Vocal Effort and Acoustic Analysis of Gargle Phonation Versus Water Swallow in Patients With Muscle Tension Dysphonia: A Clinical Trial.

PURPOSE: To determine the effects of gargle phonation (GP) on self-perceived vocal improvement, vocal effort, acoustic parameters, and speech rate in patients with muscle tension dysphonia (MTD). We hypothesized that GP would improve voice, reduce phonatory effort, and alter acoustic and speech measures. STUDY DESIGN: Prospective randomized, single-blind cross-over clinical trial METHODS: Thirty-four participants (26 females, 8 males; average age 53 years) who were diagnosed with MTD completed the Voice Handicap Index-10 (VHI-10) and were assigned three study conditions: Baseline (B), GP, and Water Swallow (WS; sham), presented in one of two counterbalanced orders B-WS-GP (WS1st) or B-GP-WS (GP1st). Participants recorded stimuli from the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) and rated their perceived vocal effort and vocal improvement. F0, vocal intensity, cepstral peak prominence (CPP), and speaking rate were measured. RESULTS: Average VHI-10 scores by group were 16 (min/max 2-29) for WS1st and 15 (min/max 3-40) for GP1st. About 73.5% reported more vocal improvement after GP, 17.65% after WS, and 8.8% noted no difference between conditions. Reduced effort was reported after GP, compared to B (P < 0.001) and WS (P = 0.005). Lower effort was also reported after the WS condition, compared to B (P = 0.011). Key acoustic findings included an increase in F0 after GP for sustained /i/ for females. CPP was significantly higher for females reading CAPE-V sentences after GP, when GP preceded WS, compared to B (P = 0.004) and WS (P = 0.003). Speech rate was faster for females after GP versus B (P = 0.029). CONCLUSIONS: GP may be beneficial in the treatment of MTD. CPP may be a useful marker for vocal improvement after GP for women with mild MTD. Further studies would benefit from having more male participants and those with moderate and severe MTD.

Visual Gaze Patterns in the Analysis of Glottic Lesions: Does Experience Increase Diagnostic Accuracy?

OBJECTIVES: The purpose of this study was to evaluate visual gaze patterns and the ability to correctly identify cancer among participants of different experience levels when viewing benign and malignant vocal cord lesions. METHODS: Thirty-one participants were divided into groups based on level of experience. These included novice (medical students, PGY1-2 otolaryngology residents), intermediate (PGY3-5 otolaryngology residents, gastroenterology fellow), advanced practice providers (physician assistants, nurse practitioners, and speech language pathologists), and experts (board-certified otolaryngologists). Each participant was shown 7 images of vocal cord pathology including glottic cancer, infectious laryngitis, and granuloma and asked to determine the likelihood of cancer on a scale of certain, probable, possible, and unlikely. Eye tracking data were collected and used to identify the area of interest (AOI) that each participant fixated on first, fixated on the longest, and had the greatest number of fixations. RESULTS: No significant differences were seen among groups when comparing AOI with first fixation, AOI with longest fixation, or AOI with most fixations. Novices were significantly more likely to rate a low likelihood of cancer when viewing infectious laryngitis compared to more experienced groups (P < .001). There was no difference in likelihood of cancer rating among groups for the remaining images. CONCLUSIONS: There was no significant difference in gaze targets among participants of different experience levels evaluating vocal cord pathology. Symmetric appearance of vocal cord lesions may explain differences seen in likelihood of cancer rating among groups. Future studies with larger sample sizes will better elucidate gaze targets that lead to accurate diagnosis of vocal cord pathology.

Guess What We Can Hear-Novel Voice Biomarkers for the Remote Detection of Disease.

The advancement of digital biomarkers and the provision of remote health care greatly progressed during the coronavirus disease 2019 global pandemic. Combining voice/speech data with artificial intelligence and machine-based learning offers a novel solution to the growing demand for telemedicine. Voice biomarkers, obtained from the extraction of characteristic acoustic and linguistic features, are associated with a variety of diseases and even coronavirus disease 2019. In the current review, we (1) describe the basis on which digital voice biomarkers could facilitate "telemedicine," (2) discuss potential mechanisms that may explain the association between voice biomarkers and disease, (3) offer a novel classification system to conceptualize voice biomarkers depending on different methods for recording and analyzing voice/speech samples, (4) outline evidence revealing an association between voice biomarkers and a number of disease states, and (5) describe the process of developing a voice biomarker from recording, storing voice samples, and extracting acoustic and linguistic features relevant to training and testing deep and machine-based learning algorithms to detect disease. We further explore several important future considerations in this area of research, including the necessity for clinical trials and the importance of safeguarding data and individual privacy. To this end, we searched PubMed and Google Scholar to identify studies evaluating the relationship between voice/speech features and biomarkers and various diseases. Search terms included digital biomarker, telemedicine, voice features, voice biomarker, speech features, speech biomarkers, acoustics, linguistics, cardiovascular disease, neurologic disease, psychiatric disease, and infectious disease. The search was limited to studies published in English in peer-reviewed journals between 1980 and the present. To identify potential studies not captured by our database search strategy, we also searched studies listed in the bibliography of relevant publications and reviews.

Landmark-based analysis of speech differentiates conversational from clear speech in speakers with muscle tension dysphonia.

This study evaluated the feasibility of differentiating conversational and clear speech produced by individuals with muscle tension dysphonia (MTD) using landmark-based analysis of speech (LMBAS). Thirty-four adult speakers with MTD recorded conversational and clear speech, with 27 of them able to produce clear speech. The recordings of these individuals were analyzed with the open-source LMBAS program, SpeechMark®, matlab Toolbox version 1.1.2. The results indicated that glottal landmarks, burst onset landmarks, and the duration between glottal landmarks differentiated conversational speech from clear speech. LMBAS shows potential as an approach for detecting the difference between conversational and clear speech in dysphonic individuals.

Visual Interpretation of Vocal Fold Paralysis in Flexible Laryngoscopy Using Eye Tracking Technology.

OBJECTIVES: Interpretation of laryngoscopy is an important diagnostic skill in otolaryngology. There is, however, limited understanding of the specific visual strategies used while assessing flexible laryngoscopy video. Eye-tracking technology allows for objective study of eye movements during dynamic tasks. The purpose of the present study was to explore visual gaze strategies during laryngoscopy interpretation of unilateral vocal fold paralysis (UVFP) across clinician experience from novice to expert. METHODS: Thirty individuals were shown five flexible laryngoscopy videos, each 10 seconds long. After viewing each video, participants reported their impressions of "left vocal fold paralysis," "right vocal fold paralysis," or "no vocal fold paralysis." Eye tracking data were collected and analyzed for duration of fixation and number of fixations on select areas of interest (AOI). Diagnostic accuracy and visual gaze patterns were compared between novice, experienced, and expert groups. RESULTS: Diagnostic accuracy among learners in the novice group was significantly lower than those in the more experienced groups (P = 0.04). All groups demonstrated similar visual gaze patterns when viewing the video with normal bilateral vocal fold mobility, spending the greatest percentage of time viewing the trachea. There were differences among groups when viewing the videos of left or right VFP, but the trachea was always in the top three structures for greatest fixation duration and highest number of fixations. CONCLUSIONS: Eye-tracking is a novel tool in the setting of laryngoscopy interpretation. With further study it has the potential to be useful for the training of otolaryngology learners to improve diagnostic skills.

Singing Voice Concern in Tertiary Laryngology Practice.

OBJECTIVES: To determine the prevalence and characteristics of patients who identify singing voice as a primary concern when presenting with general voice complaints to a voice clinic. METHODS: Data were collected from medical records on demographics, medical history, laryngoscopy exam, diagnosis, and subsequent treatments; and from self-report questionnaires including the Voice Handicap Index-10 (VHI-10) and clinical voice questionnaire. RESULTS: A total of 17% of patients presenting to a voice clinic with general voice problems who completed a VHI-10 identified singing voice as a primary concern. Compared to the reference cohort, patients concerned about singing voice report greater handicap on several questions of the VHI-10, particularly in personal and social life impact, loss of income, unpredictability of vocal clarity, subjective upset, and subjective handicap. Those concerned with singing voice were also more concerned about their vocal problem, and both more likely to be recommended voice therapy and participate in voice therapy despite no statistical differences in categorical diagnoses. CONCLUSIONS: When considering both professional and recreational singers, voice concerns occurred in 17% of the cohort under study. Patients with singing voice concerns are accounted for largely by recreational singers, who remain poorly characterized in the literature. We underscore the importance of sensitivity and responsivity to the needs of this group of patients.

Noninvasive Voice Biomarker Is Associated With Incident Coronary Artery Disease Events at Follow-up.

OBJECTIVE: To evaluate the association between a preidentified voice biomarker and incident coronary artery disease (CAD) events. METHODS: Patients referred for clinically indicated coronary angiography underwent a total of three 30-second voice recordings using the Vocalis Health smartphone application between January 1, 2015, and February 28, 2017. A pre-established voice biomarker was derived from each individual recording, and the mean biomarker value was calculated for each patient. Individuals were clinically observed through December 31, 2019. The prespecified primary outcome was a composite of presenting to the emergency department with chest pain, being admitted to the hospital with chest pain, or having an acute coronary syndrome; the prespecified secondary outcome was a composite of a positive stress test result at follow-up or the presence of CAD at follow-up coronary angiography. RESULTS: In the final analysis, 108 patients were included (mean age, 59.47±11.44 years; male, 59 [54.6%]). The median follow-up time was 24 months (range, 1 to 60 months). In multivariable Cox proportional hazards models adjusting for CAD grade on baseline angiography, a high baseline mean voice biomarker was significantly associated with both the primary (hazard ratio, 2.61; 95% CI, 1.42 to 4.80; P=.002) and secondary (hazard ratio, 3.13; 95% CI, 1.13 to 8.68; P=.03) composite outcomes. CONCLUSION: This study found a significant association between a noninvasive voice biomarker and incident CAD events at follow-up. These results may have important clinical implications for the remote and noninvasive screening of patients to identify those at risk of coronary disease and its complications.

Speech Pathology Utilization and Stroboscopy Before and After Adult Medialization Laryngoplasty.

OBJECTIVES: Evaluation of trends and utilization of speech-language-pathology (SLP) services, including stroboscopy, before and after medialization laryngoplasty (ML) over 11 years. METHODS: Retrospective national US database study conducted using OptumLabs Data Warehouse. Study cohort included patients (age ≥18 years) who underwent ML between January 2007 and December 2016. Primary outcomes were rates of SLP visits in the 12 months before and 12 months after ML. Linear regression analysis was performed assessing for trends utilization across years. Secondary outcomes were predictors of utilization After-ML using multivariable logistic regression. RESULTS: 1114 patients met criteria. Services, including stroboscopy, were utilized by 774 (69%) Before-ML and 697 (63%) After-ML. SLP services, excluding stroboscopy, were utilized by 512 (46%) Before-ML and 478 (43%) After-ML. Vocal cord paralysis was the most common diagnosis, 945 (84.8%) patients. Other service billed were stroboscopy, [Before-ML 676 (60.7%); After-ML 567 (50.9%)], voice evaluation [Before-ML 431(38.7%); After-ML 366 (32.9%)], voice therapy [Before-ML 309 (27.7%); After-ML 339 (30.4%)], laryngeal function studies, [Before-ML 175 (15.7%); After-ML 164 (14.7%)], swallow evaluations [Before-ML 150 (13.5%); After-ML 90 (8.1%)], and swallow therapy [Before-ML 53 (4.8%); After-ML 47 (4.2%)]. SLP utilization Before-ML predicted SLP utilization After-ML [Odds Ratio (95% Confidence Interval): 9.31 (6.78, 12.77)]. Nearly half (49%) of visits occurred in the 6 months around ML. Of those who had voice therapy, the majority (73.7%) had a total of 1 to 5 sessions. CONCLUSION: Based on this retrospective US national database study, SLP services and stroboscopy are a complementary component of assessment and treatment of patients who undergo ML with the majority of services occurring in the 3 months before and after ML. Future work would benefit from outcome data.

Predicting Gag, Discomfort, and Laryngeal Visualization in Patients Undergoing Flexible Laryngoscopy with Stroboscopy.

OBJECTIVE: To investigate potential associations between the Predictive Gagging Survey (PGS) with patient experience of gag and discomfort as well as provider perception of patient gag and level of laryngeal visualization during flexible laryngoscopy with stroboscopy (FL-S). METHODS: A total of 53 adult patients undergoing FL-S were recruited for this prospective non-controlled study. PGS was completed before FL-S. Patients rated perceived level of gag and discomfort on a 10-point severity scale after FL-S. Additionally, providers completed a Gagging Severity Index (GSI) reflecting their impression of patient gag and level of laryngeal visualization following FL-S. Spearman rank correlation coefficients were used to assess associations. RESULTS: There was a positive association with PGS score and patient perception of gagging (0.34; P = .013) and patient perception of discomfort (0.38; P = .005). No significant association was found between PGS score and provider GSI (-0.12; P = .39) or level of laryngeal visualization (0.15; P = .29). A negative association was found between level of laryngeal visualization and patient perception of gagging (-0.34; P = .012) and discomfort (-0.44; P = .001). No significant differences were found between current and former smokers compared to never smokers for GSI or patient-perceived gag or discomfort. CONCLUSIONS: While not predictive of GSI or level of laryngeal visualization, the PGS was found to be a useful tool in predicting patient experience of gagging and discomfort during FL-S, further reinforcing the subjective experience of this procedure. Use of the PGS may be helpful in identifying specific candidates who may struggle with subjective discomfort or gagging during FL-S for future studies considering interventions to manage and meaningfully decrease discomfort. Having such an instrument is important given the low number of individuals who struggle with discomfort during the exam.

Breathiness and Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) in Patients Undergoing Medialization Laryngoplasty With or Without Arytenoid Adduction.

OBJECTIVES: We hypothesized that, in patients with unilateral vocal fold paralysis (UVFP), the auditory-perception of breathiness measured with Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) would be higher preoperatively in patients who undergo medialization laryngoplasty (ML) with arytenoid adduction (AA) compared to ML alone. We further hypothesized that increased breathiness would correlate with increased glottal area at maximum glottal closure. STUDY DESIGN: Retrospective chart review. METHODS: CAPE-V recordings were rated by expert judges in 105 subjects with UVFP (47 ML+AA and 58 ML). Component scores of the CAPE-V prior to laryngeal framework surgery and those at 3 and/or 12 months postoperatively were compared. Assessment of glottal area width during maximum glottal closure was attempted. RESULTS: Breathiness scores prior to laryngeal framework surgery were significantly greater in UVFP patients having ML+AA compared to ML only (P < 0.001). Roughness was greater for ML only (P = 0.003). At 3 months, adjusted for age and previous injection laryngoplasty, the ML+AA group showed greater improvement for breathiness (P <0.001), loudness (P < 0.001), strain (P = 0.037), and pitch (P = 0.039), while the ML only group showed greater improvement in roughness (P = 0.009). Results were similar at 12 months. Only 26% of glottal area widths were ratable using methods previously described; therefore, no further analysis was attempted. CONCLUSIONS: In patients with UVFP baseline perception of breathiness is greater in those clinically selected for ML+AA compared to ML only. Glottal area measurements were not representative of the UVFP cohort and more stringent criteria are needed for valid and reliable glottal area assessment when using clinical flexible stroboscopic exams. Findings support the idea that surgeons may be making decisions about AA based, to at least some degree, on auditory perceptual evaluation of voice.

Cardiothoracic Patients with Unilateral Vocal Fold Paralysis: Pneumonia Rates Following Injection Laryngoplasty.

OBJECTIVE: Recurrent laryngeal nerve injury is a potential complication of cardiothoracic surgery and cause of unilateral vocal fold paralysis (UVFP). Injection laryngoplasty (IL) is an intervention offered to patients with UVFP to alleviate symptoms including dysphagia, dysphonia and weak cough. There is no definitive evidence that IL prevents pneumonia. In this study, we compare rates of pneumonia in patients with UVFP secondary to cardiothoracic surgery who did or did not undergo IL. METHODS: A retrospective chart review identified patients diagnosed with UVFP by an otolaryngologist using flexible laryngoscopy following cardiothoracic surgery from January 1, 2008 to December 31, 2017. Each subject was grouped by IL status and assessed for subsequent pneumonia within 6 months of their diagnosis of UVFP. The association of IL with pneumonia was evaluated using Cox proportional hazards regression. RESULTS: Of 92 patients who met inclusion criteria, 35 (38%) underwent IL and 57 (62%) did not. Twenty patients developed pneumonia, four who had undergone IL and 16 who had not; 12 patients developed aspiration pneumonia including two having undergone IL and 10 who had not. Those who had IL were less likely to develop total pneumonia compared to those who had not (HR = 0.33, P = .045). The protective effect of IL was not as clearly sustained when measuring for aspiration pneumonia, specifically (HR = 0.34; P = .10). DISCUSSION: Injection laryngoplasty may reduce the risk of pneumonia in patients with UVFP secondary to cardiothoracic surgery; however, further research is needed to quantify the potential protective nature of IL in this patient population. LEVEL OF EVIDENCE: 3 (A retrospective cohort study).

Non-invasive vocal biomarker is associated with pulmonary hypertension.

Emerging data suggest that noninvasive voice biomarker analysis is associated with coronary artery disease. We recently showed that a vocal biomarker was associated with hospitalization and heart failure in patients with heart failure. We evaluate the association between a vocal biomarker and invasively measured indices of pulmonary hypertension (PH). Patients were referred for an invasive cardiac hemodynamic study between January 2017 and December 2018, and had their voices recorded on three separate occasions to their smartphone prior to each study. A pre-established vocal biomarker was determined based on each individual recording. The intra-class correlation co-efficient between the separate voice recording biomarker values for each individual participant was 0.829 (95% CI 0.740-0.889) implying very good agreement between values. Thus, the mean biomarker was calculated for each patient. Patients were divided into two groups: high pulmonary arterial pressure (PAP) defined as ≥ 35 mmHg (moderate or greater PH), versus lower PAP. Eighty three patients, mean age 61.6 ± 15.1 years, 37 (44.6%) male, were included. Patients with a high mean PAP (≥ 35 mmHg) had on average significantly higher values of the mean voice biomarker compared to those with a lower mean PAP (0.74 ± 0.85 vs. 0.40 ± 0.88 p = 0.046). Multivariate logistic regression showed that an increase in the mean voice biomarker by 1 unit was associated with a high PAP, odds ratio 2.31, 95% CI 1.05-5.07, p = 0.038. This study shows a relationship between a noninvasive vocal biomarker and an invasively derived hemodynamic index related to PH obtained during clinically indicated cardiac catheterization. These results may have important practical clinical implications for telemedicine and remote monitoring of patients with heart failure and PH.

Can Ultrasound Identify Paradoxical Vocal Fold Movement? A Pilot Study.

OBJECTIVE: Vocal cord dysfunction (VCD) is characterized by paradoxical vocal fold movement (PVFM) during inspiration. The aim of this study was to determine whether ultrasound could accurately differentiate between normal and PVFM during respirations in a resting state. DESIGN: Prospective, single-subject design. SETTING: Academic medical center. PATIENTS: A speech-language pathologist who was able to volitionally alternate between normal and PVFM when breathing at rest was recruited to participate in the study. INTERVENTIONS: The subject was instructed to randomly alternate between normal and PVFM 20 times (10 times each). A single investigator imaged the vocal folds using ultrasound and reported when the subject alternated between the 2 respiratory states. MAIN OUTCOME MEASURES: The subject recorded when they changed between the 2 respiratory states, whether the investigator identified with the change occurred, and if the correct respiratory state was identified. RESULTS: The investigator recognized when the subject changed respiratory states and correctly identified the new respiratory state 100% of the time. CONCLUSIONS: The findings of the current study were promising and suggest that ultrasound may have utility in the diagnosis of VCD. However, because of the preliminary nature of these results, further research is required before recommending its clinical implementation.

Voice outcomes following medialization laryngoplasty with and without arytenoid adduction.

OBJECTIVE: Voice outcomes following medialization laryngoplasty (ML) for unilateral vocal fold paralysis (UVFP) were compared to those who underwent ML plus arytenoid adduction (AA) (ML+AA). METHODS: Single institution retrospective review of patients with UVFP undergoing ML and ML+AA (2009-2017). Demographic information and history of laryngeal procedures were collected. Preoperative and postoperative Voice Handicap Index-10 (VHI-10) and Consensus Perceptual Auditory Evaluation of Voice (CAPE-V) were assessed. RESULTS: Of 236 patients, 119 met study criteria. Of those, 70 (59%) underwent ML and 49 (41%) underwent ML+AA. Significant differences between groups at baseline were found for age at time of thyroplasty (P = 0.046), VHI-10 scores (P < 0.001), and CAPE-V scores (P = 0.007). Baseline VHI-10 scores for ML+AA (28 ± 7) were greater than those for ML alone (24 ± 7). At 12 months, overall VHI-10 scores improved compared to baseline for both groups (ML+AA = 9 ± 7, ML = 16 ± 9); however, there was greater improvement for the ML+AA group compared to ML group (P = 0.001). CAPE-V scores at 3 or 12 months improved, but differences between the groups were not statistically significant once controlled for covariates. CONCLUSION: Based on current findings, patients who undergo ML+AA likely have greater voice handicap at baseline compared to those undergoing ML alone. Patients selected for ML+AA improve as much or more than those who underwent ML alone. This highlights the importance of appropriate selection of candidates for AA. LEVEL OF EVIDENCE: 4 Laryngoscope, 129:1876-1881, 2019.

Medialization laryngoplasty/arytenoid adduction: U.S. outcomes, discharge status, and utilization trends.

OBJECTIVES/HYPOTHESIS: To evaluate trends, outcomes, and healthcare utilization following medialization laryngoplasty (ML) with or without arytenoid adduction (AA) over 10 years. STUDY DESIGN: Retrospective observational study. METHODS: Using OptumLabs Data Warehouse, trends, outcomes, and healthcare utilization from 2006 to 2015 were examined with a focus on discharge type (same day or not). Predictors of postoperative emergency department (ED) use and hospitalization were determined by multivariable logistic regression. RESULTS: Overall rate of ML was 1.09 per 100 thousand enrollees per year. Of these, 7.8% ML were combined with an AA. Outpatient same-day discharge represented 62.0% (1,142 of 1,843) of total patients, steadily increasing over the 10-year period (P < 0.01). There was a 5.9% revision ML rate and 1.0% rate of tracheotomy within 1 day of ML. A total of 5.6% visited an ED, and 5.4% were admitted to a hospital following initial discharge within 30 days. Same-day discharge was found to be a predictor of hospitalization within 30 days after ML (odds ratio [OR] 1.74, P = 0.0452), along with Elixhauser comorbidity index of 4 + (OR 5.74, P = 0.0001). Pulmonary embolism, pulmonary hypertension, and weight loss were top predictors of ED visit or hospitalization. CONCLUSION: To our knowledge, this is the first search evaluating national claims data for ML with or without AA. Overall rate of ML is low, and same-day discharge has become more common over a 10-year period, with an associated higher 30-day hospital admission risk. Correct patient selection criteria for disposition status cannot be fully determined based on current data, but a high Elixhauser comorbidity index clearly carries increased risk for hospitalization after initial discharge. LEVEL OF EVIDENCE: 4 Laryngoscope, 129:952-960, 2019.

Observational study of laryngoscopy plus flow-volume loops during exercise.

Laryngoscopy is the gold standard to diagnose exercise-induced laryngeal obstruction, though inspiratory flow-volume loop may provide a clue. We combined tidal flow-volume loop analysis plus laryngoscopy during exercise and found that cigar-shaped - not flattened - inspiratory loops are associated with obstruction. Pursed-lip breathing slows inhalation thereby reducing vocal fold adduction.

Voice Signal Characteristics Are Independently Associated With Coronary Artery Disease.

OBJECTIVE: Voice signal analysis is an emerging noninvasive diagnostic tool. The current study tested the hypothesis that patient voice signal characteristics are associated with the presence of coronary artery disease (CAD). METHODS: The study population included 138 patients who were enrolled between January 1, 2015, and February 28, 2017: 37 control subjects and 101 subjects who underwent planned coronary angiogram. All subjects had their voice signal recorded to their smartphone 3 times: reading a text, describing a positive emotional experience, and describing a negative emotional experience. The Mel Frequency Cepstral Coefficients were used to extract prespecified voice features from all 3 recordings. Voice was recorded before the angiogram and analysis was blinded with respect to patient data. RESULTS: Final study cohort included 101 patients, of whom 71 (71%) had CAD. Compared with subjects without CAD, patients with CAD were older (median, 63 years; interquartile range [IQR], 55-68 years vs median, 53 years; IQR, 42-66 years; P=.003) and had a higher 10-year atherosclerotic cardiovascular disease (ASCVD) risk score (9.4%; IQR, 5.0-18.7 vs 2.7%; IQR, 1.6-11.8; P=.005). Univariate binary logistic regression analysis identified 5 voice features that were associated with CAD (P<.05 for all). Multivariate binary logistic regression with adjustment for ASCVD risk score identified 2 voice features that were independently associated with CAD (odds ratio [OR], 0.37; 95% CI, 0.18-0.79; and 4.01; 95% CI, 1.25-12.84; P=.009 and P=.02, respectively). Both features were more strongly associated with CAD when patients were asked to describe an emotionally significant experience. CONCLUSION: This study suggests a potential relationship between voice characteristics and CAD, with clinical implications for telemedicine-when clinical health care is provided at a distance.