ML-CKDP: Machine learning-based chronic kidney disease prediction with smart web application

Journal of Pathology Informatics, Journal Year: 2024, Volume and Issue: 15, P. 100371 - 100371

Published: Feb. 22, 2024

Chronic kidney diseases (CKDs) are a significant public health issue with potential for severe complications such as hypertension, anemia, and renal failure. Timely diagnosis is crucial effective management. Leveraging machine learning within healthcare offers promising advancements in predictive diagnostics. In this paper, we developed learning-based prediction (ML‐CKDP) model dual objectives: to enhance dataset preprocessing CKD classification develop web-based application prediction. The proposed involves comprehensive data protocol, converting categorical variables numerical values, imputing missing data, normalizing via Min-Max scaling. Feature selection executed using variety of techniques including Correlation, Chi-Square, Variance Threshold, Recursive Elimination, Sequential Forward Selection, Lasso Regression, Ridge Regression refine the datasets. employs seven classifiers: Random Forest (RF), AdaBoost (AdaB), Gradient Boosting (GB), XgBoost (XgB), Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree (DT), predict CKDs. effectiveness models assessed by measuring their accuracy, analyzing confusion matrix statistics, calculating Area Under Curve (AUC) specifically positive cases. (RF) (AdaB) achieve 100% accuracy rate, evident across various validation methods splits 70:30, 80:20, K-Fold set 10 15. RF AdaB consistently reach perfect AUC scores multiple datasets, under different splitting ratios. Moreover, (NB) stands out its efficiency, recording lowest training testing times all datasets split Additionally, present real-time operationalize model, enhancing accessibility practitioners stakeholders. Web app link: https://rajib-research-kedney-diseases-prediction.onrender.com/

Language: Английский

---

Prediction and detection of terminal diseases using Internet of Medical Things: A review

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 188, P. 109835 - 109835

Published: Feb. 24, 2025

Language: Английский

---

Detection of Kidney Diseases

International Journal of E-Health and Medical Communications, Journal Year: 2024, Volume and Issue: 15(1), P. 1 - 21

Published: Sept. 13, 2024

Chronic kidney disease (CKD) is a medical condition characterized by impaired function, which leads to inadequate blood filtration. To reduce mortality rates, recent advancements in early diagnosis and treatment have been made. However, as time-consuming, an automated system necessary. Researchers employing various machine learning approaches analyze extensive complex data, aiding clinicians predicting CKD enabling intervention. Identifying the most crucial attributes for this paper's primary objective. address gap, six nature-inspired algorithms nine classifiers were compared evaluate their combined effectiveness detecting CKD. A benchmark dataset from UCI repository was utilized analysis. The proposed model outperforms other with remarkable 99.5% accuracy rate; it also achieves 58% reduction feature dimensionality. By providing reliable, cost-effective tool detection, authors aim revolutionize patient care.

Language: Английский

---

Diagnosis of COVID-19 Using Chest X-ray Images and Disease Symptoms Based on Stacking Ensemble Deep Learning

Diagnostics, Journal Year: 2023, Volume and Issue: 13(11), P. 1968 - 1968

Published: June 5, 2023

The COVID-19 virus is one of the most devastating illnesses humanity has ever faced. an infection that hard to diagnose until it caused lung damage or blood clots. As a result, insidious diseases due lack knowledge its symptoms. Artificial intelligence (AI) technologies are being investigated for early detection using symptoms and chest X-ray images. Therefore, this work proposes stacking ensemble models two types datasets, scans, identify COVID-19. first proposed model merged from outputs pre-trained in stacking: multi-layer perceptron (MLP), recurrent neural network (RNN), long short-term memory (LSTM), gated unit (GRU). Stacking trains evaluates meta-learner as support vector machine (SVM) predict final decision. Two datasets used compare with MLP, RNN, LSTM, GRU models. second DL VGG16, InceptionV3, Resnet50, DenseNet121; uses train evaluate prediction. images other result shown achieve highest performance compared each dataset.

Language: Английский

---

ACD-ML: Advanced CKD detection using machine learning: A tri-phase ensemble and multi-layered stacking and blending approach

Computer Methods and Programs in Biomedicine Update, Journal Year: 2025, Volume and Issue: unknown, P. 100173 - 100173

Published: Jan. 1, 2025

Language: Английский

---

Early prediction of CKD from time series data using adaptive PSO optimized echo state networks

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: Feb. 26, 2025

Chronic Kidney Disease (CKD) is a significant problem in today's healthcare since it challenging to detect until has improved significantly, which increases medical expenses. If CKD was detected early, the patient might qualify for more effective treatment and prevent disease from spreading further. Presently, existing methods that effectively cannot symptoms early on. This motivates researchers work on predictive model successfully detects stages. study introduces novel Adaptive Particle Swarm Optimization (APSO)-optimized Echo State Network (ESN) designed overcome key limitations of methods. ESNs, while processing temporal sequences, are highly sensitive hyperparameter settings such as spectral radius, input scaling, sparsity, directly impact stability, memory retention, Classification Accuracy (CA). To address this, APSO optimizes these hyperparameters dynamically, ensuring balanced trade-off between stability computational efficiency. Moreover, Random Matrix Theory (RMT) integrated into regulate enhancing ESN's capability handle long-term dependencies maintaining training. investigation exploited Medical Information Mart Intensive Care-III (MIMIC-III) dataset train they developed. The proposed method employs this data collection analyze complex sequences signifying present. ESN, range region sizing, can be optimized real-time with by applying (RMT). Compared different recognized models, conventional ESN standard M, recommended + proved have higher CA investigations. subsequent highest-performing 2% recall 3% precision attained 99.6%.

Language: Английский

---

Proactive healthcare: machine learning-driven insights into kidney failure prediction

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: March 25, 2025

Abstract Kidney failure, a critical condition with increasing prevalence, necessitates early detection and management to mitigate its severe health impacts. In this study, we utilize the MIMIC-IV dataset develop predictive models for identifying forecasting kidney failure using advanced machine learning techniques. We aggregated medical records from patients diagnosed alongside an equivalent non-kidney individuals, train LSTM, random forest, XGBoost models. Comprehensive data analysis was conducted extract evaluate key features related function, including correlations among lab events, prescriptions, patient demographics. These insights informed model development, enabling accurate classification of based on historical prediction onset through time-series analysis. The Random Forest outperformed others, achieving near-perfect accuracy, demonstrating their robustness in handling complex datasets. Additionally, feature prediction, event values which can inform interventions personalized treatment plans. Our findings underscore potential enhancing clinical decision-making, offering pathway more precise proactive healthcare strategies managing failure.

Language: Английский

---

Multi-level feature fusion network for kidney disease detection

Computers in Biology and Medicine, Journal Year: 2025, Volume and Issue: 191, P. 110214 - 110214

Published: April 14, 2025

Language: Английский

---

Snake-Efficient Feature Selection-Based Framework for Precise Early Detection of Chronic Kidney Disease

Diagnostics, Journal Year: 2023, Volume and Issue: 13(15), P. 2501 - 2501

Published: July 27, 2023

Chronic kidney disease (CKD) refers to impairment of the kidneys that may worsen over time. Early detection CKD is crucial for saving millions lives. As a result, several studies are currently focused on developing computer-aided systems detect in its early stages. Manual screening time-consuming and subject personal judgment. Therefore, methods based machine learning (ML) automatic feature selection used support graders. The goal identify most relevant informative subset features given dataset. This approach helps mitigate curse dimensionality, reduce enhance model performance. use natural-inspired optimization algorithms has been widely adopted develop appropriate representations complex problems by conducting blackbox process without explicitly formulating mathematical formulations. Recently, snake have developed optimal or near-optimal solutions difficult mimicking behavior snakes during hunting. objective this paper novel snake-optimized framework named CKD-SO data analysis. To select classify suitable medical data, five deployed, along with (SO) algorithm, create an extremely accurate prediction liver disease. end result can 99.7% accuracy. These results contribute our understanding preparation pipeline. Furthermore, implementing method will enable health achieve effective prevention providing interventions high burden CKD-related diseases mortality.

Language: Английский

---

Artificial intelligence for early-stage detection of chronic kidney disease

International Journal of Power Electronics and Drive Systems/International Journal of Electrical and Computer Engineering, Journal Year: 2024, Volume and Issue: 14(4), P. 4775 - 4775

Published: June 4, 2024

Early-stage detection of chronic kidney disease (CKD) is crucial in research to enable timely intervention, enhance understanding progression, reduce healthcare costs and support public health initiatives. The traditional approaches on early-stage often suffer from slow convergence not integrate advanced technologies, impacting their effectiveness. Additionally, security privacy concerns related patient data are ineffectively addressed. To overcome these issues, this incorporates novel optimized artificial intelligence-based approaches. main aim process through enhanced hybrid mud ring network (EHMRN), a technique combining light gradient boosting machine MobileNet, involving extensive collection, including large dataset 100,000 instances. introduced the optimization attain performance. Incorporating spark ensures secure cloud-based storage, enhancing compliance with regulations. This approach represents significant advancement primary stage more effectively promptly. results show that outperforms terms accuracy (99.96%), F1-score (99.91%), precision (100%), specificity (99.98%), recall (100%) execution time (0.09 s).

Language: Английский

---