Prediction and feature selection of low birth weight using machine learning algorithms

Background Predicting the prognosis of patients with acute myocardial infarction (AMI) combined with diabetes mellitus (DM) is crucial due to high in-hospital mortality rates. This study aims to develop and validate a mortality risk prediction model for these patients by interpretable machine learning (ML) methods. Methods Data were sourced from the Medical Information Mart for Intensive Care IV (MIMIC-IV, version 2.2). Predictors were selected by Least absolute shrinkage and selection operator (LASSO) regression and checked for multicollinearity with Spearman’s correlation. Patients were randomly assigned to training and validation sets in an 8:2 ratio. Seven ML algorithms were used to construct models in the training set. Model performance was evaluated in the validation set using metrics such as area under the curve (AUC) with 95% confidence interval (CI), calibration curves, precision, recall, F1 score, accuracy, negative predictive value (NPV), and positive predictive value (PPV). The significance of differences in predictive performance among models was assessed utilising the permutation test, and 10-fold cross-validation further validated the model’s performance. SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) were applied to interpret the models. Results The study included 2,828 patients with AMI combined with DM. Nineteen predictors were identified through LASSO regression and Spearman’s correlation. The Random Forest (RF) model was demonstrated the best performance, with an AUC of 0.823 (95% CI: 0.774–0.872), high precision (0.867), accuracy (0.873), and PPV (0.867). The RF model showed significant differences (p < 0.05) compared to the K-Nearest Neighbours and Decision Tree models. Calibration curves indicated that the RF model’s predicted risk aligned well with actual outcomes. 10-fold cross-validation confirmed the superior performance of RF model, with an average AUC of 0.828 (95% CI: 0.800–0.842). Significant Variables in RF model indicated that the top eight significant predictors were urine output, maximum anion gap, maximum urea nitrogen, age, minimum pH, maximum international normalised ratio (INR), mean respiratory rate, and mean systolic blood pressure. Conclusion This study demonstrates the potential of ML methods, particularly the RF model, in predicting in-hospital mortality risk for AMI patients with DM. The SHAP and LIME methods enhance the interpretability of ML models.

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

Contemporary oncology has seen a growing interest in digital technologies, whose integration with extensive healthcare and clinical data has raised new aspirations in managing patient profiles and organizing treatment plans. Among the commonly used digital technologies are Machine Learning (ML) methods that can perform many tasks, such as prediction, classification, and description, based on previously stored big data with high precision and speed. This study aims to develop a predictive ML model for early prediction of breast cancer based on a set of medically categorized risk factors. The locally collected database contained 415 instances from Al-Sadr Teaching Hospital in Basrah, Iraq, 219 (53%) of which were breast cancer patients, whereas 196 (47%) of them were control, respectively non-patients. It trained seven machine learning methods, namely Decision Tree (DT), Random Forest (RF), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Logical Regression (LR), Multinominal Naïve Bayes (NB), and Gaussian NB. The dataset was cleaned and balanced before being used. The results proved the superiority of the Decision Tree model with 96% accuracy, 96% sensitivity, and 96% specificity, the Random Forest model with 94% accuracy, 100% sensitivity, and 87% specificity, and SVM model with 92% accuracy, 96% sensitivity, and 87% specificity, respectively. Other models gave diverging results. The current study concluded that modern technologies should be employed to raise awareness and control diseases. The need to adopt Electronic Health Records (EHR) to ensure the integration of clinical data of different types recorded over time for patients contributes to building accurate and reliable prediction models.

Objective: Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions. Methods: Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis. Results: In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P＞0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P＜0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P＜0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion: Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.

BackgroundCranial, facial, nasal, and maxillary widths have been shown to be significantly affected by the individual’s sex. The present study aims to use measurements of dental arch and maxillary skeletal base to determine sex, employing supervised machine learning.Materials and methodsMaxillary and mandibular tomographic examinations from 100 patients were analyzed to investigate the inter-premolar width, inter-molar width, maxillary width, inter-pterygoid width, nasal cavity width, nostril width, and maxillary length, obtained through Cone Beam Computed Tomography scans. The following machine learning algorithms were used to build the predictive models: Logistic Regression, Gradient Boosting Classifier, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Multi-Layer Perceptron Classifier (MLP), Decision Tree, and Random Forest Classifier. A 10-fold cross-validation approach was adopted to validate each model. Metrics such as area under the curve (AUC), accuracy, recall, precision, and F1 Score were calculated for each model, and Receiver Operating Characteristic (ROC) curves were constructed.ResultsUnivariate analysis showed statistical significance (p < 0.10) for all skeletal and dental variables. Nostril width showed greater importance in two models, while Inter-molar width stood out among dental measurements. The models achieved accuracy values ranging from 0.75 to 0.85 on the test data. Logistic Regression, Random Forest, Decision Tree, and SVM models had the highest AUC values, with SVM showing the smallest disparity between cross-validation and test data for accuracy metrics.ConclusionTransverse dental arch and maxillary skeletal base measurements exhibited strong predictive capability, achieving high accuracy with machine learning methods. Among the evaluated models, the SVM algorithm exhibited the best performance. This indicates potential usefulness in forensic sex determination.

Parameter importance assessment improves efficacy of machine learning methods for predicting snow avalanche sites in Leh-Manali Highway, India

BackgroundLumbar drainage is widely used in the clinic; however, forecasting lumbar drainage-related meningitis (LDRM) is limited. We aimed to establish prediction models using supervised machine learning (ML) algorithms.MethodsWe utilized a cohort of 273 eligible lumbar drainage cases. Data were preprocessed and split into training and testing sets. Optimal hyper-parameters were archived by 10-fold cross-validation and grid search. The support vector machine (SVM), random forest (RF), and artificial neural network (ANN) were adopted for model training. The area under the operating characteristic curve (AUROC) and precision-recall curve (AUPRC), true positive ratio (TPR), true negative ratio (TNR), specificity, sensitivity, accuracy, and kappa coefficient were used for model evaluation. All trained models were internally validated. The importance of features was also analyzed.ResultsIn the training set, all the models had AUROC exceeding 0.8. SVM and the RF models had an AUPRC of more than 0.6, but the ANN model had an unexpectedly low AUPRC (0.380). The RF and ANN models revealed similar TPR, whereas the ANN model had a higher TNR and demonstrated better specificity, sensitivity, accuracy, and kappa efficiency. In the testing set, most performance indicators of established models decreased. However, the RF and AVM models maintained adequate AUROC (0.828 vs. 0.719) and AUPRC (0.413 vs. 0.520), and the RF model also had better TPR, specificity, sensitivity, accuracy, and kappa efficiency. Site leakage showed the most considerable mean decrease in accuracy.ConclusionsThe RF and SVM models could predict LDRM, in which the RF model owned the best performance, and site leakage was the most meaningful predictor.

PurposeMachine learning models were developed and validated to identify lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) using clinical factors, laboratory metrics, and 2-deoxy-2[18F]fluoro-D-glucose ([18F]F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomic features.MethodsOne hundred and twenty non-small cell lung cancer (NSCLC) patients (62 LUAD and 58 LUSC) were analyzed retrospectively and randomized into a training group (n = 85) and validation group (n = 35). A total of 99 feature parameters—four clinical factors, four laboratory indicators, and 91 [18F]F-FDG PET/CT radiomic features—were used for data analysis and model construction. The Boruta algorithm was used to screen the features. The retained minimum optimal feature subset was input into ten machine learning to construct a classifier for distinguishing between LUAD and LUSC. Univariate and multivariate analyses were used to identify the independent risk factors of the NSCLC subtype and constructed the Clinical model. Finally, the area under the receiver operating characteristic curve (AUC) values, sensitivity, specificity, and accuracy (ACC) was used to validate the machine learning model with the best performance effect and Clinical model in the validation group, and the DeLong test was used to compare the model performance.ResultsBoruta algorithm selected the optimal subset consisting of 13 features, including two clinical features, two laboratory indicators, and nine PEF/CT radiomic features. The Random Forest (RF) model and Support Vector Machine (SVM) model in the training group showed the best performance. Gender (P=0.018) and smoking status (P=0.011) construct the Clinical model. In the validation group, the SVM model (AUC: 0.876, ACC: 0.800) and RF model (AUC: 0.863, ACC: 0.800) performed well, while Clinical model (AUC:0.712, ACC: 0.686) performed moderately. There was no significant difference between the RF and Clinical models, but the SVM model was significantly better than the Clinical model. ConclusionsThe proposed SVM and RF models successfully identified LUAD and LUSC. The results indicate that the proposed model is an accurate and noninvasive predictive tool that can assist clinical decision-making, especially for patients who cannot have biopsies or where a biopsy fails.

Employee churn is a significant challenge for organizations, leading to substantial costs associated with recruiting, onboarding, and training new employees. High turnover rates can negatively impact overall productivity, employee morale, and organizational stability. Therefore, accurately predicting employee churn is crucial for companies to implement targeted retention strategies, minimize turnover, and reduce associated expenses. In this study, we leveraged machine learning techniques to predict employee churn using the "HR Analytics" dataset from Kaggle. One of the key challenges in churn prediction is class imbalance, where the number of employees who leave is significantly lower than those who stay. To address this, we applied two data-balancing techniques: Synthetic Minority Over-sampling Technique (SMOTE) and Random Over-Sampling (ROS). We then trained and evaluated four machine learning models Logistic Regression, Random Forest, Decision Tree, and Extreme Gradient Boosting (XGBoost) on the balanced datasets. The F1 scores for the SMOTE-balanced data were: Logistic Regression (0.5990), Random Forest (0.9753), Decision Tree (0.9319), and XGBoost (0.9634). Meanwhile, the ROS-balanced data produced F1 scores of: Logistic Regression (0.5978), Random Forest (0.9760), Decision Tree (0.9475), and XGBoost (0.9703). The results demonstrated that ROS yielded superior performance, particularly for the Random Forest and XGBoost models, leading us to select ROS for further hyperparameter tuning. Using RandomizedSearchCV for optimization, the Random Forest model achieved the highest F1 score of 0.9779. Finally, we deployed the optimized Random Forest model via a Flask API, enabling HR professionals to access a user-friendly web interface for realtime churn prediction. This research highlights the effectiveness of machine learning in HR analytics and underscores the practical benefits of predictive modeling in workforce management, helping organizations proactively address employee retetion challenges.

To construct a prediction model of olfactory dysfunction after transnasal sellar pituitary tumor resection based on machine learning algorithms. A cross-sectional study was conducted. From January to December 2022, 158 patients underwent transnasal sellar pituitary tumor resection in three tertiary hospitals in Sichuan Province were selected as the research objects. The olfactory status was evaluated one week after surgery. They were randomly divided into a training set and a test set according to the ratio of 8:2. The training set was used to construct the prediction model, and the test set was used to evaluate the effect of the model. Based on different machine learning algorithms, BP neural network, logistic regression, decision tree, support vector machine, random forest, LightGBM, XGBoost, and AdaBoost were established to construct olfactory dysfunction risk prediction models. The accuracy, precision, recall, F1 score, and area under the ROC curve (AUC) were used to evaluate the model's prediction performance, the optimal prediction model algorithm was selected, and the model was verified in the test set of patients. Of the 158 patients, 116 (73.42%) had postoperative olfactory dysfunction. After missing value processing and feature screening, an essential order of influencing factors of olfactory dysfunction was obtained. Among them, the duration of operation, gender, type of pituitary tumor, pituitary tumor apoplexy, nasal adhesion, age, cerebrospinal fluid leakage, blood scar formation, and smoking history became the risk factors of olfactory dysfunction, which were the key indicators of the construction of the model. Among them, the random forest model had the highest AUC of 0.846, and the accuracy, precision, recall, and F1 score were 0.750, 0.870, 0.947, and 0.833, respectively. Compared with the BP neural network, logistic regression, decision tree, support vector machine, LightGBM, XGBoost, and AdaBoost, the random forest model has more advantages in predicting olfactory dysfunction in patients after transnasal sellar pituitary tumor resection, which is helpful for early identification and intervention of high-risk clinical population, and has good clinical application prospects.

In the era of artificial intelligence, machine learning methods are successfully used in various fields. Machine learning has attracted extensive attention from investors in the financial market, especially in stock price prediction. However, one argument for the machine learning methods used in stock price prediction is that they are black-box models which are difficult to interpret. In this paper, we focus on the future stock price prediction with the historical stock price by machine learning and deep learning methods, such as support vector machine (SVM), random forest (RF), Bayesian classifier (BC), decision tree (DT), multilayer perceptron (MLP), convolutional neural network (CNN), bi-directional long-short term memory (BiLSTM), the embedded CNN, and the embedded BiLSTM. Firstly, we manually design several financial time series where the future price correlates with the historical stock prices in pre-designed modes, namely the curve-shape-feature (CSF) and the non-curve-shape-feature (NCSF) modes. In the CSF mode, the future prices can be extracted from the curve shapes of the historical stock prices. Conversely, in the NCSF mode, they can’t. Secondly, we apply various algorithms to those pre-designed and real financial time series. We find that the existing machine learning and deep learning algorithms fail in stock price prediction because in the real financial time series, less information of future prices is contained in the CSF mode, and perhaps more information is contained in the NCSF. Various machine learning and deep learning algorithms are good at handling the CSF in historical data, which are successfully applied in image recognition and natural language processing. However, they are inappropriate for stock price prediction on account of the NCSF. Therefore, accurate stock price prediction is the key to successful investment, and new machine learning algorithms handling the NCSF series are needed.&#x0D;

Machine Learning (ML) provides a theoretical and methodological framework that allows to quantify the relationship between the user's Quality of Experience (OoE) and the network's Quality of Service (QoS). In the literature, several ML-based QoS/QoE correlation models have been proposed. All of those models use inductive supervised learning techniques and most of them are built in an offline batch manner using different ML methods such as: Least Squares Regression, Artificial Neural Netwcorks, Naive Bayes classifier, Support Vector Machines, k-Nearest Neighbors, Decision Trees, and Random Forest. This paper aims to evaluate these different ML methods and determine the most suitable one for the task of establishing the QoS/QoE correlation. The comparisons show that the Decision Trees and Random Forest models give the best results to this end.

Applying data mining techniques to classify patients with suspected hepatitis C virus infection

World Health Organisation declared breast cancer (BC) as the most frequent suffering among women and accounted for 15 percent of all cancer deaths. Its accurate prediction is of utmost significance as it not only prevents deaths but also stops mistreatments. The conventional way of diagnosis includes the estimation of the tumor size as a sign of plausible cancer. Machine learning (ML) techniques have shown the effectiveness of predicting disease. However, the ML methods have been method centric rather than being dataset centric. In this paper, the authors introduce a dataset centric approach(DCA) deploying a genetic algorithm (GA) method to identify the features and a learning ensemble classifier algorithm to predict using the right features. Adaboost is such an approach that trains the model assigning weights to individual records rather than experimenting on the splitting of datasets alone and perform hyper-parameter optimization. The authors simulate the results by varying base classifiers i.e, using logistic regression (LR), decision tree (DT), support vector machine (SVM), naive bayes (NB), random forest (RF), and 10-fold cross-validations with a different split of the dataset as training and testing. The proposed DCA model with RF and 10-fold cross-validations demonstrated its potential with almost 100% performance in the classification results that no research could suggest so far. The DCA satisfies the underlying principles of data mining: the principle of parsimony, the principle of inclusion, the principle of discrimination, and the principle of optimality. This DCA is a democratic and unbiased ensemble approach as it allows all features and methods in the start to compete, but filters out the most reliable chain (of steps and combinations) that give the highest accuracy. With fewer characteristics and splits of 50-50, 66-34, and 10 fold cross-validations, the Stacked model achieves 97 % accuracy. These values and the reduction of features improve upon prior research works. Further, the proposed classifier is compared with some state-of-the-art machine-learning classifiers, namely random forest, naive Bayes, support-vector machine with radial basis function kernel, and decision tree. For testing the classifiers, different performance metrics have been employed – accuracy, detection rate, sensitivity, specificity, receiver operating characteristic, area under the curve, and some statistical tests such as the Wilcoxon signed-rank test and kappa statistics – to check the strength of the proposed DCA classifier. Various splits of training and testing data – namely, 50–50%, 66–34%, 80–20% and 10-fold cross-validation – have been incorporated in this research to test the credibility of the classification models in handling the unbalanced data. Finally, the proposed DCA model demonstrated its potential with almost 100% performance in the classification results. The output results have also been compared with other research on the same dataset where the proposed classifiers were found to be best across all the performance dimensions.

Background and objectiveThreatened abortion, a common pregnancy complication that often leading to abortion, is hard to predict due to its non-specific symptoms and difficulty in differentiating from other early pregnancy bleeding causes. Current diagnostic methods like serial ultrasounds and clinical monitoring are time-consuming and lack timeliness. To fill the gap in using advanced analytics for early detection and risk stratification, this study develops a machine learning (ML) model based on routine blood data to better predict threatened abortion, providing a reference for early detection and intervention.MethodsIn this study, we collected medical records from January 2022 to March 2024. We analyzed data from 1764 patients with threatened abortion and 1489 healthy controls. Blood test data of all participants were gathered. The Z-score normalization technique was applied to standardize blood routine indicators. This reduced the influence of outliers and noise. During hyperparameter optimization, ‘class_weight="balanced"’ was set to handle sample imbalance. The screening data was partitioned into a training set of 2928 cases (including the validation set) and a test set of 325 cases at an 8:1:1 ratio. Python was used to facilitate data transformation. Eight different ML algorithms—Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GBM), Extreme Gradient Boosting (XGB), Deep Neural Network (DNN), Decision Tree (DT) and Naive Bayes (NB)—were used to construct a threatened abortion prediction model. The prediction performances of the ML models were evaluated by calculating the area under the curve (AUC) values. We used the SHapley Additive exPlanation (SHAP) method to explain the models.ResultsComparatively, the DNN model showed the highest predictive performance among the eight models, with the highest AUC value of 96.76% and top metrics for accuracy (91.88%), specificity (91.62%), sensitivity (92.11%), and F1 score (92.48%). SHAP analysis identified Red Cell Distribution Width - Standard Deviation (RDW-SD), Platelet Distribution Width (PDW), Mean Platelet Volume (MPV), Red Cell Distribution Width - Coefficient of Variation (RDW-CV), Absolute Basophil Count (BAS#), Platelet Count (PLT), Mean Corpuscular Hemoglobin Concentration (MCHC) and Lymphocyte Percentage (LYM) as the most influential features in predicting threatened abortion, with PDW, RDW-CV, BAS#, PLT, MCHC and LYM positively contributing to the prediction, whereas RDW-SD and MPV had negative contributions.ConclusionsOur research on constructing a prediction model for threatened abortion through routine blood tests has revealed the great potential of ML algorithms in detecting threatened abortion. This algorithm is expected to analyse routine blood data to identify at-risk pregnancies at an early stage, significantly improving the early detection of this common pregnancy complication. It will assist healthcare providers in intervening earlier and reducing the incidence of abortion. However, before the model can be translated into routine clinical applications, more extensive validation studies are still needed.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12884-025-08030-z.