Search Results (26)

Artificial Intelligence (AI) is transforming the healthcare field, offering innovative tools for improving the prediction, detection, and management of diseases. In nephrology, AI holds the potential to improve the diagnosis and treatment of kidney diseases, as well as the optimization of renal replacement therapies. In this review, a comprehensive analysis of recent literature works on artificial intelligence applied to nephrology is presented. Two key research areas structure this review. The first section examines AI models used to support early prediction of acute and chronic kidney disease. The second section explores artificial intelligence applications for hemodialytic therapies in renal insufficiency. Most studies reported high accuracy (e.g., accuracy ≥ 90%) in early prediction of kidney diseases, while fewer addressed therapy optimization and complication prevention, typically reporting moderate-to-high performance (e.g., accuracy ≃ 85%). Filling this gap and developing more accessible AI solutions that address all stages of kidney disease would therefore be crucial to support physicians’ decision-making and improve patient care. Full article

Ensuring the reliability of dialysis machines and their components, such as sensors and actuators, is critical for maintaining continuous and safe dialysis treatment for patients with chronic kidney disease. This study investigates the application of Artificial Intelligence for detecting drift in dialysis machine components by comparing a Long Short-Term Memory (LSTM) neural network with a traditional linear regression model. Both models were trained to learn normal patterns from time-dependent signals monitoring the performance of specific components of a dialytic machine, such as a weight loss sensor in the present case, enabling the detection of anomalies related to sensor degradation or failure. Real-world data from multiple clinical cases were used to validate the approach. The LSTM model achieved high reconstruction accuracy on normal signals (most errors < 0.02, maximum ≈ 0.08), and successfully detected anomalies exceeding this threshold in complaint cases, where the model anticipated failures up to five days in advance. On the contrary, the linear regression model was limited to detecting only major deviations. These findings highlighted the advantages of AI-based methods in equipment monitoring, minimizing unplanned downtime, and supporting preventive maintenance strategies within dialysis care. Future work will focus on integrating this model into both clinical and home dialysis settings, aiming to develop a scalable, adaptable, and generalizable solution capable of operating effectively across various conditions. Full article

Intradialytic hypotension (IDH) is a critical complication in patients with chronic kidney disease undergoing dialysis, affecting both patient safety and treatment efficacy. This study examines the application of advanced machine learning techniques, combined with metaheuristic optimization methods, to improve predictive models for intradialytic hypotension (IDH) in hemodialysis patients. Given the critical nature of IDH, which can lead to significant complications during dialysis, the development of effective predictive tools is vital for improving patient safety and outcomes. Dialysis session data from 758 patients collected between January 2016 and October 2019 were analyzed. Particle Swarm Optimization, Grey Wolf Optimizer, Pendulum Search Algorithm, and Whale Optimization Algorithm were employed to reduce the feature space, removing approximately 45% of clinical and analytical variables while maintaining high recall for the minority class of patients experiencing hypotension. Among the evaluated models, the XGBoost classifier showed superior performance, achieving a macro F-score of 0.745 with a recall of 0.756 and a precision of 0.718. These results highlight the effectiveness of the combined approach for early identification of patients at risk for IDH, minimizing false negatives, and improving clinical decision-making in nephrology. Full article

Extracorporeal carbon dioxide removal (ECCO₂R) is an emerging technique designed to reduce carbon dioxide (CO₂) levels in venous blood while enabling lung-protective ventilation or alleviating the work of breathing. Unlike high-flow extracorporeal membrane oxygenation (ECMO), ECCO₂R operates at lower blood flows (0.4–1.5 L/min), making it less invasive, with smaller cannulas and simpler devices. Despite encouraging results in controlling respiratory acidosis, its broader adoption is hindered by complications, including haemolysis, thrombosis, and bleeding. Technological advances, including enhanced membrane design, gas exchange efficiency, and anticoagulation strategies, are essential to improving safety and efficacy. Innovations such as wearable prototypes that adapt CO₂ removal to patient activity and catheter-based systems for lower blood flow are expanding the potential applications of ECCO₂R, including as a bridge-to-lung transplantation and in outpatient settings. Promising experimental approaches include respiratory dialysis, carbonic anhydrase-coated membranes, and electrodialysis to maximise CO₂ removal. Further research is needed to optimise device performance, develop cost-effective systems, and establish standardised protocols for safe clinical implementation. As the technology matures, integration with artificial intelligence (AI) and machine learning may personalise therapy, improving outcomes. Ongoing clinical trials will be pivotal in addressing these challenges, ultimately enhancing the role of ECCO₂R in critical care and its accessibility across healthcare settings. Full article

This study aims to develop a deep learning model to predict peritoneal dialysis (PD) failure within the next three months using data from the preceding three months. Background: PD patients typically perform treatments at home and visit the clinic only once per month, leading to significant gaps in clinical care and increased risks of PD failure, which may necessitate a transition to hemodialysis (HD). Current studies on PD patients largely focus on predicting PD failure, mortality risk, and hospitalization through traditional machine learning methods, with limited application of deep learning for this purpose. Methods: We collected comprehensive patient data, including demographic information, comorbidities, medication history, biochemical test results, dialysis prescriptions, and peritoneal equilibrium test outcomes. After preprocessing, we employed time-series deep learning models to train and make predictions. Results: The model achieved a prediction accuracy of 89% and an AUROC of 92%, outperforming previous methods used for PD failure prediction. Conclusion: This approach not only improves prediction accuracy but also identifies key features that can aid clinicians in developing more precise treatment plans and enhancing patient care. Full article

Objective. To establish a risk prediction model for intradialytic hypotension (IDH) in maintenance hemodialysis (MHD) patients and to analyze the explainability of the risk prediction model. Methods. A total of 2,228,650 hemodialysis records of 1075 MHD patients were selected as the research objects. Thirteen important clinical features including demographic features and clinical features were screened, the blood pressure measured before hemodialysis was collected, then an IDH risk prediction model during hemodialysis was established based on a machine learning algorithm. The contribution of each feature to the risk prediction of IDH was measured based on the Gini evaluation index. The TreeSHAP method was used to provide global and individual explanations for the IDH risk prediction model. Results. Hemodialysis duration, pre-dialysis mean arterial pressure, and pre-dialysis systolic blood pressure were the most important predictive variables for the occurrence of IDH during hemodialysis in MHD patients. The best IDH risk prediction model based on machine learning had an accuracy of 0.92 (95% CI 0.90–0.94) and an AUC of 0.95 (95% CI 0.94–0.96), indicating that machine learning has a good effect on the prediction of IDH during hemodialysis treatment. Our research innovatively achieved IDH risk prediction during the entire hemodialysis period based on blood pressure before the start of hemodialysis and other clinical features, thus enabling the medical team to quickly adjust hemodialysis prescriptions or initiate treatment for timely management and prevention of IDH. Global and individual explanations of the IDH risk prediction model can help hemodialysis medical staff understand the overall prediction mechanism of the model, discover prediction outliers, and identify potential biases or errors in the model. Conclusions. The IDH risk prediction model has definite clinical value in actual hemodialysis treatment. Full article

Background: Low-grade inflammation is a significant component of chronic kidney disease (CKD). Systemic immune inflammation index (SII), a newly defined ratio combining neutrophil, lymphocyte, and platelet counts, has not yet been evaluated in the pediatric CKD population nor in the context of CKD progression or dialysis. Thus, this study aimed to analyze the complete blood cell count (CBC)-driven parameters, including SII, in children with CKD and to assess their potential usefulness in the prediction of the need for chronic dialysis. Methods: A single-center, retrospective study was conducted on 27 predialysis children with CKD stages 4–5 and 39 children on chronic dialysis. The data were analyzed with the artificial intelligence tools. Results: The Random Forest Classifier (RFC) model with the input variables of neutrophil count, mean platelet volume (MPV), and SII turned out to be the best predictor of the progression of pediatric CKD into end-stage kidney disease (ESKD) requiring dialysis. Out of these variables, SII showed the largest share in the prediction of the need for renal replacement therapy. Conclusions: Chronic inflammation plays a pivotal role in the progression of CKD into ESKD. Among CBC-driven ratios, SII seems to be the most useful predictor of the need for chronic dialysis in CKD children. Full article

Longer pre-transplant dialysis duration is known to be associated with worse post-transplant outcomes. Our study aimed to cluster kidney transplant recipients with prolonged dialysis duration before transplant using an unsupervised machine learning approach to better assess heterogeneity within this cohort. We performed consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 5092 kidney transplant recipients who had been on dialysis ≥ 10 years prior to transplant in the OPTN/UNOS database from 2010 to 2019. We characterized each assigned cluster and compared the posttransplant outcomes. Overall, the majority of patients with ≥10 years of dialysis duration were black (52%) or Hispanic (25%), with only a small number (17.6%) being moderately sensitized. Within this cohort, three clinically distinct clusters were identified. Cluster 1 patients were younger, non-diabetic and non-sensitized, had a lower body mass index (BMI) and received a kidney transplant from younger donors. Cluster 2 recipients were older, unsensitized and had a higher BMI; they received kidney transplant from older donors. Cluster 3 recipients were more likely to be female with a higher PRA. Compared to cluster 1, cluster 2 had lower 5-year death-censored graft (HR 1.40; 95% CI 1.16–1.71) and patient survival (HR 2.98; 95% CI 2.43–3.68). Clusters 1 and 3 had comparable death-censored graft and patient survival. Unsupervised machine learning was used to characterize kidney transplant recipients with prolonged pre-transplant dialysis into three clinically distinct clusters with variable but good post-transplant outcomes. Despite a dialysis duration ≥ 10 years, excellent outcomes were observed in most recipients, including those with moderate sensitization. A disproportionate number of minority recipients were observed within this cohort, suggesting multifactorial delays in accessing kidney transplantation. Full article

Kidney cancers are one of the most common malignancies worldwide. Accurate diagnosis is a critical step in the management of kidney cancer patients and is influenced by multiple factors including tumor size or volume, cancer types and stages, etc. For malignant tumors, partial or radical surgery of the kidney might be required, but for clinicians, the basis for making this decision is often unclear. Partial nephrectomy could result in patient death due to cancer if kidney removal was necessary, whereas radical nephrectomy in less severe cases could resign patients to lifelong dialysis or need for future transplantation without sufficient cause. Using machine learning to consider clinical data alongside computed tomography images could potentially help resolve some of these surgical ambiguities, by enabling a more robust classification of kidney cancers and selection of optimal surgical approaches. In this study, we used the publicly available KiTS dataset of contrast-enhanced CT images and corresponding patient metadata to differentiate four major classes of kidney cancer: clear cell (ccRCC), chromophobe (chRCC), papillary (pRCC) renal cell carcinoma, and oncocytoma (ONC). We rationalized these data to overcome the high field of view (FoV), extract tumor regions of interest (ROIs), classify patients using deep machine-learning models, and extract/post-process CT image features for combination with clinical data. Regardless of marked data imbalance, our combined approach achieved a high level of performance (85.66% accuracy, 84.18% precision, 85.66% recall, and 84.92% F1-score). When selecting surgical procedures for malignant tumors (RCC), our method proved even more reliable (90.63% accuracy, 90.83% precision, 90.61% recall, and 90.50% F1-score). Using feature ranking, we confirmed that tumor volume and cancer stage are the most relevant clinical features for predicting surgical procedures. Once fully mature, the approach we propose could be used to assist surgeons in performing nephrectomies by guiding the choices of optimal procedures in individual patients with kidney cancer. Full article

Background: Better understanding of the different phenotypes/subgroups of non-U.S. citizen kidney transplant recipients may help the transplant community to identify strategies that improve outcomes among non-U.S. citizen kidney transplant recipients. This study aimed to cluster non-U.S. citizen kidney transplant recipients using an unsupervised machine learning approach; Methods: We conducted a consensus cluster analysis based on recipient-, donor-, and transplant- related characteristics in non-U.S. citizen kidney transplant recipients in the United States from 2010 to 2019 in the OPTN/UNOS database using recipient, donor, and transplant-related characteristics. Each cluster’s key characteristics were identified using the standardized mean difference. Post-transplant outcomes were compared among the clusters; Results: Consensus cluster analysis was performed in 11,300 non-U.S. citizen kidney transplant recipients and identified two distinct clusters best representing clinical characteristics. Cluster 1 patients were notable for young age, preemptive kidney transplant or dialysis duration of less than 1 year, working income, private insurance, non-hypertensive donors, and Hispanic living donors with a low number of HLA mismatch. In contrast, cluster 2 patients were characterized by non-ECD deceased donors with KDPI <85%. Consequently, cluster 1 patients had reduced cold ischemia time, lower proportion of machine-perfused kidneys, and lower incidence of delayed graft function after kidney transplant. Cluster 2 had higher 5-year death-censored graft failure (5.2% vs. 9.8%; p < 0.001), patient death (3.4% vs. 11.4%; p < 0.001), but similar one-year acute rejection (4.7% vs. 4.9%; p = 0.63), compared to cluster 1; Conclusions: Machine learning clustering approach successfully identified two clusters among non-U.S. citizen kidney transplant recipients with distinct phenotypes that were associated with different outcomes, including allograft loss and patient survival. These findings underscore the need for individualized care for non-U.S. citizen kidney transplant recipients. Full article

Background: Our study aimed to characterize kidney transplant recipients who received high kidney donor profile index (KDPI) kidneys using unsupervised machine learning approach. Methods: We used the OPTN/UNOS database from 2010 to 2019 to perform consensus cluster analysis based on recipient-, donor-, and transplant-related characteristics in 8935 kidney transplant recipients from deceased donors with KDPI ≥ 85%. We identified each cluster’s key characteristics using the standardized mean difference of >0.3. We compared the posttransplant outcomes among the assigned clusters. Results: Consensus cluster analysis identified 6 clinically distinct clusters of kidney transplant recipients from donors with high KDPI. Cluster 1 was characterized by young, black, hypertensive, non-diabetic patients who were on dialysis for more than 3 years before receiving kidney transplant from black donors; cluster 2 by elderly, white, non-diabetic patients who had preemptive kidney transplant or were on dialysis less than 3 years before receiving kidney transplant from older white donors; cluster 3 by young, non-diabetic, retransplant patients; cluster 4 by young, non-obese, non-diabetic patients who received dual kidney transplant from pediatric, black, non-hypertensive non-ECD deceased donors; cluster 5 by low number of HLA mismatch; cluster 6 by diabetes mellitus. Cluster 4 had the best patient survival, whereas cluster 3 had the worst patient survival. Cluster 2 had the best death-censored graft survival, whereas cluster 4 and cluster 3 had the worst death-censored graft survival at 1 and 5 years, respectively. Cluster 2 and cluster 4 had the best overall graft survival at 1 and 5 years, respectively, whereas cluster 3 had the worst overall graft survival. Conclusions: Unsupervised machine learning approach kidney transplant recipients from donors with high KDPI based on their pattern of clinical characteristics into 6 clinically distinct clusters. Full article

Severe blood leakage resulting from the detachment of dialysis tubing is often difficult to detect by nurses in busy clinics. This paper presents a flexible blood leakage detection system featuring a ring-light sensor array with an operating wavelength of 500–700 nm, which is held in place by the gauze covering the dialysis puncture site. A ring-light sensor is connected to a bidirectional hetero-associative memory network, which interprets detected changes in signal strength, the output signal of which is transmitted via WiFi to a server at the nursing station where a machine learning algorithm determines whether blood leakage has occurred. The compact design of this early warning system greatly enhances the comfort and mobility of patients undergoing dialysis. The efficacy of the proposed system was demonstrated in experiments involving artificial blood. Full article

This study assessed the feasibility of five separate machine learning (ML) classifiers for predicting disease progression in patients with pre-dialysis chronic kidney disease (CKD). The study enrolled 858 patients with CKD treated at a veteran’s hospital in Taiwan. After classification into early and advanced stages, patient demographics and laboratory data were processed and used to predict progression to renal failure and important features for optimal prediction were identified. The random forest (RF) classifier with synthetic minority over-sampling technique (SMOTE) had the best predictive performances among patients with early-stage CKD who progressed within 3 and 5 years and among patients with advanced-stage CKD who progressed within 1 and 3 years. Important features identified for predicting progression from early- and advanced-stage CKD were urine creatinine and serum creatinine levels, respectively. The RF classifier demonstrated the optimal performance, with an area under the receiver operating characteristic curve values of 0.96 for predicting progression within 5 years in patients with early-stage CKD and 0.97 for predicting progression within 1 year in patients with advanced-stage CKD. The proposed method resulted in the optimal prediction of CKD progression, especially within 1 year of advanced-stage CKD. These results will be useful for predicting prognosis among patients with CKD. Full article

Tonometry is commonly used to provide efficient and good diagnostics for cardiovascular disease (CVD). There are many advantages of this method, including low cost, non-invasiveness and little time to perform. In this study, the effort was undertaken to check whether tonometry data hides valuable information associated with different stages of chronic kidney disease (CKD) and end-stage renal disease (ESRD) treatment. For this purpose, six groups containing patients at different stages of CKD following different ways of dialysis treatment, as well as patients without CKD but with CVD and healthy volunteers were assessed. It was revealed that each of the studied groups had a unique profile. Only the type of dialysis was indistinguishable a from tonometric perspective (hemodialysis vs. peritoneal dialysis). Several techniques were used to build profiles that independently gave the same outcome: analysis of variance, network correlation structure analysis, multinomial logistic regression, and discrimination analysis. Moreover, to evaluate the classification potential of the discriminatory model, all mentioned techniques were later compared and treated as feature selection methods. Although the results are promising, it could be difficult to express differences as simple mathematical relations. This study shows that artificial intelligence can differentiate between different stages of CKD and patients without CKD. Potential future machine learning models will be able to determine kidney health with high accuracy and thereby classify patients. ClinicalTrials.gov Identifier: NCT05214872. Full article

Background: Hospitalization-associated acute kidney injury (AKI), affecting one-in-five inpatients, is associated with increased mortality and major adverse cardiac/kidney endpoints. Early AKI risk stratification may enable closer monitoring and prevention. Given the complexity and resource utilization of existing machine learning models, we aimed to develop a simpler prediction model. Methods: Models were trained and validated to predict risk of AKI using electronic health record (EHR) data available at 24 h of inpatient admission. Input variables included demographics, laboratory values, medications, and comorbidities. Missing values were imputed using multiple imputation by chained equations. Results: 26,410 of 209,300 (12.6%) inpatients developed AKI during admission between 13 July 2012 and 11 July 2018. The area under the receiver operating characteristic curve (AUROC) was 0.86 for Random Forest and 0.85 for LASSO. Based on Youden’s Index, a probability cutoff of >0.15 provided sensitivity and specificity of 0.80 and 0.79, respectively. AKI risk could be successfully predicted in 91% patients who required dialysis. The model predicted AKI an average of 2.3 days before it developed. Conclusions: The proposed simpler machine learning model utilizing data available at 24 h of admission is promising for early AKI risk stratification. It requires external validation and evaluation of effects of risk prediction on clinician behavior and patient outcomes. Full article