Random Forest Classifier Research Articles

Comparative Analysis of Supervised Machine Learning Algorithms for Diabetes Prediction

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

Enhanced Coconut Yield Prediction Using Internet of Things and Deep Learning: A Bi-Directional Long Short-Term Memory Lévy Flight and Seagull Optimization Algorithm Approach

In coastal areas, coconuts are a common crop. Everyone from farmers to lawmakers and businesses would benefit from an accurate forecast of coconut production. Internet of Things (IoT) sensors are strategically positioned to continuously monitor the environment and gather production statistics to obtain accurate agricultural output predictions. To effectively estimate coconut prediction, this study presents an enhanced deep learning classifier called Bi-directional Long Short-Term Memory (BILSTM) with the integrated Lévy Flight and Seagull Optimization Algorithm (LFSOA). LASSO feature selection is applied to eliminate the superfluous characteristics in the yield estimation. To further enhance the coconut yield estimate, the optimal set of hyperparameters for BILSTM is tuned by the LFSOA, which helps to avoid the overfitting issue. For the results, the BILSTM is compared against different classifiers such as Recurrent Neural Network (RNN), Random Forest Classifier (RFC), and LSTM. Similarly, LFSOA-based hyperparameter tuning is contrasted with different optimization algorithms. The outputs show that LFSOA-based hyperparameter tuning in BILSTM achieved accuracy, precision, recall, and f1-score of 98.963%, 99.026%, 99.155%, and 95.758%, respectively, which are higher when compared to existing methods. Similarly, the BILSTM-LFSOA accomplished better results in statistical measures, including the Root Mean Square Error (RMSE) of 0.105, Mean Squared Error (MSE) of 0.011, Mean Absolute Error (MAE) of 0.094, and coefficient of determination (R2) of 0.954, respectively. From the overall analysis, the proposed BILSTM-LFSOA improves coconut yield prediction by achieving better results in all the performance measures when compared with existing models. The results of this study are important to many stakeholders, including but not limited to policymakers, farmers, banks, and insurance companies. As coconuts are an important crop in developing countries, accurate coconut yield forecasting will lead to greater financial and food security in these regions.

Mapping the Time-Series of Essential Urban Land Use Categories in China: A Multi-Source Data Integration Approach

Accurate, detailed, and long-term urban land use mapping is crucial for urban planning, environmental assessment, and health evaluation. Despite previous efforts, mapping essential urban land use categories (EULUCs) across multiple periods remains challenging, primarily due to the scarcity of enduring consistent socio-geographical data, such as the widely used Point of Interest (POI) data. Addressing this issue, this study presents an experimental method for mapping the time-series of EULUCs in Dalian city, China, utilizing Local Climate Zone (LCZ) data as a substitute for POI data. Leveraging multi-source geospatial big data and the random forest classifier, we delineate urban land use distributions at the parcel level for the years 2000, 2005, 2010, 2015, 2018, and 2020. The results demonstrate that the generated EULUC maps achieve promising classification performance, with an overall accuracy of 78% for Level 1 and 71% for Level 2 categories. Features derived from nighttime light data, LCZ, Sentinel-2 satellite imagery, and topographic data play leading roles in our land use classification process. The importance of LCZ data is second only to nighttime light data, achieving comparable classification accuracy to that when using POI data. Our subsequent correlation analysis reveals a significant correlation between POI and LCZ data (p = 0.4), which validates the rationale of the proposed framework. These findings offer valuable insights for long-term urban land use mapping, which can facilitate effective urban planning and resource management in the near future.

Optimizing Breast Cancer Diagnosis with Machine Learning Algorithms

Breast cancer is the most common disease among women worldwide, and it continues to pose a serious threat to global health [2]. Early and accurate diagnosis is critical for effective treatment and improved patient outcomes. Traditional diagnostic methods, while effective, have limitations in consistency and speed. Medical diagnostics have undergone a revolution with the introduction of machine learning (ML), which provides tools to analyze complex data and increase diagnosis accuracy. Using the Breast Cancer Wisconsin (Diagnostic) Dataset[1], this investigation dives into the application of several machine learning (ML) algorithms to improve the effectiveness of the diagnosis of breast cancer in terms of accuracy. Logistic Regression (LR), Decision Tree Classifier (DTC), Random Forest Classifier (RFC), Support Vector Classifier (SVC), XGBoost Classifier (XGBC), and Convolutional Neural Network (CNN) are used. Improved performance metrics were obtained across models by applying optimization approaches, particularly genetic algorithm for the selection of features, following preprocessing and initial training. RandomForestClassifier, XGBClassifier, and CNN notably showed significant enhancements in accuracy, ROC AUC score, recall, precision, and F1 score post-optimization. Ensemble methods and deep learning architectures proved effective in handling complex data and reducing overfitting, with Random Forest Classifier standing out as consistently superior. Conversely, Decision Tree Classifier and Support Vector Classifier exhibited mixed results, showcasing the importance of optimization strategies. This research shows the capability of ML in augmenting breast cancer diagnostics, advocating for further exploration of ensemble methods and advanced neural networks to refine diagnostic tools and improve patient outcomes.

Machine learning based identification potential feature genes for prediction of drug efficacy in nonalcoholic steatohepatitis animal model

BackgroundNonalcoholic Steatohepatitis (NASH) results from complex liver conditions involving metabolic, inflammatory, and fibrogenic processes. Despite its burden, there has been a lack of any approved food-and-drug administration therapy up till now.PurposeUtilizing machine learning (ML) algorithms, the study aims to identify reliable potential genes to accurately predict the treatment response in the NASH animal model using biochemical and molecular markers retrieved using bioinformatics techniques.MethodsThe NASH-induced rat models were administered various microbiome-targeted therapies and herbal drugs for 12 weeks, these drugs resulted in reducing hepatic lipid accumulation, liver inflammation, and histopathological changes. The ML model was trained and tested based on the Histopathological NASH score (HPS); while (0–4) HPS considered Improved NASH and (5–8) considered non-improved, confirmed through rats’ liver histopathological examination, incorporates 34 features comprising 20 molecular markers (mRNAs-microRNAs-Long non-coding-RNAs) and 14 biochemical markers that are highly enriched in NASH pathogenesis. Six different ML models were used in the proposed model for the prediction of NASH improvement, with Gradient Boosting demonstrating the highest accuracy of 98% in predicting NASH drug response.FindingsFollowing a gradual reduction in features, the outcomes demonstrated superior performance when employing the Random Forest classifier, yielding an accuracy of 98.4%. The principal selected molecular features included YAP1, LATS1, NF2, SRD5A3-AS1, FOXA2, TEAD2, miR-650, MMP14, ITGB1, and miR-6881-5P, while the biochemical markers comprised triglycerides (TG), ALT, ALP, total bilirubin (T. Bilirubin), alpha-fetoprotein (AFP), and low-density lipoprotein cholesterol (LDL-C).ConclusionThis study introduced an ML model incorporating 16 noninvasive features, including molecular and biochemical signatures, which achieved high performance and accuracy in detecting NASH improvement. This model could potentially be used as diagnostic tools and to identify target therapies.

Frequency data driven damage detection of polymeric composite structural health using machine learning models

AbstractFirstly, the effect of damages (crack and delamination) on frequency responses of the polymeric composite structures is predicted numerically in this research. The responses are computed numerically using the finite element technique associated with a higher‐order deformation kinematic model. The model accuracy has been verified by comparing the published frequency responses and in‐house experimental data. The verified model is extended to generate the desired data (frequencies) utilizing various input parameters related to the geometrical forms and damage types (shapes, sizes, and positions). Further, different machine learning models (MLMs) are developed using Python algorithms for the identification of structural health. In this regard, the extracted data sets are initially used to train the MLM, detect the damages, and identify types of damage and damage‐related data of polymeric structures. Out of all kinds of MLMs, it is understood that the Random Forest Classifier provides the best result, which had an accuracy of 94.66% with the optimal parameters. The precision accomplished is 97% for intact and 94% for damaged structures. The proposed algorithm is also capable of identifying the damage‐related parameters (shape, size, type, and position) and predicting the defects early to prevent unintended mishaps.

Generating high-resolution land use and land cover maps for the greater Mariño watershed in 2019 with machine learning

Land Use and Land Cover (LULC) maps are important tools for environmental planning and social-ecological modeling, as they provide critical information for evaluating risks, managing natural resources, and facilitating effective decision-making. This study aimed to generate a very high spatial resolution (0.5 m) and detailed (21 classes) LULC map for the greater Mariño watershed (Peru) in 2019, using the MORINGA processing chain. This new method for LULC mapping consisted in a supervised object-based LULC classification, using the random forest algorithm along with multi-sensor satellite imagery from which spectral and textural predictors were derived (a very high spatial resolution Pléiades image and a time serie of high spatial resolution Sentinel-2 images). The random forest classifier showed a very good performance and the LULC map was further improved through additional post-treatment steps that included cross-checking with external GIS data sources and manual correction using photointerpretation, resulting in a more accurate and reliable map. The final LULC provides new information for environmental management and monitoring in the greater Mariño watershed. With this study we contribute to the efforts to develop standardized and replicable methodologies for high-resolution and high-accuracy LULC mapping, which is crucial for informed decision-making and conservation strategies.

Glaucoma classification through SSVEP derived ON- and OFF-pathway features.

Recent evidence from small animal models and human electrophysiology suggests that the OFF-pathway is more vulnerable to glaucomatous insult than the ON-pathway. Thus, OFF-pathway based measurements of visual function may be useful in the diagnosis of Glaucoma. The steady-state visually evoked potential (SSVEP) can be used to non-invasively make such functional measurements. Here, we examine whether OFF- and ON-pathway biasing SSVEP measurements differently predict glaucoma diagnosis using a large cohort of 98 glaucoma patients and 71 controls. Using both a logistic regression with k-fold cross-validation and a random forest classifier, we show that OFF-pathway biasing features produce a small improvement in predictive accuracy over ON-pathway biasing features. However, despite our inclusion of many more response features and the retention of both participants' eyes, our classifier did not perform as well as previous reports that used the isolated-check VEP. This is likely a result of the relatively small amount of data we collected for each participant, but may also be explained by the absence of any train-test splitting in preexisting work. Nevertheless, our results support further exploration of the diagnostic potential of OFF-pathway biasing functional biomarkers for glaucoma.

The Role of Vitamin D Metabolism Genes and Their Genomic Background in Shaping Cyclosporine A Dosage Parameters after Kidney Transplantation.

Background: Kidney transplantation is followed by immunosuppressive therapy involving calcineurin inhibitors (CNIs) such as cyclosporin A. However, long-term high CNIs doses can lead to vitamin D deficiency, and genetic variations influencing vitamin D levels can indirectly impact the necessary CNIs dosage. This study investigates the impact of genetic variations of vitamin D binding protein (DBP) rs2282679 and CYP2R1 hydroxylase rs10741657 polymorphisms on the cyclosporin A dosage in kidney transplant recipients. Additional polymorphisims of genes that are predicted to influence the pharmacogenetic profile were included. Methods: Gene polymorphisms in 177 kidney transplant recipients were analyzed using data mining techniques, including the Random Forest algorithm and Classification and Regression Trees (C&RT). The relationship between the concentration/dose (C/D) ratio of cyclosporin A and genetic profiles was assessed to determine the predictive value of DBP rs2282679 and CYP2R1 rs10741657 polymorphisms. Results: Polymorphic variants of the DBP (rs2282679) demonstrated a strong predictive value for the cyclosporin A C/D ratio in post-kidney transplantation patients. By contrast, the CYP2R1 polymorphism (rs10741657) did not show predictive significance. Additionally, the immune response genes rs231775 CTLA4 and rs1800896 IL10 were identified as predictors of cyclosporin A response, though these did not result in statistically significant differences. Conclusions:DBP rs2282679 polymorphisms can significantly predict the cyclosporin A C/D ratio, potentially enhancing the accuracy of CNI dosing. This can help identify patient groups at risk of vitamin D deficiency, ultimately improving the management of kidney transplant recipients. Understanding these genetic influences allows for more personalized and effective treatment strategies, contributing to better long-term outcomes for patients.

Human Multi-Activities Classification Using mmWave Radar: Feature Fusion in Time-Domain and PCANet.

This study introduces an innovative approach by incorporating statistical offset features, range profiles, time-frequency analyses, and azimuth-range-time characteristics to effectively identify various human daily activities. Our technique utilizes nine feature vectors consisting of six statistical offset features and three principal component analysis network (PCANet) fusion attributes. These statistical offset features are derived from combined elevation and azimuth data, considering their spatial angle relationships. The fusion attributes are generated through concurrent 1D networks using CNN-BiLSTM. The process begins with the temporal fusion of 3D range-azimuth-time data, followed by PCANet integration. Subsequently, a conventional classification model is employed to categorize a range of actions. Our methodology was tested with 21,000 samples across fourteen categories of human daily activities, demonstrating the effectiveness of our proposed solution. The experimental outcomes highlight the superior robustness of our method, particularly when using the Margenau-Hill Spectrogram for time-frequency analysis. When employing a random forest classifier, our approach outperformed other classifiers in terms of classification efficacy, achieving an average sensitivity, precision, F1, specificity, and accuracy of 98.25%, 98.25%, 98.25%, 99.87%, and 99.75%, respectively.

Two-episode mineralization in the Haerdaban Pb–Zn deposit, NW China: Insights from sulfide trace elements, in situ S–Pb isotopes, and Rb–Sr geochronology

The Haerdaban Pb–Zn deposit, located in the eastern West Tianshan Orogen, hosts stratiform and vein-type mineralization within Precambrian carbonate rocks. However, there has been limited research on the distinctions and relationships between these two mineralization styles. In this study, we compared trace element distributions, fluid conditions, material sources, and mineralization ages between stratiform and vein-type mineralization and reconstructed a detailed genetic model. Two episodes and four stages of mineralization were identified, including five generations of pyrite and two generations of sphalerite. The sedimentary exhalative episode represents stratiform mineralization including Stage I pyrite–pyrrhotite layers (Py-1, Py-2a, Py-2b, and Py-3) and Stage II sphalerite–galena layers (Sph-1). The magmatic–hydrothermal episode represents vein-type mineralization including Stage III pyrite–quartz–calcite veins (Py-4) and Stage IV sphalerite–galena–quartz–calcite veins (Sph-2). LA–ICP–MS analysis of Se–Co–Ni–As–Ag–Sb–Bi contents in pyrite suggests that Py-1 to Py-3 formed under relatively low temperatures (280 ± 8 °C) and high ƒO2 sedimentary conditions. Py-4 formed under relatively high temperatures (339 ± 18 °C) and low ƒO2 hydrothermal conditions. Variations in Fe–Mn–In–Ga–Ge–Cd–Cu contents in sphalerite indicate that Sph-1 formed under relatively low temperature (211 ± 7 °C), intermediate ƒS2 (logƒS2 = −11.1 ± 0.5), and moderate pH sedimentary exhalative conditions. Sph-2 formed under relatively high temperature (292 ± 5 °C), high ƒS2 (logƒS2 = −7.4 ± 0.2), and low pH hydrothermal conditions. In situ analysis of sulfide S–Pb suggests that ore-forming materials for stratiform mineralization were primarily derived from marine sediments, while those for vein-type mineralization primarily originated from magmatic sources. Sph-1 from stratiform mineralization yielded an Rb–Sr isochron age of 719 ± 16 Ma, while Sph-2 from vein-type mineralization exhibited an Rb–Sr isochron age of 380.3 ± 7.7 Ma. Random Forest classification of trace elements in pyrite and sphalerite predicted that stratiform mineralization is of sedimentary genesis, whereas vein-type mineralization is of magmatic–hydrothermal genesis. Based on our results, we identified a two-episode mineralization history for the Haerdaban Pb–Zn deposit: Neoproterozoic syngenetic sedimentary exhalative mineralization overprinted by Devonian epigenetic magmatic–hydrothermal mineralization. The results of this study highlight the importance of considering multiple geological events in ore-forming processes and will facilitate the exploration of similar deposits in the West Tianshan Orogen.

Assessment of Valance Emotional State Using EEG-EDA Coupling and Explainable Classifiers.

Emotion influences human life and impacts daily life activities. During emotional processes, physiological signals interact with each other instead of functioning separately. Although unimodal and multimodal approaches have been explored for emotion classification, there is a lack of inclusion of central and peripheral nervous system signal interaction-based approaches. In this study, an attempt has been made to characterize valance emotional states using Electroencephalogram (EEG)- Electrodermal activity (EDA) based coupling. For this, multimodal signals are obtained from the publicly available DEAP database (n=32 subjects). The EEG signals are decomposed into θ, α, β, and bands and EDA signals are decomposed into phasic and tonic components. Then two EEG, three EDA, and two EEG-EDA coupling-based features are extracted and applied to three classifiers namely Random Forest (RF), Linear discriminant analysis, and Adaptive boosting. In addition, SHAP analysis is performed to explain classifiers' performance with respect to features. The result shows that the proposed approach is able to classify valence emotional states. The feature combination of EEG, EDA, and EEG-EDA coupling-based features with an RF classifier performs best with an F1-score of 68.21%. SHAP analysis in frontal electrodes with γ band obtained better discrimination among different valance states. This study underscores the significance of the coupling studies of EEG with EDA in classifying emotion. Therefore, the proposed approach can be extended to emotional state assessment in clinical settings.

Enriching administrative data using survey data and machine learning techniques

I propose an approach to enrich administrative data with information only available in survey data using machine learning techniques. To illustrate the approach, I replicate a prominent study that used survey data to analyze the federal minimum wage introduction in Germany. In contrast to the original study, I use the universe of German establishments rather than the limited number of establishments that participated in the survey. As the administrative data do not contain information on whether establishments were treated by the minimum wage, I use a random forest classifier, trained on survey data, to predict the treatment status of establishments. The results obtained using the administrative data are qualitatively similar to the results obtained using the survey data. Beyond replication of previous research, this approach broadens the research potential of administrative data, enabling researchers to explore more detailed research questions at scale.

Accurate diagnosis of acute appendicitis in the emergency department: an artificial intelligence-based approach.

The diagnosis of abdominal pain in emergency departments is challenging, and appendicitis is a common concern. Atypical symptoms often delay diagnosis. Although the Alvarado score aids in decision-making, its low specificity can lead to unnecessary surgeries. By leveraging machine learning, we aim to enhance diagnostic accuracy by predicting appendicitis and distinguishing it from other causes of abdominal pain in the emergency department. Data were collected from 534 patients who presented with acute abdominal pain. Patient characteristics, laboratory results, and causes of pain were recorded. Machine learning algorithms (support vector classifier, random forest classifier, gradient boosting classifier, and Gaussian naive Bayes) were used to predict the cause of pain. Model calibration was assessed using the Brier score. The mean age was 46.89 (20.3) years, with an almost equal sex distribution (49% male, 51% female). Cholecystitis was the most prevalent outcome (37.07%), followed by appendicitis (25.84%). The Gaussian naive Bayes model exhibited superior performance in terms of accuracy (95.03% 95% CI 90.44-97.83%), sensitivity (87.18% 95% CI 72.57-95.70%), and specificity (97.54% 95% CI 92.98-99.49%), while the random forest model showed a sensitivity of 79.49%, specificity of 96.72%, and accuracy of 92.55%. The gradient boosting algorithm achieved a sensitivity, specificity, and accuracy of 89.74%, 95.90%, and 94.41%, respectively. The support vector classifier demonstrated a sensitivity of 89.74%, specificity of 92.62%, and accuracy of 91.93%. The use of modern machine learning methods aids in the accurate diagnosis of appendicitis.

Machine learning-based reproducible prediction of type 2 diabetes subtypes

Aims/hypothesisClustering-based subclassification of type 2 diabetes, which reflects pathophysiology and genetic predisposition, is a promising approach for providing personalised and effective therapeutic strategies. Ahlqvist’s classification is currently the most vigorously validated method because of its superior ability to predict diabetes complications but it does not have strong consistency over time and requires HOMA2 indices, which are not routinely available in clinical practice and standard cohort studies. We developed a machine learning (ML) model to classify individuals with type 2 diabetes into Ahlqvist’s subtypes consistently over time.MethodsCohort 1 dataset comprised 619 Japanese individuals with type 2 diabetes who were divided into training and test sets for ML models in a 7:3 ratio. Cohort 2 dataset, comprising 597 individuals with type 2 diabetes, was used for external validation. Participants were pre-labelled (T2Dkmeans) by unsupervised k-means clustering based on Ahlqvist’s variables (age at diagnosis, BMI, HbA1c, HOMA2-B and HOMA2-IR) to four subtypes: severe insulin-deficient diabetes (SIDD), severe insulin-resistant diabetes (SIRD), mild obesity-related diabetes (MOD) and mild age-related diabetes (MARD). We adopted 15 variables for a multiclass classification random forest (RF) algorithm to predict type 2 diabetes subtypes (T2DRF15). The proximity matrix computed by RF was visualised using a uniform manifold approximation and projection. Finally, we used a putative subset with missing insulin-related variables to test the predictive performance of the validation cohort, consistency of subtypes over time and prediction ability of diabetes complications.ResultsT2DRF15 demonstrated a 94% accuracy for predicting T2Dkmeans type 2 diabetes subtypes (AUCs ≥0.99 and F1 score [an indicator calculated by harmonic mean from precision and recall] ≥0.9) and retained the predictive performance in the external validation cohort (86.3%). T2DRF15 showed an accuracy of 82.9% for detecting T2Dkmeans, also in a putative subset with missing insulin-related variables, when used with an imputation algorithm. In Kaplan–Meier analysis, the diabetes clusters of T2DRF15 demonstrated distinct accumulation risks of diabetic retinopathy in SIDD and that of chronic kidney disease in SIRD during a median observation period of 11.6 (4.5–18.3) years, similarly to the subtypes using T2Dkmeans. The predictive accuracy was improved after excluding individuals with low predictive probability, who were categorised as an ‘undecidable’ cluster. T2DRF15, after excluding undecidable individuals, showed higher consistency (100% for SIDD, 68.6% for SIRD, 94.4% for MOD and 97.9% for MARD) than T2Dkmeans.Conclusions/interpretationThe new ML model for predicting Ahlqvist’s subtypes of type 2 diabetes has great potential for application in clinical practice and cohort studies because it can classify individuals with missing HOMA2 indices and predict glycaemic control, diabetic complications and treatment outcomes with long-term consistency by using readily available variables. Future studies are needed to assess whether our approach is applicable to research and/or clinical practice in multiethnic populations.Graphical

Machine Learning Models for Predicting Heart Failure: Unveiling Patterns and Enhancing Precision in Cardiac Risk Assessment

Purpose This study aims to evaluate the efficacy of various machine learning models in predicting heart failure incidence using medical data, focusing on the innovative aspect of a novel dataset. Unlike previous studies that predominantly examined features such as smoking status or age, this research explores novel features. The primary challenge addressed is the utilization of these new features, coupled with machine learning techniques, to accurately diagnose heart failure. Methods Five machine learning models, including logistic regression, support vector classifier, decision tree classifier, random forest classifier, and K-nearest neighbors, were applied to analyze medical data from a dataset comprising over 900 individuals. The dataset encompasses diverse parameters such as age, sex, chest pain severity, blood pressure, cholesterol levels, blood sugar levels, and electrocardiogram results, introducing a novel approach to feature selection. Results The evaluation of machine learning models unveiled varying performances in predicting heart failure. Logistic regression and support vector classifier exhibited the highest accuracy of 88%, followed by the decision tree classifier (below 85%), random forest classifier (84%), and K-nearest neighbors (82%). Additionally, the analysis revealed a balanced dataset distribution and highlighted sex-based disparities in heart failure incidence, along with significant correlations with factors such as age, chest pain severity, blood glucose levels, and physical activity. Conclusions The findings underscore the potential of integrating multiple machine learning models for early detection of heart failure, leveraging the inclusion of novel features in the dataset. However, careful model selection is crucial to account for discrepancies in accuracy among different models, emphasizing the importance of tailoring approaches based on specific project requirements.

The impact of trust, comfortability, usability and technophobia factors on acceptance of health information technology

In the contemporary landscape of healthcare, the rapid integration of digital technologies is reshaping traditional practices. As healthcare systems increasingly embrace digitalization, there arises a critical need to comprehend the dynamic and ever-evolving role played by Information and Communication Technologies (ICTs). Amidst the rapid digitization of healthcare systems, understanding the evolving role of Information and Communication Technologies (ICTs) is paramount. This study explores the impact of Information and Communication Technologies (ICTs) on healthcare, with a focus on Health Information Technology (HIT) and its role in enhancing patient-centered care. Specifically, the research centers on Personal Health Records (PHRs), which empower patients to control their health information securely. The study aims to identify key features influencing patients’ behavioral intention to adopt HIT, utilizing a structured questionnaire and a conceptual framework based on the Technology Acceptance Model (TAM). Feature selection analysis, conducted using the Weka tool, employed various classifiers to predict users’ perceptions and behavioral intentions towards HIT adoption. Results highlight the significance of trust, comfort, usefulness, and technophobia in shaping patients’ acceptance of HIT, with Random Forest and Bayes Net classifiers emerging as key predictors. This research provides valuable insights into the critical factors driving patients’ acceptance of HIT, contributing to the ongoing discourse on the adoption of healthcare technologies.

Optimizing cropland use to reduce groundwater arsenic hazards in a naturally arsenic-enriched grain-producing region

In the Hetao Basin, a grain-producing region plagued by naturally occurring arsenic (As) pollution, understanding the role of agricultural cultivation activities in mobilizing As in groundwater is worthwhile. Here we investigated the impact of cropland use characteristics on groundwater As hazards using a model that combines Random Forest (RF) classification with SHapley Additive exPlanation (SHAP). The analysis incorporated eight cropland use characteristics and three natural factors across 1258 groundwater samples as independent variables. Additionally, an optimized cropland use strategy to mitigate groundwater As hazards was proposed. The results revealed that crop cultivation area, especially within a 2500m-radius buffer around sampling points, most significantly influenced the probability of groundwater As concentrations exceeding an irrigation safety threshold of 50 μg/L, achieving an AUC of 0.86 for this prediction. The relative importance of crop areas on As hazards were as follows: sunflower > melon > wheat > maize. Specifically, a high proportion of sunflower area (>30%), particularly in regions with longer cropland irrigation history, tended to elevate groundwater As hazards. Conversely, its negative driving force on groundwater As hazards was more pronounced with the increase in the proportion of wheat area (>5%), in contrast to other crops. Transitioning from sunflower to wheat or melon cultivation in the northeast of the Hetao Basin may contribute to lower groundwater As hazards. This study provides a scientific foundation for balancing food production with environmental safety and public health considerations.

Machine-learning models for shoulder rehabilitation exercises classification using a wearable system.

The objective of this study is to train and test machine-learning (ML) models to automatically classify shoulder rehabilitation exercises. The cohort included both healthy and patients with rotator-cuff (RC) tears. All participants performed six shoulder rehabilitation exercises, following guidelines developed by the American Society of Shoulder and Elbow Therapists. Each exercise was repeated six times, while wearing a wearable system equipped with three magneto-inertial sensors. Six supervised machine-learning models (k-Nearest Neighbours, Support Vector Machine, Decision Tree, Random Forest (RF), Logistic Regression and Adaptive Boosting) were trained for the classification. The algorithms' ability to accurately classify exercise activities was evaluated using the nested cross-validation method, with different combinations of outer and inner folds. A total of 19 healthy subjects and 17 patients with complete RC tears were enroled in the study. The highest classification performances were achieved by the RF classifier, with an accuracy of 89.91% and an F1-score of 89.89%. The results of this study highlight the feasibility and effectiveness of using wearable sensors and ML algorithms to accurately classify shoulder rehabilitation exercises. These findings suggest promising prospects for implementing the proposed wearable system in remote home-based monitoring scenarios. The ease of setup and modularity of the system reduce user burden enabling patient-driven sensor positioning. Level III.

Subject-specific atlas for automatic brain tissue segmentation of neonatal magnetic resonance images

Developing advanced systems for 3D brain tissue segmentation from neonatal magnetic resonance (MR) images is vital for newborn structural analysis. However, automatic segmentation of neonatal brain tissues is challenging due to smaller head size and inverted T1/T2 tissue contrast compared to adults. In this work, a subject-specific atlas based technique is presented for segmentation of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from neonatal MR images. It involves atlas selection, subject-specific atlas creation using random forest (RF) classifier, and brain tissue segmentation using the expectation maximization-Markov random field (EM-MRF) method. To increase the segmentation accuracy, different tissue intensity- and gradient-based features were used. Evaluation on 40 neonatal MR images (gestational age of 37–44 weeks) demonstrated an overall accuracy of 94.3% and an average Dice similarity coefficient (DSC) of 0.945 (GM), 0.947 (WM), and 0.912 (CSF). Compared to multi-atlas segmentation methods like SEGMA and EM-MRF with multiple atlases, our method improved accuracy by up to 4%, particularly in complex tissue regions. Our proposed method allows accurate brain tissue segmentation, a crucial step in brain magnetic resonance imaging (MRI) applications including brain surface reconstruction and realistic head model creation in neonates.