Diabetes Dataset Research Articles

Komparasi Algoritma Data Mining untuk Klasifikasi Penyakit Diabetes

Diabetes is one of the deadly non-communicable diseases that can attack humans. According to data from the World Health Organization (WHO), diabetes has killed at least 2 million people throughout 2019. Many recordings of each phase and condition of diabetes patients are done to support research. One of the most updated records of diabetes patients is the early stage diabetes risk prediction dataset. This dataset was released by the uci repository in late 2020 by the Diabetes Hospital in Bangladesh. Classification in data mining is a science that can extract data to look for patterns or data models to gain new knowledge. Several classification algorithms that are widely used and proven to be able to handle large data include K-NN, Naïve Bayes, and Decission Tree. This study compares the three algorithms to classify early stage diabetes risk prediction dataset. From the research results, the decision tree is the best algorithm for classifying diabetes datasets with an accuracy rate of 95.96%. Next is the KNN algorithm with an accuracy rate of 92.5%. Meanwhile, naïve Bayes only produces an accuracy rate of 86.92%. From this comparison it is known that the decision tree is the best algorithm for classifying the early stage diabetes risk prediction dataset with an accuracy rate of 95.96%.

Machine Learning Approach for Diabetes Detection Using Fine-Tuned XGBoost Algorithm

Diabetes is a chronic condition characterized by elevated blood glucose levels which leads to organ dysfunction and an increased risk of premature death. The global prevalence of diabetes has been rising, necessitating an accurate and timely diagnosis to achieve the most effective management. Recent advancements in the field of machine learning have opened new possibilities for improving diabetes detection and management. In this study, we propose a fine-tuned XGBoost model for diabetes detection. We use the Pima Indian Diabetes dataset and employ a random search for hyperparameter tuning. The fine-tuned XGBoost model is compared with six other popular machine learning models and achieves the highest performance in accuracy, precision, sensitivity, and F1-score. This study demonstrates the potential of the fine-tuned XGBoost model as a robust and efficient tool for diabetes detection. The insights of this study advance medical diagnostics for efficient and personalized management of diabetes.

Interpretable Machine Learning for Personalized Medical Recommendations: A LIME-Based Approach.

Chronic diseases are increasingly major threats to older persons, seriously affecting their physical health and well-being. Hospitals have accumulated a wealth of health-related data, including patients' test reports, treatment histories, and diagnostic records, to better understand patients' health, safety, and disease progression. Extracting relevant information from this data enables physicians to provide personalized patient-treatment recommendations. While collaborative filtering techniques and classical algorithms such as naive Bayes, logistic regression, and decision trees have had notable success in health-recommendation systems, most current systems primarily inform users of their likely preferences without providing explanations. This paper proposes an approach of deep learning with a local interpretable model-agnostic explanations (LIME)-based interpretable recommendation system to solve this problem. Specifically, we apply the proposed approach to two chronic diseases common in older adults: heart disease and diabetes. After data preprocessing, we use six deep-learning algorithms to form interpretations. In the heart-disease data set, the actual model recommendation of multi-layer perceptron and gradient-boosting algorithm differs from the local model's recommendation of LIME, which can be used as its approximate prediction. From the feature importance of these two algorithms, it can be seen that the CholCheck, GenHith, and HighBP features are the most important for predicting heart disease. In the diabetes data set, the actual model predictions of the multi-layer perceptron and logistic-regression algorithm were little different from the local model's prediction of LIME, which can be used as its approximate recommendation. Moreover, from the feature importance of the two algorithms, it can be seen that the three features of glucose, BMI, and age were the most important for predicting heart disease. Next, LIME is used to determine the importance of each feature that affected the results of the calculated model. Subsequently, we present the contribution coefficients of these features to the final recommendation. By analyzing the impact of different patient characteristics on the recommendations, our proposed system elucidates the underlying reasons behind these recommendations and enhances patient trust. This approach has important implications for medical recommendation systems and encourages informed decision-making in healthcare.

Diabetes Risk Prediction using Feature Importance Extreme Gradient Boosting (XGBoost)

Diabetes results from impaired pancreatic function as a producer of insulin and glucagon hormones, which regulate glucose levels in the blood. People with diabetes today are not only experienced adults, but pre-diabetes has been identified since the age of children and adolescents. Early prediction of diabetes can make it easier for doctors and patients to intervene as soon as possible so that the risk of complications can be reduced. One of the uses of medical data from diabetes patients is to produce a model that medical personnel can use to predict and identify diabetes in patients. Various techniques are used to provide the earliest possible prediction of diabetes based on the symptoms experienced by diabetic patients, including the use of machine learning. People can use machine learning to generate models based on historical data from diabetic patients, and predictions are made with the model. In this study, extreme gradient boosting is the machine learning technique for predicting diabetes (xgboost) using XGBoost with importance features. The diabetes dataset used in this study comes from the early stage diabetes risk prediction dataset published by UCI Machine Learning, which has 520 records and 16 attributes. The diabetes prediction model using xgboost is displayed as a tree. The model precision result in this study was 98.71%, for the F1 score was 98.18%. The accuracy obtained based on the best 10 attributes using the importance of the XGBoost feature is 98.72%.

PERBANDINGAN BERBAGAI MODEL MACHINE LEARNING UNTUK MENDETEKSI DIABETES

Diabetes mellitus, often known as diabetes, is a significant metabolic illness that has a negative impact on living organisms. It causes high blood sugar levels by either creating inadequate insulin or using it inefficiently. Diabetes that is not effectively treated raises the risk of heart attacks, retinopathy, vision loss, skin disorders, and other ailments. Early detection is critical for guiding essential actions. In this setting, machine learning (ML) has emerged as a potent tool. We used Python data manipulation tools to develop ML techniques for discovering patterns and risk factors in the Pima Indian diabetes dataset in our study. We correctly identified patients as diabetes or non-diabetic using K-Nearest Neighbors (KNN), AdaBoost, Logistic Regression (LR), Light Gradient Boosting, Random Forest (RF), dan Support Vector Machine (SVM). Notably, we used the Synthetic Minority Over-sampling Technique (SMOTE) to solve class imbalance, which enhanced model performance. By efficiently utilizing ML and SMOTE in diabetes categorization, our work greatly adds to the scientific area. We suggest studying cutting-edge technology and undertaking external validation and clinical studies to assure trustworthy and generalized models for diabetic patient care in the future. With diabetes's increasing prevalence, such improvements have enormous promise for improving early identification and management, eventually leading to better health outcomes.

Predicting the Probability of Diabetes using Data Mining Techniques

In recent years, diabetes has become a common disease, and the number of people suffering from diabetes is huge, and the prevalence and mortality rate are on the rise. Therefore, the prevention of diabetes is an important task. Data mining will play a significant role in the prevention of diabetes by predicting and analyzing the risk of diabetes in various persons with various features. We chose the Pima Indian diabetes dataset for this study, and based on a supervised learning machine learning algorithm, which is one of the simplest, most commonly used and most effective algorithms in data mining classification techniques, namely the KNN algorithm, we used data mining to make a predictive research analysis of diabetes based on the combination of disease characteristics and to predict the probability of diabetes occurrence.

Revolutionizing Diabetes Disease Prediction Through Novel Machine Learning Techniques

Diabetes is a chronic disease that affects millions of people worldwide. Accurate and timely diagnosis of diabetes is crucial for its effective treatment and management. While machine learning has shown promise in predicting the disease, missing data, outliers, class imbalance and limitations of classifiers can hinder accuracy. To address these challenges, we propose a novel machine learning approach that combines adaptive iterative imputation (AII) for missing value imputation, dynamic ensemble isolation forest (DE-IF) for outlier detection and removal, Iterated KMeans SMOTEENN (IKMSENN) for class imbalance, and an adaptive extra tree classifier (AETC) for classification. Our approach is evaluated using the Pima Indian Diabetes Dataset (PIDD), a widely used benchmark dataset in diabetes disease prediction. Experimental results show that our approach outperforms several state-of-the-art machine learning models in terms of accuracy, precision, recall, [Formula: see text]-measure, and the area under the receiver operating characteristic (ROC) curve (AUC-ROC). Our approach achieved an accuracy of 98.58%, with a precision of 0.986, recall of 0.987, [Formula: see text]-measure of 0.985, and ROC of 0.965 on the PIDD dataset. Our research presents a significant contribution to the field of diabetes disease prediction by introducing novel machine learning approaches that address common challenges such as missing data, outliers and class imbalance, as well as limitations of classifiers. Our approach has the potential to greatly improve the accuracy and effectiveness of diabetes disease prediction and has important implications for the diagnosis and management of the disease.

Design an Optimal Decision Tree based Algorithm to Improve Model Prediction Performance

Performance of decision trees is assessed by prediction accuracy for unobserved occurrences. In order to generate optimised decision trees with high classification accuracy and smaller decision trees, this study will pre-process the data. In this study, some decision tree components are addressed and enhanced. The algorithms should produce precise and ideal decision trees in order to increase prediction performance. Additionally, it hopes to create a decision tree algorithm with a tiny global footprint and excellent forecast accuracy. The typical decision tree-based technique was created for classification purposes and is used with various kinds of uncertain information. Prior to preparing the dataset for classification, the uncertain dataset was first processed through missing data treatment and other uncertainty handling procedures to produce the balanced dataset. Three different real-time datasets, including the Titanic dataset, the PIMA Indian Diabetes dataset, and datasets relating to heart disease, have been used to test the proposed algorithm. The suggested algorithm's performance has been assessed in terms of the precision, recall, f-measure, and accuracy metrics. The outcomes of suggested decision tree and the standard decision tree have been contrasted. On all three datasets, it was found that the decision tree with Gini impurity optimization performed remarkably well.

Causal discovery approach with reinforcement learning for risk factors of type II diabetes mellitus

BackgroundStatistical correlation analysis is currently the most typically used approach for investigating the risk factors of type 2 diabetes mellitus (T2DM). However, this approach does not readily reveal the causal relationships between risk factors and rarely describes the causal relationships visually.ResultsConsidering the superiority of reinforcement learning in prediction, a causal discovery approach with reinforcement learning for T2DM risk factors is proposed herein. First, a reinforcement learning model is constructed for T2DM risk factors. Second, the process involved in the causal discovery method for T2DM risk factors is detailed. Finally, several experiments are designed based on diabetes datasets and used to verify the proposed approach.ConclusionsThe experimental results show that the proposed approach improves the accuracy of causality mining between T2DM risk factors and provides new evidence to researchers engaged in T2DM prevention and treatment research.

A novel secure and distributed architecture for privacy-preserving healthcare system

Patients often visit several hospitals to obtain medication, generating a significant volume of data. Moreover, hospitals use different data analytic techniques to improve healthcare services, leading to patient data privacy. However, no integrated architecture has a trustworthy data repository and secure communication protocols to store and share the data with various parties (e.g., hospitals and data analysts) for different healthcare services. This study proposes an innovative three-tier secure and distributed privacy-preserving healthcare architecture that addresses the aforementioned challenges. The first tier introduces a trustworthy data repository called custodian, where the data owner stores encrypted data and offer real-time privacy-preserving health monitoring service. The second tier provides Elliptic Curve Cryptography-based authentication for secure data exchange between the data owner and the hospital. The third tier utilizes smart contracts and local differential privacy (LDP) for secure machine learning model training. All transactions are recorded on the blockchain and managed by a smart contract. Security analysis shows that the proposed framework ensures privacy, security, and data integrity. Performance analysis is done based on score metrics, scalability metrics, and formal analysis. A transaction takes 0.00121 s in the first tier, and in the second tier, it takes 0.1267 s. The third tier uses ɛ−LDP with a privacy budget of ɛ = 3 on Random Forest and achieves 97%, 83%, and 74% accuracy on breast cancer, heart disease, and diabetic datasets. This accuracy is higher than the previous state-of-the-art methods. Moreover, the proposed healthcare framework ensures privacy, security and outperforms the previous state-of-the-art methods.

Early Prediction of Gestational Diabetes with Parameter-Tuned K-Nearest Neighbor Classifier

Diabetes is one of the quickly spreading chronic diseases causing health complications, such as diabetes retinopathy, kidney failure, and cardiovascular disease. Recently, machine-learning techniques have been widely applied to develop a model for the early prediction of diabetes. Due to its simplicity and generalization capability, K-nearest neighbor (KNN) has been one of the widely employed machine learning techniques for diabetes prediction. Early diabetes prediction has a significant role in managing and preventing complications associated with diabetes, such as retinopathy, kidney failure, and cardiovascular disease. However, the prediction of diabetes in the early stage has remained challenging due to the accuracy and reliability of the KNN model. Thus, gird search hyperparameter optimization is employed to tune the K values of the KNN model to improve its effectiveness in predicting diabetes. The developed hyperparameter-tuned KNN model was tested on the diabetes dataset collected from the UCI machine learning data repository. The dataset contains 768 instances and 8 features. The study applied Min-max scaling to scale the data before fitting it to the KNN model. The result revealed KNN model performance improves when the hyperparameter is tuned. With hyperparameter tuning, the accuracy of KNN improves by 5.29% accuracy achieving 82.5% overall accuracy for predicting diabetes in the early stage. Therefore, the developed KNN model applied to clinical decision-making in predicting diabetes at an early stage. The early identification of diabetes could aid in early intervention, personalized treatment plans, or reducing healthcare costs reducing associated risks such as retinopathy, kidney disease, and cardiovascular disease.

A Comparison of Machine Learning Techniques for the Detection of Type-2 Diabetes Mellitus: Experiences from Bangladesh

Diabetes is a chronic disease caused by a persistently high blood sugar level, causing other chronic diseases, including cardiovascular, kidney, eye, and nerve damage. Prompt detection plays a vital role in reducing the risk and severity associated with diabetes, and identifying key risk factors can help individuals become more mindful of their lifestyles. In this study, we conducted a questionnaire-based survey utilizing standard diabetes risk variables to examine the prevalence of diabetes in Bangladesh. To enable prompt detection of diabetes, we compared different machine learning techniques and proposed an ensemble-based machine learning framework that incorporated algorithms such as decision tree, random forest, and extreme gradient boost algorithms. In order to address class imbalance within the dataset, we initially applied the synthetic minority oversampling technique (SMOTE) and random oversampling (ROS) techniques. We evaluated the performance of various classifiers, including decision tree (DT), logistic regression (LR), support vector machine (SVM), gradient boost (GB), extreme gradient boost (XGBoost), random forest (RF), and ensemble technique (ET), on our diabetes datasets. Our experimental results showed that the ET outperformed other classifiers; to further enhance its effectiveness, we fine-tuned and evaluated the hyperparameters of the ET. Using statistical and machine learning techniques, we also ranked features and identified that age, extreme thirst, and diabetes in the family are significant features that prove instrumental in the detection of diabetes patients. This method has great potential for clinicians to effectively identify individuals at risk of diabetes, facilitating timely intervention and care.

Preprocessing Using SMOTE and K-Means for Classification by Logistic Regression on Pima Indian Diabetes Dataset

Purpose: Our study aims to combine pre-processing methods to develop a training data model from the Indian diabetic Pima dataset so that it can improve the performance of machine learning in recognizing diabetesDesign/methodology/approach: This research was started through several stages such as collecting the Pima indian diabetes dataset, pre-processing including k-means clustering, oversampling using SMOTE, then undersampling the dataset whose cluster is a minority in each class. Furthermore, the dataset is classified using machine learning namely logistic regression through 10 cross validationFindings/result: The results of this classification performance show that the accuracy reaches 99.5% and is higher than the method in previous studies.Originality/value/state of the art:The method in this study uses SMOTE to handle data imbalances and k-means clustering to remove outliers by removing labels that do not match the majority cluster in each class so that clean data is produced and validation using logistic regression is more accurate than previous studies.Tujuan: Penelitian ini bertujuan untuk menerapkan metode pre-processing untuk membentuk model data latih dari dataset Pima Indian diabetes sehingga dapat meningkatkan performa mesin pembelajaran dalam mengenali diabetes.Perancangan/metode/pendekatan: Riset ini dimulai melalui beberapa tahap yakni pengumpulan dataset Pima Indian diabetes, pre-processing meliputi clustering, oversampling menggunakan SMOTE, kemudian undersampling pada dataset pada klaster minoritas pada setiap kelas. Selanjutnya dataset diklasifikasikan menggunakan machine learning yakni metode regresi logistik melalui 10 cross validationHasil: Hasil dari performa klasifikasi ini menunjukkan akurasi mencapai 99,5% dan lebih tinggi daripada metode pada penelitian sebelumnya.Keaslian/ state of the art: Metode dalam penelitian ini menggunakan SMOTE untuk menangani ketidakseimbangan data dan k-means klastering untuk membuang outlier dengan cara menghapus label yang tidak sesuai dengan klaster mayoritas pada setiap kelas sehingga dihasilkan data yang bersih dan pada validasi menggunakan logistic regression lebih akurat daripada penelitian sebelumnya.

Machine Learning Based Diabetes Detection Model for False Negative Reduction

Diabetes is a chronic disease characterized by the inability of the pancreas to produce enough insulin or the body’s inability to use insulin efficiently. This disease is becoming increasingly prevalent worldwide and can result in severe complications such as blindness, kidney failure, and stroke. Early detection of diabetes can potentially save millions of lives globally, making it a crucial focus of research. In this study, we propose a machine learning model to aid in predicting diabetes. The model comprises several machine learning methods: Linear Regression (LnR), Logistic Regression (LR), k-nearest neighbor (KNN), Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), and Decision Tree (DT). Prior to feeding the pre-processed data into the machine learning model for evaluation, we conducted several pre-processing steps, such as removing null values, standardizing data using normalization, and labeling data using the label encoding process. Imbalanced datasets can adversely affect the accuracy of machine learning algorithms, and we address this problem by balancing the datasets using the Synthetic Minority Oversampling Technique (SMOTE) method. We assessed the model’s performance on two datasets and found that the random forest algorithm produced optimal results, with 97% accuracy on the diabetes dataset 2019 and 80% accuracy on the Pima Indian dataset. However, using a balanced dataset, we can significantly reduce the number of false-negative detections.

Indeterminacy Handling of Adaptive Neuro-fuzzy Inference System Using Neutrosophic Set Theory: A Case Study for the Classification of Diabetes Mellitus

Early diabetes diagnosis allows patients to begin treatment on time, reducing or eliminating the risk of serious consequences. In this paper, we propose the Neutrosophic-Adaptive Neuro-Fuzzy Inference System (N-ANFIS) for the classification of diabetes. It is an extension of the generic ANFIS model. Neutrosophic logic is capable of handling the uncertain and imprecise information of the traditional fuzzy set. The suggested method begins with the conversion of crisp values to neutrosophic sets using a trapezoidal and triangular neutrosophic membership function. These values are fed into an inferential system, which compares the most impacted value to a diagnosis. The result demonstrates that the suggested model has successfully dealt with vague information. For practical implementation, a single-value neutrosophic number has been used; it is a special case of the neutrosophic set. To highlight the promising potential of the suggested technique, an experimental investigation of the well-known Pima Indian diabetes dataset is presented. The results of our trials show that the proposed technique attained a high degree of accuracy and produced a generic model capable of effectively classifying previously unknown data. It can also surpass some of the most advanced classification algorithms based on machine learning and fuzzy systems.

COMPARATIVE ANALYSIS OF ACCURACY OF RANDOM FOREST AND GRADIENT BOOSTING CLASSIFIER ALGORITHM FOR DIABETES CLASSIFICATION

Diabetes is a disease characterized by high blood sugar (glucose) levels. If blood sugar is not controlled properly, it can cause various critical diseases, one of which is diabetes. The purpose of this study was to determine the results of a comparison of the accuracy values ​​of the Random Forest Algorithm and the Gradient Boosting Classifier Algorithm in the classification of diabetes which will be tested for accuracy, Precision, Recall, and F1 score performance. The method used in this study was descriptive and the data source used the Pima Indians Diabetes Dataset from Kaggle. Based on data analysis using a ratio of 80:20, the Random Forest Algorithm has an accuracy of 79% obtained from the results of the confusion matrix. From the confusion matrix results, the results obtained were AUC 0.835, Recall 78%, and Precision 90%. Based on the results of Recall and Precision, an F1 score of 83% was obtained. Whereas the Boosting Classifier Algorithm has an accuracy result obtained from the results of the confusion matrix which is 81%. From the confusion matrix results, the AUC results were 0.877, Recall 83%, and Precision 67%. Based on the results of Recall and Precision, an F1 score of 74% was obtained. In this study, the accuracy evaluation results obtained were through the results of the Confusion matrix and the AUC value. These results indicate that the Gradient Boosting Classifier Algorithm has a more excellent accuracy evaluation result compared to the Random Forest Algorithm.

A Transformer on Tabular Data Comparative Analysis with Linear and Tree Base Machine Learning Algorithm on Diabetic Dataset

A Transformer on Tabular Data Comparative Analysis with Linear and Tree Base Machine Learning Algorithm on Diabetic Dataset

A diabetes prediction model based on Boruta feature selection and ensemble learning

Background and objectiveAs a common chronic disease, diabetes is called the “second killer” among modern diseases. Currently, there is no medical cure for diabetes. We can only rely on medication for auxiliary treatment. However, many diabetic patients still die each year. In addition, a considerable number of people do not pay attention to their physical health or opt out of treatment due to lack of money, which eventually leads to various complications. Therefore, diagnosing diabetes at an early stage and intervening early is necessary; thus, developing an early detection method for diabetes is essential.MethodsIn this study, a diabetes prediction model based on Boruta feature selection and ensemble learning is proposed. The model contains the use of Boruta feature selection, the extraction of salient features from datasets, the use of the K-Means++ algorithm for unsupervised clustering of data and stacking of an ensemble learning method for classification. It has been validated on a diabetes dataset.ResultsThe experiments were performed on the PIMA Indian diabetes dataset. The model was evaluated by accuracy, precision and F1 index. The obtained results show that the accuracy rate of the model reaches 98% and achieves good results.ConclusionCompared with other diabetes prediction models, this model achieved better results, and the obtained results indicate that this model is superior to other models in diabetes prediction and has better performance.

Diabetes disease prediction using firefly optimization-based cat-boost classifier in big data analytics

Globally, diabetes directly causes 1.5 million fatalities each year. It is necessary to predict such diseases at an earlier stage and cure them. Since modern healthcare data comprises huge amounts of information, it is tough to process such data in conventional databases. Previously, various machine learning (ML) algorithms were used to predict diabetics, and their performance was evaluated. But still, those existing algorithms result in poor accuracy and performance.This work proposes a FOCB (Firefly Optimization-based CatBoost) classifier for predicting diabetes. The PIMA Indian diabetic dataset has been taken as the input dataset. The proposed FOCB algorithm has been compared with various machine learning algorithms. From the results, we can see that the FOCB classifier gives the best accuracy of 96% with improved performance. The proposed system has been compared with other FO-based machine learning algorithms like NB, KNN, RF, AB, GB, XGB, CNN, DBN, and CB, and it has been proven that CB based on FO produces better accuracy with less hamming loss.

Comparative analysis of predictive machine learning algorithms for diabetes mellitus

Diabetes mellitus (DM) is a serious worldwide health issue, and its prevalence is rapidly growing. It is a spectrum of metabolic illnesses defined by perpetually increased blood glucose levels. Undiagnosed diabetes can lead to a variety of problems, including retinopathy, nephropathy, neuropathy, and other vascular abnormalities. In this context, machine learning (ML) technologies may be particularly useful for early disease identification, diagnosis, and therapy monitoring. The core idea of this study is to identify the strong ML algorithm to predict it. For this several ML algorithms were chosen i.e., support vector machine (SVM), Naïve Bayes (NB), K nearest neighbor (KNN), random forest (RF), logistic regression (LR), and decision tree (DT), according to studied work. Two, Pima Indian diabetic (PID) and Germany diabetes datasets were used and the experiment was performed using Waikato environment for knowledge analysis (WEKA) 3.8.6 tool. This article discussed about performance matrices and error rates of classifiers for both datasets. The results showed that for PID database (PIDD), SVM works better with an accuracy of 74% whereas for Germany KNN and RF work better with 98.7% accuracy. This study can aid healthcare facilities and researchers in comprehending the value and application of ML algorithms in predicting diabetes at an early stage.