Development of a Digital Content-Free Speech Analysis Tool for the Measurement of Mental Health and Follow-Up for Mental Disorders: Protocol for a Case-Control Study
Bibliographic record
Abstract
BACKGROUND: The prevalence of mental disorders worldwide is very high. The guideline-oriented care of patients depends on early diagnosis and regular and valid evaluation of their treatment to be able to quickly intervene should the patient's mental health deteriorate. To ensure effective treatment, the level of experience of the physician or therapist is of importance, both in the initial diagnosis and in the treatment of mental illnesses. Nevertheless, experienced physicians and psychotherapists are not available in enough numbers everywhere, especially in rural areas or in less developed countries. Human speech can reveal a speaker's mental state by altering its noncontent aspects (speech melody, intonations, speech rate, etc). This is noticeable in both the clinic and everyday life by having prior knowledge of the normal speech patterns of the affected person, and with enough time spent listening to the patient. However, this time and experience are often unavailable, leaving unused opportunities to capture linguistic, noncontent information. To improve the care of patients with mental disorders, we have developed a concept for assessing their most important mental parameters through a noncontent analysis of their active speech. Using speech analysis for the assessment and tracking of mental health patients 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 objective of this study is to evaluate measurements of participants' mental state by comparing the analysis of noncontent speech parameters to the results of several psychological questionnaires (Symptom Checklist-90 [SCL-90], the Patient Health Questionnaire [PHQ], and the Big 5 Test). METHODS: In this paper, we described a case-controlled study (with a case group and one control group). The participants will be recruited in an outpatient neuropsychiatric treatment center. Inclusion criteria are a neurological or psychiatric diagnosis made by a specialist, no terminal or life-threatening illnesses, and fluent use of the German language. Exclusion criteria include psychosis, dementia, speech or language disorders in neurological diseases, addiction history, a suicide attempt recently or in the last 12 months, or insufficient language skills. The measuring instrument will be the VoiceSense digital voice analysis tool, which enables the analysis of 200 specific speech parameters, and the assessment of findings using psychometric instruments and questionnaires (SCL-90, PHQ, Big 5 Test). RESULTS: The study is ongoing as of September 2019, but we have enrolled 254 participants. There have been 161 measurements completed at timepoint 1, and a total of 62 participants have completed every psychological and speech analysis measurement. CONCLUSIONS: It appears that the tone and modulation of speech are as important, if not more so, than the content, and should not be underestimated. This is particularly evident in the interpretation of the psychological findings thus far acquired. Therefore, the application of a software analysis tool could increase the accuracy of finding assessments and improve patient care. TRIAL REGISTRATION: ClinicalTrials.gov NCT03700008; https://clinicaltrials.gov/ct2/show/NCT03700008. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/13852.
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 | 0.004 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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".