Pima Indian Diabetes Dataset Research Articles

Random Oversampling-Based Diabetes Classification via Machine Learning Algorithms

Diabetes mellitus is considered one of the main causes of death worldwide. If diabetes fails to be treated and diagnosed earlier, it can cause several other health problems, such as kidney disease, nerve disease, vision problems, and brain issues. Early detection of diabetes reduces healthcare costs and minimizes the chance of serious complications. In this work, we propose an e-diagnostic model for diabetes classification via a machine learning algorithm that can be executed on the Internet of Medical Things (IoMT). The study uses and analyses two benchmarking datasets, the PIMA Indian Diabetes Dataset (PIDD) and the Behavioral Risk Factor Surveillance System (BRFSS) diabetes dataset, to classify diabetes. The proposed model consists of the random oversampling method to balance the range of classes, the interquartile range technique-based outlier detection to eliminate outlier data, and the Boruta algorithm for selecting the optimal features from the datasets. The proposed approach considers ML algorithms such as random forest, gradient boosting models, light gradient boosting classifiers, and decision trees, as they are widely used classification algorithms for diabetes prediction. We evaluated all four ML algorithms via performance indicators such as accuracy, F1 score, recall, precision, and AUC-ROC. Comparative analysis of this model suggests that the random forest algorithm outperforms all the remaining classifiers, with the greatest accuracy of 92% on the BRFSS diabetes dataset and 94% accuracy on the PIDD dataset, which is greater than the 3% accuracy reported in existing research. This research is helpful for assisting diabetologists in developing accurate treatment regimens for patients who are diabetic.

Utilizing Attention-Enhanced Deep Neural Networks for Large-Scale Preliminary Diabetes Screening in Population Health Data

Early screening for diabetes can promptly identify potential early stage patients, possibly delaying complications and reducing mortality rates. This paper presents a novel technique for early diabetes screening and prediction, called the Attention-Enhanced Deep Neural Network (AEDNN). The proposed AEDNN model incorporates an Attention-based Feature Weighting Layer combined with deep neural network layers to achieve precise diabetes prediction. In this study, we utilized the Diabetes-NHANES dataset and the Pima Indians Diabetes dataset. To handle significant missing values and outliers, group median imputation was applied. Oversampling techniques were used to balance the diabetes and non-diabetes groups. The data were processed through an Attention-based Feature Weighting Layer for feature extraction, producing a feature matrix. This matrix was subjected to Hadamard product operations with the raw data to obtain weighted data, which were subsequently input into deep neural network layers for training. The parameters were fine-tuned and the L2 regularization and dropout layers were added to enhance the generalization performance of the model. The model’s reliability was thoroughly assessed through various metrics, including the accuracy, precision, recall, F1 score, mean squared error (MSE), and R2 score, as well as the ROC and AUC curves. The proposed model achieved a prediction accuracy of 98.4% in the Pima Indians Diabetes dataset. When the test dataset was expanded to the large-scale Diabetes-NHANES dataset, which contains 52,390 samples, the test precision of the model improved further to 99.82%, with an AUC of 0.9995. A comparative analysis was conducted using multiple models, including logistic regression with L1 regularization, support vector machine (SVM), random forest, K-nearest neighbors (KNNs), AdaBoost, XGBoost, and the latest semi-supervised XGBoost. The feature extraction method using attention mechanisms was compared with the classical feature selection methods, Lasso and Ridge. The experiments were performed on the same dataset, and the conclusion was that the Attention-based Ensemble Deep Neural Network (AEDNN) outperformed all the aforementioned methods. These results indicate that the model not only performs well on smaller datasets but also fully leverages its advantages on larger datasets, demonstrating strong generalization ability and robustness. The proposed model can effectively assist clinicians in the early screening of diabetes patients. This is particularly beneficial for the preliminary screening of high-risk individuals in large-scale, extensive healthcare datasets, followed by detailed examination and diagnosis. Compared to the existing methods, our AEDNN model showed an overall performance improvement of 1.75%.

Next-Gen Public Healthcare: Modeling an Advanced Framework for Diabetes Management

Advancements in biotechnology and public health technologies have significantly increased public health data, aiding early disease detection and prevention, particularly in diabetes, which can lead to serious public health issues. In this study, we propose a novel crow search-driven dynamic random forest for (CS-DRF) for diabetes management reorganization. The goal of this integrated strategy is to enhance diabetes treatment results and diagnosis. The Pima Indian Diabetes (PID) dataset is gathered from open-source Kaggle website for diabetes management. We implement our recommended evaluation technique using Python software. The findings showed that the CS-DRF performed more effectively than the others regarding F1-score-93.25%, accuracy-95.46%, specificity-92.38 %, sensitivity-92.22%, and precision-93.28%. The study's validation results demonstrate how advanced the structure model based on machine learning is in detecting diabetes management.

Comparative Analysis of Supervised Machine Learning Algorithms for Diabetes Prediction

Diabetes Mellitus is a chronic disease with far-reaching consequences, necessitating innovative diagnostic approaches. Current methods have limitations, highlighting the need for advanced techniques. This research leveraged machine learning algorithms to predict diabetes using the Pima Indian Diabetes Dataset. Six algorithms were developed and compared: Logistic Regression, Support Vector Machine, K-Nearest Neighbor, Naive Bayes, Random Forest, and Decision Tree. Standard evaluation metrics assessed their performance. The Random Forest Classifier emerged as the top-performing algorithm, achieving an impressive 91% accuracy and demonstrating exceptional reliability. This study showcases machine learning's potential to transform diabetes diagnosis and management. The developed web application provides a user-friendly interface for predicting diabetes, facilitating timely intervention and improved health outcomes. The findings contribute significantly to the development of intelligent disease prediction systems, promoting early detection and enhanced patient care. By harnessing machine learning, this research pioneers a new frontier in diabetes diagnosis, paving the way for improved patient outcomes and enhanced healthcare services.

APPLICATION OF ADASYN OVERSAMPLING TECHNIQUE ON K-NEAREST NEIGHBOR ALGORITHM

The K-Nearest Neighbor Algorithm is a commonly used data mining algorithm for classification due to its effectiveness with large datasets and noise. However, class imbalance may impact classification results, where data with unbalanced classes may classify new data based on the majority class and ignore minority class data. The research analyzed whether applying the Adaptive Synthetic (ADASYN) oversampling technique in the K-Nearest Neighbor Algorithm can handle data imbalance problems. The study looks at the resulting accuracy, specificity, and sensitivity values. ADASYN oversamples the minority class data based on the model's difficulty level of data learning using distribution weights. This research uses the Pima Indian Diabetes Dataset from the Kaggle website. The dependent variable was diabetes mellitus status, while the independent variables were number of pregnancies, glucose levels, diastolic blood pressure, insulin levels, Body Mass Index (BMI), and age. The study found that the accuracy, specificity, and sensitivity values were 72.88%, 73.42%, and 71.79%, respectively. Based on the results of the analysis, it can be concluded that using ADASYN in the K-Nearest Neighbor Algorithm to classify diabetes mellitus in Pima Indian women is good enough to address imbalanced data. It is shown that the ADASYN oversampling technique can help the K-Nearest Neighbor Algorithm to classify new data without ignoring the data of the minority class.

Apply multiple machine learning models to diabetes prediction

Diabetes mellitus, a pervasive and chronic metabolic disorder, imposes a substantial burden on global health systems due to its requirement for lifelong management and the myriad of complications associated with inadequate control. The ability to accurately forecast the onset of this disease is paramount, as it enables preemptive interventions and tailored treatment strategies that can significantly mitigate its impact. This paper investigates the application of machine learning techniques and deep learning models in diabetes prediction. This paper makes use of the Pima Indian Diabetes Dataset (PIDD) from Kaggle, which has 768 data entries and eight characteristics like blood pressure, blood sugar, and body mass index (BMI). Various algorithms, including Support Vector Machine (SVM), Decision Trees(DT), Random Forest(RF) , and Fully Connected Neural Network (FCNN), are implemented and compared. Identifying the strengths and limitations of each model, the results emphasize the potential of advanced computational models in improving the accuracy and clinical usefulness of diabetes prediction. The best-performing model is the FCNN model, with a test accuracy of 78.67% and an AUC value of 83.36%.

A deep neural network prediction method for diabetes based on Kendall's correlation coefficient and attention mechanism.

Diabetes is a chronic disease, which is characterized by abnormally high blood sugar levels. It may affect various organs and tissues, and even lead to life-threatening complications. Accurate prediction of diabetes can significantly reduce its incidence. However, the current prediction methods struggle to accurately capture the essential characteristics of nonlinear data, and the black-box nature of these methods hampers its clinical application. To address these challenges, we propose KCCAM_DNN, a diabetes prediction method that integrates Kendall's correlation coefficient and an attention mechanism within a deep neural network. In the KCCAM_DNN, Kendall's correlation coefficient is initially employed for feature selection, which effectively filters out key features influencing diabetes prediction. For missing values in the data, polynomial regression is utilized for imputation, ensuring data completeness. Subsequently, we construct a deep neural network (KCCAM_DNN) based on the self-attention mechanism, which assigns greater weight to crucial features affecting diabetes and enhances the model's predictive performance. Finally, we employ the SHAP model to analyze the impact of each feature on diabetes prediction, augmenting the model's interpretability. Experimental results show that KCCAM_DNN exhibits superior performance on both PIMA Indian and LMCH diabetes datasets, achieving test accuracies of 99.090% and 99.333%, respectively, approximately 2% higher than the best existing method. These results suggest that KCCAM_DNN is proficient in diabetes prediction, providing a foundation for informed decision-making in the diagnosis and prevention of diabetes.

Comparison of Machine Learning Models for Diabetes Prediction

The prevalence of chronic diabetic disease has significantly increased recently. Blood sugar levels rise with diabetes, which also causes additional issues like blurred vision, kidney failure, nerve damage, and stroke. Early diabetes detection helps guide the implementation of the necessary measures. Everyone's attention is being drawn to the sharp rise in the number of diabetics. Different models have been built in this study to categorize diabetic and non-diabetic individuals. The classification models for the PIMA Indian Diabetes dataset have been implemented using machine learning algorithms likeLogistic Regression (LR), K-Nearest Neighbors (KNN), Random Forest(RF), and Support Vector Machine (SVM). Deep learning perspective algorithm such as Multi Layered Feed Forward Neural Network (MLFNN) also been implemented and comparisons were made. For better comparisons, accuracy and execution times for each algorithm are recorded. To further improve the diabetes dataset's classification accuracy, various activation functions, learning algorithms, and approaches to deal with missing information are taken into account. The results of MLFNN are then contrasted with machine learning algorithms. MLFNN has the highest achieved classification accuracy (92%) of all the classifiers and it will be more accurate if it is implemented in larger datasets. These models are built to improve the standard of the patient care. This research is helpful in predicting pre-diabetes and identifying the risk factors linked to the development of diabetes from clinical data.

Classification of Diabetes Using Ensemble Machine Learning Techniques

Diabetes is a widespread chronic condition that impacts people all over the globe and requires a clear and timely diagnosis. Untreated diabetes leads to retinopathy, nephropathy, and damage to the nervous system. In this context, Machine Learning (ML) might be used to detect health problems early, diagnose them, and track their progress. Ensemble techniques are a promising approach that combines many classifiers to improve forecast accuracy and resilience. This study investigates the categorization of diabetes using an ensemble machine learning technique known as a voting classifier. Using a variety of classifiers, including Light Gradient Boosting Machine (LightGBM), Gradient Boost classifier (GBC), and Random Forest (RF). The predictions are aggregated using voting methods to get a final classification result. The research is carried out using two benchmarking datasets: the Pima Indian Diabetes Dataset (PIDD) and the German Dataset. The Boruta technique is used to choose the best attributes from the datasets, while the Random Over Sampling approach balances the range of classes and eliminates abnormal data using the interquartile range approach. The findings showed that the combination of the Boruta feature selection algorithm and ensemble Voting Classifier performed better for both PIDD and German datasets with an accuracy of 93% and 90% respectively. These algorithms are evaluated and the maximum accuracy is produced using the combination of the Boruta feature selection algorithm and ensemble Voting Classifier. This research helps medical professionals in the early prediction of diabetes, reducing physician’s time.

Prediction of Diabetes Mellitus using Artificial Intelligence Techniques

Diabetes Mellitus (DM) is a global health challenge, demanding proficient predictive models for early identification and intervention. This study adopts a comprehensive strategy for diabetes prediction with Machine learning algorithms, utilizing PIMA Indian diabetes dataset which encompasses clinical, demographic and lifestyle data. Employing techniques like Recursive Feature Elimination (RFE) and correlation analysis, the feature selection process identifies influential predictors, including glucose levels, Body Mass Index (BMI), Blood Pressure and diabetic history of family. A distinctive facet of this study involves integrating IBM Auto AI, automating the machine learning pipeline for tasks like feature engineering, hyperparameter tuning and model selection. Through comparative analysis, the research evaluates the efficiency and performance enhancements achieved through automation in contrast to manually-tailored models. Evaluation metrics encompass accuracy, precision, recall, and F1 score. Crossvalidation, particularly k-fold cross-validation, ensures model generalization to diverse subsets of the dataset. The research outcomes offer valuable insights into the optimal amalgamation of AI techniques for diabetes prediction, underscoring the significance of interpretability, performance, and automation in healthcare analytics. The proposed Methodology is evaluated with different classifiers with Auto AI and without Auto AI techniques. Using IBM Auto AI,Gradient boosting algorithm performed well with 84.4 % accuracy and Logistic Regression showed good accuracy of 84. 4% among conventional machine learning techniques without Auto AI using Pima Indian Diabetes Dataset.

Comparative Analysis of Machine Learning Algorithms for Diabetic Disease Identification

This article introduces a comparative analysis of different types of machine learning algorithms (MLAs) used for diabetic disease identification. Today machine learning algorithms are a major role in solving and identifying the different type of diseases in the medical sector. In the early prediction of diabetic to easily treat physicians and protect from other diseases in patients seven types of MLAs such as support vector machine (SVM), decision tree (DT), logistic regression (LGR), Gradient boost method (GDBM), k-nearest neighbour (KNN), XG boost (XGBM) and random forest (RF) are used for diabetic identification. PIMA Indian diabetic dataset (PIMAIDD) is used to train and test the MLAs. Confusion matrix, accuracy (ACR), precision (PCN), recall (RCL), f1-score (FSC), receiver operating curve (ROC) and K-fold cross-validation are the metrics used for performance evaluation of MLAs and experiments are implemented by Jupyter notebook and python sci-kit libraries. Six types of test cases were conducted whereas test case 4 (70%-30%) was well performed in which RF reported better results in diabetic identification that differentiates from other machine learning metric scores.

SDAGS: SMOTE+FOREST DIFFUSION-BASED DATA AUGMENTATION AND GBT-BASED STACKING ENSEMBLE LEARNING FOR HOLISTIC AI-POWERED DIABETES MELLITUS PREDICTION

It's critical to track and anticipate diabetes in emerging nations like Vietnam, particularly for those with type 1 diabetes. This article proposes SDAPS, an AI-powered diabetes prediction technique. Our method is based on two ideas: (i) using the SFDM method to make the training data better by combining the oversampling of the Forest Diffusion Model with the SMOTE data balancing method; and (ii) making the GSDP model by stacking different boosting machine learning models together. We also suggest an AI-powered blood glucose monitoring and recommendation system based on SDAPS to provide diabetic patients with all-encompassing assistance with blood glucose monitoring, dietary counseling, physical activity, and the proper use of medications. Our thorough experiments using the Pima Indians diabetes dataset and the 5-fold cross-validation evaluation method demonstrate that SDAPS outperforms the state-of-the-art methods, with the following results: sensitivity, specificity, F1, accuracy, and precision: 98.03\%, 99.49%, 98.74%, 98.75%, and 98.00%, respectivelyOrder

Diabetes Prediction Using Machine Learning

Diabetes, characterized by high blood sugar levels over time, poses challenges for accurate prediction due to limited labelled data and data quality issues like outliers and missing values. To address these challenges, our research introduces a robust prediction framework. This framework integrates techniques such as outlier rejection, filling missing values, standardizing data, selecting relevant features, and employing K-fold cross-validation. We utilize a range of machine learning algorithms including k-nearest Neighbour, Decision Trees, Random Forest, AdaBoost, Naive Bayes, XGBoost, and Multilayer Perceptron (MLP). Additionally, we propose a weighted ensembling technique to enhance prediction accuracy. The weights for ensembling are determined based on the performance of each classifier using the Area Under ROC Curve (AUC) metric. We optimize model performance through hyperparameter tuning using grid search. Our experiments are conducted using the Pima Indian Diabetes Dataset under uniform conditions. The ensembling classifier we propose achieves superior performance with a sensitivity of 0.789, specificity of 0.934, false omission rate of 0.092, diagnostic odds ratio of 66.234, and AUC of 0.950. This outperforms existing methods by 2.00% in terms of AUC. Our framework surpasses other approaches discussed in the literature and shows promise for improving diabetes prediction. We have released our source code for diabetes prediction to the public.

Machine learning technique for detecting diabetes disease

Diabetes is considered a critical disease and it has been a growing concern owing to its increased morbidity. Moreover, the average age of people who are affected by diabetes illness has currently declined to the mid-20s. Given the high prevalence, it is necessary to address this problem effectively. Due to the significant prevalence of diabetes illness, it is essential to handle and address this issue appropriately. Currently, machine learning methods are considered a vital area for detecting and diagnosing disease. These methods can learn from data and classify data based on the coordinate subjects. This paper presents a model for detecting diabetes illness based on a machine learning technique. The Support Vector Machine (SVM) algorithm is used for classifying the people who are categorized as patients with diabetes disease from the people who are categorized as non-diabetic. Further, the database is compiled from the Pima Indian Diabetes Dataset (PIDD). The results show that the proposed model achieves 81.8% accuracy. Moreover, the proposed model achieves 84.34% sensitivity and 74.35% specificity.

Diabetes Mellitus prediction using Improved Chaotic Whale Optimization and Data mining techniques

Automation of disease detection is now prevalent in healthcare systems. Diabetes mellitus is a serious issue that has become prominent worldwide. It is a hereditary illness that impairs human existence at every stage of development. Each year, millions more people develop diabetes, which also has an impact on young people. Currently, the medical industry is shifting toward automation, as the process of identifying diseases needs periodic human verification. A single model for diabetes prediction is insufficient for complicated problems since it might not be appropriate for training huge data. In this proposed approach, a novel method which combines the outcomes of more than one algorithm is suggested. An ensemble approach using data mining techniques such as Decision Trees, Random Forests, AdaBoost, Gradient Boosting and XGBoost is employed to predict diabetes mellitus. Feature selection methods such as Averaged Fisher score and Kolmogorov-Smirnov score are used to choose the prominent characteristics from PIMA Indian Diabetes dataset. Further, the most optimal features are selected using Improved Chaotic Whale Optimization algorithm. The proposed approach produces predictions that are 98.8% accurate and reliable.

E-Diagnostic system for diabetes disease prediction on an IoMT environment-based hyper AdaBoost machine learning model

One of the most fatal and serious diseases that humans have encountered is diabetes, an illness affecting thousands of individuals yearly. In this era of digital systems, diabetes prediction based on machine learning (ML) is gaining high momentum. One of the benefits of treating patients early in the course of their noncommunicable diseases (NCDs) is that they can avoid costly therapies when the illness worsens later in life. Incidentally, diabetes is complicated by the dearth of medical professionals in underserved areas, such as distant rural communities. In these situations, the Internet of Medical Things and machine learning (ML) models can be used to offer healthcare practitioners the necessary prediction tools to more effectively and timely make decisions, thus assisting the early identification and diagnosis of NCDs. In this study, four conventional and hyper-AdaBoost ML models were trained and tested on the PIMA Indian Diabetes dataset. Patients with diabetes were classified on the basis of laboratory findings. Pre-processing tasks, such as the handling of imbalanced data and missing values, were performed prior to feature importance and normalisation activities. The algorithm with the best performance was examined using precision, accuracy, F1, recall and area under the curve metrics. Then, all ML models were hyper parametrically tuned via grid search to optimise their performance and reduce their error times. The decision process was also evaluated to further enhance the models. The AdaBoost-ET model performed even when features were not selected for binary classification. The model proposed in this study can predict diabetes with unprecedented high accuracy compared with the models in previous studies.

An Improved Ensemble Machine Learning Approach for Diabetes Diagnosis

Diabetes is recognized as one of the most detrimental diseases worldwide, characterized by elevated levels of blood glucose stemming from either insulin deficiency or decreased insulin efficacy. Early diagnosis of diabetes enables patients to initiate treatment promptly, thereby minimizing or eliminating the risk of severe complications. Although years of research in computational diagnosis have demonstrated that machine learning offers a robust methodology for predicting diabetes, existing models leave considerable room for improvement in terms of accuracy. This paper proposes an improved ensemble machine learning approach using multiple classifiers for diabetes diagnosis based on the Pima Indians Diabetes Dataset (PIDD). The proposed ensemble voting classifier amalgamates five machine learning algorithms: Decision Tree (DT), Logistic Regression (LR), K-Nearest Neighbor (KNN), Random Forests (RF), and XGBoost. We obtained the individual model accuracies and used the ensemble method to improve accuracy. The proposed approach uses a pre-processing stage of standardization and imputation and applies the Local Outlier Factor (LOF) to remove data anomalies. The model was evaluated using sensitivity, specificity, and accuracy criteria. With a reported accuracy of 81%, the proposed approach shows promise compared to prior classification techniques.

A Cloud-Connected Digital System for Type-1 Diabetes Prediction using Time Series LSTM Model

Abstract Millions of people worldwide suffer from diabetes, a medical condition that is spreading at an accelerating pace. Numerous studies show that risk factors that may arise from diabetes can be avoided if the disease is detected early. The health-care monitoring system has benefited greatly from early diabetes prediction made possible by the integration of Deep Learning (DL) and Machine Learning (ML) algorithms. The objective of many early studies was to increase the prediction model accuracy. However, DL algorithms often cannot fully exploit the potential of the available datasets because they are too small. This study includes a very accurate DL model as well as a novel system that integrates cloud services and allows users to directly enhance an existing data set, which can increase the accuracy of DL techniques. Therefore, the Long Short-Term Memory (LSTM) model with controller is chosen for efficient type-1 diabetes prediction. Experimental validation of the proposed Nonlinear Model Predictive Control (NMPC)_LSTM algorithm method is compared with other conventional DL algorithms. The proposed controller method achieves excellent blood glucose set point tracking and the proposed algorithms achieves 98.95% accuracy for the obtained data. It outperforms other existing methods with an increase in percentage accuracy compared to the Benchmark Pima Indian Diabetes Datasets (PIDD).

A heuristic‐based hybrid sampling method using a combination of SMOTE and ENN for imbalanced health data

AbstractHealth datasets often exhibit class imbalance, with healthy individuals being the majority class and patients being the minority class. As in many applications, machine learning methods are frequently used in the prediction and detection of diseases. The class imbalance presents a significant challenge for machine learning classifiers, particularly in their ability to accurately and effectively classify data from minority and majority classes. Therefore, data preprocessing is crucial before classifying the imbalanced data. In this study, we present GASMOTEPSO_ENN method that combines the synthetic minority oversampling technique (SMOTE) and edited nearest neighbour (ENN) algorithms using genetic algorithm (GA) and particle swarm optimization (PSO) heuristics as a preprocessing method to classify the imbalanced health datasets. In the experiments, chronic kidney disease (CKD), cerebral stroke prediction (CSP), and PIMA Indian diabetes (PID) datasets were utilized to assess the performance of the proposed method with metrics derived from the confusion matrix. The GASMOTEPSO_ENN method can classify the various diseases into different two classes of patients and healthy individuals with acceptable Matthews correlation coefficient (MCC) metric using the machine learning algorithms (Logistic regression (LR) 1.00 for CKD dataset, extreme gradient boosting (XGBoost) 0.94 for CSP dataset, and support vector machine (SVM) 0.87 for PID dataset). Moreover, the proposed method also performed well with other metrics in all datasets, and the analysis of the model results in relation to existing literature reveals that the proposed model demonstrably produces superior results.

Comparative analysis of machine learning algorithms for Diabetes Mellitus prediction

Type II Diabetes Mellitus (T2DM) has become an increasingly prevalent disease due to the rising number of the obese population. Even though this disorder is the leading cause of more severe health complications, studies have shown that T2DM is largely preventable if detected in an early phase. To improve current diagnosis and prognosis procedures, this study aims to examine three machine learning algorithmsK-Nearest Neighbor (KNN), Random Forest (RF), and Support Vector Classification (SVC)and their potential in making accurate predictions on the outcomes of the Pima Indians Diabetes Dataset (PIDD). After training and 5-fold cross validation, the results show that the RF algorithm has the highest accuracy at 75.25%, followed by SVC at 74.91% and KNN at 71.01%. In addition, feature importances were evaluated for all three models, yet we observed a drastic difference in the top-ranked features across different models, which implies that more training and larger datasets are necessary before realizing these computational approaches into practice. Nevertheless, the potential of these approaches highlighted in this study demonstrated that machine learning is a burgeoning strategy in clinical use and in solving real-world problems.