EUVIMEDSkopri EUVIMED
QuerschnittstudieOpen access

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

Erklärbare Machine-Learning-Modelle zur Analyse von Einflussfaktoren auf die Nutzung von mHealth-Apps bei Angehörigen von Patient:innen mit Schlaganfall in chinesischen Gemeinden: Querschnittsstudie

Yun Du iD, Jun-Ying Fan iD, Guang-Zhi Liu iD, Zi-Yue Yang iD, Yang Lei iD, Yu-Fang Guo iD

JMIR mHealth and uHealth · 2025-11-24 · 13 · e73903-e73903

DOI: 10.2196/73903 ↗

Auf einen Blick

Bei 360 Angehörigen von Patient:innen mit Schlaganfall nutzten 206 mHealth-Apps. Das beste Modell zur Vorhersage der Nutzung war die logistische Regression; wichtige Einflussfaktoren wurden mit SHAP identifiziert.

Fragestellung

Wie ist die Nutzung von mHealth-Apps unter familiären Pflegepersonen von Patient:innen mit Schlaganfall und welche Faktoren beeinflussen sie?

Methode

Querschnittsstudie mit Fragebögen; 6 Machine-Learning-Modelle; Interpretation des besten Modells mit SHAP.

Ergebnisse

360 Angehörige wurden von März 2023 bis November 2023 eingeschlossen, 206 (57,2 %) nutzten mHealth-Apps. Für die Nutzung zeigte die logistische Regression die beste Leistung: AUC 0,753 (95 %-KI 0,698–0,802), Accuracy 0,694 (95 %-KI 0,647–0,742), Sensitivität 0,748 (95 %-KI 0,688–0,806), Spezifität 0,623 (95 %-KI 0,547–0,698).

Schlussfolgerung der Autor:innen

Die Autor:innen schließen, dass Entwickler:innen und Politikgestaltung die genannten Einflussfaktoren bei Entwicklung und Verbreitung von mHealth-Apps berücksichtigen sollten.

Kernaussagen

  • 206 von 360 Angehörigen nutzten mHealth-Apps
  • Logistische Regression: AUC 0,753 (95 %-KI 0,698–0,802)
  • Wichtige Faktoren: Bildungsniveau, Alter und Selbstpflegefähigkeit

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

At a glance

Querschnittstudie in JMIR mHealth and uHealth, published online on 2025-11-24. Written by Yun Du and 5 co-authors. Institution: School of Nursing and Rehabilitation, Shandong University, 44 Wen Hua Xi Road, Jinan, Shandong, 250012, China, 86 15269163352. Major MEDLINE topics: Caregivers, Machine Learning, Stroke, Mobile Applications. Cited 4 times so far (Crossref); 53 references. The full text is freely available in PubMed Central.

Auf einen BlickAstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

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.

Subjects

MeSH terms (MEDLINE)

CaregiversMachine LearningStrokeMobile ApplicationsHumansCross-Sectional StudiesMaleFemaleMiddle AgedChinaSurveys and QuestionnairesAdultAgedTelemedicineEast Asian People

Author keywords

strokecaregiverscommunityinfluencing factorsmHealthmachine learning modelmobile health

Authors and institutions

  • School of Nursing and Rehabilitation, Shandong University, 44 Wen Hua Xi Road, Jinan, Shandong, 250012, China, 86 15269163352.
  • Department of Neurology, The Affiliated Hospital of Xuzhou Medical University, Xuzhou, China.
  • School of Nursing, Nanjing Medical University, Nanjing, China.

ORCID profiles: Yun Du, Jun-Ying Fan, Guang-Zhi Liu, Zi-Yue Yang, Yang Lei, Yu-Fang Guo

Cite

APA

Du, Y., Fan, J. Y., Liu, G. Z., Yang, Z. Y., Lei, Y., & Guo, Y. F. (2025). 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. JMIR mHealth and uHealth, 13, e73903-e73903. https://doi.org/10.2196/73903

Vancouver

Du Y, Fan JY, Liu GZ, Yang ZY, Lei Y, Guo YF. 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. JMIR mHealth and uHealth. 2025;13:e73903-e73903. doi:10.2196/73903

BibTeX
@article{Du2025,
  author = {Du, Yun and Fan, Jun-Ying and Liu, Guang-Zhi and Yang, Zi-Yue and Lei, Yang and Guo, Yu-Fang},
  title = {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},
  journal = {JMIR mHealth and uHealth},
  year = {2025},
  volume = {13},
  pages = {e73903--e73903},
  doi = {10.2196/73903}
}
Start for free →