서브메뉴
검색
Machine Learning-Assisted Treatment Selection for Smoking Cessation
Machine Learning-Assisted Treatment Selection for Smoking Cessation
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202104845
- ISBN
- 9798290939889
- DDC
- 157
- 저자명
- Fronk, Gaylen E.
- 서명/저자
- Machine Learning-Assisted Treatment Selection for Smoking Cessation
- 발행사항
- [Sl] : The University of Wisconsin - Madison, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 104 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-02, Section: B.
- 주기사항
- Advisor: Curtin, John J.
- 학위논문주기
- Thesis (Ph.D.)--The University of Wisconsin - Madison, 2025.
- 초록/해제
- 요약Precision mental health seeks to select the right treatment for a patient given personal characteristics. The purpose of this project was to build a machine learning model that could select among first-line medication treatments for cigarette smoking. We used data from a previously completed comparative effectiveness trial in which participants were richly characterized at baseline before being randomly assigned to varenicline, combination nicotine replacement therapy, or nicotine patch. We built a model predicting treatment success (abstinent vs. smoking) using baseline characteristics and their interactions with treatment. Models were fit, selected, and evaluated using nested cross-validation and the performance metric area under the receiving operator characteristic curve (auROC). Our best models had a median auROC of 0.69 in held-out test sets. We used this model to calculate probabilities of smoking cessation success for each participant on each of the three treatments to identify their model-predicted best treatment. Individuals who received their model-predicted best treatment during the original trial were more likely to quit successfully than individuals who did not (OR = 1.851, p = 0.004). This project produces a clinically implementable treatment selection model to assist people quitting cigarette smoking.
- 일반주제명
- Clinical psychology
- 일반주제명
- Psychology
- 일반주제명
- Mental health
- 키워드
- Machine learning
- 기타저자
- The University of Wisconsin - Madison Psychology
- 기본자료저록
- Dissertations Abstracts International. 87-02B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359173
■00520260202104845
■006m o d
■007cr#unu||||||||
■020 ▼a9798290939889
■035 ▼a(MiAaPQ)AAI32173430
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a157
■1001 ▼aFronk, Gaylen E.
■24510▼aMachine Learning-Assisted Treatment Selection for Smoking Cessation
■260 ▼a[Sl]▼bThe University of Wisconsin - Madison▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a104 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-02, Section: B.
■500 ▼aAdvisor: Curtin, John J.
■5021 ▼aThesis (Ph.D.)--The University of Wisconsin - Madison, 2025.
■520 ▼aPrecision mental health seeks to select the right treatment for a patient given personal characteristics. The purpose of this project was to build a machine learning model that could select among first-line medication treatments for cigarette smoking. We used data from a previously completed comparative effectiveness trial in which participants were richly characterized at baseline before being randomly assigned to varenicline, combination nicotine replacement therapy, or nicotine patch. We built a model predicting treatment success (abstinent vs. smoking) using baseline characteristics and their interactions with treatment. Models were fit, selected, and evaluated using nested cross-validation and the performance metric area under the receiving operator characteristic curve (auROC). Our best models had a median auROC of 0.69 in held-out test sets. We used this model to calculate probabilities of smoking cessation success for each participant on each of the three treatments to identify their model-predicted best treatment. Individuals who received their model-predicted best treatment during the original trial were more likely to quit successfully than individuals who did not (OR = 1.851, p = 0.004). This project produces a clinically implementable treatment selection model to assist people quitting cigarette smoking.
■590 ▼aSchool code: 0262.
■650 4▼aClinical psychology
■650 4▼aPsychology
■650 4▼aMental health
■653 ▼aMachine learning
■653 ▼aPrecision medicine
■653 ▼aSmoking cessation
■653 ▼aTreatment selection
■653 ▼aMedication treatments
■690 ▼a0622
■690 ▼a0621
■690 ▼a0347
■71020▼aThe University of Wisconsin - Madison▼bPsychology.
■7730 ▼tDissertations Abstracts International▼g87-02B.
■790 ▼a0262
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359173▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
