Current progress in artificial intelligence-assisted medical image analysis for chronic kidney disease: A literature review

Development and validation of multi-center serum creatinine-based models for noninvasive prediction of kidney fibrosis in chronic kidney disease

OBJECTIVE

Kidney fibrosis is a key pathological feature in the progression of chronic kidney disease (CKD), traditionally diagnosed through invasive kidney biopsy. This study aimed to develop and validate a noninvasive, multi-center predictive model incorporating machine learning (ML) for assessing kidney fibrosis severity using biochemical markers.

METHODS

This multi-center retrospective study included 598 patients with kidney fibrosis from four hospitals. A training cohort of 360 patients from Shanghai Tongji Hospital was used to develop a predictive nomogram and ML model, with fibrosis severity classified as mild or moderate-to-severe based on Banff scores. Logistic regression identified key predictors, which were incorporated into a nomogram and ML model. An external validation cohort of 238 patients from three additional hospitals was used for model evaluation.

RESULTS

Serum creatinine (Scr), estimated glomerular filtration rate (eGFR), parathyroid hormone (PTH), brain natriuretic peptide (BNP), and sex were identified as independent predictors of kidney fibrosis severity. The nomogram demonstrated superior discriminative ability in the training cohort (AUC: 0.89, 95% CI: 0.85-0.92) compared to eGFR (AUC: 0.83, 95% CI: 0.78-0.87) and Scr (AUC: 0.87, 95% CI: 0.83-0.91). Among ML models, the Random Forest (RF) model achieved the highest AUC (0.98). In external validation, the nomogram and RF models maintained robust performance with AUCs of 0.86 and 0.79, respectively.

CONCLUSION

This study presents a validated, noninvasive, multi-center Scr-based machine learning model for assessing kidney fibrosis severity in CKD. The integration of a clinical nomogram and ML approach offers a novel, practical alternative to biopsy for dynamic fibrosis evaluation.

A population based optimization of convolutional neural networks for chronic kidney disease prediction

Chronic kidney disease (CKD) is a global public health concern, and the timely detection of the disease is priceless. Most of the classical machine learning models have the major drawbacks of being unsophisticated, non-robust, and non-accurate. This research work is therefore seeking to introduce OptiNet-CKD, a paradigm based on a DNN that has been integrated with a developed population optimization algorithm (POA) for CKD prediction optimization. POA is unlike gradient-based optimization methods in that it uses an initialized population of networks and perturbs their weight values to provide a broader exploration of the solution space. The model is more robust and less likely to overfit, and the predictions are likely to be more accurate since this approach helps to avoid the local minima problem suffered by gradient-based optimizers. To preprocess it for DNN learning, a CKD dataset with 400 records containing numerical and categorical features was imputed for missing data and scaled for its features. The model was evaluated using performance metrics such as accuracy, precision, recall, F1-score, and ROC AUC. OptiNet-CKD achieved 100% accuracy, 1.0 precision, 1.0 recall, 1.0 F1-score, and 1.0 ROC-AUC from traditional models (logistic regression, decision trees) and even fundamental deep neural networks. Results show that OptiNet-CKD is a reliable and robust prediction method for CKD, with more substantial generalization and performance than the existing methods. A combination of DNN and POA constitutes a promising approach for medical data analysis, especially for the diagnosis of CKD. POA expands the solution space, helping to expunge the model from falling into local minima and giving the model increased power in generalizing complicated medical data. Based on the simplicity of the algorithm, together with the structured formula and the extractions made in the preprocessing step, this framework can be extended to other medical conditions with similar data complexities, providing a potent tool for improving diagnostic accuracy in healthcare.

Artificial intelligence in chronic kidney disease management: a scoping review

Rationale: Chronic kidney disease (CKD) is a major public health problem worldwide associated with cardiovascular disease, renal failure, and mortality. To effectively address this growing burden, innovative solutions to management are urgently required. We conducted a scoping review to identify key use cases in which artificial intelligence (AI) could be leveraged for improving management of CKD. Additionally, we examined the challenges faced by AI in CKD management, proposed potential solutions to overcome these barriers. Methods: We reviewed 41 articles published between 2014-2024 which examined various AI techniques including machine learning (ML) and deep learning (DL), unsupervised clustering, digital twin, natural language processing (NLP) and large language models (LLMs) in CKD management. We focused on four areas: early detection, risk stratification and prediction, treatment recommendations and patient care and communication. Results: We identified 41 articles published between 2014-2024 that assessed image-based DL models for early detection (n = 6), ML models for risk stratification and prediction (n = 14) and treatment recommendations (n = 4), and NLP and LLMs for patient care and communication (n = 17). Key challenges in integrating AI models into healthcare include technical issues such as data quality and access, model accuracy, and interpretability, alongside adoption barriers like workflow integration, user training, and regulatory approval. Conclusions: There is tremendous potential of integrating AI into clinical care of CKD patients to enable early detection, prediction, and improved patient outcomes. Collaboration among healthcare providers, researchers, regulators, and industries is crucial to developing robust protocols that ensure compliance with legal standards, while minimizing risks and maintaining patient safety.

Combining artificial intelligence assisted image segmentation and ultrasound based radiomics for the prediction of carotid plaque stability

PURPOSE

Utilizing artificial intelligence (AI) technology for the segmentation of plaques on ultrasound images to evaluate the stability of carotid artery plaques and analyze its diagnostic accuracy in differentiating vulnerable plaques from stable ones.

METHODS

A retrospective study was conducted on 202 patients with ischemic stroke, who were divided into vulnerable plaque group (85 cases) and stable plaque group (117 cases) based on the results of carotid color Doppler ultrasound examination. From the vulnerable plaque group, 63 cases were randomly selected as the modeling group and 22 cases as the validation group; similarly, from the stable plaque group, 87 cases were randomly selected as the modeling group and 30 cases as the validation group. Based on the ultrasound images of the modeling group, plaques were segmented using artificial intelligence technology, and 1414 radiomics features were extracted. These features were then subjected to dimensionality reduction and feature selection using the least absolute shrinkage and selection operator (LASSO) method. Subsequently, a Support Vector Machine (SVM) model was constructed and validated using the selected features. The sensitivity, specificity, and Area Under the Curve (AUC) of the model were evaluated through the analysis of the receiver operating characteristic (ROC) curve.

RESULTS

A total of 43 radiomics feature parameters were selected by the LASSO method. The training group for the SVM model had an AUC of 89.42% (95% CI: 80.74-98.10%), sensitivity of 79.84%, and specificity of 93.10%, while the validation group had an AUC of 82.73% (95% CI: 71.64-93.81%), sensitivity of 81.82%, and specificity of 80.00%.

CONCLUSION

The use of artificial intelligence technology for the segmentation of plaques in ultrasound images, coupled with the analysis of radiomics models, can efficiently distinguish the stability of carotid artery plaques, providing a diagnostic basis for the clinical prediction of ischemic stroke.

CLINICAL TRIAL NUMBER

Not applicable.

Using machine learning models for predicting monthly iPTH levels in hemodialysis patients

BACKGROUND AND OBJECTIVE

Intact parathyroid hormone (iPTH), also known as active parathyroid hormone, is an important indicator commonly for monitoring secondary hyperparathyroidism (SHPT) in patients undergoing hemodialysis. The aim of this study was to use machine learning (ML) models to predict monthly iPTH levels in patients undergoing hemodialysis.

METHODS

We conducted a retrospective study on patients undergoing regular hemodialysis. Patients' blood examinations data was collected from Taiwan Society of Nephrology - Kidney Dialysis, Transplantation (TSN-KiDiT) registration system, and patients' medications data was collected from Pingtung Christian Hospital (PTCH), Taiwan. We used five different ML models to classify patients into three distinct categories based on their iPTH levels: iPTH < 150, iPTH ≥ 150 & iPTH < 600, and iPTH ≥ 600(pg/ml).

RESULTS

We ultimately included 1,351 patients in our study and processed the data in four different ways. These methods varied based on the duration of the data (either using data from just one month or continuously over three months) and the number of features used (either all 52 features or only 20 most important features identified by SHapley Additive exPlanations (SHAP) analysis). The XGBoost model, using data from a continuous three-month period and all available features, yielded the best Weighted AUROC (0.922).

CONCLUSIONS

ML is highly effective in predicting iPTH levels in hemodialysis patients, notably accurate for those with iPTH over 600 pg/ml. This method enables early identification of high-risk patients, reducing reliance on retrospective blood test assessments. Future research should focus on advancing explainable AI methods to foster clinicians' trust, and developing adaptable ML frameworks that could seamlessly integrate with existing healthcare systems.

A recursive embedding and clustering technique for unraveling asymptomatic kidney disease using laboratory data and machine learning

Traditional methods for diagnosing chronic kidney disease (CKD) via laboratory data may not be capable of identifying early kidney disease. Kidney biopsy is unsuitable for regular screening, and imaging tests are costly and time-consuming. Several studies have implemented artificial intelligence (AI) to detect CKD. However, these studies used small datasets, had overfitting problems, lacked generalizability, or used complex algorithms that may require additional computational resources. In this study, we collected and analyzed center-based data and used a recursive embedding and clustering technique to reduce their dimensionality. We identified three clusters from 1600 records. We focused on the second cluster, as most of the characteristics had values in the normal ranges. Normal range values for most indicators generally represent stable kidney function with minor signs of strain, which often remain asymptomatic. Creatinine and eGFR levels within the threshold ranges indicate early kidney stress without filtration issues, which require close monitoring. The gradient-boosting algorithm showed superior performance among all algorithms in detecting these clusters. We evaluated an additional 400 unlabeled records to validate our method. This research can help clinicians automatically detect initial signs in numerous patients via routine tests to prevent the consequences of late-stage CKD detection.

Usefulness of Radiomics and Kidney Volume Based on Non-Enhanced Computed Tomography in Chronic Kidney Disease: Initial Report

INTRODUCTION

Chronic kidney disease (CKD) is classified according to the estimated glomerular filtration rate (eGFR), but kidney volume (KV) can also provide meaningful information. Very few radiomics (RDX) studies on CKD have utilized computed tomography (CT). This study aimed to determine whether non-enhanced computed tomography (NECT)-based RDX can be useful in evaluation of patients with CKD and to compare it with KV.

METHODS

The NECT scans of 64 subjects with impaired kidney function (defined as <60 mL/min/1.73 m2) and 60 controls with normal kidney function were retrospectively analyzed. Kidney segmentations, volume measurements, and RDX features extraction were performed. Machine-learning models using RDX were constructed to classify the kidneys as having structural markers of impaired or normal function.

RESULTS

The median KV in the impaired kidney function group was 114.83 mL vs. 159.43 mL (p < 0.001) in the control group. There was a statistically significant strong positive correlation between KV and eGFR (rs = 0.579, p < 0.001) and a strong negative correlation between KV and serum creatinine level (rs = -0.514, p < 0.001). The KV-based models achieved the best area under the curve (AUC) of 0.746, whereas the RDX-based models achieved the best AUC of 0.878.

CONCLUSIONS

RDX can be useful in identifying patients with impaired kidney function on NECT. RDX-based models outperformed KV-based models. RDX has the potential to identify patients with a higher risk of CKD based on imaging, which, as we believe, can indirectly support clinical decision-making.

Artificial Intelligence to Diagnose Complications of Diabetes

Artificial intelligence (AI) is increasingly being used to diagnose complications of diabetes. Artificial intelligence is technology that enables computers and machines to simulate human intelligence and solve complicated problems. In this article, we address current and likely future applications for AI to be applied to diabetes and its complications, including pharmacoadherence to therapy, diagnosis of hypoglycemia, diabetic eye disease, diabetic kidney diseases, diabetic neuropathy, diabetic foot ulcers, and heart failure in diabetes.Artificial intelligence is advantageous because it can handle large and complex datasets from a variety of sources. With each additional type of data incorporated into a clinical picture of a patient, the calculation becomes increasingly complex and specific. Artificial intelligence is the foundation of emerging medical technologies; it will power the future of diagnosing diabetes complications.

Noninvasive diagnosis of interstitial fibrosis in chronic kidney disease: a systematic review and meta-analysis

RATIONALE AND OBJECTIVES

Researchers have delved into noninvasive diagnostic methods of renal fibrosis (RF) in chronic kidney disease, including ultrasound (US), magnetic resonance imaging (MRI), and radiomics. However, the value of these diagnostic methods in the noninvasive diagnosis of RF remains contentious. Consequently, the present study aimed to systematically delineate the accuracy of the noninvasive diagnosis of RF.

MATERIALS AND METHODS

A systematic search covering PubMed, Embase, Cochrane Library, and Web of Science databases for all data available up to 28 July 2023 was conducted for eligible studies.

RESULTS

We included 21 studies covering 4885 participants. Among them, nine studies utilized US as a noninvasive diagnostic method, eight studies used MRI, and four articles employed radiomics. The sensitivity and specificity of US for detecting RF were 0.81 (95% CI: 0.76-0.86) and 0.79 (95% CI: 0.72-0.84). The sensitivity and specificity of MRI were 0.77 (95% CI: 0.70-0.83) and 0.92 (95% CI: 0.85-0.96). The sensitivity and specificity of radiomics were 0.69 (95% CI: 0.59-0.77) and 0.78 (95% CI: 0.68-0.85).

CONCLUSIONS

The current early noninvasive diagnostic methods for RF include US, MRI, and radiomics. However, this study demonstrates that US has a higher sensitivity for the detection of RF compared to MRI. Compared to US, radiomics studies based on US did not show superior advantages. Therefore, challenges still exist in the current radiomics approaches for diagnosing RF, and further exploration of optimized artificial intelligence (AI) algorithms and technologies is needed.

Artificial intelligence in predicting chronic kidney disease prognosis. A systematic review and meta-analysis

BACKGROUND

Chronic kidney disease (CKD) is a common condition that can lead to serious health complications. Artificial Intelligence (AI) has shown the potential to improve the prediction of CKD progression, offering increased accuracy over traditional methods. Therefore, this systematic review and meta-analysis examine the diagnostic performance of various AI models in predicting CKD.

METHOD

Search was performed in different databases for studies reporting the diagnostic accuracy of AI-based prediction models for the progression of CKD. Meanwhile, pre-defined eligibility criteria were used for the selection of studies. Pooled sensitivity, specificity, and area under curve (AUC) were calculated utilizing Meta-disc 1.4. Quality assessment was performed using the prediction model risk of bias assessment tool (PROBAST).

RESULTS

A total of 33 studies were included. The pooled sensitivity of prediction tools was 0.43 (95% CI, 0.41-0.44, I2 = 99.3%, p < 0.01). A significant difference (p < 0.01) was also observed in the pooled specificity 0.92 (95% CI, 0.91-0.92, I2 = 99.5%). Positive likelihood ratio (PLP) and negative likelihood ratio (NLR) were 5.12 (95% CI: 3.60-7.27, I2 = 91.3%, p < 0.01) and 0.28 (95% CI: 0.21-0.37, I2 = 99.3%, p < 0.01), respectively and AUC was 0.89, suggesting a diagnostic accuracy of AI-based prediction models for the progression of CKD.

CONCLUSIONS

This study demonstrates the promising potential of AI models in predicting CKD progression. However, further efforts are needed to optimize model performance, particularly in balancing sensitivity and specificity to ensure generalizability across diverse populations. Limitations of this study include the potential for overfitting in certain AI models due to imbalanced datasets. The high heterogeneity and the lack of standardized predictors limit the generalizability of findings across different populations.

Deep Learning-Based Automated Imaging Classification of ADPKD

Introduction

The Mayo imaging classification model (MICM) requires a prestep qualitative assessment to determine whether a patient is in class 1 (typical) or class 2 (atypical), where patients assigned to class 2 are excluded from the MICM application.

Methods

We developed a deep learning-based method to automatically classify class 1 and 2 from magnetic resonance (MR) images and provide classification confidence utilizing abdominal T 2 -weighted MR images from 486 subjects, where transfer learning was applied. In addition, the explainable artificial intelligence (XAI) method was illustrated to enhance the explainability of the automated classification results. For performance evaluations, confusion matrices were generated, and receiver operating characteristic curves were drawn to measure the area under the curve.

Results

The proposed method showed excellent performance for the classification of class 1 (97.7%) and 2 (100%), where the combined test accuracy was 98.01%. The precision and recall for predicting class 1 were 1.00 and 0.98, respectively, with F 1 -score of 0.99; whereas those for predicting class 2 were 0.87 and 1.00, respectively, with F 1 -score of 0.93. The weighted averages of precision and recall were 0.98 and 0.98, respectively, showing the classification confidence scores whereas the XAI method well-highlighted contributing regions for the classification.

Conclusion

The proposed automated method can classify class 1 and 2 cases as accurately as the level of a human expert. This method may be a useful tool to facilitate clinical trials investigating different types of kidney morphology and for clinical management of patients with autosomal dominant polycystic kidney disease (ADPKD).

Evaluating ChatGPT's efficacy in assessing the safety of non-prescription medications and supplements in patients with kidney disease

Background

This study investigated the efficacy of ChatGPT-3.5 and ChatGPT-4 in assessing drug safety for patients with kidney diseases, comparing their performance to Micromedex, a well-established drug information source. Despite the perception of non-prescription medications and supplements as safe, risks exist, especially for those with kidney issues. The study's goal was to evaluate ChatGPT's versions for their potential in clinical decision-making regarding kidney disease patients.

Method

The research involved analyzing 124 common non-prescription medications and supplements using ChatGPT-3.5 and ChatGPT-4 with queries about their safety for people with kidney disease. The AI responses were categorized as "generally safe," "potentially harmful," or "unknown toxicity." Simultaneously, these medications and supplements were assessed in Micromedex using similar categories, allowing for a comparison of the concordance between the two resources.

Results

Micromedex identified 85 (68.5%) medications as generally safe, 35 (28.2%) as potentially harmful, and 4 (3.2%) of unknown toxicity. ChatGPT-3.5 identified 89 (71.8%) as generally safe, 11 (8.9%) as potentially harmful, and 24 (19.3%) of unknown toxicity. GPT-4 identified 82 (66.1%) as generally safe, 29 (23.4%) as potentially harmful, and 13 (10.5%) of unknown toxicity. The overall agreement between Micromedex and ChatGPT-3.5 was 64.5% and ChatGPT-4 demonstrated a higher agreement at 81.4%. Notably, ChatGPT-3.5's suboptimal performance was primarily influenced by a lower concordance rate among supplements, standing at 60.3%. This discrepancy could be attributed to the limited data on supplements within ChatGPT-3.5, with supplements constituting 80% of medications identified as unknown.

Conclusion

ChatGPT's capabilities in evaluating the safety of non-prescription drugs and supplements for kidney disease patients are modest compared to established drug information resources. Neither ChatGPT-3.5 nor ChatGPT-4 can be currently recommended as reliable drug information sources for this demographic. The results highlight the need for further improvements in the model's accuracy and reliability in the medical domain.

New Challenges in the Diagnosis of Kidney Damage Due to Immune Checkpoint Inhibitors Therapy: An Observational Clinical Study

In recent years, immunotherapy has been postulated as one of the most effective strategies in the fight against cancer. The greatest success in this field has been achieved with the inhibition of molecules involved in slowing down the adaptive immune response by immune checkpoint inhibitors (ICIs). Despite its efficacy, ICI treatment has side effects. Regarding kidney damage, it is estimated that 4.9% of patients treated with ICIs develop renal injury. Furthermore, cancer patients who develop renal dysfunction have a worse prognosis. Current diagnostics are insufficient to predict the underlying renal injury and to identify the type of damage. Our hypothesis is that the renal injury could be subclinical, so the possibility of using new urinary biomarkers could be a useful diagnostic tool that would allow these patients to be managed in a preventive (risk biomarkers) and early (early biomarkers) way and even to clarify whether the renal damage is due to this therapy or to other factors (differential diagnostic biomarkers). A prospective study to validate risk and early and differential biomarkers in patients treated with ICIs is proposed to test this hypothesis. The results derived from this study will improve the clinical practice of cancer treatment with ICIs and therefore the life expectancy and quality of life of patients. Trial Registration: ClinicalTrials.gov, NCT04902846.