AUC-ROC Score Research Articles

Comparison of Machine Learning Models in Predicting Mental Health Sequelae Following Concussion in Youth.

Youth who experience concussions may be at greater risk for subsequent mental health challenges, making early detection crucial for timely intervention. This study utilized Bidirectional Long Short-Term Memory (BiLSTM) networks to predict mental health outcomes following concussion in youth and compared its performance to traditional models. We also examined whether incorporating social determinants of health (SDoH) improved predictive power, given the disproportionate impact of concussions and mental health issues on disadvantaged populations. We evaluated the models using accuracy, area under the curve (AUC) of the receiver operating characteristic (ROC), and other performance metrics. Our BiLSTM model with SDoH data achieved the highest accuracy (0.883) and AUC-ROC score (0.892). Unlike traditional models, our approach provided real-time predictions at each visit within 12 months of the index concussion, aiding clinicians in making timely, visit-specific referrals for further treatment and interventions.

MDbDMRP: A novel molecular descriptor-based computational model to identify drug-miRNA relationships.

MicroRNAs (miRNAs) are important in gene expression regulation and many other biological processes and have emerged as promising therapeutic targets. Identifying potential drug-miRNA relationships is helpful in disease therapy and pharmaceutical engineering in medical research. However, accurately predicting these relationships remains a significant computational challenge. This study introduces MDbDMRP, a novel molecular descriptors-based drug-miRNA relationship prediction computational model designed to address this challenge. MDbDMRP leverages the power of machine learning to predict new drug-miRNA associations and non-associations. The model achieves exceptional performance, exceeding an average score of 0.92 across various evaluation metrics, including accuracy, precision, recall, and F1-score. Furthermore, it demonstrates a remarkable ability to distinguish between positive and negative interactions, as evidenced by an outstanding AUC-ROC score of 0.9864. The results obtained from MDbDMRP were further validated through molecular docking, reinforcing its performance. These results position MDbDMRP as a valuable tool for researchers aiming to unlock the potential of miRNAs in drug discovery.

EARLY DETECTION OF ORAL DISEASES USING MACHINE LEARNING: A COMPARATIVE STUDY OF PREDICTIVE MODELS AND DIAGNOSTIC ACCURACY

Early detection of oral diseases is crucial for effective treatment and improved patient outcomes. This study develops and evaluates machine learning models for the detection of early-stage oral diseases using a comprehensive and diverse dataset comprising clinical records, demographic information, and intraoral images. The methodology involves systematic data preprocessing, feature selection, model training, and evaluation. Several machine learning algorithms, including Gradient Boosting, Random Forest, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes, were employed and compared to identify the most effective model. Gradient Boosting achieved the highest performance with an accuracy of 95.2% and an AUC-ROC score of 0.98, demonstrating superior ability to classify early-stage oral diseases. Random Forest followed closely with an accuracy of 94.5% and an AUC-ROC score of 0.96. In contrast, SVM and KNN showed moderate performance with accuracies of 89.7% and 87.3%, respectively, while Naïve Bayes exhibited the lowest accuracy at 82.1%. The results highlight the importance of advanced ensemble methods in achieving higher accuracy and better classification for early detection. The study underscores the potential of machine learning to revolutionize oral healthcare by enabling timely disease detection, reducing diagnostic errors, and improving treatment outcomes. These findings contribute to the growing body of literature on artificial intelligence in healthcare and provide a foundation for developing scalable diagnostic solutions in clinical practice.

Colon Tumor Discrimination Combining Independent Endoscopic Probe-Based Raman Spectroscopy and Optical Coherence Tomography Modalities with Bayes Rule.

Colorectal cancer is one of the most prevalent forms of cancer globally. The most common routine diagnostic methods are the examination of the interior of the colon during colonoscopy or sigmoidoscopy, which frequently includes the removal of a biopsy sample. Optical methods, such as Raman spectroscopy (RS) and optical coherence tomography (OCT), can help to improve diagnostics and reduce the number of unnecessary biopsies. For in vivo use, we have developed fiber-optic probes, one for single-point Raman measurements and one for volumetric OCT. Here, we present the results of a clinical study using these fiber-optic probes in an ex vivo setting. The goal was to evaluate the beneficial effect of combining these two modalities on the AUC ROC score of the machine learning models for the discrimination of cancerous and healthy tissue. In the initial stage of the investigation, both modalities were validated separately using linear discriminant analysis. RS was subjected to spectral preprocessing, while OCT underwent texture feature extraction. Subsequently, both modalities were integrated using the Bayes rule, resulting in an enhanced area under the curve score of 0.93, representing an improvement over the 0.77 score for Raman spectroscopy and 0.86 for OCT.

Predicting Consumer Perceptions of Metaverse Shopping Through Insights from Machine Learning Models

This study investigates consumer perceptions of Metaverse shopping and the factors that influence these perceptions, using machine learning models to classify and analyze the data. Four models—Logistic Regression, Random Forest, Support Vector Machines (SVM), and K-Nearest Neighbors (KNN)—were employed to predict whether consumers view Metaverse shopping favorably or unfavorably. Among these, the SVM model achieved the highest performance, with an accuracy of 94.17%, precision of 97.14%, and an AUC-ROC score of 98.13%. These results indicate that machine learning can reliably classify consumer perceptions based on demographic and experience-related data. Furthermore, the Random Forest model was used to analyze the importance of features influencing consumer attitudes. The findings revealed that experience-related factors—such as interactivity, personalization, and consumer engagement—were more significant in shaping perceptions than product-specific attributes. The most important feature, MC2 (interactivity), contributed 23.6% to the model’s predictive power, highlighting the importance of user experience in driving positive sentiment. These insights suggest that businesses aiming to enter the Metaverse retail space should focus on enhancing the overall shopping experience to foster positive consumer perceptions. Machine learning models provide valuable tools for understanding consumer behavior and tailoring virtual shopping environments accordingly. This research offers a data-driven approach to predicting and understanding consumer perceptions of the Metaverse, providing actionable insights for businesses in this emerging market.

Multimodal machine learning for language and speech markers identification in mental health

BackgroundThere are numerous papers focusing on diagnosing mental health disorders using unimodal and multimodal approaches. However, our literature review shows that the majority of these studies either use unimodal approaches to diagnose a variety of mental disorders or employ multimodal approaches to diagnose a single mental disorder instead. In this research we combine these approaches by first identifying and compiling an extensive list of mental health disorder markers for a wide range of mental illnesses which have been used for both unimodal and multimodal methods, which is subsequently used for determining whether the multimodal approach can outperform the unimodal approaches.MethodsFor this study we used the well known and robust multimodal DAIC-WOZ dataset derived from clinical interviews. Here we focus on the modalities text and audio. First, we constructed two unimodal models to analyze text and audio data, respectively, using feature extraction, based on the extensive list of mental disorder markers that has been identified and compiled by us using related and earlier studies. For our unimodal text model, we also propose an initial pragmatic binary label creation process. Then, we employed an early fusion strategy to combine our text and audio features before model processing. Our fused feature set was then given as input to various baseline machine and deep learning algorithms, including Support Vector Machines, Logistic Regressions, Random Forests, and fully connected neural network classifiers (Dense Layers). Ultimately, the performance of our models was evaluated using accuracy, AUC-ROC score, and two F1 metrics: one for the prediction of positive cases and one for the prediction of negative cases.ResultsOverall, the unimodal text models achieved an accuracy ranging from 78% to 87% and an AUC-ROC score between 85% and 93%, while the unimodal audio models attained an accuracy of 64% to 72% and AUC-ROC scores of 53% to 75%. The experimental results indicated that our multimodal models achieved comparable accuracy (ranging from 80% to 87%) and AUC-ROC scores (between 84% and 93%) to those of the unimodal text models. However, the majority of the multimodal models managed to outperform the unimodal models in F1 scores, particularly in the F1 score of the positive class (F1 of 1s), which reflects how well the models perform in identifying the presence of a marker.ConclusionsIn conclusion, by refining the binary label creation process and by improving the feature engineering process of the unimodal acoustic model, we argue that the multimodal model can outperform both unimodal approaches. This study underscores the importance of multimodal integration in the field of mental health diagnostics and sets the stage for future research to explore more sophisticated fusion techniques and deeper learning models.

Assessing decision tree, random forest, and XGBoost models for human capital readiness predictions in low-income areas

This article investigates applying advanced machine learning models, including Random Forest, XGBoost, and LightGBM, to predict human capital readiness in the low-income Kut Bak district. Human capital readiness, encompassing skills, knowledge, and health, is crucial for socio-economic development but remains under-researched in impoverished regions. The dataset comprises 953 individuals from 302 households, with variables including age, gender, health, employment status, and various socio-economic factors. The methodology involves rigorous data preparation, including cleaning, encoding, and normalizing, followed by feature selection and splitting the dataset into training (80%) and testing (20%) sets. The models were evaluated using a 10-fold cross-validation strategy, ensuring robust and generalizable findings. The results indicate that XGBoost outperforms the other models, achieving a mean cross-validation accuracy of 0.991, precision of 0.993, recall of 0.992, F1-score of 0.992, and an AUC-ROC score of 0.995. Random Forest follows closely with a mean accuracy of 0.987, precision of 0.990, recall of 0.988, F1-score of 0.989, and an AUC-ROC score of 0.993. LightGBM, while still performing well, shows slightly lower metrics with a mean accuracy of 0.975, precision of 0.978, recall of 0.976, F1-score of 0.977, and an AUC-ROC score of 0.980. The confusion matrix analysis reveals that XGBoost has the highest number of correct classifications, with 64 true negatives, 0 false positives, 2 false negatives, and 125 true positives. The feature importance analysis highlights ‘Family Responsibilities’, ‘Elderly’, and ‘Crop Cultivation Specialist’ occupation as significant predictors across models, though LightGBM emphasizes ‘Age’ and ‘Gender’. This research underscores the utility of machine learning in socio-economic planning, offering actionable insights for policymakers aiming to enhance human capital readiness in economically disadvantaged areas. Future research should focus on expanding datasets, fine-tuning model parameters, and exploring additional socio-demographic variables for improved predictive accuracy.

Machine learning-based prediction of bioactivity in HIV-1 protease: insights from electron density analysis.

Aim: To develop a model for predicting the biological activity of compounds targeting the HIV-1 protease and to establish factors influencing enzyme inhibition.Materials & methods: Machine learning models were built based on a combination of Richard Bader's theory of Atoms in Molecules and topological analysis of electron density using experimental x-ray 'protein-ligand' complexes and inhibition constants data.Results & conclusion: Among all the models tested, logistic regression achieved the highest accuracy of 0.76 on the test set. The model's ability to differentiate between less active and highly active classes was relatively good, as indicated by an AUC-ROC score of 0.77. The analysis identified several critical factors affecting the biological activity of HIV-1 protease inhibitors, including the electron density contribution of hydrogen atoms, bond-critical points and particular amino acid residues. These findings provide new insights into how these molecular factors influence HIV-1 protease inhibition, emphasizing the importance of hydrogen bonding, glycine's flexibility and hydrophobic interactions in ligand binding.

PTB-DDI: An Accurate and Simple Framework for Drug-Drug Interaction Prediction Based on Pre-Trained Tokenizer and BiLSTM Model.

The simultaneous use of two or more drugs in clinical treatment may raise the risk of a drug-drug interaction (DDI). DDI prediction is very important to avoid adverse drug events in combination therapy. Recently, deep learning methods have been applied successfully to DDI prediction and improved prediction performance. However, there are still some problems with the present models, such as low accuracy due to information loss during molecular representation or incomplete drug feature mining during the training process. Aiming at these problems, this study proposes an accurate and simple framework named PTB-DDI for drug-drug interaction prediction. The PTB-DDI framework consists of four key modules: (1) ChemBerta tokenizer for molecular representation, (2) Bidirectional Long Short-Term Memory (BiLSTM) to capture the bidirectional context-aware features of drugs, (3) Multilayer Perceptron (MLP) for mining the nonlinear relationship of drug features, and (4) interaction predictor to perform an affine transformation and final prediction. In addition, we investigate the effect of dual-mode on parameter-sharing and parameter-independent within the PTB-DDI framework. Furthermore, we conducted comprehensive experiments on the two real-world datasets (i.e., BIOSNAP and DrugBank) to evaluate PTB-DDI framework performance. The results show that our proposed framework has significant improvements over the baselines based on both datasets. Based on the BIOSNAP dataset, the AUC-ROC, PR-AUC, and F1 scores are 0.997, 0.995, and 0.984, respectively. These metrics are 0.896, 0.873, and 0.826 based on the DrugBank dataset. Then, we conduct the case studies on the three newly approved drugs by the Food and Drug Administration (FDA) in 2024 using the PTB-DDI framework in dual modes. The obtained results indicate that our proposed framework has advantages for predicting drug-drug interactions and that the dual modes of the framework complement each other. Furthermore, a free website is developed to enhance accessibility and user experience.

Lung nodule classification using radiomics model trained on degraded SDCT images

Background and objectiveLow-dose computed tomography (LDCT) screening has shown promise in reducing lung cancer mortality; however, it suffers from high false positive rates and a scarcity of available annotated datasets. To overcome these challenges, we propose a novel approach using synthetic LDCT images generated from standard-dose CT (SDCT) scans from the LIDC-IDRI dataset. Our objective is to develop and validate an interpretable radiomics-based model for distinguishing likely benign from likely malignant pulmonary nodules. MethodsFrom a total of 1010 CT images (695 SDCTs and 315 LDCTs), we degraded SDCTs in the sinogram domain and obtained 1950 nodules as the training set. The 675 nodules from the LDCTs were stratified into 50%-50% partitions for validation and testing. Radiomic features were extracted from nodules, and three feature sets were assessed using: a) only shape and size (SS) features, b) all features but SS features, and c) all features. A systematic pipeline was developed to optimize the feature set and evaluate multiple machine learning models. Models were trained using degraded SDCT, validated and tested on the LDCT nodules. ResultsTraining a logistic regression model using three SS features yielded the most promising results, achieving on the test set mean balanced accuracy, sensitivity, specificity, and AUC-ROC scores of 0.81, 0.76, 0.85, and 0.87, respectively. ConclusionsOur study demonstrates the feasibility and effectiveness of using synthetic LDCT images for developing a relatively accurate radiomics-based model in lung nodule classification. This approach addresses challenges associated with LDCT screening, offering potential implications for improving lung cancer detection and reducing false positives.

A hybrid approach of vision transformers and CNNs for detection of ulcerative colitis

Ulcerative Colitis is an Inflammatory Bowel disease caused by a variety of factors that lead to a serious impact on the quality of life of the patients if left untreated. Due to complexities in the identification procedures of this disease, the treatment timeline and quality can be severely affected, leading to further consequences for the sufferer. The difficulties in identification are due to high patients to healthcare professionals ratio. Researchers have proposed variety of machine/deep learning methods for automated detection of ulcerative colitis, however, several challenges exists including class imbalance problem, comprehensive feature extraction and accurate classification. We propose a novel method for accurate detection of ulcerative colitis with augmentation techniques to overcome class imbalance issue, a comprehensive feature vector extraction using custom architecture of Vision Transformer (ViT) and accurate classification using customized Convolutional Neural Network (CNN). We used the TMC-UCM and LIMUC datasets in this research for training and testing of proposed method and achieved accuracy of 90% with AUC-ROC scores of 0.91, 0.81, 0.94, and 0.94 for the endoscopic classes of Mayo 0, Mayo 1, Mayo 2, and Mayo 3 respectively. We have compared the proposed method with existing state of the art methods and conclude that the proposed method outperforms the existing methods.

Machine learning and multisource data analysis approach towards traffic accident risk prediction

Traffic accidents are continually a concern across the world bringing with them huge economic costs and high rates of fatality and injuries each single year. Predictive modeling can lessen such risks if the accident hotspots and timing can easily be ascertained. This study collects various data including historical accident reports, water and meteorological conditions, road characteristics, and telematics data, to form traffic accident risk predictive models. To construct and analyze these predictive models, we use various machine learning techniques such as logistic regression, decision trees, and ensemble methods (Random Forest and Gradient Boosting). The results bear out as efficient and effective, ensemble models are streets ahead than regression-based techniques with Gradient Boosting achieving AUC-ROC scores of up to 0.89. The results of this research can also assist in applying effective safety measures in a more cost-effective manner as well as facilitate the development of efficient transport management systems and policies.

Drug–target prediction through self supervised learning with dual task ensemble approach

Drug–Target interaction (DTI) prediction, a transformative approach in pharmaceutical research, seeks novel therapeutic applications for computational method based virtual screening, existing drugs to address untreated diseases and discovery of existing drugs side effects. The proposed model predict DTI through Heterogeneous biological network by combining drug, genes and disease related knowledge. For the purpose of embedding extraction Self-supervised learning (SSL) has been used which, trains models through pretext tasks, eliminating the need for manual annotations. The pretext tasks are related to either structural based information or similarity based information. To mitigate GNN vulnerability to non-robustness, ensemble learning can be incorporated into GNNs, harnessing multiple models to enhance robustness. This paper introduces a Graph neural network based architecture consisting of task based module and ensemble module for link prediction of DTI. The ensemble module of dual task combinations, both in cold start and warm start scenarios achieve very good performance as it provide 0.960 in cold start and 0.970 in warm start mean AUCROC score with less deviation.

Exploring the impact of opioids on serum chemistry: Insights from FT-Raman spectroscopy and biochemical analysis

Opioids are drugs whose use has increased dramatically over the last two decades. Opioids are a family of drugs that includes the illegal drug heroin, synthetic opioids such as fentanyl, and painkillers that are legally available on prescription. Unfortunately, too long use of these drugs can lead to addiction, which might cause disturbed physiological and mental effects. Regular opioid usage might cause common mental disorders such as depression, anxiety, and panic disorder. However, there is still no rapid detection method to describe the chemical changes caused by the Opioid use disorder. For this reason, this study used conventional FT-Raman spectroscopic techniques with multivariate analysis to detect chemical changes in serum following opiate administration. In the FT-Raman spectrum collected from opioid-addicted patients, significant shifts of peaks at 892 cm−1, 966 cm−1, 1286 cm−1, 1459 cm−1 and 2940 cm−1 were visible in comparison with the spectrum of serum collected from the control group. Furthermore, changes in the ratio of amides and lipids were observed in the non-control group, suggesting that opioids could cause structural changes in the compounds. Synchronous spectra show auto peaks at 2914 cm−1, 3415 cm−1 while asynchronous negative cross area between 1005 cm−1 and 1800 cm−1 and around 3000 cm−1 indicate higher presence of polysaccharides and amides in comparison with other compounds in serum collected from non-control group. Finally, the PCA model, utilizing three components that explain 94.89 % of the data variation within the 300–3700 cm⁻¹ range, demonstrates excellent performance. The ensemble classification method achieves accuracies of 97.96 % and 95.00 % on the training and test datasets, respectively. Furthermore, the method achieves AUC-ROC scores of 1.00 and 0.99 for the training and test sets, effectively distinguishing between control and opioid-addicted individuals.

A Comparative Study of Machine Learning Models for Predicting Customer Churn in Retail Banking: Insights from Logistic Regression, Random Forest, GBM, and SVM

Customer churn poses a significant challenge in the retail banking sector, leading to substantial financial losses and undermining long-term growth. This study explores the effectiveness of various machine learning models, including Logistic Regression, Random Forest, Gradient Boosting Machine (GBM), and Support Vector Machine (SVM), in predicting customer churn. Utilizing a comprehensive dataset derived from a leading bank, we conducted extensive data preprocessing and feature engineering before evaluating model performance through metrics such as accuracy, precision, recall, F1-score, and AUC-ROC. Our findings reveal that the Gradient Boosting Machine outperforms its counterparts, achieving an accuracy of 87.2%, with an AUC-ROC score of 0.91, indicating its exceptional ability to distinguish between churned and non-churned customers. Random Forest follows closely, exhibiting robust performance, while SVM and Logistic Regression demonstrate moderate accuracy levels. This research underscores the transformative potential of machine learning in enhancing customer retention strategies within the banking industry. By identifying at-risk customers and understanding the underlying factors contributing to churn, banks can implement targeted interventions to improve customer satisfaction and loyalty. The study further suggests avenues for future research, including the exploration of real-time data analysis and the integration of qualitative customer insights, to refine predictive models and retention strategies.

Classification of Prostate Cancer in 3D Magnetic Resonance Imaging Data based on Convolutional Neural Networks

Abstract Prostate cancer is a commonly diagnosed cancerous disease among men world-wide. Even with modern technology such as multi-parametric magnetic resonance tomography and guided biopsies, the process for diagnosing prostate cancer remains time consuming and requires highly trained professionals. In this paper, different convolutional neural networks (CNN) are evaluated on their abilities to reliably classify whether an MRI sequence contains malignant lesions. Implementations of a ResNet, a ConvNet and a ConvNeXt for 3D image data are trained and evaluated. The models are trained using different data augmentation techniques, learning rates, and optimizers. The data is taken from a private dataset, provided by Cantonal Hospital Aarau. The best result was achieved with a ResNet3D, yielding an average precision score of 0.4583 and AUC ROC score of 0.6214.

Survival analysis for lung cancer patients: A comparison of Cox regression and machine learning models

IntroductionSurvival analysis based on cancer registry data is of paramount importance for monitoring the effectiveness of health care. As new methods arise, the compendium of statistical tools applicable to cancer registry data grows. In recent years, machine learning approaches for survival analysis were developed. The aim of this study is to compare the model performance of the well established Cox regression and novel machine learning approaches on a previously unused dataset. Material and MethodsThe study is based on lung cancer data from the Schleswig-Holstein Cancer Registry. Four survival analysis models are compared: Cox Proportional Hazard Regression (CoxPH) as the most commonly used statistical model, as well as Random Survival Forests (RSF) and two neural network architectures based on the DeepSurv and TabNet approaches. The models are evaluated using the concordance index (C-I), the Brier score and the AUC-ROC score. In addition, to gain more insight in the decision process of the models, we identified the features that have an higher impact on patient survival using permutation feature importance scores and SHAP values. ResultsUsing a dataset including the cancer stage established by the Union for International Cancer Control (UICC), the best performing model is the CoxPH (C-I: 0.698±0.005), while using a dataset which includes the tumor size, lymph node and metastasis status (TNM) leads to the RSF as best performing model (C-I: 0.703±0.004). The explainability metrics show that the models rely on the combined UICC stage and the metastasis status in the first place, which corresponds to other studies. DiscussionThe studied methods are highly relevant for epidemiological researchers to create more accurate survival models, which can help physicians make informed decisions about appropriate therapies and management of patients with lung cancer, ultimately improving survival and quality of life.

Radiomics Based Differentiation of Glioblastoma and Metastatic Disease: Impact of Different T1-Contrast Enhanced Sequences on Radiomic Features and Model Performance.

To evaluate the radiomics-based model performance for differentiation between glioblastoma (GB) and brain metastases (BM) using magnetization prepared rapid gradient echo (MPRAGE) and volumetric interpolated breath-hold examination (VIBE) T1-contrast enhanced sequences. T1-CE MPRAGE and VIBE sequences acquired in 108 patients (31 GBs and 77 BM) during the same MRI session were retrospectively evaluated. Post standardized image pre-processing and segmentation, radiomics features were extracted from necrotic and enhancing tumor components. Pearson correlation analysis of radiomics features from tumor subcomponents was also performed. A total of 90 machine learning (ML) pipelines were evaluated using a five-fold cross validation. Performance was measured by mean AUC-ROC, Log-loss and Brier scores. A feature-wise comparison showed that the radiomic features between sequences were strongly correlated, with the highest correlation for shape-based features. The mean AUC across the top-ten pipelines ranged between 0.851-0.890 with T1-CE MPRAGE and between 0.869-0.907 with T1-CE VIBE sequence. Top performing models for the MPRAGE sequence commonly used support vector machines, while those for VIBE sequence used either support vector machines or random forest. Common feature reduction methods for top-performing models included linear combination filter and least absolute shrinkage and selection operator (LASSO) for both sequences. For the same ML-feature reduction pipeline, model performances were comparable (AUC-ROC difference range: [-0.078, 0.046]). Radiomic features derived from T1-CE MPRAGE and VIBE sequences are strongly correlated and may have similar overall classification performance for differentiating GB from BM. BM: Brain metastases, GB: glioblastoma, T1-CE: T1 contrast enhanced sequence, MPRAGE: magnetization prepared rapid gradient echo, ML: machine learning, RF: random forest, VIBE: volumetric interpolated breath-hold examination.

Predictive risk modeling for child maltreatment detection and enhanced decision-making: Evidence from Danish administrative data.

Child maltreatment is a widespread problem with significant costs for both victims and society. In this retrospective cohort study, we develop predictive risk models using Danish administrative data to predict removal decisions among referred children and assess the effectiveness of caseworkers in identifying children at risk of maltreatment. The study analyzes 195,639 referrals involving 102,309 children Danish Child Protection Services received from April 2016 to December 2017. We implement four machine learning models of increasing complexity, incorporating extensive background information on each child and their family. Our best-performing model exhibits robust predictive power, with an AUC-ROC score exceeding 87%, indicating its ability to consistently rank referred children based on their likelihood of being removed. Additionally, we find strong positive correlations between the model's predictions and various adverse child outcomes, such as crime, physical and mental health issues, and school absenteeism. Furthermore, we demonstrate that predictive risk models can enhance caseworkers' decision-making processes by reducing classification errors and identifying at-risk children at an earlier stage, enabling timely interventions and potentially improving outcomes for vulnerable children.

Leveraging multivariate analysis and adjusted mutual information to improve stroke prediction and interpretability.

To develop a machine learning model to accurately predict stroke risk based on demographic and clinical data. It also sought to identify the most significant stroke risk factors and determine the optimal machine learning algorithm for stroke prediction. This cross-sectional study analyzed data on 438,693 adults from the 2021 Behavioral Risk Factor Surveillance System. Features encompassed demographics and clinical factors. Descriptive analysis profiled the dataset. Logistic regression quantified risk relationships. Adjusted mutual information evaluated feature importance. Multiple machine learning models were built and evaluated on metrics like accuracy, AUC ROC, and F1 score. Key factors significantly associated with higher stroke odds included older age, diabetes, hypertension, high cholesterol, and history of myocardial infarction or angina. Random forest model achieved the best performance with accuracy of 72.46%, AUC ROC of 0.72, and F1 score of 0.74. Cross-validation confirmed its reliability. Top features were hypertension, myocardial infarction history, angina, age, diabetes status, and cholesterol. The random forest model robustly predicted stroke risk using demographic and clinical variables. Feature importance highlighted priorities like hypertension and diabetes for clinical monitoring and intervention. This could help enable data-driven stroke prevention strategies.