1
|
Khalid F, Alsadoun L, Khilji F, Mushtaq M, Eze-Odurukwe A, Mushtaq MM, Ali H, Farman RO, Ali SM, Fatima R, Bokhari SFH. Predicting the Progression of Chronic Kidney Disease: A Systematic Review of Artificial Intelligence and Machine Learning Approaches. Cureus 2024; 16:e60145. [PMID: 38864072 PMCID: PMC11166249 DOI: 10.7759/cureus.60145] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 05/12/2024] [Indexed: 06/13/2024] Open
Abstract
Chronic kidney disease (CKD) is a progressive condition characterized by gradual loss of kidney function, necessitating timely monitoring and interventions. This systematic review comprehensively evaluates the application of artificial intelligence (AI) and machine learning (ML) techniques for predicting CKD progression. A rigorous literature search identified 13 relevant studies employing diverse AI/ML algorithms, including logistic regression, support vector machines, random forests, neural networks, and deep learning approaches. These studies primarily aimed to predict CKD progression to end-stage renal disease (ESRD) or the need for renal replacement therapy, with some focusing on diabetic kidney disease progression, proteinuria, or estimated glomerular filtration rate (GFR) decline. The findings highlight the promising predictive performance of AI/ML models, with several achieving high accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve scores. Key factors contributing to enhanced prediction included incorporating longitudinal data, baseline characteristics, and specific biomarkers such as estimated GFR, proteinuria, serum albumin, and hemoglobin levels. Integration of these predictive models with electronic health records and clinical decision support systems offers opportunities for timely risk identification, early interventions, and personalized management strategies. While challenges related to data quality, bias, and ethical considerations exist, the reviewed studies underscore the potential of AI/ML techniques to facilitate early detection, risk stratification, and targeted interventions for CKD patients. Ongoing research, external validation, and careful implementation are crucial to leveraging these advanced analytical approaches in clinical practice, ultimately improving outcomes and reducing the burden of CKD.
Collapse
Affiliation(s)
- Fizza Khalid
- Nephrology, Sharif Medical City Hospital, Lahore, PAK
| | - Lara Alsadoun
- Trauma and Orthopedics, Chelsea and Westminster Hospital, London, GBR
| | - Faria Khilji
- Internal Medicine, Tehsil Headquarter Hospital, Shakargarh, PAK
- Internal Medicine, Quaid-e-Azam Medical College, Bahawalpur, PAK
| | - Maham Mushtaq
- Medicine and Surgery, King Edward Medical University, Lahore, PAK
| | | | | | - Husnain Ali
- Medicine and Surgery, King Edward Medical University, Lahore, PAK
| | - Rana Omer Farman
- Medicine and Surgery, King Edward Medical University, Lahore, PAK
| | - Syed Momin Ali
- Medicine and Surgery, King Edward Medical University, Lahore, PAK
| | - Rida Fatima
- Medicine and Surgery, Fatima Jinnah Medical University, Lahore, PAK
| | | |
Collapse
|
2
|
Saito H, Yoshimura H, Tanaka K, Kimura H, Watanabe K, Tsubokura M, Ejiri H, Zhao T, Ozaki A, Kazama S, Shimabukuro M, Asahi K, Watanabe T, Kazama JJ. Predicting CKD progression using time-series clustering and light gradient boosting machines. Sci Rep 2024; 14:1723. [PMID: 38242985 PMCID: PMC10798962 DOI: 10.1038/s41598-024-52251-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Accepted: 01/16/2024] [Indexed: 01/21/2024] Open
Abstract
Predicting the transition of kidney function in chronic kidney disease is difficult as specific symptoms are lacking and often overlooked, and progress occurs due to complicating factors. In this study, we applied time-series cluster analysis and a light gradient boosting machine to predict the trajectories of kidney function in non-dialysis dependent chronic kidney disease patients with baseline estimated glomerular filtration rate (GFR) ≥ 45 mL/min/1.73 m2. Based on 5-year changes in estimated GFR, participants were stratified into groups with similar trajectories by cluster analysis. Next, we applied the light gradient boosting machine algorithm and Shapley addictive explanation to develop a prediction model for clusters and identify important parameters for prediction. Data from 780 participants were available for analysis. Participants were classified into five classes (Class 1: n = 78, mean [± standard deviation] estimated GFR 100 ± 19.3 mL/min/1.73 m2; Class 2: n = 176, 76.0 ± 9.3 mL/min/1.73 m2; Class 3: n = 191, 59.8 ± 5.9 mL/min/1.73 m2; Class 4: n = 261, 52.7 ± 4.6 mL/min/1.73 m2; and Class 5: n = 74, 53.5 ± 12.0 mL/min/1.73 m2). Declines in estimated GFR were 8.9% in Class 1, 12.2% in Class 2, 4.9% in Class 3, 12.0% in Class 4, and 45.1% in Class 5 during the 5-year period. The accuracy of prediction was 0.675, and the top three most important Shapley addictive explanation values were 1.61 for baseline estimated GFR, 0.12 for hemoglobin, and 0.11 for body mass index. The estimated GFR transition of patients with preserved chronic kidney disease mostly depended on baseline estimated GFR, and the borderline for estimated GFR trajectory was nearly 50 mL/min/1.73 m2.
Collapse
Affiliation(s)
- Hirotaka Saito
- Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan
| | - Hiroki Yoshimura
- Department of Radiation Health Management, Fukushima Medical University, Fukushima, Japan
| | - Kenichi Tanaka
- Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan.
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan.
| | - Hiroshi Kimura
- Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan
| | - Kimio Watanabe
- Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan
| | - Masaharu Tsubokura
- Department of Radiation Health Management, Fukushima Medical University, Fukushima, Japan
| | - Hiroki Ejiri
- Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan
| | - Tianchen Zhao
- Department of Radiation Health Management, Fukushima Medical University, Fukushima, Japan
| | - Akihiko Ozaki
- Department of Thyroid and Endocrinology, Fukushima Medical University, Fukushima, Japan
| | - Sakumi Kazama
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan
| | - Michio Shimabukuro
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan
- Department of Diabetes, Endocrinology, and Metabolism, Fukushima Medical University, Fukushima, Japan
| | - Koichi Asahi
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan
- Division of Nephrology and Hypertension, Iwate Medical University, Yahaba, Japan
| | - Tsuyoshi Watanabe
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan
| | - Junichiro J Kazama
- Department of Nephrology and Hypertension, Fukushima Medical University, 1 Hikariga-Oka, Fukushima City, Fukushima, 960-1295, Japan
- Division of Advanced Community Based Care for Lifestyle Related Diseases, Fukushima Medical University, Fukushima, Japan
| |
Collapse
|