Analysis of clinical predictors of kidney diseases in type 2 diabetes patients based on machine learning

Machine learning-based risk predictive models for diabetic kidney disease in type 2 diabetes mellitus patients: a systematic review and meta-analysis

Background

Machine learning (ML) models are being increasingly employed to predict the risk of developing and progressing diabetic kidney disease (DKD) in patients with type 2 diabetes mellitus (T2DM). However, the performance of these models still varies, which limits their widespread adoption and practical application. Therefore, we conducted a systematic review and meta-analysis to summarize and evaluate the performance and clinical applicability of these risk predictive models and to identify key research gaps.

Methods

We conducted a systematic review and meta-analysis to compare the performance of ML predictive models. We searched PubMed, Embase, the Cochrane Library, and Web of Science for English-language studies using ML algorithms to predict the risk of DKD in patients with T2DM, covering the period from database inception to April 18, 2024. The primary performance metric for the models was the area under the receiver operating characteristic curve (AUC) with a 95% confidence interval (CI). The risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST) checklist.

Results

26 studies that met the eligibility criteria were included into the meta-analysis. 25 studies performed internal validation, but only 8 studies conducted external validation. A total of 94 ML models were developed, with 81 models evaluated in the internal validation sets and 13 in the external validation sets. The pooled AUC was 0.839 (95% CI 0.787-0.890) in the internal validation and 0.830 (95% CI 0.784-0.877) in the external validation sets. Subgroup analysis based on the type of ML showed that the pooled AUC for traditional regression ML was 0.797 (95% CI 0.777-0.816), for ML was 0.811 (95% CI 0.785-0.836), and for deep learning was 0.863 (95% CI 0.825-0.900). A total of 26 ML models were included, and the AUCs of models that were used three or more times were pooled. Among them, the random forest (RF) models demonstrated the best performance with a pooled AUC of 0.848 (95% CI 0.785-0.911).

Conclusion

This meta-analysis demonstrates that ML exhibit high performance in predicting DKD risk in T2DM patients. However, challenges related to data bias during model development and validation still need to be addressed. Future research should focus on enhancing data transparency and standardization, as well as validating these models' generalizability through multicenter studies.

Systematic Review Registration

https://inplasy.com/inplasy-2024-9-0038/, identifier INPLASY202490038.

Unveiling the utility of artificial intelligence for prediction, diagnosis, and progression of diabetic kidney disease: an evidence-based systematic review and meta-analysis

OBJECTIVE

The purpose of this study was to conduct a systematic investigation of the potential of artificial intelligence (AI) models in the prediction, detection of diagnostic biomarkers, and progression of diabetic kidney disease (DKD). In addition, we compared the performance of non-logistic regression (LR) machine learning (ML) models to conventional LR prediction models.

METHODS

Until January 30, 2024, a comprehensive literature review was conducted by investigating databases such as Medline (via PubMed) and Cochrane. Research that is inclusive of AI or ML models for the prediction, diagnosis, and progression of DKD was incorporated. The area under the Receiver Operating Characteristic Curve (AUROC) served as the principal outcome metric for assessing model performance. A meta-analysis was performed utilizing MedCalc statistical software to calculate pooled AUROC and assess the performance differences between LR and non-LR models.

RESULTS

A total of 57 studies were included in the meta-analysis. The pooled AUROC of AI or ML model was 0.84 (95% CI = 0.81-0.86, p < 0.0001) for analyzing prediction of DKD, 0.88 (95%CI = 0.84-0.92, p < 0.0001) for detecting diagnostic biomarkers, and 0.80 (95% CI = 0.77-0.82, p < 0.0001) for analyzing progression of DKD. The pooled AUROC of LR and non-LR ML models exhibited no significant differences across all categories (p > 0.05), except for the random forest (RF) model, which displayed a statistically significant increase in predictive accuracy compared to LR for DKD occurrence (p < 0.04).

CONCLUSION

ML models showed solid DKD prediction effectiveness, with pooled AUROC values over 0.8, suggesting good performance. These data demonstrated that non-LR and LR models perform similarly in overall CKD management, but the RF model outperforms the LR model, particularly in predicting the occurrence of DKD. These findings highlight the promise of AI technologies for better DKD management. To improve model reliability, future study should include extended follow-up periods as well as external validation.

Risk prediction models for diabetic nephropathy among type 2 diabetes patients in China: a systematic review and meta-analysis

Objective

This study systematically reviews and meta-analyzes existing risk prediction models for diabetic kidney disease (DKD) among patients with type 2 diabetes, aiming to provide references for scholars in China to develop higher-quality risk prediction models.

Methods

We searched databases including China National Knowledge Infrastructure (CNKI), Wanfang Data, VIP Chinese Science and Technology Journal Database, Chinese Biomedical Literature Database (CBM), PubMed, Web of Science, Embase, and the Cochrane Library for studies on the construction of DKD risk prediction models among type 2 diabetes patients, up until 28 December 2023. Two researchers independently screened the literature and extracted and evaluated information according to a data extraction form and bias risk assessment tool for prediction model studies. The area under the curve (AUC) values of the models were meta-analyzed using STATA 14.0 software.

Results

A total of 32 studies were included, with 31 performing internal validation and 22 reporting calibration. The incidence rate of DKD among patients with type 2 diabetes ranged from 6.0% to 62.3%. The AUC ranged from 0.713 to 0.949, indicating the prediction models have fair to excellent prediction accuracy. The overall applicability of the included studies was good; however, there was a high overall risk of bias, mainly due to the retrospective nature of most studies, unreasonable sample sizes, and studies conducted in a single center. Meta-analysis of the models yielded a combined AUC of 0.810 (95% CI: 0.780-0.840), indicating good predictive performance.

Conclusion

Research on DKD risk prediction models for patients with type 2 diabetes in China is still in its initial stages, with a high overall risk of bias and a lack of clinical application. Future efforts could focus on constructing high-performance, easy-to-use prediction models based on interpretable machine learning methods and applying them in clinical settings.

Registration

This systematic review and meta-analysis was conducted following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement, a recognized guideline for such research.

Systematic review registration

https://www.crd.york.ac.uk/prospero/, identifier CRD42024498015.

Dysregulated coagulation system links to inflammation in diabetic kidney disease

Diabetic kidney disease (DKD) is a significant contributor to end-stage renal disease worldwide. Despite extensive research, the exact mechanisms responsible for its development remain incompletely understood. Notably, patients with diabetes and impaired kidney function exhibit a hypercoagulable state characterized by elevated levels of coagulation molecules in their plasma. Recent studies propose that coagulation molecules such as thrombin, fibrinogen, and platelets are interconnected with the complement system, giving rise to an inflammatory response that potentially accelerates the progression of DKD. Remarkably, investigations have shown that inhibiting the coagulation system may protect the kidneys in various animal models and clinical trials, suggesting that these systems could serve as promising therapeutic targets for DKD. This review aims to shed light on the underlying connections between coagulation and complement systems and their involvement in the advancement of DKD.

Coagulation Function and Type 2 Diabetic Kidney Disease: A Real-World Observational Study

Objectives

Type 2 diabetic kidney disease (DKD), a chronic microvascular complication of diabetes, may exhibit a complex interrelation with coagulation function. This study is aimed at elucidating the association between coagulation function and DKD.

Methods

This was a real-world observational study conducted in Beijing, involving 2,703 participants. All patients with diabetes were classified into two groups, viz., DKD and non-DKD groups. Effect magnitudes are denoted as odds ratios (OR) with a 95% confidence interval (CI). To mitigate potential bias in group comparisons, we employed propensity score matching (PSM).

Results

After adjusting for variables such as age, gender, systolic blood pressure (SBP), hemoglobin A1c (HbA1c), triglyceride (TG), c-reactive protein (CRP), platelet (PLT), and serum albumin (sALB), it was discerned that fibrinogen (FIB) (OR, 95% CI, P: 1.565, 1.289-1.901, <0.001) and fibrinogen degradation products (FDP) (1.203, 1.077-1.344, 0.001) were significantly correlated with an increased risk of DKD. To facilitate clinical applications, a nomogram prediction model was established, demonstrating commendable accuracy for DKD prediction.

Conclusions

Our findings suggest that elevated levels of FIB and FDP serve as potential risk indicators for DKD, and coagulation function may play an important role in the occurrence and development of DKD.

Serum anti-phospholipase A2 receptor antibody in pathological diagnosis of type 2 diabetes mellitus patients with proteinuria

Patients with diabetes mellitus complicated with proteinuria can be diabetic nephropathy (DN), diabetic complicated with non-diabetic kidney disease (NDKD), or DN with NDKD. Among these membranous nephropathy accounted for a large proportion of DN with NDRD. At present, serum anti-phospholipase A2 receptor (PLA2R) antibody is widely used in the diagnosis and evaluation of therapy in idiopathic membranous nephropathy, our study aimed to investigate the diagnostic significance of anti-PLA2R antibody in type 2 diabetes mellitus (T2DM) patients with proteinuria, providing a method for patients with contraindications of kidney biopsy. Eighty-seven T2DM patients with proteinuria who went on kidney biopsy were divided into the DN group, idiopathic membranous nephropathy (IMN) group, and others group according to their pathological results. In our study, 52.87% and 28.74% of patients were found to have IMN and diabetic nephropathy respectively. The levels of anti-PLA2R antibody, total cholesterol, triglyceride, and estimated glomerular filtration rate (eGFR) were higher in the IMN group, while the prevalence of diabetic retinopathy (DR), systolic blood pressure (SBP) and HbA1c were higher in the DN group. For T2DM patients with proteinuria, anti-PLA2R antibody (AUC = 0.904, 95%CI 0.838-0.970) has a high diagnostic value for IMN. The duration of diabetes (OR = 0.798, P = 0.030), eGFR level (OR = 1.030, P = 0.024), and positive anti-PLA2R antibody (OR = 72.727, P < 0.001) favor the diagnosis of IMN, while DR (OR = 50.234, P < 0.001), SBP (OR = 1.041, P = 0.030), and negative anti-PLA2R antibody (OR = 0.008, P  = 0.001) is beneficial to the diagnosis of DN. Our study found that NDKD is not uncommon in patients with T2DM and proteinuria, and IMN was the main pathological type. Positive anti-PLA2R antibody has a strong accuracy in the diagnosis of IMN in patients with T2DM and proteinuria.

The Diagnostic Performance of a Clinical Diagnosis of Diabetic Kidney Disease

BACKGROUND

Diabetic kidney disease (DKD), a common cause of CKD and kidney failure, is usually diagnosed clinically. However, there is little evidence comparing the performance of a clinical diagnosis to biopsy-proven diagnosis.

PURPOSE OF THE STUDY

Diagnostic performance of a clinical diagnosis was determined in a group of patients with diabetes and chronic kidney disease who underwent kidney biopsy after an initial clinical diagnosis.

METHODS

A data analysis of 54 patients who were part of a study cohort for a prospective analysis of cardiovascular and kidney outcomes and who had undergone kidney biopsy after an initial clinical diagnosis of DKD or non-DKD (NDKD) at enrolment was used. We determined the sensitivity, specificity, and positive and negative predictive values of a clinical diagnosis of DKD.

RESULTS

A total of 37 of 43 patients clinically diagnosed with DKD also had biopsy-proven DKD, whilst only 1 of 11 patients who had clinically diagnosed NDKD had biopsy-proven DKD. Sensitivity was 97.4%, specificity was 62.5%, positive predictive value 86%, and negative predictive value 90.9%. Comparable values were obtained when analysis was restricted to those with primary rather than secondary diagnosis of DKD or when restricted to those with only DKD found at biopsy.

CONCLUSION

A clinical diagnosis of DKD has high sensitivity and is unlikely to overlook cases but may lead to overdiagnosis.