Diabetes Prediction Using Machine Learning with Feature Engineering and Hyperparameter Tuning

Evaluation of multispectral imaging for freeze damage assessment in strawberries using AI-based computer vision technology

Health care Management System (HMS) is a key to successful management of any health care industry. Health care management systems have so many research dimensions such as identifying disease and diagnostic, drug discovery manufacturing, Bioinformatics’ problem, personalized treatments, Patient image analysis and so on. Heart Disease Prediction (HDP) is a process of identifying heart disease in advance and recognizes patient health condition by applying techniques on patient heart related symptoms. Now a day’s the problem of identifying heart diseases is solved by machine learning techniques. In this paper we construct a heart disease prediction method using combined feature selection and classification machine learning techniques. According to the existing study the one of the main difficult in heart disease prediction system is that the available data in open sources are not properly recorded the necessary characteristics and there is some lagging in finding the useful features from the available features. The process of removing inappropriate features from an available feature set while preserving sufficient classification accuracy is known as feature selection. A methodology is proposed in this paper that consists of two phases: Phase one employs two broad categories of feature selection techniques to identify the efficient feature sets and it is given to the input of our second phase such as classification. In this work we will concentrate on filter-based method for feature selection such as Chi-square, Fast Correlation Based Filter (FCBF), Gini Index (GI), RelifeF, and wrapper-based method for feature selection such as Backward Feature Elimination (BFE), Exhaustive Feature Selection (EFS), Forward Feature Selection (FFS), and Recursive Feature Elimination (RFE). The UCI heart disease data set is used to evaluate the output in this study. Finally, the proposed system's performance is validated by various experiments setups.

Simple SummaryThe objective response rate of lenvatinib combined with transarterial chemoembolization for unresectable hepatocellular carcinoma is unsatisfactory. We aimed to develop predictive models using demographic characteristics, pre-treatment serum biomarkers and tumor characteristics of unresectable hepatocellular carcinoma patients by five machine learning algorithms to predict the response under combined treatments. We identified the 10 most important predictors, including K, low-density lipoprotein, D-dimer, red blood cell, alanine aminotransferase, albumin, monocyte, tumor size, triglyceride, and age. In addition, we applied the Shapley Additive exPlanation to explain the best-performing random forest predictive model to provide a reasonable explanation of the efficacy prediction at an individualized level. The combination of machine learning and Shapley Additive exPlanation can provide valuable suggestions for clinical decision making.Background: Lenvatinib and transarterial chemoembolization (TACE) are first-line treatments for unresectable hepatocellular carcinoma (HCC), but the objective response rate (ORR) is not satisfactory. We aimed to predict the response to lenvatinib combined with TACE before treatment for unresectable HCC using machine learning (ML) algorithms based on clinical data. Methods: Patients with unresectable HCC receiving the combination therapy of lenvatinib combined with TACE from two medical centers were retrospectively collected from January 2020 to December 2021. The response to the combination therapy was evaluated over the following 4–12 weeks. Five types of ML algorithms were applied to develop the predictive models, including classification and regression tree (CART), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), random forest (RF), and support vector machine (SVM). The performance of the models was assessed by the receiver operating characteristic (ROC) curve and area under the receiver operating characteristic curve (AUC). The Shapley Additive exPlanation (SHAP) method was applied to explain the model. Results: A total of 125 unresectable HCC patients were included in the analysis after the inclusion and exclusion criteria, among which 42 (33.6%) patients showed progression disease (PD), 49 (39.2%) showed stable disease (SD), and 34 (27.2%) achieved partial response (PR). The nonresponse group (PD + SD) included 91 patients, while the response group (PR) included 34 patients. The top 40 most important features from all 64 clinical features were selected using the recursive feature elimination (RFE) algorithm to develop the predictive models. The predictive power was satisfactory, with AUCs of 0.74 to 0.91. The SVM model and RF model showed the highest accuracy (86.5%), and the RF model showed the largest AUC (0.91, 95% confidence interval (CI): 0.61–0.95). The SHAP summary plot and decision plot illustrated the impact of the top 40 features on the efficacy of the combination therapy, and the SHAP force plot successfully predicted the efficacy at the individualized level. Conclusions: A new predictive model based on clinical data was developed using ML algorithms, which showed favorable performance in predicting the response to lenvatinib combined with TACE for unresectable HCC. Combining ML with SHAP could provide an explicit explanation of the efficacy prediction.

BACKGROUNDThe International Study Group of Pancreatic Surgery has established the definition and grading system for postpancreatectomy acute pancreatitis (PPAP). There are no established machine learning models for predicting PPAP following pancreaticoduodenectomy (PD).AIMTo explore the predictive model of PPAP, and test its predictive efficacy to guide the clinical work.METHODSClinical data from consecutive patients who underwent PD between 2016 and 2024 were retrospectively collected. An analysis of PPAP risk factors was performed, various machine learning algorithms [logistic regression, random forest, gradient boosting decision tree, extreme gradient boosting, light gradient boosting machine, and category boosting (CatBoost)] were utilized to develop predictive models. Recursive feature elimination was employed to select several variables to achieve the optimal machine algorithm.RESULTSThe study included 381 patients, of whom 88 (23.09%) developed PPAP. PPAP patients exhibited a significantly higher incidence of postoperative pancreatic fistula (55.68% vs 14.68%, P < 0.001), grade C postoperative pancreatic fistula (9.09% vs 1.37%, P = 0.001). The CatBoost algorithm outperformed other algorithms with a mean area under the receiver operating characteristic curve of 0.859 [95% confidence interval (CI): 0.814-0.905] in the training cohort and 0.822 (95%CI: 0.717-0.927) in the testing cohort. According to shapley additive explanations analysis, pancreatic texture, main pancreatic duct diameter, body mass index, estimated blood loss, and surgery time were the most important variables based on recursive feature elimination. The CatBoost algorithm based on selected variables demonstrated superior performance, with an area under the receiver operating characteristic curve of 0.837 (95%CI: 0.788-0.886) in the training cohort and 0.812 (95%CI: 0.697-0.927) in the testing cohort.CONCLUSIONWe developed the first machine learning-based predictive model for PPAP following PD. This predictive model can assist surgeons in anticipating and managing this complication proactively.

Cancer remains a leading cause of global mortality, where early detection significantly improves survival rates. This study presents a machine learning (ML) framework for cancer prediction using clinical datasets, addressing critical gaps in conventional diagnostic methods. We analyzed demographic, lifestyle, and biomarker data from 5,000 patients (breast, lung, and colorectal cancers), incorporating feature engineering to handle missing values and class imbalances. Five ML algorithms—Random Forest (RF), XG Boost, Support Vector Machines (SVM), Logistic Regression (LR), and Neural Networks (NN)—were trained to classify malignancy risk. Data preprocessing included SMOTE oversampling and Standard Scalar normalization, followed by Recursive Feature Elimination (RFE) to prioritize high-impact predictors (e.g., tumor size, genetic mutations, and biomarker levels). Hyper parameter tuning via Grid Search CV optimized model performance, evaluated using 5-fold cross-validation.

ObjectiveAsthma, a chronic respiratory condition characterized by airway inflammation and constriction, affects millions of individuals worldwide, resulting in high healthcare expenses and a lower quality of life. Early prediction and control of asthma risk are critical for avoiding exacerbations and improving outcomes.MethodsIn this study, we describe a comprehensive asthma prediction model that uses machine learning and deep learning techniques to estimate asthma risk based on a variety of health and environmental parameters. Recursive feature elimination and Extra Trees Classifier were used to choose features, and the synthetic minority over-sampling approach was used to balance the dataset to overcome class imbalance. Hyperparameter tuning was used to optimize performance for 12 machine learning models such as extreme gradient boosting, Random Forest, and support vector machine as well as deep learning models, including multilayer perceptrons, convolutional neural networks, recurrent neural network, and artificial neural network.ResultsAfter hyperparameter adjustment, ensemble approaches that used both hard and soft voting were evaluated. When hyperparameter adjustment was used, the soft voting ensemble that combined XGBoost and CatBoost achieved the highest accuracy (93.61%). Shapley additive explanations and local interpretable model-agnostic explanations were employed to make predictions interpretable, providing information on feature contributions and boosting clinician confidence. A Flask server and web interface were also deployed, enabling real-time user interaction where patients and medical professionals could enter data and obtain asthma risk estimations immediately.ConclusionsThis study presents an accurate and explainable asthma risk prediction framework using ensemble machine and deep learning models, achieving 93.61% accuracy with real-time clinical applicability.

BackgroundDepression is a prevalent and challenging mental health condition, often resistant to traditional therapies. Repetitive transcranial magnetic stimulation (rTMS) is an FDA-approved treatment for resistant depression, but predicting treatment response remains difficult. Metabolic factors, such as obesity, diabetes, and associated inflammatory pathways, are increasingly recognized as influencing depression treatment outcomes. Leveraging machine learning may provide insights into how these factors predict rTMS efficacy, enabling more personalized treatments.Aims & ObjectivesThis study aims to identify key metabolic and clinical factors that predict rTMS treatment outcomes in patients with major depressive disorder (MDD) and bipolar disorder (BD). To achieve this, machine learning models were employed to develop predictive frameworks tailored for small participant groups.MethodSixty-eight patients (28 with BD) participated, undergoing 12 sessions of rTMS targeting the left dorsolateral prefrontal cortex. Participants were assessed at baseline, Week 4, and Week 12 using the Hamilton Depression Rating Scale (HDRS). Predictive models were developed using recursive feature elimination (RFE) and four machine learning algorithms: Random Forest, Gradient Boosting, Extra Trees, and XGBoost. Key features identified included body mass index (BMI), cholesterol ratios, and insulin resistance markers. SHAP (Shapley Additive Explanation) values were applied for model interpretation.ResultsAt Week 4, the remission rate was 59.6%, with BMI, systolic blood pressure (SBP), and LDL/HDL ratio emerging as significant predictors. The Extra Trees model achieved the highest performance (AUC = 0.766, accuracy = 0.726). At Week 12, remission was 61.5%, and predictors included insulin resistance (HOMA-IR), brain-derived neurotrophic factor (BDNF), and LDL/HDL ratio. The Gradient Boosting model excelled (AUC = 0.862, accuracy = 0.773). SHAP analysis highlighted BMI and HOMA-IR as the most influential factors at Weeks 4 and 12, respectively.Discussion & ConclusionsThe study underscores the impact of metabolic health on depression treatment outcomes. Metabolic dysregulation, particularly obesity and insulin resistance, may impair neuroplasticity and inflammation pathways, complicating treatment. BDNF's role in neurogenesis and metabolism was also highlighted as pivotal for recovery. Machine learning models demonstrated robust predictive performance, emphasizing the potential of integrating clinical and metabolic data to refine rTMS treatment approaches.Metabolic and clinical factors significantly influence rTMS outcomes in depression. Machine learning models, especially Extra Trees and Gradient Boosting, offer promising tools for individualized treatment planning. Future research should validate these findings in larger populations and explore additional biomarkers. Personalized approaches that account for metabolic health could reduce the trial-and-error nature of depression treatment and improve patient outcomes.

Recent technological advances allowed an exponential expansion of biological sequence data, and the extraction of meaningful information through Machine Learning (ML) algorithms. This knowledge improved the understanding of the mechanisms related to several fatal diseases, e.g., Cancer and COVID-19, helping to develop innovative solutions, such as CRISPR-based gene editing, coronavirus vaccine, and precision medicine. These advances benefit our society and economy, directly impacting peoples lives in various areas, such as health care, drug discovery, forensic analysis, and food analysis. Nevertheless, ML approaches applied to biological data require representative, quantitative, and informative features. Necessarily, as many ML algorithms can handle only numerical data, sequences need to be translated into a feature vector. This process, known as feature extraction, is a fundamental step for the elaboration of high-quality ML-based models in bioinformatics, by allowing the feature engineering stage, with the design and selection of suitable features. Feature engineering, ML algorithm selection, and hyperparameter tuning are often manual and time-consuming processes, requiring extensive domain knowledge, and performed manually by a human expert. To deal with this problem, we developed a new package, BioAutoML, which automatically runs an end-to-end ML pipeline. BioAutoML extracts numerical and informative features from biological sequence databases, automating feature selection, recommendation of ML algorithm(s), and tuning of hyperparameters, using Automated ML (AutoML). BioAutoML has two components, divided into four modules, (1) automated feature engineering (feature extraction and selection modules) and (2) Metalearning (algorithm recommendation and hyperparameter tuning modules). Our experimental results, assessing the relevance of our proposal, indicate robust results for different problem domains, such as SARS-CoV-2, anticancer peptides, HIV sequences, and non-coding RNAs. According to our systematic review, our proposal is innovative compared to available studies in the literature, being the first study to propose automated feature engineering and metalearning for biological sequences. BioAutoML has a high potential to significantly reduce the expertise required to use ML pipelines, aiding researchers in combating diseases, particularly in low- and middle-income countries. This initiative can provide biologists, physicians, epidemiologists, and other stakeholders with an opportunity for widespread use of these techniques to enhance the health and well-being of their communities.

Serious bacterial infections (SBIs) are linked to unplanned hospital admissions and a high mortality rate. The early identification of SBIs is crucial in clinical practice. This study aims to establish and validate clinically applicable models designed to identify SBIs in patients with infective fever. Clinical data from 945 patients with infective fever, encompassing demographic and laboratory indicators, were retrospectively collected from a 2200-bed teaching hospital between January 2013 and December 2020. The data were randomly divided into training and test sets at a ratio of 7:3. Various machine learning (ML) algorithms, including Boruta, Lasso (least absolute shrinkage and selection operator), and recursive feature elimination, were utilized for feature filtering. The selected features were subsequently used to construct models predicting SBIs using logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) with 5-fold cross-validation. Performance metrics, including the receiver operating characteristic (ROC) curve and area under the ROC curve (AUC), accuracy, sensitivity, and other relevant parameters, were used to assess model performance. Considering both model performance and clinical needs, 2 clinical timing-sequence warning models were ultimately confirmed using LR analysis. The corresponding predictive nomograms were then plotted for clinical use. Moreover, a physician, blinded to the study, collected additional data from the same center involving 164 patients during 2021. The nomograms developed in the study were then applied in clinical practice to further validate their clinical utility. In total, 69.9% (661/945) of the patients developed SBIs. Age, hemoglobin, neutrophil-to-lymphocyte ratio, fibrinogen, and C-reactive protein levels were identified as important features by at least two ML algorithms. Considering the collection sequence of these indicators and clinical demands, 2 timing-sequence models predicting the SBI risk were constructed accordingly: the early admission model (model 1) and the model within 24 hours of admission (model 2). LR demonstrated better stability than RF and XGBoost in both models and performed the best in model 2, with an AUC, accuracy, and sensitivity of 0.780 (95% CI 0.720-841), 0.754 (95% CI 0.698-804), and 0.776 (95% CI 0.711-832), respectively. XGBoost had an advantage over LR in AUC (0.708, 95% CI 0.641-775 vs 0.686, 95% CI 0.617-754), while RF achieved better accuracy (0.729, 95% CI 0.673-780) and sensitivity (0.790, 95% CI 0.728-844) than the other 2 approaches in model 1. Two SBI-risk prediction nomograms were developed for clinical use based on LR, and they exhibited good performance with an accuracy of 0.707 and 0.750 and a sensitivity of 0.729 and 0.927 in clinical application. The clinical timing-sequence warning models demonstrated efficacy in predicting SBIs in patients suspected of having infective fever and in clinical application, suggesting good potential in clinical decision-making. Nevertheless, additional prospective and multicenter studies are necessary to further confirm their clinical utility.

ObjectiveEnhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice.MethodsResearches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized.ResultsBased on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics.ConclusionResearchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.

Diabetes Mellitus (DM) is caused due to the elevated levels of blood sugar i.e., said to be hyperglycemia. The DM is a metabolic chronic disease; therefore, early diagnosis and treatment is necessary to avoid life-threatening risks. According to the World Health Organization (WHO), the diabetes cause high mortality rate with 1.5 million deaths in a year. With the remarkable improvisations in the technology, the disease can be diagnosed earlier. In this paper, we have developed a decision-making support with the machine learning algorithms for DM diagnosis. The Pima Indians Diabetes dataset was chosen to train with Machine Learning algorithms. Our approach begins with Exploratory data analysis, and later the data is sent for data pre-processing and perform the feature Selection techniques. The important features are selected and finally, the data is trained with six various Machine learning (ML) algorithms such as Naïve Bayes, KNN, Random Forest, Logistic Regression, Decision Tree, and eXtreme gradient boosting. The Experimental results of the ML algorithms are calculated by the performance metrics in which that the eXtreme Gradient Boosting has scored highest with 88.2% accuracy than other machine learning algorithms.

Blood pressure abnormality detection and Interpretation utilizing Explainable Artificial Intelligence

Bone marrow is the source of many blood-related diseases, such as blood cancers, and Bone Marrow Transplantation (BMT), also known as Hematopoietic Stem Cell Transplantation (HSCT), is a life-saving surgical procedure. However, this treatment is associated with a high risk of mortality. Predicting survival after BMT is therefore essential for effective and accurate treatment. BMT is considered a treatment-related mortality due to several primary causes of death such as infections, toxicity, and Graft-versus-Host Disease (GvHD) that occur after treatment. In addition, several risk factors affect the success of BMT and long-term survival after treatment. Therefore, there is a need for a prediction system based on machine learning techniques that can predict whether the patient will survive after BMT or not, which will definitely help the physicians to make the right decisions before performing the surgery for the patient. In this paper, using a publicly available BMT dataset from the University of California, Irvine ML repository (UCI ML repository), different machine learning models were investigated to predict the survival status of children undergoing BMT treatment. In particular, Random Forest (RF), Bagging Classifier, Extreme Gradient Boost (XGBoost), Adaptive Boosting (AdaBoost), Decision Tree (DT), Gradient Boost (GB), and K-Nearest Neighbors (KNN) were trained on the given dataset. The dataset consists of 45 variables after applying a series of preprocessing steps and removing the multicollinearity features based on the correlation heat map. Then, a feature engineering and modelling step was applied to identify the most significant features, followed by the use of machine learning models to simplify the overall classification process. It’s important to note that the most important features obtained by DT and those obtained by GB were the most suitable for training the Bagging classifier and the KNN model, respectively. In addition to that, hyper-parameters optimization using Grid Search Cross-Validation (GSCV) was applied to both approaches to improve the accuracy of the survival prediction. RF, AdaBoost, GB, and Bagging techniques have achieved the best accuracy of 97.37%

Mental stress is a growing global health concern, closely linked to psychological, behavioral, and physiological disorders. Accurate and early prediction of mental stress is crucial for timely interventions and improved health outcomes. Despite numerous studies leveraging machine learning (ML) techniques for stress classification, many have overlooked the integration of systematic feature selection and comprehensive model evaluation, limiting generalizability and interpretability. To address these gaps, this study proposes a robust ML-based framework that combines optimized feature selection methods - Recursive Feature Elimination (RFE), Extra Trees (ET), and Boruta - with various classification algorithms including Random Forest (RF), K-Nearest Neighbors (KNN), Decision Tree (DT), Multilayer Perceptron (MLP), Support Vector Machine (SVM), Gradient Boosting, and voting classifier. The models were evaluated using 10-fold cross-validation and ranked using the TOPSIS multi-criteria decision-making approach. The experimental results demonstrate high predictive performance across models (accuracy ≥ 0.98), with RF, DT, MLP, and Gradient Boosting achieving perfect accuracy (1.00). Among all configurations, the RF-Boruta model emerged as the most optimal (TOPSIS score: 0.914558). These findings highlight the effectiveness of combining systematic feature optimization with ML classification for accurate and interpretable stress prediction, offering valuable insights for data-driven mental health interventions.

Diabetes, also known as chronic illness, is a group of metabolic diseases due to a high level of sugar in the blood over a long period. The risk factor and severity of diabetes can be reduced significantly if the precise early prediction is possible. The robust and accurate prediction of diabetes is highly challenging due to the limited number of labeled data and also the presence of outliers (or missing values) in the diabetes datasets. In this literature, we are proposing a robust framework for diabetes prediction where the outlier rejection, filling the missing values, data standardization, feature selection, K-fold cross-validation, and different Machine Learning (ML) classifiers (k-nearest Neighbour, Decision Trees, Random Forest, AdaBoost, Naive Bayes, and XGBoost) and Multilayer Perceptron (MLP) were employed. The weighted ensembling of different ML models is also proposed, in this literature, to improve the prediction of diabetes where the weights are estimated from the corresponding Area Under ROC Curve (AUC) of the ML model. AUC is chosen as the performance metric, which is then maximized during hyperparameter tuning using the grid search technique. All the experiments, in this literature, were conducted under the same experimental conditions using the Pima Indian Diabetes Dataset. From all the extensive experiments, our proposed ensembling classifier is the best performing classifier with the sensitivity, specificity, false omission rate, diagnostic odds ratio, and AUC as 0.789, 0.934, 0.092, 66.234, and 0.950 respectively which outperforms the state-of-the-art results by 2.00 % in AUC. Our proposed framework for the diabetes prediction outperforms the other methods discussed in the article. It can also provide better results on the same dataset which can lead to better performance in diabetes prediction. Our source code for diabetes prediction is made publicly available.