โก Quick Summary
This study explored the use of mobile health (mHealth) apps among family caregivers of stroke patients in Chinese communities, utilizing machine learning models to identify key influencing factors. The findings revealed that 57.2% of caregivers used mHealth apps, with significant determinants including educational level and hedonic motivation.
๐ Key Details
- ๐ Participants: 360 family caregivers of stroke patients
- ๐งฉ Study Duration: March 2023 to November 2023
- โ๏ธ Methodology: Cross-sectional survey with machine learning analysis
- ๐ Best Performing Model: Logistic regression with AUC of 0.753
๐ Key Takeaways
- ๐ฑ mHealth apps are increasingly used by family caregivers to support stroke patients.
- ๐ Logistic regression was the most effective model for predicting app usage.
- ๐ SHAP analysis identified educational level, age, and self-care ability as key factors influencing app use.
- ๐ง Hedonic motivation and usage habits significantly impacted caregivers’ app usage behavior.
- ๐ Findings suggest that developers should focus on older adults and lower educational levels to enhance app accessibility.
- ๐ก Convenience and effort expectations are crucial for increasing mHealth app adoption.
- ๐ Overall accuracy of the logistic regression model was 69.4%.
- ๐ Random forest model showed an AUC of 0.773 for usage behavior.
๐ Background
Family caregivers play a vital role in the care of stroke patients, often facing challenges in accessing reliable health information and support. The advent of mobile health (mHealth) applications offers a promising solution to enhance caregiving practices. However, understanding the factors that influence the adoption and effective use of these apps is essential for their success.
๐๏ธ Study
This cross-sectional study aimed to assess the current state of mHealth app usage among family caregivers of stroke patients in Chinese communities. Researchers employed a comprehensive approach, utilizing face-to-face questionnaires to gather data on caregivers’ profiles, app usage, and various motivational factors. A total of 12 machine learning models were constructed, with a focus on interpreting the results through the SHAP algorithm.
๐ Results
Out of the 360 caregivers surveyed, 206 (57.2%) reported using mHealth apps. The logistic regression model emerged as the top performer, achieving an AUC of 0.753 and an accuracy of 69.4%. The SHAP analysis highlighted that the most significant factors influencing app usage included educational level, age, and the patient’s self-care ability. The random forest model, which focused on usage behavior, achieved an AUC of 0.773.
๐ Impact and Implications
The findings of this study have important implications for the development and promotion of mHealth applications. By understanding the key determinants of app usage, developers and policymakers can tailor their strategies to better meet the needs of family caregivers. Focusing on older adults with lower educational levels and enhancing the convenience of app usage can significantly improve the effectiveness and adoption of mHealth solutions in caregiving contexts.
๐ฎ Conclusion
This research underscores the potential of machine learning in analyzing the factors that affect the use of mHealth apps among family caregivers. By addressing the identified determinants, stakeholders can enhance the accessibility and effectiveness of these applications, ultimately improving the quality of care for stroke patients. The future of mHealth apps looks promising, and continued research in this area is essential for maximizing their impact.
๐ฌ Your comments
What are your thoughts on the role of mHealth apps in supporting family caregivers? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Interpretable Machine Learning Models for Analyzing Determinants Affecting the Use of mHealth Apps Among Family Caregivers of Patients With Stroke in Chinese Communities: Cross-Sectional Survey Study.
Abstract
BACKGROUND: Mobile health (mHealth) apps are believed to be an effective method to support family caregivers to better care for patients with stroke. This study’s purpose was to explore the status and the influencing factors of mHealth app use among family caregivers of patients with stroke via machine learning (ML) models.
OBJECTIVE: This study aimed to understand the status quo of mHealth app use among community family caregivers of patients with stroke and the factors influencing their use behavior. Six ML models were used to construct the classifier, and the Shapley Additive Explanations (SHAP) algorithm was introduced to interpret the best ML model.
METHODS: In this cross-sectional study, family carers of patients with stroke were recruited. Data on their basic profile and mHealth app use were obtained through face-to-face questionnaires. Hedonic motivation, usage habits, and other relevant information were additionally measured among app users. A total of 12 models were constructed using six ML algorithms. The top-performing logistic regression and random forest models were further analyzed with SHAP to interpret key influencing factors.
RESULTS: A total of 360 family caregivers of patients with stroke were included in this study from March 2023 to November 2023, of which 206 (57.2%) reported having used mHealth apps. Of the 6 ML models, the logistic regression model performed the best in terms of whether caregivers used the mHealth app, with an area under the receiver operating characteristic curve of 0.753 (95% CI 0.698-0.802), accuracy of 0.694 (95% CI 0.647-0.742), sensitivity of 0.748 (95% CI 0.688-0.806), and specificity of 0.623 (95% CI 0.547-0.698). SHAP analysis showed that the top 5 most influencing factors were educational level, age, the patient’s self-care ability, the relationship with the cared-for individual, and the duration of illness. The random forest model performed best in terms of use behavior with an area under the receiver operating characteristic curve of 0.773 (95% CI 0.725-0.818), accuracy of 0.602 (95% CI 0.534-0.665), sensitivity of 0.476 (95% CI 0.420-0.533), and specificity of 0.769 (95% CI 0.738-0.797). The SHAP analysis revealed that hedonic motivation, habits, occupation, convenience conditions, and effort expectations were the 5 most significant influencing factors.
CONCLUSIONS: The research results indicate that the software developers and policymakers of mHealth apps should take the abovementioned influencing factors into consideration when developing and promoting the software. We should focus on the older adults with lower educational levels, lower the threshold for software use, and provide more convenient conditions. By grasping the hedonistic tendencies and habitual usage characteristics of users, they can provide them with more concise and accurate health information, which will enhance the popularity and effectiveness of mHealth apps.
Author: [‘Du Y’, ‘Fan JY’, ‘Liu GZ’, ‘Yang ZY’, ‘Lei Y’, ‘Guo YF’]
Journal: JMIR Mhealth Uhealth
Citation: Du Y, et al. Interpretable Machine Learning Models for Analyzing Determinants Affecting the Use of mHealth Apps Among Family Caregivers of Patients With Stroke in Chinese Communities: Cross-Sectional Survey Study. Interpretable Machine Learning Models for Analyzing Determinants Affecting the Use of mHealth Apps Among Family Caregivers of Patients With Stroke in Chinese Communities: Cross-Sectional Survey Study. 2025; 13:e73903. doi: 10.2196/73903