Blockchain and Fuzzy Logic-Based Secure Disease Prediction Model for IoMT Applications
The IoMT makes it feasible to improve people's protection, health, and ability to forecast and treat illnesses. Cutting-edge technologies like machine learning, fuzzy logic, and the blockchain may have a significant positive impact on the healthcare sector. Blockchain provides a convincing solution to the security problems with IoMT, enabling a smarter, safer healthcare system. As a result, this article suggests a Private Blockchain IoMT Framework (PBIoMT) for fuzzy logic and machine learning-based disease prediction. As categorization systems advance, machine learning algorithms for massive healthcare data are becoming increasingly significant. People who are healthy and those who have a condition are separated in this analysis. This study employs an Adaptive Neuro-Fuzzy Inference System (ANFIS) for data protection based on blockchain technology to improve and gain a degree of security regarding data integrity, breaches, etc., while storing this data on the cloud. In this setup, the call is made using a fuzzy logic system, and the doctor has the means to contact the patient, thanks to data analytics. The experiments' findings demonstrate that the proposed method outperforms the existing methods for disease prediction. The experiment's findings demonstrate that, with an accuracy ratio of 92%, precision ratio of 89%, recall ratio of 89%, and f-score ratio of 91%, the suggested approach outperforms the state-of-the-art by a wide margin.
Authors
- Osama A. Mohammed (ORCID: https://orcid.org/0000-0002-2586-4046)
- Majid A. Al-Taee (ORCID: https://orcid.org/0000-0002-3252-3637)
- Rozi Mahmud (ORCID: https://orcid.org/0000-0002-9543-3452)
- Amal Hasan Jumaa
- Aaied Eqab Muraay Majed
Institutions
- University of Kirkuk (IQ)
- Al-Nisour University College (IQ)
Publication Details
- Published
- 2024-12-12
- DOI
- https://doi.org/10.1109/icercs63125.2024.10895436
- Primary Topic
- Brain Tumor Detection and Classification
- Type
- article
- Field-Weighted Citation Impact
- 0.00