Chronic kidney disease diagnostic tools based on machine learning algorithms: a review / Muhamad Huzaimi Abdul Ghafar ... [et al.]
Chronic kidney disease (CKD) is a global health crisis, responsible for approximately 60% of worldwide deaths. With a projected increase in CKD patients on dialysis exceeding 2 million by 2030, there is an urgent need for improved diagnostic methods. Current procedures, such as laborious and time-co...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
UiTM Press
2025
|
| Subjects: | |
| Online Access: | https://ir.uitm.edu.my/id/eprint/114917/1/114917.pdf https://ir.uitm.edu.my/id/eprint/114917/ https://jeesr.uitm.edu.my |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Chronic kidney disease (CKD) is a global health crisis, responsible for approximately 60% of worldwide deaths. With a projected increase in CKD patients on dialysis exceeding 2 million by 2030, there is an urgent need for improved diagnostic methods. Current procedures, such as laborious and time-consuming blood tests, fail to differentiate between drug-resistant phases of CKD. This paper aims to explore the potential of Artificial Intelligence (AI) tools, specifically machine learning (ML), in revolutionizing CKD diagnosis. This work intends to enlighten the evolution of ML techniques in CKD diagnosis and their contemporary applications. We conducted an extensive literature review, identifying 70 papers pertaining to ML-based CKD diagnostic tools recently published. These papers were thoroughly examined to categorize the diverse AI methods utilized in medical diagnostics, particularly those aimed at CKD detection. The review identified a range of AI methods used in CKD diagnosis, signifying substantial progress in this domain over the last decade. These methods show promise in addressing the challenges associated with early CKD detection. This paper highlights the evolving landscape of ML applications in CKD diagnosis and their current relevance. This paper concludes with a discussion of prospects for future research on AI-based CKD diagnostic systems, including deep learning algorithms applied to an
assortment of open problems and challenges. |
|---|