AI-Based Personalized Exercise Prescription Through Mobile Health on Physical Activity and Health Outcomes in Older Adults: A Feasibility Study
Artificial Intelligence-based Personalized Exercise Prescription Through Mobile Health on Physical Activity and Health Outcomes in Older Adults: A Feasibility Study
연구 개요
상세 설명
By the late 2070s, the global population aged 65 and older is projected to reach 2.2 billion, surpassing the number of children under age 18. In 2020, about 1 in 6 people in the United States (U.S) were age 65 and over, compared to less than 1 in 20 in 1920. The number of U.S. adults 65 years and over is projected to increase to 82 million by 2050, with the older group's share of the total population projected to rise to 23%. Ageing brings about an increased vulnerability to mental health challenges, and chronic conditions such as heart disease, cancer, diabetes, and Alzheimer's. Among adults ages 65 and older, more than 90% have at least one chronic condition and 88% have at least one multiple chronic condition. Chronic conditions contribute to over 75% of healthcare expenditures for individuals aged 65 and above in the U.S, amounting to over $1.5 trillion. An active lifestyle reduces the likelihood of developing chronic diseases and also enhances the overall health outcomes of the older adult population. Despite these benefits, a majority of older adults fail to meet the recommended U.S. physical activity guidelines (150 minutes of moderate intensity PA a week).
Mobile health (mHealth) technologies-such as smartphone applications (apps), wearables, and other mobile devices-have emerged as an increasingly adopted tool for promoting health among older adults. Several studies have demonstrated the potential of mHealth technologies to increase PA, reduce sedentary time, and improve health outcomes. However, findings have shown that the sustainability of mHealth-based exercise interventions remains uncertain. Recent reviews also emphasized the need for more personalized, adaptable mHealth solutions tailored to older adults' unique health conditions and physical ability to ensure better engagement and more durable behavior change. While recent studies show that personalized mHealth-based exercise programs outperform one-size-fits-all approaches, yet their impact is constrained by insufficient personalization data, low adherence, limited scalability, and inadequate integration of behavior-change techniques (BCTs).
Emerging evidence suggests that Artificial Intelligence (AI) can enhance PA. Integrating AI with mHealth tools-such as smartphone apps and wearable devices grounded in BCTs-offers a promising pathway to deliver an automated exercise program tailored to each person's PA goals, health status, and overall well-being, reaching many people at once with the potential of helping older adults adhere longer to an active lifestyle. Such an approach aligns with the growing emphasis on precision health and scalable interventions for aging populations. Despite this promise, the feasibility, acceptability, appropriateness and preliminary impact of an AI-driven, personalized exercise program delivered through mHealth and grounded in SDT and BCTs on older adults' PA and health outcomes remain unexplored.
The purpose of this research is to investigate the feasibility, acceptability, appropriateness, and preliminary efficacy of a wearable and artificial intelligence-driven mobile application-based exercise prescription grounded in self-determination theory (SDT) and behavioral change techniques (BCTs) among older
연구 유형
등록 (추정된)
단계
- 해당 없음
연락처 및 위치
연구 연락처
- 이름: John Oginni, MS
- 전화번호: 8659747971
- 이메일: pael@utk.edu
연구 장소
-
-
Tennessee
-
Knoxville, Tennessee, 미국, 37996-2700
- 모병
- Kinesiology, Recreation, and Sport Studies (865) 974-3340 krss@utk.edu
-
연락하다:
- John Oginni
- 전화번호: (865) 974-3340
- 이메일: joginni@vols.utk.edu
-
-
참여기준
자격 기준
공부할 수 있는 나이
- 고령자
건강한 자원 봉사자를 받아들입니다
설명
Inclusion Criteria:
- Be aged 65 years or older.
- Own a smartphone (Android or iOS) compatible with study applications.
- Have reliable access to the internet or Wi-Fi.
- Demonstrate basic digital literacy sufficient to operate a smartphone (e.g., ability to open applications, navigate simple interfaces, and follow on-screen instructions), with or without initial guidance from the research staff.
- Be able to safely engage in physical activity, as determined by the Physical Activity Readiness Questionnaire for Everyone (PAR-Q+) or physician approval if indicated.
- Report engaging in less than 150 minutes of moderate-to-vigorous physical activity (MVPA) per week.
- Be able to communicate in English sufficiently to complete study procedures and assessments.
Exclusion Criteria:
- Are younger than 65 years of age.
- Do not own a compatible smartphone (Android or iOS) or do not have reliable internet/Wi-Fi access.
- Are deemed unable to safely participate in physical activity based on the screening process (including PAR-Q+, STEADI, and research staff assessment), or do not obtain required physician clearance when indicated.
- Currently meet or exceed 150 minutes of moderate-to-vigorous physical activity (MVPA) per week.
- Are unable to communicate in English sufficiently to understand study procedures, provide informed consent, or complete study-related assessments.
- Have any medical, physical, or cognitive condition that, in the judgment of the research team, would make participation unsafe or prevent completion of study procedures.
공부 계획
연구는 어떻게 설계됩니까?
디자인 세부사항
- 주 목적: 방지
- 할당: 해당 없음
- 중재 모델: 단일 그룹 할당
- 마스킹: 없음(오픈 라벨)
무기와 개입
참가자 그룹 / 팔 |
개입 / 치료 |
|---|---|
|
실험적: Single-arm
All participants will be provided the researcher-developed sFitRx fitness application and a Fitbit Flex 2 tracker.
sFitRx will provide participants with an established daily and weekly exercise prescription program based on each participant's: (1) daily step goals, (2) previous week's PA, as collected by the Fitbit Flex 2; and (3) current physical conditioning and well-being, as collected by sFitRx.
The sFitRx will provide participants with a video demonstration of warm up exercise and all prescribed exercise types, including aerobics, resistance, balance, and flexibility exercises.
These exercises follow a graded task BCT.
For instance, a participant with a low baseline PA might be prescribed a beginner programs with a base (entry) level of 1.1.
However, the sFitRx will progressively modify the individual exercise program based on the % of exercise completed, daily goal and other metrics.
|
All participants will be provided the researcher-developed sFitRx mHealth application.
sFitRx will provide participants with an established daily and weekly exercise prescription program based on each participant's: (1) daily step goals, (2) previous week's PA, as collected by the Fitbit Flex 2; and (3) current physical conditioning and well-being, as collected by sFitRx.
The sFitRx will provide participants with a video demonstration of warm up exercise and all prescribed exercise types, including aerobics, resistance, balance, and flexibility exercises.
These exercises follow a graded task BCT.
The exercise program delivered by the sFitRx app is grounded in self-determination theory, most especially in satisfying the basic psychological needs that drive intrinsic motivation.
|
연구는 무엇을 측정합니까?
주요 결과 측정
결과 측정 |
측정값 설명 |
기간 |
|---|---|---|
|
Recruitment
기간: Pre-intervention
|
Number screened/month per recruitment method
|
Pre-intervention
|
|
Enrollment
기간: Pre-intervention
|
Number excluded by criterion; Number that decline participation; Reason for declining participation (open-ended); Average time from screening to enrollment (minutes/hours/days/month).
|
Pre-intervention
|
|
Participant Dropout Rate
기간: Baseline (week 1) - Follow up (Week 10)
|
Number dropouts from AI-based exercise intervention; Reason for dropout (open-ended).
|
Baseline (week 1) - Follow up (Week 10)
|
|
Retention
기간: Baseline (week 1) - Follow up (Week 10)
|
Number that completed the intervention program
|
Baseline (week 1) - Follow up (Week 10)
|
|
Adherence
기간: Baseline (week 1) - Follow up (Week 10)
|
Percentage of the exercise program completed weekly (%)
|
Baseline (week 1) - Follow up (Week 10)
|
|
Intervention Feasibility, Acceptability, and Appropriateness
기간: At follow up (week 10)
|
Intervention Feasibility (ease of delivery).
will be assessed using the Weiner et al. (2017)1 validated questionnaire for the feasibility of intervention measure (FIM).
This questionnaire contains 4-item questions on a 5-point Likert scale (completely disagree [1]-completely agree [5]), with a score range of 1-5.
Intervention Acceptability (assessing participant satisfaction).
will be obtained after the intervention (8 weeks) on a 1-5 Likert scale of 4-item questions, including "The exercise program delivered by the app meets my approval" using the Acceptability of Intervention Measure (AIM) by Weiner et al., 20171.
Appropriateness (perceived fit for rural older adults).
will be assessed using the Weiner et al., 20171 intervention appropriateness measure (IAM).
The IAM is on 1-5 Likert scale of 4-item questions, including "The exercise program seems fitting", "The exercise program seems suitable".
The AIM and IAM are robust, with Cronbach alphas of 0.89 and 0.87, respectively.
|
At follow up (week 10)
|
2차 결과 측정
결과 측정 |
측정값 설명 |
기간 |
|---|---|---|
|
Fitbit Daily Step
기간: Baseline (week 0) and Follow up (week 10)
|
Fitbit Flex 2 will be used to assess participants' daily steps
|
Baseline (week 0) and Follow up (week 10)
|
|
Physical Activity
기간: Baseline (week 1) and Follow up (Week 10)
|
We will use the Physical Activity Scale for the Elderly to assess PA across leisure (6-item question), household (3-item question), and occupational domains (1-item question) over the past 7 days.
Higher scores means more physical activity.
(Low activity: <100; Moderate: 100-250; High: >250)
|
Baseline (week 1) and Follow up (Week 10)
|
|
Depression
기간: Baseline (week 0) and Follow up (week 10)
|
Depression will be measured using Patient Health Questionnaire (PHQ-8), a 8-item symptom severity rating scale for depression (Kroenke et al., 2009). PHQ-8 is a validated diagnostic and severity measure of symptoms of depressive disorders. Adults with scores of 0-4 are considered to have no or minimal symptoms of depression. Score 5-9 are considered mild symptom Score 10-14 are considered moderate symptom Score 15-24 are considered severe symptom |
Baseline (week 0) and Follow up (week 10)
|
|
Anxiety
기간: Baseline (week 0) and Follow up (week 10)
|
Anxiety will be assessed using the Geriatric Anxiety Scale (GAS). GAS is a 10-item rating scale on a 4-Likert Scale (Not at all [0] to All of the time [3]). Item 1 through 10 are summed to provide a total score. The higher the score, the worse the anxiety outcome. Score 1-6 are considered minimal symptom Score 7-9 are considered mild symptom Score 10 is considered moderate Score 12-30 are considered severe symptom |
Baseline (week 0) and Follow up (week 10)
|
|
Older Adult Quality of Life
기간: Baseline (week 0) and Follow up (week 10)
|
Quality of life (QoL) will be assessed using the Older Adult Quality of Life Scale. Each of the 13 items is scored Strongly agree=1, Agree=2, Neither=3, Disagree=4, Strongly disagree=5. The items are summed for a total OPQOL-Brief score, then positive items are reverse coded, so that higher scores represented higher QoL. Minimum: 13 (very poor quality of life) Maximum: 65 (excellent quality of life) |
Baseline (week 0) and Follow up (week 10)
|
공동 작업자 및 조사자
수사관
- 수석 연구원: Zan Gao, PhD, University Of Tennessee,knoxville
연구 기록 날짜
연구 주요 날짜
연구 시작 (추정된)
기본 완료 (추정된)
연구 완료 (추정된)
연구 등록 날짜
최초 제출
QC 기준을 충족하는 최초 제출
처음 게시됨 (실제)
연구 기록 업데이트
마지막 업데이트 게시됨 (실제)
QC 기준을 충족하는 마지막 업데이트 제출
마지막으로 확인됨
추가 정보
이 연구와 관련된 용어
키워드
기타 연구 ID 번호
- STUDY00000770
약물 및 장치 정보, 연구 문서
미국 FDA 규제 의약품 연구
미국 FDA 규제 기기 제품 연구
이 정보는 변경 없이 clinicaltrials.gov 웹사이트에서 직접 가져온 것입니다. 귀하의 연구 세부 정보를 변경, 제거 또는 업데이트하도록 요청하는 경우 register@clinicaltrials.gov. 문의하십시오. 변경 사항이 clinicaltrials.gov에 구현되는 즉시 저희 웹사이트에도 자동으로 업데이트됩니다. .