Stroke Assist: A Smart System for Post-stroke Rehabilitation using IoT and Machine Learning
Keywords:
ESP32, Healthcare, IoT, Machine learning, Python web application, Smart wearable, Stroke monitoring, ThingSpeakAbstract
Stroke is a leading cause of long-term disability and mortality, requiring continuous monitoring and timely intervention to prevent recurrent attacks. This study presents the design and implementation of a smart IoT-based health monitoring system for stroke patients that continuously tracks vital parameters such as oxygen levels, heartbeat, and body movements. The system integrates sensors, including an ECG, heartbeat sensor, and ADXL345 accelerometer with an ESP32 microcontroller, transmitting real-time data to the ThingSpeak cloud via Wi-Fi. A Python-based web application developed using Flask/Django retrieves and visualizes the data through ThingSpeak APIs, enabling caregivers and physicians to monitor patient health and recovery trends remotely. Furthermore, machine learning algorithms, including K-nearest neighbors (KNN), random forest, logistic regression, and support vector machine (SVM), are used to predict abnormal physiological conditions or potential health risks analyze historical data to predict stroke recurrence risks and recovery patterns, and provide early warnings for abnormal health conditions. The system also delivers personalized therapy recommendations based on analytical insights and triggers emergency alerts via Telegram during critical events. Experimental results demonstrate reliable real-time monitoring, accurate prediction of recovery trends, and timely alert generation. The proposed system offers a cost-effective, intelligent, and scalable platform for continuous post-stroke rehabilitation and proactive healthcare management.
References
Y. N. Rimal, N. Sharma, A. Alsadoon, and S. K. Abbas, “A comparative analysis of ensemble autoML machine learning prediction accuracy of STEM student grade prediction: a multi-class classification prospective,” Multimedia Tools and Applications, vol. 84, pp. 38343–38369, Mar. 2025.
N. Sengupta, A. S. Rao, B. Yan, and M. Palaniswami, “A survey of wearable sensors and machine learning algorithms for automated stroke rehabilitation,” in IEEE Access, vol. 12, pp. 36026–36054, 2024.
S. R. Kopalli et al., “Artificial intelligence in stroke rehabilitation: From acute care to long-term recovery,” Neuroscience, vol. 572, pp. 214–231, Mar. 2025.
T. Tahsin, K. M. Mumenin, H. Akter, J. J. Tiang, and Abdullah-Al Nahid, “Machine learning-based stroke patient rehabilitation stage classification using Kinect data,” Applied Sciences, vol. 14, no. 15, p. 6700, Jul. 2024.
S. Fatima, A. Hussain, S. B. Amir, S. H. Ahmed, and S. M. H. Aslam, “XGBoost and random forest algorithms: An in-depth analysis,” Pakistan Journal of Scientific Research, vol. 3, no. 1, pp. 26–31, 2023.
G. Yang et al., “An IoT-enabled stroke rehabilitation system based on smart wearable armband and machine learning,” in IEEE Journal of Translational Engineering in Health and Medicine, vol. 6, pp. 1–10, 2018.
J.-P. Lai, Y.-L. Lin, H.-C. Lin, C.-Y. Shih, Y.-P. Wang, and P.-F. Pai, “Tree-based machine learning models with optuna in predicting impedance values for circuit analysis,” Micromachines, vol. 14, no. 2, p. 265, Jan. 2023.
V. U. Pugliese, C. M. Hirata, and R. D. Costa, “Comparing supervised classification methods for financial domain problems,” in Proceedings of the 22nd International Conference on Enterprise Information Systems (ICEIS 2020), vol. 1, pp. 440–451.
J. Lou, “Comparative analysis of logistic regression, random forest, and XGBoost for click-through rate prediction in digital advertising,” Advances in Economics, Business and Management Research, pp. 462–470, 2024.
S. Fatima, Syeda F. Nasim, F. Arif, I. Siddiqui, H. Siddiqui, and M. Arshad, “A detailed study on machine learning models with respect to wall-following robots,” Research Square, Sep. 2022.
C. Raffel et al., “Exploring the limits of transfer learning with a unified text-to-text transformer,” Journal of Machine Learning Research, vol. 21, pp. 1–67, 2020.
I. L. Markov et al., “Scalable end-to-end ML Platforms: from AutoML to self-serve,” arXiv.org, 2023.
C. Cortes and V. Vapnik, “Support-vector networks,” Machine Learning, vol. 20, no. 3, pp. 273–297, Sep. 1995.
M. Feurer, K. Eggensperger, S. Falkner, M. Lindauer, and F. Hutter, “Auto-sklearn 2.0: Hands-free automl via meta-learning.,” Journal of Machine Learning Research, vol. 23, no. 1, pp. 11936–11996, 2022.
X. He, K. Zhao, and X. Chu, “AutoML: A survey of the state-of-the-art,” Knowledge-based Systems, vol. 212, p. 106622, Jan. 2021.
A. J. Smola and B. Schölkopf, “A tutorial on support vector regression,” Statistics and Computing, vol. 14, no. 3, pp. 199–222, Aug. 2004.
