patients with mental health issues opens up the possibility of remote, automatic, and ongoing evaluation when used with patients' smartphones, as part of the current trends toward the increasing use of digital and mobile health tools. OBJECTIVE: The primary aim of this study is to evaluate the measurements of the presence or absence of depressive mood in participants by comparing the analysis of noncontentual speech parameters with the results of the Patient Health Questionnaire-9. METHODS: This proof-of-concept study included participants in different affective phases (with and without depression). The inclusion criteria included a neurological or psychiatric diagnosis made by a specialist and fluent use of the German language. The measuring instrument was the VoiceSense digital voice analysis tool, which enables the analysis of 200 specific speech parameters based on machine learning and the assessment of the findings using Patient Health Questionnaire-9. RESULTS: A total of 292 psychiatric and voice assessments were performed with 163 participants (males: n=47, 28.8%) aged 15 to 82 years. Of the 163 participants, 87 (53.3%) were not depressed at the time of assessment, and 88 (53.9%) participants had clinically mild to moderate depressive phases. Of the 163 participants, 98 (32.5%) showed subsyndromal symptoms, and 19 (11.7%) participants were severely depressed. In the speech analysis, a clear differentiation between the individual depressive levels, as seen in the Patient Health Questionnaire-9, was also shown, especially the clear differentiation between nondepressed and depressed participants. The study showed a Pearson correlation of 0.41 between clinical assessment and noncontentual speech analysis (P<.001). CONCLUSIONS: The use of speech analysis shows a high level of accuracy, not only in terms of the general recognition of a clinically relevant depressive state in the participants. Instead, there is a high degree of agreement regarding the extent of depressive impairment with the assessment of experienced clinical practitioners. From our point of view, the application of the noncontentual analysis system in everyday clinical practice makes sense, especially with the idea of a quick and unproblematic assessment of the state of mind, which can even be carried out without personal contact. TRIAL REGISTRATION: ClinicalTrials.gov NCT03700008; https://clinicaltrials.gov/ct2/show/NCT03700008.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".