1
|
Chen L, Shao X, Yu P. Machine learning prediction models for diabetic kidney disease: systematic review and meta-analysis. Endocrine 2024; 84:890-902. [PMID: 38141061 DOI: 10.1007/s12020-023-03637-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/18/2023] [Accepted: 11/28/2023] [Indexed: 12/24/2023]
Abstract
BACKGROUND Machine learning is increasingly recognized as a viable approach for identifying risk factors associated with diabetic kidney disease (DKD). However, the current state of real-world research lacks a comprehensive systematic analysis of the predictive performance of machine learning (ML) models for DKD. OBJECTIVES The objectives of this study were to systematically summarize the predictive capabilities of various ML methods in forecasting the onset and the advancement of DKD, and to provide a basic outline for ML methods in DKD. METHODS We have searched mainstream databases, including PubMed, Web of Science, Embase, and MEDLINE databases to obtain the eligible studies. Subsequently, we categorized various ML techniques and analyzed the differences in their performance in predicting DKD. RESULTS Logistic regression (LR) was the prevailing ML method, yielding an overall pooled area under the receiver operating characteristic curve (AUROC) of 0.83. On the other hand, the non-LR models also performed well with an overall pooled AUROC of 0.80. Our t-tests showed no statistically significant difference in predicting ability between LR and non-LR models (t = 1.6767, p > 0.05). CONCLUSION All ML predicting models yielded relatively satisfied DKD predicting ability with their AUROCs greater than 0.7. However, we found no evidence that non-LR models outperformed the LR model. LR exhibits high performance or accuracy in practice, while it is known for algorithmic simplicity and computational efficiency compared to others. Thus, LR may be considered a cost-effective ML model in practice.
Collapse
Affiliation(s)
- Lianqin Chen
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien-I Memorial Hospital & Tianjin Institute of Endocrinology, Tianjin Medical University, Tianjin, 300134, China
| | - Xian Shao
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien-I Memorial Hospital & Tianjin Institute of Endocrinology, Tianjin Medical University, Tianjin, 300134, China
| | - Pei Yu
- NHC Key Laboratory of Hormones and Development, Tianjin Key Laboratory of Metabolic Diseases, Chu Hsien-I Memorial Hospital & Tianjin Institute of Endocrinology, Tianjin Medical University, Tianjin, 300134, China.
| |
Collapse
|
2
|
Oliullah K, Rasel MH, Islam MM, Islam MR, Wadud MAH, Whaiduzzaman M. A stacked ensemble machine learning approach for the prediction of diabetes. J Diabetes Metab Disord 2024; 23:603-617. [PMID: 38932863 PMCID: PMC11196524 DOI: 10.1007/s40200-023-01321-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/06/2023] [Accepted: 09/22/2023] [Indexed: 06/28/2024]
Abstract
Objectives Diabetes has become a leading cause of mortality in both developed and developing countries, impacting a growing number of individuals worldwide. As the prevalence of the disease continues to rise, researchers have diligently worked towards developing accurate diabetes prediction models. The primary aim of this study is to utilize a diverse set of machine learning algorithms to detect the presence of diabetes, particularly in females, at an early stage. By leveraging these methods, this research seeks to provide physicians with valuable tools to identify the disease early, enabling timely interventions and improving patient outcomes. Methods In this study, some state-of-the-art machine learning techniques, such as random forest classifiers with gridsearchCV, XGBoost, NGBoost, Bagging, LightGBM, and AdaBoost classifiers, were employed. These models were chosen as the base layer of our proposed stacked ensemble model because of their high accuracy. Before feeding the data into the models, the dataset was preprocessed to ensure optimal performance and obtain improved results. Results The accuracy achieved in this study was 92.91%, which demonstrates its competitiveness with the existing approaches. Moreover, the utilization of the Shapley additive explanation (SHAP) facilitated the interpretation of machine learning models. Conclusion We anticipate that these findings will be beneficial to healthcare providers, stakeholders, students, and researchers involved in diabetes prediction research and development.
Collapse
Affiliation(s)
- Khondokar Oliullah
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh
| | - Mahedi Hasan Rasel
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh
| | - Md. Manzurul Islam
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh
| | - Md. Reazul Islam
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh
| | - Md. Anwar Hussen Wadud
- Department of Computer Science and Engineering, Bangladesh University of Business and Technology, Dhaka, Bangladesh
| | - Md. Whaiduzzaman
- School of Information Systems, Queensland University of Technology, Brisbane, Australia
| |
Collapse
|
3
|
Wu S, Wang H, Pan D, Guo J, Zhang F, Ning Y, Gu Y, Guo L. Navigating the future of diabetes: innovative nomogram models for predicting all-cause mortality risk in diabetic nephropathy. BMC Nephrol 2024; 25:127. [PMID: 38600468 PMCID: PMC11008048 DOI: 10.1186/s12882-024-03563-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/29/2024] [Accepted: 03/26/2024] [Indexed: 04/12/2024] Open
Abstract
OBJECTIVE This study aims to establish and validate a nomogram model for the all-cause mortality rate in patients with diabetic nephropathy (DN). METHODS We analyzed data from the National Health and Nutrition Examination Survey (NHANES) spanning from 2007 to 2016. A random split of 7:3 was performed between the training and validation sets. Utilizing follow-up data until December 31, 2019, we examined the all-cause mortality rate. Cox regression models and Least Absolute Shrinkage and Selection Operator (LASSO) regression models were employed in the training cohort to develop a nomogram for predicting all-cause mortality in the studied population. Finally, various validation methods were employed to assess the predictive performance of the nomogram, and Decision Curve Analysis (DCA) was conducted to evaluate the clinical utility of the nomogram. RESULTS After the results of LASSO regression models and Cox multivariate analyses, a total of 8 variables were selected, gender, age, poverty income ratio, heart failure, body mass index, albumin, blood urea nitrogen and serum uric acid. A nomogram model was built based on these predictors. The C-index values in training cohort of 3-year, 5-year, 10-year mortality rates were 0.820, 0.807, and 0.798. In the validation cohort, the C-index values of 3-year, 5-year, 10-year mortality rates were 0.773, 0.788, and 0.817, respectively. The calibration curve demonstrates satisfactory consistency between the two cohorts. CONCLUSION The newly developed nomogram proves to be effective in predicting the all-cause mortality risk in patients with diabetic nephropathy, and it has undergone robust internal validation.
Collapse
Affiliation(s)
- Sensen Wu
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China
| | - Hui Wang
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China
| | - Dikang Pan
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China
| | - Julong Guo
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China
| | - Fan Zhang
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China
| | - Yachan Ning
- Department of Intensive Care Medicine, Xuanwu Hospital, Capital Medical University, Beijing, China
| | - Yongquan Gu
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China.
| | - Lianrui Guo
- Department of Vascular Surgery, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, China.
| |
Collapse
|
4
|
Kanbour S, Harris C, Lalani B, Wolf RM, Fitipaldi H, Gomez MF, Mathioudakis N. Machine Learning Models for Prediction of Diabetic Microvascular Complications. J Diabetes Sci Technol 2024; 18:273-286. [PMID: 38189280 PMCID: PMC10973856 DOI: 10.1177/19322968231223726] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/09/2024]
Abstract
IMPORTANCE AND AIMS Diabetic microvascular complications significantly impact morbidity and mortality. This review focuses on machine learning/artificial intelligence (ML/AI) in predicting diabetic retinopathy (DR), diabetic kidney disease (DKD), and diabetic neuropathy (DN). METHODS A comprehensive PubMed search from 1990 to 2023 identified studies on ML/AI models for diabetic microvascular complications. The review analyzed study design, cohorts, predictors, ML techniques, prediction horizon, and performance metrics. RESULTS Among the 74 identified studies, 256 featured internally validated ML models and 124 had externally validated models, with about half being retrospective. Since 2010, there has been a rise in the use of ML for predicting microvascular complications, mainly driven by DKD research across 27 countries. A more modest increase in ML research on DR and DN was observed, with publications from fewer countries. For all microvascular complications, predictive models achieved a mean (standard deviation) c-statistic of 0.79 (0.09) on internal validation and 0.72 (0.12) on external validation. Diabetic kidney disease models had the highest discrimination, with c-statistics of 0.81 (0.09) on internal validation and 0.74 (0.13) on external validation, respectively. Few studies externally validated prediction of DN. The prediction horizon, outcome definitions, number and type of predictors, and ML technique significantly influenced model performance. CONCLUSIONS AND RELEVANCE There is growing global interest in using ML for predicting diabetic microvascular complications. Research on DKD is the most advanced in terms of publication volume and overall prediction performance. Both DR and DN require more research. External validation and adherence to recommended guidelines are crucial.
Collapse
Affiliation(s)
| | - Catharine Harris
- Division of Endocrinology, Diabetes,
& Metabolism, Johns Hopkins University School of Medicine, Baltimore, MD,
USA
| | - Benjamin Lalani
- Division of Endocrinology, Diabetes,
& Metabolism, Johns Hopkins University School of Medicine, Baltimore, MD,
USA
| | - Risa M. Wolf
- Division of Pediatric Endocrinology,
Johns Hopkins University School of Medicine, Baltimore, MD, USA
| | - Hugo Fitipaldi
- Department of Clinical Sciences, Lund
University Diabetes Centre, Lund University, Malmö, Sweden
| | - Maria F. Gomez
- Department of Clinical Sciences, Lund
University Diabetes Centre, Lund University, Malmö, Sweden
| | - Nestoras Mathioudakis
- Division of Endocrinology, Diabetes,
& Metabolism, Johns Hopkins University School of Medicine, Baltimore, MD,
USA
| |
Collapse
|
5
|
Huang AA, Huang SY. Increasing transparency in machine learning through bootstrap simulation and shapely additive explanations. PLoS One 2023; 18:e0281922. [PMID: 36821544 PMCID: PMC9949629 DOI: 10.1371/journal.pone.0281922] [Citation(s) in RCA: 12] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/23/2022] [Accepted: 02/05/2023] [Indexed: 02/24/2023] Open
Abstract
Machine learning methods are widely used within the medical field. However, the reliability and efficacy of these models is difficult to assess, making it difficult for researchers to identify which machine-learning model to apply to their dataset. We assessed whether variance calculations of model metrics (e.g., AUROC, Sensitivity, Specificity) through bootstrap simulation and SHapely Additive exPlanations (SHAP) could increase model transparency and improve model selection. Data from the England National Health Services Heart Disease Prediction Cohort was used. After comparison of model metrics for XGBoost, Random Forest, Artificial Neural Network, and Adaptive Boosting, XGBoost was used as the machine-learning model of choice in this study. Boost-strap simulation (N = 10,000) was used to empirically derive the distribution of model metrics and covariate Gain statistics. SHapely Additive exPlanations (SHAP) to provide explanations to machine-learning output and simulation to evaluate the variance of model accuracy metrics. For the XGBoost modeling method, we observed (through 10,000 completed simulations) that the AUROC ranged from 0.771 to 0.947, a difference of 0.176, the balanced accuracy ranged from 0.688 to 0.894, a 0.205 difference, the sensitivity ranged from 0.632 to 0.939, a 0.307 difference, and the specificity ranged from 0.595 to 0.944, a 0.394 difference. Among 10,000 simulations completed, we observed that the gain for Angina ranged from 0.225 to 0.456, a difference of 0.231, for Cholesterol ranged from 0.148 to 0.326, a difference of 0.178, for maximum heart rate (MaxHR) ranged from 0.081 to 0.200, a range of 0.119, and for Age ranged from 0.059 to 0.157, difference of 0.098. Use of simulations to empirically evaluate the variability of model metrics and explanatory algorithms to observe if covariates match the literature are necessary for increased transparency, reliability, and utility of machine learning methods. These variance statistics, combined with model accuracy statistics can help researchers identify the best model for a given dataset.
Collapse
Affiliation(s)
- Alexander A. Huang
- Department of Statistics and Data Science, Cornell University, Ithaca, New York, United States of America
- Department of MD Education, Northwestern University Feinberg School of Medicine, Chicago, Illinois, United States of America
| | - Samuel Y. Huang
- Department of Statistics and Data Science, Cornell University, Ithaca, New York, United States of America
- Department of Internal Medicine, Virginia Commonwealth University School of Medicine, Richmond, Virginia, United States of America
| |
Collapse
|