Explainable AI-Powered IoT Systems for Predictive and Preventive Healthcare - A Framework for Personalized Health Management and Wellness Optimization
Main Article Content
Abstract
With the growing integration of Internet of Things (IoT) technologies and Artificial Intelligence (AI) in healthcare, it is crucial to prioritize transparency and interpretability in the decision-making process. This paper presents a novel framework that utilizes Explainable AI (XAI) to improve the interpretability of predictive healthcare models. The proposed system integrates feature importance-based methodologies with the Local Interpretable Model-agnostic Explanations (LIME) technique to offer a comprehensive comprehension of the predictive and preventive healthcare recommendations. The framework commences by conducting an in-depth examination of the present condition of Internet of Things (IoT) in the healthcare sector, as well as the importance of predictive and preventive healthcare. The literature review examines the difficulties related to the comprehensibility of artificial intelligence (AI) in the healthcare field and presents feature importance-based approaches and LIME as potential remedies. The focus is on the hybrid approach that combines these techniques, as it has the potential to offer precise predictions while also ensuring a strong level of interpretability. The methodology section delineates the procedure for gathering healthcare data and IoT sensor data, subsequently followed by preprocessing measures such as data cleansing and feature engineering. The predictive models undergo a process of selection, training, and evaluation, with the primary objective of attaining a notable accuracy level of 0.961. This text provides a detailed explanation of how the combination of feature importance-based approaches and LIME improves the transparency and interpretability of the model. An extensive case study is provided to illustrate the implementation of the suggested framework in an actual situation. The results and evaluation section showcases the exceptional precision of 0.961, as well as enhanced interpretability scores and decreased computational time in comparison to the baseline XAI models. The discussion section juxtaposes the suggested hybrid approach with conventional models, examines ethical considerations, and investigates the scalability and generalizability of the framework. To conclude, the paper provides a concise overview of the findings and implications of the Explainable AI-Powered IoT Systems for Predictive and Preventive Healthcare framework. This hybrid approach demonstrates high accuracy, improved interpretability, and efficient computational performance, making it a promising advancement in personalized health management and wellness optimization. This research adds to the expanding collection of literature on Explainable Artificial Intelligence (XAI) in the healthcare sector, thus opening up possibilities for future research avenues and practical applications in this domain.
Article Details
This work is licensed under a Creative Commons Attribution-NoDerivatives 4.0 International License.
References
A. S. Albahri et al., “A systematic review of trustworthy and explainable artificial intelligence in healthcare: Assessment of quality, bias risk, and data fusion,” Inf. Fusion, vol. 96, pp. 156–191, 2023, doi: https://doi.org/10.1016/j.inffus.2023.03.008.
S. Bharati, M. R. H. Mondal, P. Podder, and U. Kose, “Explainable Artificial Intelligence (XAI) with IoHT for Smart Healthcare: A Review,” Internet of Things, vol. Part F739, pp. 1–24, 2023, doi: 10.1007/978-3-031-08637-3_1.
A. Chaddad et al., “Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine,” IEEE/CAA J. Autom. Sin., vol. 10, no. 4, pp. 859–876, 2023, doi: 10.1109/JAS.2023.123123.
A. Chaddad, J. Peng, J. Xu, and A. Bouridane, “Survey of Explainable AI Techniques in Healthcare,” Sensors, vol. 23, no. 2, pp. 1–19, 2023, doi: 10.3390/s23020634.
M. A. Rahman, M. S. Hossain, A. J. Showail, N. A. Alrajeh, and M. F. Alhamid, “A secure, private, and explainable IoHT framework to support sustainable health monitoring in a smart city,” Sustain. Cities Soc., vol. 72, p. 103083, 2021, doi: https://doi.org/10.1016/j.scs.2021.103083.
C. C. Yang, “Explainable Artificial Intelligence for Predictive Modeling in Healthcare,” J. Healthc. Informatics Res., vol. 6, no. 2, pp. 228–239, 2022, doi: 10.1007/s41666-022-00114-1.
V. Chamola, V. Hassija, A. R. Sulthana, D. Ghosh, D. Dhingra, and B. Sikdar, “A Review of Trustworthy and Explainable Artificial Intelligence (XAI),” IEEE Access, vol. 11, no. August 2023, pp. 78994–79015, 2023, doi: 10.1109/ACCESS.2023.3294569.
A. Raza, K. P. Tran, L. Koehl, and S. Li, “Designing ECG monitoring healthcare system with federated transfer learning and explainable AI,” Knowledge-Based Syst., vol. 236, p. 107763, 2022, doi: 10.1016/j.knosys.2021.107763.
S. Muneer and H. Raza, “An IoMT enabled smart healthcare model to monitor elderly people using Explainable Artificial Intelligence ( EAI ),” J. NCBAE, vol. 1, no. June, pp. 16–22, 2022.
M. H. Wang, K. K. lung Chong, Z. Lin, X. Yu, and Y. Pan, “An Explainable Artificial Intelligence-Based Robustness Optimization Approach for Age-Related Macular Degeneration Detection Based on Medical IOT Systems,” Electron., vol. 12, no. 12, 2023, doi: 10.3390/electronics12122697.
Tadeusz Chmielniak, & Nadica Stojanovic. (2022). Design of Computer Aided Design in the Field of Mechanical Engineering . Acta Energetica, (01), 08–16. Retrieved from https://www.actaenergetica.org/index.php/journal/article/view/460
I. García-Magariño, R. Muttukrishnan, and J. Lloret, “Human-centric AI for trustworthy IoT systems with explainable multilayer perceptrons,” IEEE Access, vol. 7, pp. 125562–125574, 2019, doi: 10.1109/ACCESS.2019.2937521.
Deepanshi, I. Budhiraja, D. Garg, and N. Kumar, “Choquet integral based deep learning model for COVID-19 diagnosis using eXplainable AI for NG-IoT models,” Comput. Commun., vol. 212, pp. 227–238, 2023, doi: https://doi.org/10.1016/j.comcom.2023.09.032.
A. K. Sangaiah, S. Rezaei, A. Javadpour, and W. Zhang, “Explainable AI in big data intelligence of community detection for digitalization e-healthcare services,” Appl. Soft Comput., vol. 136, p. 110119, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110119.
R. Kumar, D. Javeed, A. Aljuhani, A. Jolfaei, P. Kumar, and A. K. M. N. Islam, “Blockchain-Based Authentication and Explainable AI for Securing Consumer IoT Applications,” IEEE Trans. Consum. Electron., pp. 1–10, 2023, doi: 10.1109/TCE.2023.3320157.
T. Vats et al., “Explainable context-aware IoT framework using human digital twin for healthcare,” Multimed. Tools Appl., 2023, doi: 10.1007/s11042-023-16922-5.
F. Di Martino and F. Delmastro, Explainable AI for clinical and remote health applications: a survey on tabular and time series data, vol. 56, no. 6. Springer Netherlands, 2023.
P. N. Srinivasu, N. Sandhya, R. H. Jhaveri, and R. Raut, “From Blackbox to Explainable AI in Healthcare: Existing Tools and Case Studies,” Mob. Inf. Syst., vol. 2022, 2022, doi: 10.1155/2022/8167821.
D. Saraswat et al., “Explainable AI for Healthcare 5.0: Opportunities and Challenges,” IEEE Access, vol. 10, no. July, pp. 84486–84517, 2022, doi: 10.1109/ACCESS.2022.3197671.
S. K. Jagatheesaperumal, Q. V. Pham, R. Ruby, Z. Yang, C. Xu, and Z. Zhang, “Explainable AI Over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions,” IEEE Open J. Commun. Soc., vol. 3, no. November, pp. 2106–2136, 2022, doi: 10.1109/OJCOMS.2022.3215676.
I. Kok, F. Y. Okay, O. Muyanli, and S. Ozdemir, “Explainable Artificial Intelligence (XAI) for Internet of Things: A Survey,” IEEE Internet Things J., vol. 10, no. 16, pp. 14764–14779, 2023, doi: 10.1109/JIOT.2023.3287678.