서브메뉴
검색
Patient Perceptions of Machine Learning-Enabled Digital Mental Health
Patient Perceptions of Machine Learning-Enabled Digital Mental Health
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151101
- ISBN
- 9798382321356
- DDC
- 610
- 저자명
- Guo, Clara.
- 서명/저자
- Patient Perceptions of Machine Learning-Enabled Digital Mental Health
- 발행사항
- [Sl] : Yale University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 41 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
- 주기사항
- Advisor: Chahine, Teresa;Herzog, Erica.
- 학위논문주기
- Thesis (D.Med.)--Yale University, 2024.
- 초록/해제
- 요약Objective: The mental health crisis is accelerating, with 55.8M American adults in treatment in 2022. Digital mental health is a growing field with implications for mental health care. The objective of this study was to understand patients' mental health treatment experience and the relationship with their perspectives of a novel digital health product geared toward improving care quality.Methods: In December 2023, an IRB-exempt questionnaire was sent to undergraduate and graduate students at campuses across the North-East United States, as well as healthcare-focused Slack® groups.Results: Of the 1,127 respondents, 28% were actively in treatment for their mental health, 25% were treated in the past, and 1% was on a waiting list. Of those with treatment exposure currently or in the past, 85% experienced challenges with communication during their clinical encounter. Among those, 69% experienced a negative emotional impact, began avoiding care, or even terminated care. Over half (57%) currently use or have used a digital health product. With an overview of the novel digital health product, 71% were Very Likely to share data related to sleep and 62% were Very Likely to share activity data. There was a statistically significant association between treatment exposure and likelihood of data sharing (for Sleep: chi squared χ2 (df = 2, n = 1,124) = 14.03, p = 0.001; for Activity: χ2 (df = 2, n = 1,121) = 22.13, p 0.001). Fewer respondents were Very Likely to share sleep and activity compared to expected frequencies if they had exposure to treatment with challenges. For mobile application retention, 351 respondents would fill out a 2-3-minute survey daily and 541 would consider it.Conclusion: There exists a Data Gap between patients and clinicians, driven by communication challenges that impact the care experience for patients. There exists a clear role for a digital health product that addresses the Data Gap to improve care quality, assuming privacy concerns and patient retention incentives are addressed and implemented.
- 일반주제명
- Medicine
- 일반주제명
- Psychology
- 키워드
- Machine learning
- 키워드
- Emotional impact
- 기타저자
- Yale University Yale School of Medicine
- 기본자료저록
- Dissertations Abstracts International. 85-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160692
■00520250211151101
■006m o d
■007cr#unu||||||||
■020 ▼a9798382321356
■035 ▼a(MiAaPQ)AAI31143027
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a610
■1001 ▼aGuo, Clara.
■24510▼aPatient Perceptions of Machine Learning-Enabled Digital Mental Health
■260 ▼a[Sl]▼bYale University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a41 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-11, Section: B.
■500 ▼aAdvisor: Chahine, Teresa;Herzog, Erica.
■5021 ▼aThesis (D.Med.)--Yale University, 2024.
■520 ▼aObjective: The mental health crisis is accelerating, with 55.8M American adults in treatment in 2022. Digital mental health is a growing field with implications for mental health care. The objective of this study was to understand patients' mental health treatment experience and the relationship with their perspectives of a novel digital health product geared toward improving care quality.Methods: In December 2023, an IRB-exempt questionnaire was sent to undergraduate and graduate students at campuses across the North-East United States, as well as healthcare-focused Slack® groups.Results: Of the 1,127 respondents, 28% were actively in treatment for their mental health, 25% were treated in the past, and 1% was on a waiting list. Of those with treatment exposure currently or in the past, 85% experienced challenges with communication during their clinical encounter. Among those, 69% experienced a negative emotional impact, began avoiding care, or even terminated care. Over half (57%) currently use or have used a digital health product. With an overview of the novel digital health product, 71% were Very Likely to share data related to sleep and 62% were Very Likely to share activity data. There was a statistically significant association between treatment exposure and likelihood of data sharing (for Sleep: chi squared χ2 (df = 2, n = 1,124) = 14.03, p = 0.001; for Activity: χ2 (df = 2, n = 1,121) = 22.13, p 0.001). Fewer respondents were Very Likely to share sleep and activity compared to expected frequencies if they had exposure to treatment with challenges. For mobile application retention, 351 respondents would fill out a 2-3-minute survey daily and 541 would consider it.Conclusion: There exists a Data Gap between patients and clinicians, driven by communication challenges that impact the care experience for patients. There exists a clear role for a digital health product that addresses the Data Gap to improve care quality, assuming privacy concerns and patient retention incentives are addressed and implemented.
■590 ▼aSchool code: 0265.
■650 4▼aMedicine
■650 4▼aPsychology
■653 ▼aDigital health product
■653 ▼aMachine learning
■653 ▼aEmotional impact
■653 ▼aMobile application
■653 ▼aPatient perceptions
■690 ▼a0564
■690 ▼a0621
■690 ▼a0800
■71020▼aYale University▼bYale School of Medicine.
■7730 ▼tDissertations Abstracts International▼g85-11B.
■790 ▼a0265
■791 ▼aD.Med.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160692▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
