Detection of Lower Albuminuria Levels and Early Development of Diabetic Kidney Disease Using an Artificial Intelligence-Based Rule Extraction Approach

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.

The automatic detection of diabetic kidney disease from retinal vascular parameters combined with clinical variables using artificial intelligence in type-2 diabetes patients

BACKGROUND

Diabetic kidney disease (DKD) has become the largest cause of end-stage kidney disease. Early and accurate detection of DKD is beneficial for patients. The present detection depends on the measurement of albuminuria or the estimated glomerular filtration rate, which is invasive and not optimal; therefore, new detection tools are urgently needed. Meanwhile, a close relationship between diabetic retinopathy and DKD has been reported; thus, we aimed to develop a novel detection algorithm for DKD using artificial intelligence technology based on retinal vascular parameters combined with several easily available clinical parameters in patients with type-2 diabetes.

METHODS

A total of 515 consecutive patients with type-2 diabetes mellitus from Xiangyang Central Hospital were included. Patients were stratified by DKD diagnosis and split randomly into either the training set (70%, N = 360) or the testing set (30%, N = 155) (random seed = 1). Data from the training set were used to develop the machine learning algorithm (MLA), while those from the testing set were used to validate the MLA. Model performances were evaluated.

RESULTS

The MLA using the random forest classifier presented optimal performance compared with other classifiers. When validated, the accuracy, sensitivity, specificity, F1 score, and AUC for the optimal model were 84.5%(95% CI 83.3-85.7), 84.5%(82.3-86.7), 84.5%(82.7-86.3), 0.845(0.831-0.859), and 0.914(0.903-0.925), respectively.

CONCLUSIONS

A new machine learning algorithm for DKD diagnosis based on fundus images and 8 easily available clinical parameters was developed, which indicated that retinal vascular changes can assist in DKD screening and detection.

Diabetic Nephropathy: Pathogenesis to Cure

Diabetic nephropathy (DN) is a leading cause of end-stage renal disorder (ESRD). It is defined as the increase in urinary albumin excretion (UAE) when no other renal disease is present. DN is categorized into microalbuminuria and macroalbuminuria. Factors like high blood pressure, high blood sugar levels, genetics, oxidative stress, hemodynamic and metabolic changes affect DN. Hyperglycemia causes renal damage through activating protein kinase C (PKC), producing advanced end glycation products (AGEs) and reactive oxygen species (ROS). Growth factors, chemokines, cell adhesion molecules, inflammatory cytokines are found to be elevated in the renal tissues of the diabetic patient. Many different and new diagnostic methods and treatment options are available due to the increase in research efforts and progression in medical science. However, until now, no permanent cure is available. This article aims to explore the mechanism, diagnosis, and therapeutic strategies in current use for increasing the understanding of DN.

Comparison of Different Machine Learning Techniques to Predict Diabetic Kidney Disease

Background

Diabetic kidney disease (DKD), one of the complications of diabetes in patients, leads to progressive loss of kidney function. Timely intervention is known to improve outcomes. Therefore, screening patients to identify high-risk populations is important. Machine learning classification techniques can be applied to patient datasets to identify high-risk patients by building a predictive model.

Objective

This study aims to identify a suitable classification technique for predicting DKD by applying different classification techniques to a DKD dataset and comparing their performance using WEKA machine learning software.

Methods

The performance of nine different classification techniques was analyzed on a DKD dataset with 410 instances and 18 attributes. Data preprocessing was carried out using the PartitionMembershipFilter. A 10-fold cross validation was performed on the dataset. The performance was assessed on the basis of the execution time, accuracy, correctly and incorrectly classified instances, kappa statistics (K), mean absolute error, root mean squared error, and true values of the confusion matrix.

Results

With an accuracy of 93.6585% and a higher K value (0.8731), IBK and random tree classification techniques were found to be the best performing techniques. Moreover, they also exhibited the lowest root mean squared error rate (0.2496). There were 15 false-positive instances and 11 false-negative instances with these prediction models.

Conclusions

This study identified IBK and random tree classification techniques as the best performing classifiers and accurate prediction methods for DKD.

Chronic Kidney Disease Testing Among Primary Care Patients With Type 2 Diabetes Across 24 U.S. Health Care Organizations

OBJECTIVE

Clinical guidelines for people with diabetes recommend chronic kidney disease (CKD) testing at least annually using estimated glomerular filtration rate (eGFR) and urinary albumin-to-creatinine ratio (uACR). We aimed to understand CKD testing among people with type 2 diabetes in the U.S.

RESEARCH DESIGN AND METHODS

Electronic health record data were analyzed from 513,165 adults with type 2 diabetes receiving primary care from 24 health care organizations and 1,164 clinical practice sites. We assessed the percentage of patients with both one or more eGFRs and one or more uACRs and each test individually in the 1, 2, and 3 years ending September 2019 by health care organization and clinical practice site. Elevated albuminuria was defined as uACR ≥30 mg/g.

RESULTS

The 1-year median testing rate across organizations was 51.6% for both uACR and eGFR, 89.5% for eGFR, and 52.9% for uACR. uACR testing varied (10th-90th percentile) from 44.7 to 63.3% across organizations and from 13.3 to 75.4% across sites. Over 3 years, the median testing rate for uACR across organizations was 73.7%. Overall, the prevalence of detected elevated albuminuria was 15%. The average prevalence of detected elevated albuminuria increased linearly with uACR testing rates at sites, with estimated prevalence of 6%, 15%, and 30% at uACR testing rates of 20%, 50%, and 100%, respectively.

CONCLUSIONS

While eGFR testing rates are uniformly high among people with type 2 diabetes, testing rates for uACR are suboptimal and highly variable across and within the organizations examined. Guideline-recommended uACR testing should increase detection of CKD.

Use of an artificial intelligence-based rule extraction approach to predict an emergency cesarean section

Objective

One of the major problems with artificial intelligence (AI) is that it is generally known as a “black box”. Therefore, the present study aimed to construct an emergency cesarean section (CS) prediction system using an AI‐based rule extraction approach as a “white box” to detect the cause for the emergency CS.

Methods

Data were collected from all perinatal records of all delivery outcomes at Osaka Medical College between December 2014 and July 2019. We identified the delivery method for all deliveries after 36 gestational weeks as either (1) vaginal delivery or scheduled CS, or (2) emergency CS. From among these, we selected 52 risk factors to feed into an AI‐based rule extraction algorithm to extract rules to predict an emergency CS.

Results

We identified 1513 singleton deliveries (1285 [84.9%] vaginal deliveries, 228 emergency CS [15.1%]) and extracted 15 rules. We achieved an average accuracy of 81.90% using five‐fold cross‐validation and an area under the receiving operating characteristic curve of 71.46%.

Conclusion

To our knowledge, this is the first study to use interpretable AI‐based rule extraction technology to predict an emergency CS. This system appears to be useful for identifying hidden factors for emergency CS.

This is the first study to construct a prediction system for an emergency cesarean section using an artificial intelligence‐based “white box” rule extraction approach.

Poor Glycemic Control Can Increase the Plasma Kidney Injury Molecule-1 Concentration in Normoalbuminuric Children and Adolescents with Diabetes Mellitus

Diabetic nephropathy (DN) is a serious microvascular complication in childhood diabetes and microalbuminuria has been a solid indicator in the assessment of DN. Nevertheless, renal injury may still occur in the presence of normoalbuminuria (NA) and various tubular injury biomarkers have been proposed to assess such damage. This case-controlled study aimed to evaluate plasma and urinary neutrophil gelatinase-associated lipocalin and kidney injury molecule-1 (KIM-1) levels in diabetic children particularly in those with normo- and high-NA stages and determine their role in predicting DN. Fifty-four children/adolescents with type 1 and 2 diabetes and forty-four controls aged 7–18 years were included. The baseline clinical and laboratory characteristics including plasma and urinary biomarkers were compared. The plasma KIM-1 levels were significantly higher in diabetic children than in the controls and in high-NA children than normo-NA children. Glycosylated hemoglobin (HbA1c) was identified as a significant risk factor for increased plasma KIM-1. The optimal cutoff for HbA1c when the plasma KIM-1 was > 23.10 pg/mL was 6.75% with an area under the curve of 0.77. For diabetic children with mildly increased albuminuria, the plasma KIM-1 complementary to MA may help increase the yield of detecting DN. Our findings also suggested an HbA1c cutoff of 6.75% correlated with increased plasma KIM-1.

The evolution and future of diabetic kidney disease research: a bibliometric analysis

BACKGROUND

Diabetic kidney disease (DKD) is one of the most important complications of diabetic mellitus. It is essential for nephrologists to understand the evolution and development trends of DKD.

METHODS

Based on the total cited numbers in the Web of Science Core Collection, which was searched through September 28th, 2020, we performed a bibliometric analysis of the top 100 most cited full-length original articles on the subject of DKD. The timespans, authors, contributions, subcategories, and topics of those 100 articles were analysed. In addition, the evolution of topics in DKD research was investigated.

RESULTS

There were 23,968 items under the subject of DKD in the Web of Science Core Collection. The top 100 cited articles, published from 1999 to 2017, were cited 38,855 times in total. Researchers from the USA contributed the most publications. The number of articles included in 'Experimental studies (EG)', 'Clinical studies (CS)', 'Epidemiological studies (ES)', and 'Pathological and pathophysiological studies (PP)' were 65, 26, 7, and 2, respectively. Among the 15 topics, the most popular topic is the renin-angiotensin-aldosterone system (RAAS), occurring in 26 articles, including 6 of the top 10 most cited articles. The evolution of topics reveals that the role of RAAS inhibitor is a continuous hotspot, and sodium-glucose cotransporter 2 (SGLT-2) inhibitor and glucagon-like peptide 1 (GLP-1) agonist are two renoprotective agents which represent novel therapeutic methods in DKD. In addition, the 26 clinical studies among the top 100 most cited articles were highlighted, as they help guide clinical practice to better serve patients.

CONCLUSIONS

This bibliometric analysis of the top 100 most cited articles revealed important studies, popular topics, and trends in DKD research to assist researchers in further understanding the subject.