PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

AI-based tool uses speech patterns to detect moderate to severe depression

Evaluation of an AI-based voice biomarker tool to detect signals consistent with moderate to severe depression

AI-based tool uses speech patterns to detect moderate to severe depression
2025-01-27
(Press-News.org) Background and Goal: Depression impacts an  estimated 18 million Americans each year,  yet depression screening rarely occurs in the outpatient setting. This study evaluated an AI-based machine learning biomarker tool that uses speech patterns to detect moderate to severe depression, aiming to improve access to screening in primary care settings.

Study Approach: The study analyzed over 14,000 voice samples from U.S. and Canadian adults. Participants answered the question, “How was your day?” with at least 25 seconds of free-form speech. The tool analyzed vocal biomarkers associated with depression, including speech cadence, hesitations, pauses, and other acoustic features. These were compared to results from the Patient Health Questionnaire-9 (PHQ-9), a standard depression screening tool. A PHQ-9 score of 10 or higher indicated moderate to severe depression. The AI tool provided three outputs: Signs of Depression Detected, Signs of Depression Not Detected, and Further Evaluation Recommended (for uncertain cases).

Main Results: The dataset used to train the AI model consisted of 10,442 samples, while an additional 4,456 samples were used in a validation set to assess its accuracy. 

The tool demonstrated a sensitivity of 71%, correctly identifying depression in 71% of people who had it.

Specificity was 74%, correctly ruling out depression in 74% of people who did not have it.

Why It Matters: The study findings suggest that machine learning technology could serve as a complementary decision-support tool for assessing depression.

Evaluation of an AI-Based Voice Biomarker Tool to Detect Signals Consistent With Moderate to Severe Depression

Alexa Mazur, BA, et al 

Kintsugi Mindful Wellness, Inc, San Francisco, California

PERMANENT LINK 

END

[Attachments] See images for this press release:
AI-based tool uses speech patterns to detect moderate to severe depression AI-based tool uses speech patterns to detect moderate to severe depression 2 AI-based tool uses speech patterns to detect moderate to severe depression 3

ELSE PRESS RELEASES FROM THIS DATE:

Taking blood pressure in a public or noisy settings does not affect reading

2025-01-27
Embargoed for release until 5:00 p.m. ET on Monday 27 January 2025     @Annalsofim           Below please find summaries of new articles that will be published in the next issue of Annals of Internal Medicine. The summaries are not intended to substitute for the full articles as a source of information. This information is under strict embargo and by taking it into possession, media representatives are committing to the terms of the embargo not only on their own behalf, but also on behalf of the organization they represent.           ----------------------------        1. ...

Primary care physicians face significant gaps in caring for adopted adults with limited family medical history

Primary care physicians face significant gaps in caring for adopted adults with limited family medical history
2025-01-27
Background and Goal: Adopted individuals often have limited access to their family medical history, complicating  their health care. This study explored the approaches of primary care physicians when caring for adult adopted patients with limited family medical history. Study Approach: Researchers conducted in-depth interviews, including hypothetical clinical scenarios,  with 23 primary care physicians from Rhode Island and Minnesota to understand their experiences, practices, knowledge, and training gaps when addressing limited family medical history and adoption-related issues. Main Results:  Primary care physicians report ...

Support program for small, rural primary care clinics increases their ability to prescribe buprenorphine for opioid use disorder fivefold

Support program for small, rural primary care clinics increases their ability to prescribe buprenorphine for opioid use disorder fivefold
2025-01-27
Background and Goal: Despite the removal of the X-waiver requirement, which once restricted clinicians from prescribing buprenorphine for opioid use disorder (OUD), only a small percentage of primary care clinicians currently prescribe medication for OUD (MOUD). This study evaluated a structured support program to help small, rural primary care clinics improve their capacity to provide this treatment.  Study Approach: Researchers worked with 15 primary care practices in Colorado over a 12-month period from January 2022 through January 2023. The program provided clinics with monthly educational sessions, direct access to an addiction medicine specialist, and support from practice facilitators ...

Peer health navigators improve health equity and patient well-being for transgender and gender-diverse patients

2025-01-27
Background and Goal: Transgender and gender-diverse individuals often experience additional difficulties navigating health care. This study examined the effectiveness of a peer health navigator pilot program in Saskatchewan, Canada that aimed to improve access to affirming health care for transgender and gender-diverse individuals. Study Approach: Two peer health navigators were recruited to pilot the program. The navigators were required to be transgender or gender diverse and have experience in health care or community-based organizations. Navigators supported clients by providing information on gender transition and ...

Flexible practice-centric approach improves behavioral health integration in primary care practices

2025-01-27
ackground and Goal: Integrated behavioral health (IBH), which combines behavioral health and primary care, improves patient outcomes and experience. This study evaluated whether a tailored, toolkit-based intervention could improve IBH and patient outcomes in primary care practices serving patients with multiple chronic medical and behavioral health conditions. Study Approach: The study used a cluster randomized controlled trial design. Practices were randomized into two groups. The intervention arm received ...

Study highlights general practitioner strategies to ease type 2 diabetes management burden

Study highlights general practitioner strategies to ease type 2 diabetes management burden
2025-01-27
Background and Goal: Managing type 2 diabetes involves complex treatment, workload, and costs that impose a significant burden on individuals, impacting their physical and mental health. This study examines how general practitioners (GPs) in China identify and respond to these burdens during patient consultations. Study Approach: The study examined video recordings of 29 GP-patient consultations recorded between 2018 and 2019 in a primary care clinic in China. Researchers reviewed these consultations for discussions related to treatment burdens in managing type 2 diabetes and analyzed the interviews to identify specific burdens and the strategies GPs employed to address them. Main ...

Special report proposes strategies for preserving diversity in medicine after reshaped affirmative action policies

2025-01-27
Background and Goal: In 2023, the Supreme Court of the United States (SCOTUS) struck down race-conscious admissions in higher education, reshaping affirmative action policies. This special report examines the ruling’s wide-reaching effects, particularly on underrepresented minority (URM) students, and proposes strategies for preserving diversity in higher education and professional fields, including medicine. Key Insights: Institutions such as MIT and Amherst College have reported significant declines in Black and Latino student enrollment. In medical school admissions, the lack of standardized guidelines ...

Annals of Family January/February 2025 Tip Sheet

2025-01-27
Editorial Family Medicine Journal Editors Suggest Guiding Principles for AI Use in Publishing Background: This editorial by editors of family medicine journals provides a unified stance on the use of artificial intelligence (AI) in family medicine research and publishing.  Editorial Stance: Family medicine journals must address the implications of AI, including ethical considerations, accuracy, and potential for bias. The authors recommend guiding principles for AI use in family medicine publishing, emphasizing: Full disclosure of AI tool use in research and manuscript preparation Accountability ...

International disease classification codes ambiguities create challenges in comparing respiratory infection diagnosis

2025-01-27
Background and Goal: The International Classification of Diseases (ICD) system standardizes diagnostic codes globally, enabling accurate comparisons of health data. This study investigated regional differences in respiratory infection diagnoses in Poland to identify potential ambiguities in ICD coding and their implications for data comparability. Study Approach: Researchers analyzed over 292 million primary care visits for acute respiratory infections in Poland between 2010 and 2019, using ICD-10 codes (J00–J22). Diagnosis data were ...

Family medicine department chairs face high patient care demands and barriers to scholarly activity

2025-01-27
Background and Goal: Research in family medicine is vital for improving patient care, health care systems, and population health. However, family medicine faces barriers to producing scholarly work, including high patient care demands and limited funding. This study examined whether financial incentives and department size influence the amount and type of scholarly activity produced by family medicine departments. Study Approach: Researchers surveyed family medicine department chairs across the U.S. and Canada using a Council of Academic Family Medicine Educational Research Alliance (CERA) questionnaire. The survey gathered data ...

LAST 30 PRESS RELEASES:

Brain mapping unlocks key Alzheimer’s insights

Clinical trial tests novel stem-cell treatment for Parkinson’s disease

Awareness of rocky mountain spotted fever saves lives

Breakthrough in noninvasive monitoring of molecular processes in deep tissue

BU researcher named rising star in endocrinology

Stressed New Yorkers can now seek care at Mount Sinai’s new resilience-focused medical practice

BU researchers uncover links between metabolism and aggressive breast cancer

Engineers took apart batteries from Tesla and China’s leading EV manufacturer to see what’s inside

Paralyzed man moves robotic arm with his thoughts

Planetary science: More potential locations for ice on Moon

Injectable Therapy is 'magic' for those who can’t take HIV pills

siRNA-AGO2 complex inhibits bacterial gene translation: a novel therapeutic strategy for superbug infection

Memory is impaired in aged rats after 3 days of high-fat eating

Artificial muscles for tremor suppression

A new way to engineer composite materials

AERA selects 29 exemplary scholars as 2025 Fellows

Touchless tech: Control fabrics with a wave of your finger

JMIR aging invites submissions on the social and cultural drivers of health in aging adults

New research sheds light on why scleroderma affects mostly women and how to treat it

Lack of appropriate mental health care impacts quality of life for people with COPD

Yawn! Many people are bored by spiritual practice

A new algorithm sheds light on ‘disordered’ proteins

How’s the weather on Mars?

Plants struggled for millions of years after the world’s worst climate catastrophe

Clinical trial opens to study groundbreaking 3D printed device for babies with rare respiratory disease

Effects of shenfu decoction on neutrophil chemotactic function in septic mice

ESMT Berlin offers scholarships in executive leadership

New WSU study shows how scarcity pricing helps 'cult wineries' drive demand

New discovery and grant to accelerate Strep A vaccine efforts

Novel enzyme found in gut bacteria could revolutionize prebiotic research

[Press-News.org] AI-based tool uses speech patterns to detect moderate to severe depression
Evaluation of an AI-based voice biomarker tool to detect signals consistent with moderate to severe depression