Using speech recognition technology to investigate the association between timing-related speech features and depression severity.
Ontology highlight
ABSTRACT: Background
There are no reliable and validated objective biomarkers for the assessment of depression severity. We aimed to investigate the association between depression severity and timing-related speech features using speech recognition technology.Method
Patients with major depressive disorder (MDD), those with bipolar disorder (BP), and healthy controls (HC) were asked to engage in a non-structured interview with research psychologists. Using automated speech recognition technology, we measured three timing-related speech features: speech rate, pause time, and response time. The severity of depression was assessed using the Hamilton Depression Rating Scale 17-item version (HAMD-17). We conducted the current study to answer the following questions: 1) Are there differences in speech features among MDD, BP, and HC? 2) Do speech features correlate with depression severity? 3) Do changes in speech features correlate with within-subject changes in depression severity?Results
We collected 1058 data sets from 241 individuals for the study (97 MDD, 68 BP, and 76 HC). There were significant differences in speech features among groups; depressed patients showed slower speech rate, longer pause time, and longer response time than HC. All timing-related speech features showed significant associations with HAMD-17 total scores. Longitudinal changes in speech rate correlated with changes in HAMD-17 total scores.Conclusions
Depressed individuals showed longer response time, longer pause time, and slower speech rate than healthy individuals, all of which were suggestive of psychomotor retardation. Our study suggests that speech features could be used as objective biomarkers for the assessment of depression severity.
SUBMITTER: Yamamoto M
PROVIDER: S-EPMC7485753 | biostudies-literature | 2020
REPOSITORIES: biostudies-literature
Publications
Using speech recognition technology to investigate the association between timing-related speech features and depression severity.
Yamamoto Mao M Takamiya Akihiro A Sawada Kyosuke K Yoshimura Michitaka M Kitazawa Momoko M Liang Kuo-Ching KC Fujita Takanori T Mimura Masaru M Kishimoto Taishiro T
PloS one 20200911 9
<h4>Background</h4>There are no reliable and validated objective biomarkers for the assessment of depression severity. We aimed to investigate the association between depression severity and timing-related speech features using speech recognition technology.<h4>Method</h4>Patients with major depressive disorder (MDD), those with bipolar disorder (BP), and healthy controls (HC) were asked to engage in a non-structured interview with research psychologists. Using automated speech recognition techn ...[more]
Similar Datasets
Project description:The aim was to define the association between the severity of depression, prosody, and voice acoustic features in women suffering from depression and its comparisons with nondepressed people. Prosody and acoustic features in 30 women with major depression hospitalized in a psychiatric ward and 30 healthy women were investigated in a cross-sectional study. To define the severity of depression, the Hamilton Rating Scale for Depression (HRS-D) was applied. Acoustic parameters such as jitter, shimmer, cepstral peak prominence (CPP), standard deviation of fundamental frequency (SD F0), harmonic-to-noise ratio, and F0 and also some speech prosodic features including the speed of speech, switching pause duration means, and durations of produced sentences with different modals were measured quantitatively. Also, six raters judged the patient's prosody qualitatively. SPSS V.28 was used for all statistical analyses (p < 0.05). There was a significant correlation between HRS-D with jitter, SD F0, speed of speech, and switching pause means (p ≤ 0.05). The means of CPP and duration of producing emotional sentences differed between the depression and control groups. The HRS-D scores were significantly correlated with switching pauses in patients (Pearson coefficient = 0.47, p=0.05). The results of the perceptual evaluation of prosody judged by six raters showed an 85% correlation between them (p ≤ 0.001). Some acoustic and prosodic parameters are different between healthy women and those with depression disorder (e.g., CPP and duration of emotional sentences) and may also have an association with the severity of depression (e.g., jitter, SD F0, speed of speech, and switching pause means) in women with depression disorder. It was indicated that the best sentence modal to assess prosody in patients with depression would be exclamatory ones compared to declarative and interrogative sentences.
| S-EPMC10715859 | biostudies-literature
Project description:BackgroundSeveral studies have investigated the acoustic effects of diagnosed anxiety and depression. Anxiety and depression are not characteristics of the typical aging process, but minimal or mild symptoms can appear and evolve with age. However, the knowledge about the association between speech and anxiety or depression is scarce for minimal/mild symptoms, typical of healthy aging. As longevity and aging are still a new phenomenon worldwide, posing also several clinical challenges, it is important to improve our understanding of non-severe mood symptoms' impact on acoustic features across lifetime. The purpose of this study was to determine if variations in acoustic measures of voice are associated with non-severe anxiety or depression symptoms in adult population across lifetime.MethodsTwo different speech tasks (reading vowels in disyllabic words and describing a picture) were produced by 112 individuals aged 35-97. To assess anxiety and depression symptoms, the Hospital Anxiety Depression Scale (HADS) was used. The association between the segmental and suprasegmental acoustic parameters and HADS scores were analyzed using the linear multiple regression technique.ResultsThe number of participants with presence of anxiety or depression symptoms is low (>7: 26.8% and 10.7%, respectively) and non-severe (HADS-A: 5.4 ± 2.9 and HADS-D: 4.2 ± 2.7, respectively). Adults with higher anxiety symptoms did not present significant relationships associated with the acoustic parameters studied. Adults with increased depressive symptoms presented higher vowel duration, longer total pause duration and short total speech duration. Finally, age presented a positive and significant effect only for depressive symptoms, showing that older participants tend to have more depressive symptoms.ConclusionsNon-severe depression symptoms can be related to some acoustic parameters and age. Depression symptoms can be explained by acoustic parameters even among individuals without severe symptom levels.
| S-EPMC8031302 | biostudies-literature
Project description:ImportanceMultiple studies have evaluated associations between post-cochlear implant (CI) speech recognition outcomes and patient-related factors. Current literature often appears equivocal or contradictory, so little is known about the factors that contribute to successful speech recognition outcomes with CIs.ObjectiveTo use a meta-analysis to pool data from the extant literature and provide an objective summary of existing evidence on associations of patient-related factors and CI speech recognition outcomes.Data sourcesA literature search was performed using PubMed, Scopus, and CINAHL databases in January 2019 using the following search terms: cochlear implant or cochlear implants or cochlear implantation and speech recognition or word recognition or sentence recognition. Studies of postlingually deafened adult CI recipients that reported word or sentence recognition scores were included.Study selectionInclusion criteria were postlingual adult CI recipients 18 years or older with word or sentence recognition scores at minimum 6-month postimplantation. Studies that included patients undergoing revision or reimplantation surgery were excluded.Data extraction and synthesisFollowing the Preferred Reporting Items for Systemic Reviews and Meta-analyses (PRISMA) guidelines, 1809 unique articles underwent review by abstract, and 121 articles underwent full-text review, resulting in 13 articles of 1095 patients for a meta-analysis of correlations. Random-effects model was used when the heterogeneity test yielded a low P value (P < .05).Main outcomes and measuresThe planned primary outcome was the pooled correlation values between postimplant speech recognition scores and patient-related factors.ResultsOf the 1095 patients included from the 13 studies, the mean age at implantation ranged from 51.2 to 63.7 years and the mean duration of hearing loss ranged from 9.5 to 31.8 years; for the 825 patients for whom sex was reported, 421 (51.0%) were women. A weak negative correlation was observed between age at implantation and postimplant sentence recognition in quiet (r = -0.31 [95% CI, -0.41 to -0.20]). Other correlations between patient-related factors and postimplant word or sentence recognition were statistically significant, but all correlations were absent to negligible (r = 0.02-0.27).Conclusions and relevanceGiven that most associations were weak, negligible, or absent, patient-related factors often thought to affect CI speech recognition ability offer limited assistance in clinical decision-making in cochlear implantation. Additional research is needed to identify patient-related and other factors that predict CI outcomes, including speech recognition and other important variables related to success with CIs.
| S-EPMC7226297 | biostudies-literature
Project description:BACKGROUND: Treacher Collins syndrome (TCS, OMIM 154500) is a rare congenital disorder of craniofacial development. Characteristic hypoplastic malformations of the ears, zygomatic arch, mandible and pharynx have been described in detail. However, reports on the impact of these malformations on speech are few. Exploring speech features and investigating if speech function is related to phenotypic severity are essential for optimizing follow-up and treatment. METHODS: Articulation, nasal resonance, voice and intelligibility were examined in 19 individuals (5-74 years, median 34 years) divided into three groups comprising children 5-10 years (n?=?4), adolescents 11-18 years (n?=?4) and adults 29 years and older (n?=?11). A speech composite score (0-6) was calculated to reflect the variability of speech deviations. TCS severity scores of phenotypic expression and total scores of Nordic Orofacial Test-Screening (NOT-S) measuring orofacial dysfunction were used in analyses of correlation with speech characteristics (speech composite scores). RESULTS: Children and adolescents presented with significantly higher speech composite scores (median 4, range 1-6) than adults (median 1, range 0-5). Nearly all children and adolescents (6/8) displayed speech deviations of articulation, nasal resonance and voice, while only three adults were identified with multiple speech aberrations. The variability of speech dysfunction in TCS was exhibited by individual combinations of speech deviations in 13/19 participants. The speech composite scores correlated with TCS severity scores and NOT-S total scores. Speech composite scores higher than 4 were associated with cleft palate. The percent of intelligible words in connected speech was significantly lower in children and adolescents (median 77%, range 31-99) than in adults (98%, range 93-100). Intelligibility of speech among the children was markedly inconsistent and clearly affecting the understandability. CONCLUSIONS: Multiple speech deviations were identified in children, adolescents and a subgroup of adults with TCS. Only children displayed markedly reduced intelligibility. Speech was significantly correlated with phenotypic severity of TCS and orofacial dysfunction. Follow-up and treatment of speech should still be focused on young patients, but some adults with TCS seem to require continuing speech and language pathology services.
| S-EPMC4101868 | biostudies-literature
Project description:BackgroundThe use of mobile devices to continuously monitor objectively extracted parameters of depressive symptomatology is seen as an important step in the understanding and prevention of upcoming depressive episodes. Speech features such as pitch variability, speech pauses, and speech rate are promising indicators, but empirical evidence is limited, given the variability of study designs.ObjectivePrevious research studies have found different speech patterns when comparing single speech recordings between patients and healthy controls, but only a few studies have used repeated assessments to compare depressive and nondepressive episodes within the same patient. To our knowledge, no study has used a series of measurements within patients with depression (eg, intensive longitudinal data) to model the dynamic ebb and flow of subjectively reported depression and concomitant speech samples. However, such data are indispensable for detecting and ultimately preventing upcoming episodes.MethodsIn this study, we captured voice samples and momentary affect ratings over the course of 3 weeks in a sample of patients (N=30) with an acute depressive episode receiving stationary care. Patients underwent sleep deprivation therapy, a chronotherapeutic intervention that can rapidly improve depression symptomatology. We hypothesized that within-person variability in depressive and affective momentary states would be reflected in the following 3 speech features: pitch variability, speech pauses, and speech rate. We parametrized them using the extended Geneva Minimalistic Acoustic Parameter Set (eGeMAPS) from open-source Speech and Music Interpretation by Large-Space Extraction (openSMILE; audEERING GmbH) and extracted them from a transcript. We analyzed the speech features along with self-reported momentary affect ratings, using multilevel linear regression analysis. We analyzed an average of 32 (SD 19.83) assessments per patient.ResultsAnalyses revealed that pitch variability, speech pauses, and speech rate were associated with depression severity, positive affect, valence, and energetic arousal; furthermore, speech pauses and speech rate were associated with negative affect, and speech pauses were additionally associated with calmness. Specifically, pitch variability was negatively associated with improved momentary states (ie, lower pitch variability was linked to lower depression severity as well as higher positive affect, valence, and energetic arousal). Speech pauses were negatively associated with improved momentary states, whereas speech rate was positively associated with improved momentary states.ConclusionsPitch variability, speech pauses, and speech rate are promising features for the development of clinical prediction technologies to improve patient care as well as timely diagnosis and monitoring of treatment response. Our research is a step forward on the path to developing an automated depression monitoring system, facilitating individually tailored treatments and increased patient empowerment.
| S-EPMC10835582 | biostudies-literature
Project description:Depression is one of the significant mental health issues affecting all age groups globally. While it has been widely recognized to be one of the major disease burdens in populations, complexities in definitive diagnosis present a major challenge. Usually, trained psychologists utilize conventional methods including individualized interview assessment and manually administered PHQ-8 scoring. However, heterogeneity in symptomatic presentations, which span somatic to affective complaints, impart substantial subjectivity in its diagnosis. Diagnostic accuracy is further compounded by the cross-sectional nature of sporadic assessment methods during physician-office visits, especially since depressive symptoms/severity may evolve over time. With widespread acceptance of smart wearable devices and smartphones, passive monitoring of depression traits using behavioral signals such as speech presents a unique opportunity as companion diagnostics to assist the trained clinicians in objective assessment over time. Therefore, we propose a framework for automated depression classification leveraging alterations in speech patterns in the well documented and extensively studied DAIC-WOZ depression dataset. This novel tensor-based approach requires a substantially simpler implementation architecture and extracts discriminative features for depression recognition with high f1 score and accuracy. We posit that such algorithms, which use significantly less compute load would allow effective onboard deployment in wearables for improve diagnostics accuracy and real-time monitoring of depressive disorders.
| S-EPMC9371305 | biostudies-literature
Project description:ImportanceThe association between major depressive disorder (MDD) and obesity may stem from shared immunometabolic mechanisms particularly evident in MDD with atypical features, characterized by increased appetite and/or weight (A/W) during an active episode.ObjectiveTo determine whether subgroups of patients with MDD stratified according to the A/W criterion had a different degree of genetic overlap with obesity-related traits (body mass index [BMI] and levels of C-reactive protein [CRP] and leptin).Design, setting, and patientsThis multicenter study assembled genome-wide genotypic and phenotypic measures from 14 data sets of the Psychiatric Genomics Consortium. Data sets were drawn from case-control, cohort, and population-based studies, including 26 628 participants with established psychiatric diagnoses and genome-wide genotype data. Data on BMI were available for 15 237 participants. Data were retrieved and analyzed from September 28, 2015, through May 20, 2017.Main outcomes and measuresLifetime DSM-IV MDD was diagnosed using structured diagnostic instruments. Patients with MDD were stratified into subgroups according to change in the DSM-IV A/W symptoms as decreased or increased.ResultsData included 11 837 participants with MDD and 14 791 control individuals, for a total of 26 628 participants (59.1% female and 40.9% male). Among participants with MDD, 5347 (45.2%) were classified in the decreased A/W and 1871 (15.8%) in the increased A/W subgroups. Common genetic variants explained approximately 10% of the heritability in the 2 subgroups. The increased A/W subgroup showed a strong and positive genetic correlation (SE) with BMI (0.53 [0.15]; P = 6.3 × 10-4), whereas the decreased A/W subgroup showed an inverse correlation (-0.28 [0.14]; P = .06). Furthermore, the decreased A/W subgroup had a higher polygenic risk for increased BMI (odds ratio [OR], 1.18; 95% CI, 1.12-1.25; P = 1.6 × 10-10) and levels of CRP (OR, 1.08; 95% CI, 1.02-1.13; P = 7.3 × 10-3) and leptin (OR, 1.09; 95% CI, 1.06-1.12; P = 1.7 × 10-3).Conclusions and relevanceThe phenotypic associations between atypical depressive symptoms and obesity-related traits may arise from shared pathophysiologic mechanisms in patients with MDD. Development of treatments effectively targeting immunometabolic dysregulations may benefit patients with depression and obesity, both syndromes with important disability.
| S-EPMC6396812 | biostudies-literature
Project description:BackgroundClinical documentation has undergone a change due to the usage of electronic health records. The core element is to capture clinical findings and document therapy electronically. Health care personnel spend a significant portion of their time on the computer. Alternatives to self-typing, such as speech recognition, are currently believed to increase documentation efficiency and quality, as well as satisfaction of health professionals while accomplishing clinical documentation, but few studies in this area have been published to date.ObjectiveThis study describes the effects of using a Web-based medical speech recognition system for clinical documentation in a university hospital on (1) documentation speed, (2) document length, and (3) physician satisfaction.MethodsReports of 28 physicians were randomized to be created with (intervention) or without (control) the assistance of a Web-based system of medical automatic speech recognition (ASR) in the German language. The documentation was entered into a browser's text area and the time to complete the documentation including all necessary corrections, correction effort, number of characters, and mood of participant were stored in a database. The underlying time comprised text entering, text correction, and finalization of the documentation event. Participants self-assessed their moods on a scale of 1-3 (1=good, 2=moderate, 3=bad). Statistical analysis was done using permutation tests.ResultsThe number of clinical reports eligible for further analysis stood at 1455. Out of 1455 reports, 718 (49.35%) were assisted by ASR and 737 (50.65%) were not assisted by ASR. Average documentation speed without ASR was 173 (SD 101) characters per minute, while it was 217 (SD 120) characters per minute using ASR. The overall increase in documentation speed through Web-based ASR assistance was 26% (P=.04). Participants documented an average of 356 (SD 388) characters per report when not assisted by ASR and 649 (SD 561) characters per report when assisted by ASR. Participants' average mood rating was 1.3 (SD 0.6) using ASR assistance compared to 1.6 (SD 0.7) without ASR assistance (P<.001).ConclusionsWe conclude that medical documentation with the assistance of Web-based speech recognition leads to an increase in documentation speed, document length, and participant mood when compared to self-typing. Speech recognition is a meaningful and effective tool for the clinical documentation process.
| S-EPMC4642384 | biostudies-literature
Project description:BackgroundPsychiatry faces a challenge due to the lack of objective biomarkers, as current assessments are based on subjective evaluations. Automated speech analysis shows promise in detecting symptom severity in depressed patients. This project aimed to identify discriminating speech features between patients with major depressive disorder (MDD) and healthy controls (HCs) by examining associations with symptom severity measures.MethodsForty-four MDD patients from the Psychiatry Department, University Hospital Aachen, Germany and fifty-two HCs were recruited. Participants described positive and negative life events, which were recorded for analysis. The Beck Depression Inventory (BDI-II) and the Hamilton Rating Scale for Depression gauged depression severity. Transcribed audio recordings underwent feature extraction, including acoustics, speech rate, and content. Machine learning models including speech features and neuropsychological assessments, were used to differentiate between the MDD patients and HCs.ResultsAcoustic variables such as pitch and loudness differed significantly between the MDD patients and HCs (effect sizes 𝜼2 between 0.183 and 0.3, p < 0.001). Furthermore, variables pertaining to temporality, lexical richness, and speech sentiment displayed moderate to high effect sizes (𝜼2 between 0.062 and 0.143, p < 0.02). A support vector machine (SVM) model based on 10 acoustic features showed a high performance (AUC = 0.93) in differentiating between HCs and patients with MDD, comparable to an SVM based on the BDI-II (AUC = 0.99, p = 0.01).ConclusionsThis study identified robust speech features associated with MDD. A machine learning model based on speech features yielded similar results to an established pen-and-paper depression assessment. In the future, these findings may shape voice-based biomarkers, enhancing clinical diagnosis and MDD monitoring.
| S-EPMC11559157 | biostudies-literature
Project description:BackgroundThe Overall Depression Severity and Impairment Scale (ODSIS) is a brief, five-item measure for assessing the frequency and intensity of depressive symptoms, as well as functional impairments in pleasurable activities, work or school, and interpersonal relationships due to depression. Although this scale is expected to be useful in various psychiatric and mental health settings, the reliability, validity, and interpretability have not yet been fully examined. This study was designed to examine the reliability, factorial, convergent, and discriminant validity of a Japanese version of the ODSIS, as well as its ability to distinguish between individuals with and without a major depressive disorder diagnosis.MethodsFrom a pool of registrants at an internet survey company, 2830 non-clinical and clinical participants were selected randomly (619 with major depressive disorder, 619 with panic disorder, 576 with social anxiety disorder, 645 with obsessive-compulsive disorder, and 371 non-clinical panelists). Participants were asked to respond to the ODSIS and conventional measures of depression, functional impairment, anxiety, neuroticism, satisfaction with life, and emotion regulation.ResultsExploratory and confirmatory factor analysis of three split subsamples indicated the unidimensional factor structure of ODSIS. Multi-group confirmatory factor analysis showed invariance of factor loadings between non-clinical and clinical subsamples. The ODSIS also showed excellent internal consistency and test-retest intraclass correlation coefficients. Convergence and discriminance of the ODSIS with various measures were in line with our expectations. Receiver operating characteristic curve analyses showed that the ODSIS was able to detect a major depressive syndrome accurately.ConclusionsThis study supports the reliability and validity of ODSIS in a non-western population, which can be interpreted as demonstrating cross-cultural validity.
| S-EPMC4395441 | biostudies-literature