Predicting major adverse cardiac events in diabetes and chronic kidney disease: a machine learning study from the Silesia Diabetes-Heart Project

Cardiovascular Diabetology, Год журнала: 2025, Номер 24(1)

Опубликована: Фев. 15, 2025

Язык: Английский

---

Integrating explainable machine learning and user-centric model for diagnosing cardiovascular disease: A novel approach

Intelligent Systems with Applications, Год журнала: 2024, Номер 23, С. 200428 - 200428

Опубликована: Авг. 24, 2024

Conventional machine learning techniques in diagnosing cardiovascular disease have a limitation owing to the lack of interpretability models. This study utilised an explainable approach predict likelihood having CVD. Four models were employed for CVD diagnosis: Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF), and Extreme Gradient Boost (XGB). Shapley Additive Explanations (SHAP) used provide reasoning models' predictions. Using these explanations, user interface was developed assist All four classification demonstrated good accuracy CVD, with KNN model showcasing best performance (Accuracy: 71 %). SHAP provided behind predictions, predictive by embedding explanations transparency model's decisions.

Язык: 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, Год журнала: 2025, Номер unknown, С. 100173 - 100173

Опубликована: Янв. 1, 2025

Язык: Английский

---

Implementation of Machine Learning and Ensemble Learning Models for the Prediction of CKD and Drugs Side-Effect

Lecture notes in electrical engineering, Год журнала: 2025, Номер unknown, С. 93 - 110

Опубликована: Янв. 1, 2025

Язык: Английский

---

Developing a CKD prognostic model: Integrating feature extraction and classifiers for early detection

Biomedical Signal Processing and Control, Год журнала: 2025, Номер 106, С. 107726 - 107726

Опубликована: Фев. 24, 2025

Язык: Английский

---

Explainable AI for Chronic Kidney Disease Prediction in Medical IoT: Integrating GANs and Few-Shot Learning

Bioengineering, Год журнала: 2025, Номер 12(4), С. 356 - 356

Опубликована: Март 29, 2025

According to recent global public health studies, chronic kidney disease (CKD) is becoming more and recognized as a serious risk many people are suffering from this disease. Machine learning techniques have demonstrated high efficiency in identifying CKD, but their opaque decision-making processes limit adoption clinical settings. To address this, study employs generative adversarial network (GAN) handle missing values CKD datasets utilizes few-shot techniques, such prototypical networks model-agnostic meta-learning (MAML), combined with explainable machine predict CKD. Additionally, traditional models, including support vector machines (SVM), logistic regression (LR), decision trees (DT), random forests (RF), voting ensemble (VEL), applied for comparison. unravel the “black box” nature of predictions, various AI, SHapley Additive exPlanations (SHAP) local interpretable explanations (LIME), understand predictions made by model, thereby contributing process significant parameters diagnosis Model performance evaluated using predefined metrics, results indicate that models integrated GANs significantly outperform techniques. Prototypical achieve highest accuracy 99.99%, while MAML reaches 99.92%. Furthermore, attain F1-score, recall, precision, Matthews correlation coefficient (MCC) 99.89%, 99.9%, 100%, respectively, on raw dataset. As result, experimental clearly demonstrate effectiveness suggested method, offering reliable trustworthy model classify This framework supports objectives Medical Internet Things (MIoT) enhancing smart medical applications services, enabling accurate prediction detection facilitating optimal making.

Язык: Английский

---

Recent trends in diabetes mellitus diagnosis: an in-depth review of artificial intelligence-based techniques

Diabetes Research and Clinical Practice, Год журнала: 2025, Номер unknown, С. 112221 - 112221

Опубликована: Май 1, 2025

Язык: Английский

---

A machine learning-based prediction of hospital mortality in mechanically ventilated ICU patients

PLoS ONE, Год журнала: 2024, Номер 19(9), С. e0309383 - e0309383

Опубликована: Сен. 4, 2024

Background Mechanical ventilation (MV) is vital for critically ill ICU patients but carries significant mortality risks. This study aims to develop a predictive model estimate hospital among MV patients, utilizing comprehensive health data assist physicians with early-stage alerts. Methods We developed Machine Learning (ML) framework predict in receiving MV. Using the MIMIC-III database, we identified 25,202 eligible through ICD-9 codes. employed backward elimination and Lasso method, selecting 32 features based on clinical insights literature. Data preprocessing included eliminating columns over 90% missing using mean imputation remaining values. To address class imbalance, used Synthetic Minority Over-sampling Technique (SMOTE). evaluated several ML models, including CatBoost, XGBoost, Decision Tree, Random Forest, Support Vector (SVM), K-Nearest Neighbors (KNN), Logistic Regression, 70/30 train-test split. The CatBoost was chosen its superior performance terms of accuracy, precision, recall, F1-score, AUROC metrics, calibration plots. Results involved cohort attained an 0.862, increase from initial 0.821, which best reported It also demonstrated accuracy 0.789, F1-score 0.747, better calibration, outperforming other models. These improvements are due systematic feature selection robust gradient boosting architecture CatBoost. Conclusion methodology significantly reduced number relevant features, simplifying computational processes, critical previously overlooked. Integrating these tuning parameters, our strong generalization unseen data. highlights potential as crucial tool ICUs, enhancing resource allocation providing more personalized interventions patients.

Язык: Английский

---

Machine learning approaches for predicting and diagnosing chronic kidney disease: current trends, challenges, solutions, and future directions

International Urology and Nephrology, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 19, 2024

Язык: Английский

---

VGG-16 based Deep Learning Approach for Cephalometric Landmark Detection

The Open Public Health Journal, Год журнала: 2024, Номер 17(1)

Опубликована: Ноя. 28, 2024

Aims The aim of this research work is to compare the accuracy and precision manual landmark identification versus automated methods using deep learning neural networks. Background Cephalometric detection a critical task in orthodontics maxillofacial surgery accurate landmarks essential for treatment planning precise diagnosis outcomes. It entails locating particular anatomical on lateral cephalometric radiographs skull that can be utilised evaluate relationships between skeleton teeth as well soft tissue profiles. Many software tools approaches have been implemented over time increase dependability analysis. Objective primary objective effectiveness an learning-based VGG-16 algorithm its performance against traditional terms precision. Methods study employs VGG16 transfer model dataset X-ray images from IEEE 2015 ISBI Challenge automatically identify 19 radiographs. fine-tuned predict XY coordinates these enhancing analysis by minimizing intervention improving consistency. Results experimental findings indicate presented system has attained Successful Detection Rates (SDR) 26.84%, 41.57%, 59.89% 94.42% 2, 2.5, 3 4mm range respectively Mean Radial Error (MRE) 2.67mm. Conclusion This paper approach widely used architecture computer vision. Through experiments it shown achieve state-of-the-art detection. results demonstrated extract relevant features allowing accurately detect landmarks. also fine-tuning pre-trained data improve task. suggested technique may enhance facilitate clinical decision-making surgery.

Язык: Английский

---