AUC Metrics Research Articles

A Lightweight Hand Attitude Estimation Method Based on GCN Feature Enhancement

In this study, a hand pose estimation method based on GCN feature enhancement is proposed to address the problem of the time-consuming nature and neglection of the internal relationships between hand joint points, which results in the low accuracy of hand pose estimation. Firstly, a lightweight feature extraction network RexNet is used, and deep separable convolutions are used instead of ordinary convolutions to reduce the model parameters and computational complexity. Secondly, deconvolution is added to the backend of the network to obtain preliminary estimation results of joint points. Finally, the GCN feature enhancement module is used to modify the preliminary estimation results to improve the accuracy of hand pose estimation. The proposed method is tested for accuracy on the CMU-Hand and RHD datasets. The results show that the proposed method achieves an AUC metric of 80.1% on the CMU-Hand dataset and 97.0% on the RHD dataset, and the accuracy of hand pose estimation is high.

Assessing the detection of lateral movement through unsupervised learning techniques

Lateral movement (LM) is an umbrella term for techniques through which attackers spread from an entry point to the rest of the network. Typically, LM involves both pivoting through multiple systems and privilege escalation. As LM techniques proliferate and evolve, there is a need for advanced security controls able to detect and possibly nip such attacks in the bud. Based on the published literature, we argue that although LM-focused intrusion detection systems have received considerable attention, a prominent issue remains largely unaddressed. This concerns the detection of LM through unsupervised machine learning (ML) techniques. This work contributes to this field by capitalizing on the LMD-2023 dataset containing traces of 15 diverse LM attack techniques as they were logged by the system monitor (Sysmon) service of the MS Windows platform. We provide a panorama of this sub-field and associated methodologies, exploring the potential of standard ML-based detection. In further detail, in addition to analyzing feature selection and preprocessing, we detail and evaluate a plethora of unsupervised ML techniques, both shallow and deep. The derived scores for the best performer in terms of the AUC and F1 metrics are quite promising, around 94.7%/93% and 95.2%/93.8%, for the best shallow and deep neural network model, respectively. On top of that, in an effort to further improve on those metrics, we devise and evaluate a two-stage ML model, surpassing the previous best score by approximately 3.5%. Overall, to our knowledge, this work provides the first full-blown study on LM detection via unsupervised learning techniques, therefore it is anticipated to serve as a groundwork for anyone working in this timely field.

DKVMN&MRI: A new deep knowledge tracing model based on DKVMN incorporating multi-relational information.

Knowledge tracing is a technology that models students' changing knowledge state over learning time based on their historical answer records, thus predicting their learning ability. It is the core module that supports the intelligent education system. To address the problems of sparse input data, lack of interpretability and weak capacity to capture the relationship between exercises in the existing models, this paper build a deep knowledge tracing model DKVMN&MRI based on the Dynamic Key-Value Memory Network (DKVMN) that incorporates multiple relationship information including exercise-knowledge point relations, exercise-exercise relations, and learning-forgetting relations. In the model, firstly, the Q-matrix is utilized to map the link between knowledge points and exercises to the input layer; secondly, improved DKVMN and LSTM are used to model the learning process of learners, then the Ebbinghaus forgetting curve function is introduced to simulate the process of memory forgetting in learners, and finally, the prediction strategies of Item Response Theory (IRT) and attention mechanism are used to combine the similarity relationship between learners' knowledge state and exercises to calculate the probability that learners would correctly respond during the subsequent time step. Through extensive experiments on three real-world datasets, we demonstrate that DKVMN&MRI has significant improvements in both AUC and ACC metrics contrast with the latest models. Furthermore, the study provides explanations at both the exercise level and learner knowledge state level, demonstrating the interpretability and efficacy of the proposed model.

Fake Review Detection Using Machine learning and Deep Learning

The widespread adoption of Web 2.0 platforms has enabled consumers to share their opinions on products and services, influencing purchasing decisions. However, the proliferation of spam reviews has undermined the credibility of online reviews. This study aims to identify and evaluate existing approaches for detecting reviews, individual spammers, and Organizations. We categorized machine learning (ML) and deep learning (DL) techniques used for Review detection and assessed their effectiveness. Our findings indicate that accuracy is the most frequently used metric (25%), followed by recall (24%) and precision (22%). Additionally, we observed that utilizing the entire Amazon dataset can enhance the performance of F-measure, AUC, and F1-score metrics by 7%. Our study concludes that SMS spam filtering strategies are often effective in combating spam reviews. Furthermore, we developed a taxonomy of existing methodologies and observed a significant number of studies employing SMS anti-spam applications. This research uncovered innovative applications of ML and DL to spam review detection, offering a novel approach to addressing this issue. Our findings provide both academics and practitioners with a deeper understanding of the challenges in spam review identification and potential avenues for improvement using ML techniques.

TCDDU-Net: combining transformer and convolutional dual-path decoding U-Net for retinal vessel segmentation

Accurate segmentation of retinal blood vessels is crucial for enhancing diagnostic efficiency and preventing disease progression. However, the small size and complex structure of retinal blood vessels, coupled with low contrast in corresponding fundus images, pose significant challenges for this task. We propose a novel approach for retinal vessel segmentation, which combines the transformer and convolutional dual-path decoding U-Net (TCDDU-Net). We propose the selective dense connection swin transformer block, which converts the input feature map into patches, introduces MLPs to generate probabilities, and performs selective fusion at different stages. This structure forms a dense connection framework, enabling the capture of long-distance dependencies and effective fusion of features across different stages. The subsequent stage involves the design of the background decoder, which utilizes deformable convolution to learn the background information of retinal vessels by treating them as segmentation objects. This is then combined with the foreground decoder to form a dual-path decoding U-Net. Finally, the foreground segmentation results and the processed background segmentation results are fused to obtain the final retinal vessel segmentation map. To evaluate the effectiveness of our method, we performed experiments on the DRIVE, STARE, and CHASE datasets for retinal vessel segmentation. Experimental results show that the segmentation accuracies of our algorithms are 96.98, 97.40, and 97.23, and the AUC metrics are 98.68, 98.56, and 98.50, respectively.In addition, we evaluated our methods using F1 score, specificity, and sensitivity metrics. Through a comparative analysis, we found that our proposed TCDDU-Net method effectively improves retinal vessel segmentation performance and achieves impressive results on multiple datasets compared to existing methods.

Quantifying the degree of scientific innovation breakthrough: Considering knowledge trajectory change and impact

Scientific breakthroughs have the potential to reshape the trajectory of knowledge flow and significantly impact later research. The aim of this study is to introduce the Degree of Innovation Breakthrough (DIB) metric to more accurately quantify the extent of scientific breakthroughs. The DIB metric takes into account changes in the trajectory of knowledge flow, as well as the deep and width of impact, and it modifies the traditional assumption of equal citation contributions by assigning weighted citation counts. The effectiveness of the DIB metric is assessed using ROC curves and AUC metrics, demonstrating its ability to differentiate between high and low scientific breakthroughs with high sensitivity and minimal false positives. Based on ROC curves, this study proposes a method to calculate the threshold for high scientific breakthrough, reducing subjectivity. The effectiveness of the proposed method is demonstrated through a dataset consisting of 1108 award-winning computer science papers and 9832 matched control papers, showing that the DIB metric surpasses single-dimensional metrics. The study also performs a granular analysis of the innovation breakthrough degree of non-award-winning papers, categorizing them into four types based on originality and impact through 2D histogram visualization, and suggests tailored management strategies. Through the adoption of this refined classification strategy, the management of innovation practices can be optimized, ultimately fostering the enhancement of innovative research outcomes. The quantitative tools introduced in this paper offer guidance for researchers in the fields of science intelligence mining and science trend prediction.

Machine learning-based discrimination of benign and malignant breast lesions on US: The contribution of shear-wave elastography

PurposeTo build and validate a combined radiomics and machine learning (ML) approach using B-mode US and SWE images to differentiate benign from malignant solid breast lesions (BLs) and compare its performance with that of an expert radiologist. MethodsPatients with at least one BI-RADS 2–6 BL who performed breast US integrated with SWE were retrospectively included. B-mode US and SWE images were manually segmented to extract radiomics features. A multi-step feature selection process was performed and a predictive model built using the Logistic Regression algorithm. The diagnostic accuracy was evaluated with the AUC and Matthews Correlation Coefficient (MCC) metrics. The performance of the ML classifier was compared to that of an expert radiologist. Results427 Bls were included and divided into a training (286 BLs, of which 127 benign and 159 malignant) and a test set (141 BLs, of which 59 benign and 82 malignant). Of 1098 features extracted from B-mode US and SWE images, 13 were finally selected. The ML classifier showed an AUC of 0.768 and 0.746, and an MCC of 0.403 and 0.423 in the training and test sets, respectively. The performance was higher than that of the expert radiologist assessing only B-mode US images, but significantly lower when SWE images were also provided. ConclusionA ML approach based on B-mode US and SWE images may represent a potential tool in the characterization of BLs. SWE still gives its most relevant contribution in the clinical setting rather than included in a radiomics pipeline.

Comparative Analysis of Machine Learning Models and Hybrid Ensemble Approach’s for Landslide Prediction

The NH-44 Jammu Srinagar National Highway in India is susceptible to landslides, rock falls and shooting stones due to its geological characteristics and steep slopes. This study aims to compare the performance of various Machine Learning (ML) algorithms and hybrid models in predicting landslides using historical data. Seven optimized ML approaches Support Vector Classifier (SVC), Logistic Regression (LR), Decision Tree (DT), K Nearest Classifier (KNC), Random Forest (RF), GaussianNB (GNB) and AdaBoost Classifier (ABC) are used. Additionally, two Hybrid Ensemble methods, the Voting Hybrid Model (VHM) and Stacking Hybrid Model (SHM), are introduced. The performance of each model is evaluated using accuracy, precision, recall, F1-score and AUC metrics. Results indicate that all the models performed well, with hybrid ensemble models surpassing all individual algorithms. The Stacking Hybrid Model (SHM) excels achieving 99.4% accuracy and 98.5% AUC, outperforming the Voting Hybrid Model (VHM). Hybrid models consistently outperform individual models in accuracy and AUC. These proposed methods exhibit robustness and enhanced results in addressing this issue. This framework can help to predict the landslides with high accuracy which can save the lives through timely evacuations from high-risk areas.

CNVoyant a machine learning framework for accurate and explainable copy number variant classification

The precise classification of copy number variants (CNVs) presents a significant challenge in genomic medicine, primarily due to the complex nature of CNVs and their diverse impact on rare genetic diseases (RGDs). This complexity is compounded by the limitations of existing methods in accurately distinguishing between benign, uncertain, and pathogenic CNVs. Addressing this gap, we introduce CNVoyant, a machine learning-based multi-class framework designed to enhance the clinical significance classification of CNVs. Trained on a comprehensive dataset of 52,176 ClinVar entries across pathogenic, uncertain, and benign classifications, CNVoyant incorporates a broad spectrum of genomic features, including genome position, disease-gene annotations, dosage sensitivity, and conservation scores. Models to predict the clinical significance of copy number gains and losses were trained independently. Final models were selected after testing 29 machine learning architectures and 10,000 hyperparameter combinations each for deletions and duplications via fivefold cross-validation. We validate the performance of CNVoyant by leveraging a comprehensive set of 21,574 CNVs from the DECIPHER database, a highly regarded resource known for its extensive catalog of chromosomal imbalances linked to clinical outcomes. Compared to alternative approaches, CNVoyant shows marked improvements in precision-recall and ROC AUC metrics for binary pathogenic classifications while going one step further, offering multi-classification of clinical significance and corresponding SHAP explainability plots. Additionally, when provided germline CNV calls from real-world RGD cases with diagnostic CNV(s), CNVoyant correctly classified all diagnostic CNVs as having pathogenic significance with high confidence. This large-scale validation demonstrates CNVoyant’s superior accuracy and underscores its potential to aid genomic researchers and clinical geneticists in interpreting the clinical implications of real CNVs.

Using machine learning to predict investors’ switching behaviour

Individual investors’ decisions to switch investments very often lead to significantly lower investment returns so having an effective predictive model of these switches would be of value to clients, advisors and investment managers. A random forest algorithm was applied to a new dataset of over 20 million observations relating to 95,685 clients on Momentum Investments’ platform between 2018 and 2024. It identified a combination of investor characteristics (number of holdings, past switching behaviour, total assets) and external features (past returns, macroeconomic variables) as the key features of investor switch behaviour. This model exceeds commercially accepted standards in respect of the AUC and Gini metrics showcasing the model’s strength in its ranking capability. It can thus provide a useful basis for client segmentation and engagement by financial advisors.

Implementing machine learning to predict survival outcomes in patients with resected pulmonary large cell neuroendocrine carcinoma

ABSTRACT Background The post-surgical prognosis for Pulmonary Large Cell Neuroendocrine Carcinoma (PLCNEC) patients remains largely unexplored. Developing a precise prognostic model is vital to assist clinicians in patient counseling and creating effective treatment strategies. Research design and methods This retrospective study utilized the Surveillance, Epidemiology, and End Results database from 2000 to 2018 to identify key prognostic features for Overall Survival (OS) in PLCNEC using Boruta analysis. Predictive models employing XGBoost, Random Forest, Decision Trees, Elastic Net, and Support Vector Machine were constructed and evaluated based on Area Under the Receiver Operating Characteristic Curve (AUC), calibration plots, Brier scores, and Decision Curve Analysis (DCA). Results Analysis of 604 patients revealed eight significant predictors of OS. The Random Forest model outperformed others, with AUC values of 0.765 and 0.756 for 3 and 5-year survival predictions in the training set, and 0.739 and 0.706 in the validation set, respectively. Its superior validation cohort performance was confirmed by its AUC, calibration, and DCA metrics. Conclusions This study introduces a novel machine learning-based prognostic model with a supportive web-based platform, offering valuable tools for healthcare professionals. These advancements facilitate more personalized clinical decision-making for PLCNEC patients following primary tumor resection.

ADVANCED MACHINE LEARNING AND DEEP LEARNING APPROACHES FOR PREDICTING AVIAN INFLUENZA OUTBREAKS

This study examines avian influenza outbreak identification using advanced machine learning models. The dataset includes geographical coordinates, species information, and temporal data. Initial preprocessing involved converting columns to numerical types and removing outliers with the Isolation Forest algorithm, isolating 5% of the data as outliers. Data cleaning ensured dataset integrity. Feature correlations were analyzed, focusing on those linked to H5 highly pathogenic avian influenza (HPAI). Machine learning models, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine (SVM), and Gradient Boosting, were used to predict the target variable. Performance was evaluated using ROC curve and AUC metrics, with the Random Forest model showing the highest AUC score. Deep learning models, specifically a neural network and a convolutional neural network (CNN), were implemented to enhance predictive accuracy. The CNN outperformed traditional machine learning models, demonstrating the potential of deep learning in epidemiological predictions. The study underscores the efficacy of these techniques in predicting avian influenza outbreaks, highlighting the importance of advanced analytical methods in public health predictive modeling

Comparison of the impact of dimensionality reduction and data splitting on classification performance in credit risk assessment

Credit risk assessment (CRA) plays an important role in credit decision-making process of financial institutions. Today, developing big data analysis and machine learning methods have marked a new era in credit risk estimation. In recent years, using machine learning methods in credit risk estimation has emerged as an alternative method for financial institutions. The past demographic and financial data of the person whose CRA will be performed is important for creating an automatic artificial intelligence credit score prediction model based on machine learning. It is also necessary to use features correctly to create accurate machine learning models. This article aims to investigate the effects of dimensionality reduction and data splitting steps on the performance of classification algorithms widely used in the literature. In our study, dimensionality reduction was performed using Principal Component Analysis (PCA). Random Forest (RF), Logistic Regression (LR), Decision Tree (DT), Naive Bayes (NB) algorithms were chosen for classification. Percentage splitting (PER, 66–34%) and k-fold (k = 10) cross-validation techniques were used when dividing the data set into training and test data. The results obtained were evaluated with accuracy, recall, F1 score, precision, and AUC metrics. German data set was used in this study. The effect of data splitting and dimension reduction on the classification of CRA systems was examined. The highest ACC in PER and CV data splitting was obtained with the RF algorithm. Using data splitting methods and PCA, the highest accuracy was observed with RF and the highest AUC with NB, with 13 PCs in which 80% of the variance was obtained. As a result, the data set consisting of a total of 20 features, expressed by 13 PCs, achieved similar or higher success than the results obtained from the original data set.

Prediction of 30-day mortality for ICU patients with Sepsis-3

BackgroundThere is a growing demand for advanced methods to improve the understanding and prediction of illnesses. This study focuses on Sepsis, a critical response to infection, aiming to enhance early detection and mortality prediction for Sepsis-3 patients to improve hospital resource allocation.MethodsIn this study, we developed a Machine Learning (ML) framework to predict the 30-day mortality rate of ICU patients with Sepsis-3 using the MIMIC-III database. Advanced big data extraction tools like Snowflake were used to identify eligible patients. Decision tree models and Entropy Analyses helped refine feature selection, resulting in 30 relevant features curated with clinical experts. We employed the Light Gradient Boosting Machine (LightGBM) model for its efficiency and predictive power.ResultsThe study comprised a cohort of 9118 Sepsis-3 patients. Our preprocessing techniques significantly improved both the AUC and accuracy metrics. The LightGBM model achieved an impressive AUC of 0.983 (95% CI: [0.980–0.990]), an accuracy of 0.966, and an F1-score of 0.910. Notably, LightGBM showed a substantial 6% improvement over our best baseline model and a 14% enhancement over the best existing literature. These advancements are attributed to (I) the inclusion of the novel and pivotal feature Hospital Length of Stay (HOSP_LOS), absent in previous studies, and (II) LightGBM’s gradient boosting architecture, enabling robust predictions with high-dimensional data while maintaining computational efficiency, as demonstrated by its learning curve.ConclusionsOur preprocessing methodology reduced the number of relevant features and identified a crucial feature overlooked in previous studies. The proposed model demonstrated high predictive power and generalization capability, highlighting the potential of ML in ICU settings. This model can streamline ICU resource allocation and provide tailored interventions for Sepsis-3 patients.

CfExplainer: Explainable just-in-time defect prediction based on counterfactuals

Just-in-time (JIT) defect prediction helps rationally allocate testing resources and reduce testing costs. However, most JIT defect prediction models lack explainability, which significantly affects their credibility. Recently, the local interpretable model-agnostic explanations (LIME) method has been used widely in model-explainable research, and many improved LIME-based methods have been proposed. However, problems with respect to explanation effectiveness and reliability remain, which seriously affects the practical use of LIME. To address this problem, CfExplainer, a local rule-based model-agnostic approach, is proposed. The approach first applies counterfactuals to generate synthetic instances. It then mines weighted class association rules based on synthetic instances, and it optimises the process of generating, ranking, pruning, and predicting the class association rules. Next, it employs the rules with the highest priority to explain the prediction results of the model. Experiments were conducted using the public datasets employed in related studies. Compared to other state-of-the-art methods, in terms of explanation effectiveness, CfExplainer's instance similarity improves by 26.5 %-31.2 %, and local model fittness improves by 2.0 %-3.5 %, 2.3 %-3 %, and 0.7 %-7.5 % on the AUC, F1-score, and Popt metrics, respectively. In terms of the reliability of the explanation, explanations that are 2.6 %-4.7 % more unique and 2.5 %-5.9 % more consistent with the actual characteristics of defect-introducing commits than other state-of-the-art methods. Thus, the explanations of the proposed approach can enhance the model credibility and help guide developers in fixing defects and reducing the risk of introducing them.

GamaNNet: A Novel Plant Pathologist-Level CNN Architecture for Intelligent Diagnosis

Plant pathologies significantly jeopardise global food security, necessitating the development of prompt and precise diagnostic methods. This study employs advanced deep learning techniques to evaluate the performance of nine convolutional neural networks (CNNs) in identifying a spectrum of phytosanitary issues affecting the foliage of Solanum lycopersicum (tomato). Ten thousand RGB images of leaf tissue were subsampled in training (64%), validation (16%), and test (20%) sets to rank the most suitable CNNs in expediting the diagnosis of plant disease. The study assessed the performance of eight well-known networks under identical hyperparameter conditions. Additionally, it introduced the GamaNNet architecture, a custom-designed model optimised for superior performance on this specific type of dataset. The investigational results were most promising for the innovative GamaNNet and ResNet-152, which both exhibited a 91% accuracy rate, as evidenced by their confusion matrices, ROC curves, and AUC metrics. In comparison, LeNet-5 and ResNet-50 demonstrated lower assertiveness, attaining accuracies of 74% and 69%, respectively. GoogLeNet and Inception-v3 emerged as the frontrunners, displaying diagnostic preeminence, achieving an average F1-score of 97%. Identifying such pathologies as Early Blight, Late Blight, Corynespora Leaf Spot, and Septoria Leaf Spot posed the most significant challenge for this class of problem.

Enhancing cardiovascular risk assessment with advanced data balancing and domain knowledge-driven explainability

In medical risk prediction, such as predicting heart disease, machine learning (ML) classifiers must achieve high accuracy, precision, and recall to minimize the chances of incorrect diagnoses or treatment recommendations. However, real-world datasets often have imbalanced data, which can affect classifier performance. Traditional data balancing methods can lead to overfitting and underfitting, making it difficult to identify potential health risks accurately. Early prediction of heart attacks is of paramount importance, and researchers have developed ML-based systems to address this problem. However, much of the existing ML research is based on a single dataset, often ignoring performance evaluation across multiple datasets. As the demand for interpretable ML models grows, model interpretability becomes central to revealing insights and feature effects within predictive models. To address these challenges, we present a novel data balancing technique that uses a divide-and-conquer strategy with the K-Means clustering algorithm to segment the dataset. The performance of our approach is highlighted through comparisons with established techniques, which demonstrate the superiority of our proposed method. To address the challenge of inter-dataset discrepancies, we use two different datasets. Our holistic pipeline, strengthened by the innovative balancing technique, effectively addresses performance discrepancies, culminating in a significant improvement from 81% to 90%. Furthermore, through advanced statistical analysis, it has been determined that the 95% confidence interval for the AUC metric of our method ranges from 0.8187 to 0.8411. This observation serves to underscore the consistency and reliability of our approach, demonstrating its ability to achieve high performance across a range of scenarios. Incorporating Explainable AI (XAI), we examine the feature rankings and their contributions within the best performing Random Forest model. While the domain expert feedback is consistent with the explanatory power of XAI, some differences remain. Nevertheless, a remarkable convergence in feature ranking and weighting is observed, bridging the insights from XAI tools and domain expert perspectives.

BiRNN-DDI: A Drug-Drug Interaction Event Type Prediction Model Based on Bidirectional Recurrent Neural Network and Graph2Seq Representation.

Research on drug-drug interaction (DDI) prediction, particularly in identifying DDI event types, is crucial for understanding adverse drug reactions and drug combinations. This work introduces a Bidirectional Recurrent Neural Network model for DDI event type prediction (BiRNN-DDI), which simultaneously considers structural relationships and contextual information. Our BiRNN-DDI model constructs drug feature graphs to mine structural relationships. For contextual information, it transforms drug graphs into sequences and employs a two-channel structure, integrating BiRNN, to obtain contextual representations of drug-drug pairs. The model's effectiveness is demonstrated through comparisons with state-of-the-art models on two DDI event-type benchmarks. Extensive experimental results reveal that BiRNN-DDI surpasses other models in accuracy, AUPR, AUC, F1 score, Precision, and Recall metrics on both small and large datasets. Additionally, our model exhibits a lower parameter space, indicating more efficient learning of drug feature representations and prediction of potential DDI event types.

Prediction of diabetes mellitus using XGBoost model

With the number of health-threatening diseases and deaths on the rise, medical decision support systems continue to prove effective in improving the efficiency of physicians and other healthcare providers and supporting clinical decisions. Diabetes remains one of the leading diseases responsible for many deaths worldwide. Diabetes is characterized by elevated blood glucose levels, which can have serious consequences for other organs in the body. According to the International Diabetes Alliance (IDA), 382 million people currently have diabetes and this number is expected to double to 592 million by 2035. This paper proposes a clinical prediction model for diabetes based on machine learning (ML).As traditional ML models, we consider the most commonly used classifiers, the Logic Tree (LR) and XGBoost. We compare these ML models. On the other hand, we also use deep learning (DL) models and apply a fully convolutional neural network (DNN) for diabetes prediction and recognition. The proposed models were evaluated in the public Kaggle database: prediction performance at each level was analyzed using the Precision, Recall, AUC, accuracy and F1 metrics, and overall prediction efficiency was assessed using accuracy and its macro-average: DL, LR, The overall accuracy obtained by XGBoost was 91.88%, 88.75% and 97.12% respectively. The experimental results show that XGBoost is more effective at predicting diabetes than deep learning and LR methods.

Prediction of diabetes mellitus using XGBoost model

With the number of health-threatening diseases and deaths on the rise, medical decision support systems continue to prove effective in improving the efficiency of physicians and other healthcare providers and supporting clinical decisions. Diabetes remains one of the leading diseases responsible for many deaths worldwide. Diabetes is characterized by elevated blood glucose levels, which can have serious consequences for other organs in the body. According to the International Diabetes Alliance (IDA), 382 million people currently have diabetes and this number is expected to double to 592 million by 2035. This paper proposes a clinical prediction model for diabetes based on machine learning (ML).As traditional ML models, we consider the most commonly used classifiers, the Logic Tree (LR) and XGBoost. We compare these ML models. On the other hand, we also use deep learning (DL) models and apply a fully convolutional neural network (DNN) for diabetes prediction and recognition. The proposed models were evaluated in the public Kaggle database: prediction performance at each level was analyzed using the Precision, Recall, AUC, accuracy and F1 metrics, and overall prediction efficiency was assessed using accuracy and its macro-average: DL, LR, The overall accuracy obtained by XGBoost was 91.88%, 88.75% and 97.12% respectively. The experimental results show that XGBoost is more effective at predicting diabetes than deep learning and LR methods.