Annals of Family Medicine最新文献

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

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2025-01-13 DOI: 10.1370/afm.240091

Alexa Mazur, Harrison Costantino, Prentice Tom, Michael P Wilson, Ronald G Thompson

{"title":"Evaluation of an AI-Based Voice Biomarker Tool to Detect Signals Consistent With Moderate to Severe Depression.","authors":"Alexa Mazur, Harrison Costantino, Prentice Tom, Michael P Wilson, Ronald G Thompson","doi":"10.1370/afm.240091","DOIUrl":"https://doi.org/10.1370/afm.240091","url":null,"abstract":"Purpose: Mental health screening is recommended by the US Preventive Services Task Force for all patients in areas where treatment options are available. Still, it is estimated that only 4% of primary care patients are screened for depression. The goal of this study was to evaluate the efficacy of machine learning technology (Kintsugi Voice, v1, Kintsugi Mindful Wellness, Inc) to detect and analyze voice biomarkers consistent with moderate to severe depression, potentially allowing for greater compliance with this critical primary care public health need.Methods: We performed a cross-sectional study from February 1, 2021 to July 31, 2022 to examine ≥25 seconds of free-form speech content from English-speaking samples captured from 14,898 unique adults in the United States and Canada. Participants were recruited via social media, provided informed consent, and their voice biomarker results were compared with a self-reported Patient Health Questionnaire-9 (PHQ-9) at a cut-off score of 10 (moderate to severe depression).Results: From as few as 25 seconds of free-form speech, machine learning technology was able to detect vocal characteristics consistent with an increased PHQ-9 ≥10, with a sensitivity of 71.3 (95% CI, 69.0-73.5) and a specificity of 73.5 (95% CI, 71.5-75.5).Conclusions: Machine learning has potential utility in helping clinicians screen patients for moderate to severe depression. Further research is needed to measure the effectiveness of machine learning vocal detection and analysis technology in clinical deployment.","PeriodicalId":50973,"journal":{"name":"Annals of Family Medicine","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980604","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

For AI in Primary Care, Start With the Problem.

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2025-01-13 DOI: 10.1370/afm.240504

John Thomas Menchaca

引用次数: 0

Use of AI in Family Medicine Publications: A Joint Editorial From Journal Editors.

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2025-01-13 DOI: 10.1370/afm.240575

Sarina Schrager, Dean A Seehusen, Sumi Sexton, Caroline R Richardson, Jon Neher, Nicholas Pimlott, Marjorie A Bowman, José Rodríguez, Christopher P Morley, Li Li, James Dom Dera

引用次数: 0

Evaluation of a Program Designed to Support Implementation of Prescribing Medication for Treatment of Opioid Use Disorder in Primary Care Practices.

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2025-01-13 DOI: 10.1370/afm.3190

Tristen L Hall, David Mendez, Chelsea Sobczak, Susan Mathieu, Kimberly Wiggins, Kathy Cebuhar, Lauren Quintana, Jacob Weiss, Kyle Knierim

{"title":"Evaluation of a Program Designed to Support Implementation of Prescribing Medication for Treatment of Opioid Use Disorder in Primary Care Practices.","authors":"Tristen L Hall, David Mendez, Chelsea Sobczak, Susan Mathieu, Kimberly Wiggins, Kathy Cebuhar, Lauren Quintana, Jacob Weiss, Kyle Knierim","doi":"10.1370/afm.3190","DOIUrl":"https://doi.org/10.1370/afm.3190","url":null,"abstract":"Purpose: Offering medication for opioid use disorder (MOUD) in primary care can increase access to effective opioid use disorder treatment and help address the US opioid crisis. We describe a primary care office-based opioid treatment program and addiction consultation service model designed to support small, rural clinics to increase their capacity for MOUD.Methods: This is an evaluation of an intervention to increase clinic capacity to offer MOUD. The intervention consists of a standardized curriculum, addiction medicine consultants, practice facilitation, and financial incentives. Fifteen Colorado primary care practices participated from January 2022 through January 2023. Primary outcomes included overall change in the number of active buprenorphine prescriptions and implementation of MOUD milestones before and after the intervention.Results: The mean number of active buprenorphine prescriptions in the 3 months preceding the intervention (baseline) increased from 2.1 (SD = 7.7) to 11.3 (SD = 11.2) at 13 months. Adjusted means from the Poisson model demonstrated significant improvement over time (P <.001). Mean implementation of MOUD milestones ranged from 23% to 40% at baseline and grew to 84% to 93% by the end of the program (P <.001).Conclusions: This model supported primary care practices that were initially doing little to no MOUD prescribing, to prescribe at significantly higher levels by the end of the program. This scalable model for addiction consultation in primary care settings illustrates how education and support to clinical teams can help practices makes changes, especially those with limited MOUD experience.","PeriodicalId":50973,"journal":{"name":"Annals of Family Medicine","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980603","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The AI Moonshot: What We Need and What We Do Not.

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2025-01-13 DOI: 10.1370/afm.240602

José E Rodríguez, Yves Lussier

引用次数: 0

Primary Care Physicians' Responses to Treatment Burden in People With Type 2 Diabetes: A Qualitative Video Analysis in China.

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2025-01-13 DOI: 10.1370/afm.240171

Kai Lin, Mi Yao, Lesley Andrew, Runqi Lin, Rouyan Li, Yilin Chen, Xinxin Ji, Jacques Oosthuizen, Moira Sim, Yongsong Chen

{"title":"Primary Care Physicians' Responses to Treatment Burden in People With Type 2 Diabetes: A Qualitative Video Analysis in China.","authors":"Kai Lin, Mi Yao, Lesley Andrew, Runqi Lin, Rouyan Li, Yilin Chen, Xinxin Ji, Jacques Oosthuizen, Moira Sim, Yongsong Chen","doi":"10.1370/afm.240171","DOIUrl":"https://doi.org/10.1370/afm.240171","url":null,"abstract":"Purpose: This study aimed to examine the approaches general practitioners (GPs) use to respond to the treatment burden faced by people with type 2 diabetes.Methods: We retrospectively analyzed 29 videos of GP-patient consultations in an academic general practice clinic in China. Thematic analysis and a framework matrix approach were used to identify patterns in GPs' responses to the identified issues.Results: The median length of the 29 video-recorded consultations was 23 minutes 54 seconds. We identified 77 segments focusing on discussions about treatment burden. In 37.7% of these segments, the GP elicited and responded to discussions about treatment burden, whereas in 23.4%, the patient initiated the discussion and the GP responded to it, leaving 39.0% in which the patient initiated the discussion but the GP did not respond. In thematic analysis, medication was the component of treatment burden most frequently identified by both patients and GPs, followed by personal resources, medical information, and administrative burden. General practitioners used 12 response approaches to address patients' treatment burden. The most frequently used included active listening and nonverbal skills, shared decision making, and confidence and self-efficacy support, which were broadly applied across various issues. In contrast, GPs typically reserved health record management, motivational interviewing, and awareness of the patient's background for specific issues.Conclusions: In clinical encounters, GPs used a wide variety of approaches to respond to different aspects of the treatment burden of type 2 diabetes. Our findings emphasize the need to improve GPs' response strategies through increased responsiveness and more rapid surfacing of issues during visits.","PeriodicalId":50973,"journal":{"name":"Annals of Family Medicine","volume":" ","pages":""},"PeriodicalIF":4.4,"publicationDate":"2025-01-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142980606","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Human Face of War. 战争中的人性

IF 4.4 2区医学

Annals of Family Medicine Pub Date : 2024-11-25 DOI: 10.1370/afm.240463

Caroline R Richardson