Artificial Intelligence in Healthcare

Artificial Intelligence Model: Optimizing Cancer Risk Level Predictions Using Machine learning and deep learning approaches

This study uses ML and DL models to predict cancer risk using a Kaggle dataset, finding that Random Forest achieves high accuracy in risk classification.

MetaAMI: A Novel Meta-Learning Approach for Predicting In-Hospital Mortality in Acute Myocardial Infarction

MetaAMI uses a meta-learning framework with random projections to predict in-hospital mortality in AMI patients, outperforming baseline classifiers across multiple metrics.

Comorbidity structure as an inductive bias: Comparing output-head designs for multi-label prediction of diabetes and myocardial infarction complications

This paper compares output-head designs for predicting diabetes and myocardial infarction complications, finding that symmetric CRF outperformed others in diabetes but no single method dominated in myocardial infarction.

The Conductome: A Bayesian Classifier Approach to Predicting and Understanding Behaviour

The paper introduces a Bayesian classifier framework to predict behaviour by operationalizing it as a Conductome, demonstrating its effectiveness on a dataset predicting sedentariness.

Adaptive Feature-Weighted Stacking Ensemble for Short-Term Risk Prediction of Prolonged Length of Stay in Elderly Trauma Patients

The paper introduces an adaptive feature-weighted stacking ensemble model for predicting prolonged length of stay in elderly trauma patients, showing improved predictive accuracy over standard methods.

A Supervised Machine Learning Approach with Feature Selection for Sex-Specific Biomarker Prediction

The paper develops a supervised machine learning model to predict sex-specific biomarkers, finding higher prediction accuracy in males than females for most biomarkers.

Brain Stroke Prediction: A PSO Optimized Stacked Ensemble Machine Learning Approach with SMOTEEN Data Balancing

This paper develops a PSO-optimized stacked ensemble machine learning model with SMOTEEN for stroke prediction, achieving 95.57% accuracy and outperforming traditional models.

Fetal Health Classification Based on CTG

This paper applies machine learning models to CTG data to classify fetal health, finding gradient boosting provides the highest accuracy.

Hand Drawing Image based Causal Representation Learning for Robust Parkinson's Disease Feature Extraction and Detection

This paper develops a causal representation learning framework using hand-drawn images to extract robust Parkinson's Disease features for improved early detection.

Explainable AI Based Coronary Heart Disease Prediction: Enhancing Model Transparency in Clinical Decision Making

This study compares eight machine learning models for coronary heart disease prediction, identifies key features, and uses SHAP and LIME to improve model interpretability.

A diagnostic support system based on interpretable machine learning and oscillometry for accurate diagnosis of respiratory dysfunction in silicosis

This paper develops an AI-assisted diagnostic system using machine learning and oscillometry to improve silicosis diagnosis with high accuracy.

Graph Autoencoder and StrNN based Causal Analysis of Mortality in Heart Failure Patients

This paper uses causal deep learning methods to identify key mechanisms of mortality in heart failure patients from observational data.

Machine learning model to predict risk assessment of a child inheriting a genetic disorder

This paper develops a machine learning model to predict genetic disorder risk in children based on family history and clinical data, achieving high cross-validation scores.

Towards Reliable Diabetes Prediction: Innovations in Data Engineering and Machine Learning Applications

This paper develops a machine learning model for diabetes prediction using data preprocessing and random oversampling, achieving high accuracy across multiple datasets.

Comparative Analysis of Machine Learning Algorithms for Breast Cancer Classification: SVM Outperforms XGBoost, CNN, RNN, and Others

This study compares ten machine learning algorithms for breast cancer classification using physical attributes, finding SVM achieves the highest accuracy of 98.2456%.

Discovering biomarkers associated and predicting cardiovascular disease with high accuracy using a novel nexus of machine learning techniques for precision medicine

This study identifies 18 significant transcriptomic biomarkers for cardiovascular disease with 96% accuracy using a combination of statistical tests and machine learning classifiers.

Prediction of Heart Disease and Survivability using Support Vector Machine and Naive Bayes Algorithm

This paper compares SVM and Naive Bayes algorithms for predicting heart disease and survivability using a clinical dataset, finding Naive Bayes achieves 93% accuracy for survivability.

Prediction Analysis of Preterm Neonates Mortality using Machine Learning Algorithms via Python Programming

This paper predicts preterm neonatal mortality using machine learning models in Python, achieving 91.5% accuracy in survival prediction.

Development and validation of a type 2 diabetes machine learning classification model for EHR-based diagnostics and clinical decision support

This paper develops and validates a machine learning model for type 2 diabetes diagnosis using electronic health records, achieving high AUC, specificity, and sensitivity.

Machine Learning Algorithms for Predicting Coronary Artery Disease: Efforts Toward an Open Source Solution

This study applies six machine learning algorithms to predict coronary artery disease using the Cleveland dataset, finding neural networks achieve high accuracy and recall.

A Proposal of New Feature Selection Method Sensitive to Outliers and Correlation

The paper proposes a new feature selection method that improves classification performance in disease diagnosis by addressing outliers and correlation, outperforming the traditional t-Score method.

Performance and efficiency of machine learning algorithms for analyzing rectangular biomedical data

This study compares the performance and efficiency of four machine learning algorithms on a large rectangular biomedical dataset, finding similar accuracy but varying efficiency with dimension reduction.

Compressive Big Data Analytics: An Ensemble Meta-Algorithm for High-dimensional Multisource Datasets

This paper introduces an improved version of the CBDA algorithm for handling high-dimensional multisource datasets, validated on synthetic and real-world health data.

Different Perspective of Machine Learning Technique to Better Predict Breast Cancer Survival

This study compares machine learning algorithms for predicting breast cancer survival, finding genetic programming to be the most effective for feature selection and classification.

PECLIDES Neuro - A Personalisable Clinical Decision Support System for Neurological Diseases

PECLIDES Neuro is a personalisable clinical decision support system that provides transparent diagnosis for neurological diseases using random forests and user interaction.

Distance and Colour-based Scores for Blood Test Risk Stratification

The paper introduces numerical and colour-based risk stratification scores to quantify abnormal blood analyte values and tests their effectiveness in distinguishing healthy individuals from those with diseases.

Nationwide prediction of type 2 diabetes comorbidities

This study uses machine learning on Danish health registers to predict five-year risk of T2D comorbidities, showing modest improvements over reference models.

Knowledge discovery with Bayesian Rule Learning for actionable biomedicine

This paper introduces BRL-KD, a Bayesian Rule Learning extension that incorporates clinical utility to generate interpretable models for cardiovascular disease prediction, balancing statistical significance and clinical relevance.

Machine Learning Models of Breast Cancer Risk Prediction

This study compares machine learning models for breast cancer risk prediction using clinical features from 116 patients, finding KNN to have the highest accuracy.

A short review of machine learning methods for classifying the outcome of Gestational Diabetes

The paper compares machine learning methods to classify gestational diabetes using the PIMA Indians diabetes dataset, finding the method with the lowest misclassification rate as the best.