Multiple Machine Learning Techniques Research Articles

Evaluating the predictive value of angiogenesis-related genes for prognosis and immunotherapy response in prostate adenocarcinoma using machine learning and experimental approaches

BackgroundAngiogenesis, the process of forming new blood vessels from pre-existing ones, plays a crucial role in the development and advancement of cancer. Although blocking angiogenesis has shown success in treating different types of solid tumors, its relevance in prostate adenocarcinoma (PRAD) has not been thoroughly investigated.MethodThis study utilized the WGCNA method to identify angiogenesis-related genes and assessed their diagnostic and prognostic value in patients with PRAD through cluster analysis. A diagnostic model was constructed using multiple machine learning techniques, while a prognostic model was developed employing the LASSO algorithm, underscoring the relevance of angiogenesis-related genes in PRAD. Further analysis identified MAP7D3 as the most significant prognostic gene among angiogenesis-related genes using multivariate Cox regression analysis and various machine learning algorithms. The study also investigated the correlation between MAP7D3 and immune infiltration as well as drug sensitivity in PRAD. Molecular docking analysis was conducted to assess the binding affinity of MAP7D3 to angiogenic drugs. Immunohistochemistry analysis of 60 PRAD tissue samples confirmed the expression and prognostic value of MAP7D3.ResultOverall, the study identified 10 key angiogenesis-related genes through WGCNA and demonstrated their potential prognostic and immune-related implications in PRAD patients. MAP7D3 is found to be closely associated with the prognosis of PRAD and its response to immunotherapy. Through molecular docking studies, it was revealed that MAP7D3 exhibits a high binding affinity to angiogenic drugs. Furthermore, experimental data confirmed the upregulation of MAP7D3 in PRAD, correlating with a poorer prognosis.ConclusionOur study confirmed the important role of angiogenesis-related genes in PRAD and identified a new angiogenesis-related target MAP7D3.

MultiToxPred 1.0: a novel comprehensive tool for predicting 27 classes of protein toxins using an ensemble machine learning approach

Protein toxins are defense mechanisms and adaptations found in various organisms and microorganisms, and their use in scientific research as therapeutic candidates is gaining relevance due to their effectiveness and specificity against cellular targets. However, discovering these toxins is time-consuming and expensive. In silico tools, particularly those based on machine learning and deep learning, have emerged as valuable resources to address this challenge. Existing tools primarily focus on binary classification, determining whether a protein is a toxin or not, and occasionally identifying specific types of toxins. For the first time, we propose a novel approach capable of classifying protein toxins into 27 distinct categories based on their mode of action within cells. To accomplish this, we assessed multiple machine learning techniques and found that an ensemble model incorporating the Light Gradient Boosting Machine and Quadratic Discriminant Analysis algorithms exhibited the best performance. During the tenfold cross-validation on the training dataset, our model exhibited notable metrics: 0.840 accuracy, 0.827 F1 score, 0.836 precision, 0.840 sensitivity, and 0.989 AUC. In the testing stage, using an independent dataset, the model achieved 0.846 accuracy, 0.838 F1 score, 0.847 precision, 0.849 sensitivity, and 0.991 AUC. These results present a powerful next-generation tool called MultiToxPred 1.0, accessible through a web application. We believe that MultiToxPred 1.0 has the potential to become an indispensable resource for researchers, facilitating the efficient identification of protein toxins. By leveraging this tool, scientists can accelerate their search for these toxins and advance their understanding of their therapeutic potential.

Research Paper on Diseases Prediction Using Machine Learning

There may be drawbacks to using traditional methods for both diagnosis and treatment, especially in the case of serious disorders. Consequently, it's critical to have accurate and analysis of health issues in a timely manner for efficient treatment and prevention. When developing a medical diagnosis system, machine learning (ML) algorithms can be a useful tool as they can yield more accurate disease predictions than traditional approaches. Our team has effectively created a disease prediction system by utilizing multiple machine learning techniques, such as Decision trees, Naive Bayes, and KNN. We have established a framework that facilitates the creation and utilization of prediction models through the implementation of a rule-based methodology. Because of the system's exceptional accuracy, doctors are better equipped to predict and diagnose illnesses early on and resolve health-related issues more skill fully. Index Terms: Prediction, Symptoms of Disease, Machine Learning, Classification

Synergizing multiple machine learning techniques and remote sensing for advanced landslide susceptibility assessment: a case study in the Three Gorges Reservoir Area

Synergizing multiple machine learning techniques and remote sensing for advanced landslide susceptibility assessment: a case study in the Three Gorges Reservoir Area

Leveraging K-Nearest Neighbors for Enhanced Fruit Classification and Quality Assessment

This study investigates the application of the K-Nearest Neighbors (KNN) algorithm for fruit classification and quality assessment, aiming to enhance agricultural practices through machine learning. Employing a comprehensive dataset that encapsulates various fruit attributes such as size, weight, sweetness, crunchiness, juiciness, ripeness, acidity, and quality, the research leverages a 5-fold cross-validation method to ensure the reliability and generalizability of the KNN model's performance. The findings reveal that the KNN algorithm demonstrates high accuracy, precision, recall, and F1-Score across all metrics, indicating its efficacy in classifying fruits and predicting their quality accurately. These results not only validate the algorithm's potential in agricultural applications but also align with existing research on machine learning's capability to tackle complex classification problems. The study's discussions extend to the practical implications of implementing a KNN-based model in the agricultural sector, highlighting the possibility of revolutionizing quality control and inventory management processes. Moreover, the research contributes to the field by confirming the hypothesis regarding the effectiveness of KNN in agricultural settings and lays the foundation for future explorations that could integrate multiple machine learning techniques for enhanced outcomes. Recommendations for subsequent studies include expanding the dataset and exploring algorithmic synergies, aiming to further the advancements in agricultural technology and machine learning applications.

Emotion Fusion-Sense (Emo Fu-Sense) – A novel multimodal emotion classification technique

Human emotions play a vital role in overall well-being. With the advent of advance technologies growing interest has been observed in developing a multimodal emotion classification system that can accurately interpret human emotions. The article presents a comprehensive overview of a multimodal emotion classification system (Emo Fu-Sense) designed to capture the rich and nuanced nature of human emotions. Objective of Emo Fu-Sense is to integrates information from Electrocardiogram (ECG), Galvanic Skin Response (GSR), Electroencephalograph (EEG), respiration amplitude and body temperature to achieve holistic understanding of emotional states. To effectively extract information from multimodal data, designed system employs conventional methods with sophisticated machine learning algorithms including Long Short-Term Memory (LSTM), a variety of Recurrent Neural Network (RNN). Recommended solution extracts column wise features independently from different modalities based on the windowing operation. Finally, feature fusion and modality biasing were used to combine the information from different modalities. The proposed method has not only highlighted the limitations of unimodal system but has achieved a classification accuracy of 92.62 %, with an average F1-Score of 93 % and 9.2 % of Mean Absolute Error (MAE). Obtained results are better than existing state-of-the-art approaches. Evaluation of the multimodal emotion classification system was conducted on MAHNOB-HCI dataset, which encompasses a wide range of emotional expressions across various contexts and individuals. The integration of multiple modalities and advanced machine learning techniques enables a more comprehensive understanding of emotional states and highlights the significance of research and development in the field of affective computing.

Wild Horse Optimizer and Support Vector Machine (SVM) Classifier Predicts The Heart Disease Converging Nature-Motivated Optimization and Machine Learning

Background: As one of the leading causes of morbidity and mortality worldwide, the diagnosis of acute cardiovascular disease (acute CVD) in emergency settings remains a significant challenge. Machine learning (ML) is artificial intelligence that allows computer programs to learn from and analyze large data sets without human intervention. As a diagnostic tool, ML presents numerous advantages, such as convenience, speed, and affordability. Methods: This research utilized a new model for predicting heart disease for feature selection(Wild Horse Optimizer, WHO) and another classification model (Support Vector Machine, SVM). In the WHO algorithm, like envisioning social behaviors of wild horses, we observe that wild horses display diverse behaviors like leading, grazing, moving, mating and chase. One odd behavior about wild horses is that young foals will break away from the herd to avoid the breed in its related herd before reaching maturity. It defines the decencies of the horses. Discussion: Multiple ML techniques were employed to train classifiers using the Cleveland heart disease dataset after conducting feature selection using WHO algorithm. The performance of these models was evaluated based on different parameters like Sensitivity, Accuracy, Specificity, and AUC. The SVM classifier model trained using the WHO approach proved better than the existing methods. In the research, we proposed a Wild Horse Optimization algorithm to optimize the features for Heart Disease prediction. After feature optimization, the optimized dataset is then given to Support Vector machine classification, which performs the classification of heart disease. After evaluating different experimental results, authors conclude that combining this feature selection algorithm and SVM as a classifier for forecasting heart disease is very effective. With the help of this approach, we can improve the early detection of heart disease and effectively manage severe heart disease. The experimental result graph shows an increased accuracy rate of the spectra feature subject.

SADXAI: Predicting social anxiety disorder using multiple interpretable artificial intelligence techniques

Social anxiety disorder (SAD), also known as social phobia, is a psychological condition in which a person has a persistent and overwhelming fear of being negatively judged or observed by other individuals. This fear can affect them at work, in relationships and other social activities. The intricate combination of several environmental and biological factors is the reason for the onset of this mental condition. SAD is diagnosed using a test called the “Diagnostic and Statistical Manual of Mental Health Disorders (DSM-5), which is based on several physical, emotional and demographic symptoms. Artificial Intelligence has been a boon for medicine and is regularly used to diagnose various health conditions and diseases. Hence, this study used demographic, emotional, and physical symptoms and multiple machine learning (ML) techniques to diagnose SAD. A thorough descriptive and statistical analysis has been conducted before using the classifiers. Among all the models, the AdaBoost and logistic regression obtained the highest accuracy of 88 % each. Four eXplainable artificial techniques (XAI) techniques are utilized to make the predictions interpretable, transparent and understandable. According to XAI, the “Liebowitz Social Anxiety Scale questionnaire” and “The fear of speaking in public” are the most critical attributes in the diagnosis of SAD. This clinical decision support system framework could be utilized in various suitable locations such as schools, hospitals and workplaces to identify SAD in people.

Mining phase separation-related diagnostic biomarkers for endometriosis through WGCNA and multiple machine learning techniques: a retrospective and nomogram study.

The objective of this study was to investigate the role of phase separation-related genes in the development of endometriosis (EMs) and to identify potential characteristic genes associated with the condition. We used GEO database data, including 74 non-endometriosis and 74 varying-degree EMs patients. Our approach involved identifying significant gene modules, exploring gene intersections, identifying core genes, and screening for potential EMs biomarkers using weighted gene co-expression network analysis (WGCNA) and various machine learning approaches. We also performed gene set enrichment analysis (GSEA) to understand relevant pathways. This comprehensive approach helps investigate EMs genetics and potential biomarkers. Nine genes were identified at the intersection, suggesting their involvement in EMs. GSEA linked DEGs to pathways like complement and coagulation cascades, DNA replication, chemokines, apical plasma membrane processes, and diseases such as Hepatitis B, Human T-cell leukemia virus 1 infection, and COVID-19. Five feature genes (FOS, CFD, CCNA1, CA4, CST1) were selected by machine learning for an effective EMs diagnostic nomogram. GSEA indicated their roles in mismatch repair, cell cycle regulation, complement and coagulation cascades, and IL-17 inflammation. Notable differences in immune cell proportions (CD4 T cells, CD8 T cells, DCs, macrophages) were observed between normal and disease groups, suggesting immune involvement. This study suggests the potential involvement of phase separation-related genes in the pathogenesis of endometriosis (EMs) and identifies promising biomarkers for diagnosis. These findings have implications for further research and the development of new therapeutic strategies for EMs.

Hybrid Theory‐Guided Data Driven Framework for Calculating Irrigation Water Use of Three Staple Cereal Crops in China

AbstractCurrent irrigation water use (IWU) estimation methods confront uncertainties warranting further attention, primarily stemming from constraints within model structure and data quality. This study proposes a hybrid framework that integrates multiple machine learning (ML) methods with theory‐guided strategies to calculate IWU for three principal cereal crops within the Chinese agricultural landscape. We generated high resolution time series data sets of evapotranspiration and surface soil moisture (SM) using remote sensing resources. ML techniques, along with the Bayesian three‐cornered hat ensemble, were employed to drive multiple remote sensing‐derived data sets in IWU calculation. We applied two theory‐guided mechanisms to quantify irrigation signals: first, converting original SM values into logarithmic terms, and second, extracting process‐based SM residuals. Proposed framework has been validated at 12 field stations across China, yielding coefficient of determination (R2) ranging from 0.54 to 0.70, and root mean square error (RMSE) spanning 278–335 mm/yr. Our framework demonstrates considerable strength in IWU estimation when compared to reported IWU values form 341 cities across China. Specifically, for rice, wheat, and maize, the R2 values range from 0.78 to 0.83, 0.68 to 0.76, and 0.53 to 0.64, respectively, with corresponding RMSE measuring 0.22–0.25, 0.10–0.12, and 0.11–0.13 km3/yr, respectively. These findings highlight the effectiveness of theory‐guided strategies in discerning irrigation‐related information, thereby improving overall model performance. Attention should be directed toward the uncertainties in evapotranspiration and precipitation products on model performance, which remained modest, with a relative change of less than 5%.

A Security Analysis Model for IoT-ecosystem Using Machine Learning- (ML) Approach

Introduction:: The attacks on IoT systems are increasing as the devices and communication networks are progressively integrated. If no attacks are found in IoT for a long time, it will affect the availability of services that can result in data leaks and can create a significant impact on the associated costs and quality of services. Therefore, the attacks and security vulnerability in the IoT ecosystem must be detected to provide robust security and defensive mechanisms for real-time applications. Method:: This paper proposes an analytical design of an intelligent attack detection framework using multiple machine learning techniques to provide cost-effective and efficient security analysis services in the IoT ecosystem. Result:: The performance validation of the proposed framework is carried out by multiple performance indicators. Conclusion:: The simulation outcome exhibits the effectiveness of the proposed system in terms of accuracy and F1-score for the detection of various types of attacking scenarios.

Systemic Lupus Erythematosus: How Machine Learning Can Help Distinguish between Infections and Flares.

Systemic Lupus Erythematosus (SLE) is a multifaceted autoimmune ailment that impacts multiple bodily systems and manifests with varied clinical manifestations. Early detection is considered the most effective way to save patients' lives, but detecting severe SLE activity in its early stages is proving to be a formidable challenge. Consequently, this work advocates the use of Machine Learning (ML) algorithms for the diagnosis of SLE flares in the context of infections. In the pursuit of this research, the Random Forest (RF) method has been employed due to its performance attributes. With RF, our objective is to uncover patterns within the patient data. Multiple ML techniques have been scrutinized within this investigation. The proposed system exhibited around a 7.49% enhancement in accuracy when compared to k-Nearest Neighbors (KNN) algorithm. In contrast, the Support Vector Machine (SVM), Binary Linear Discriminant Analysis (BLDA), Decision Trees (DT) and Linear Regression (LR) methods demonstrated inferior performance, with respective values around 81%, 78%, 84% and 69%. It is noteworthy that the proposed method displayed a superior area under the curve (AUC) and balanced accuracy (both around 94%) in comparison to other ML approaches. These outcomes underscore the feasibility of crafting an automated diagnostic support method for SLE patients grounded in ML systems.

Accessory genes define species-specific routes to antibiotic resistance.

A deeper understanding of the relationship between the antimicrobial resistance (AMR) gene carriage and phenotype is necessary to develop effective response strategies against this global burden. AMR phenotype is often a result of multi-gene interactions; therefore, we need approaches that go beyond current simple AMR gene identification tools. Machine-learning (ML) methods may meet this challenge and allow the development of rapid computational approaches for AMR phenotype classification. To examine this, we applied multiple ML techniques to 16,950 bacterial genomes across 28 genera, with corresponding MICs for 23 antibiotics with the aim of training models to accurately determine the AMR phenotype from sequenced genomes. This resulted in a >1.5-fold increase in AMR phenotype prediction accuracy over AMR gene identification alone. Furthermore, we revealed 528 unique (often species-specific) genomic routes to antibiotic resistance, including genes not previously linked to the AMR phenotype. Our study demonstrates the utility of ML in predicting AMR phenotypes across diverse clinically relevant organisms and antibiotics. This research proposes a rapid computational method to support laboratory-based identification of the AMR phenotype in pathogens.

Machine learning applications for anomaly detection in Smart Water Metering Networks: A systematic review

The digitization of the water sector has led to the emergence of Smart Water Metering Networks (SWMNs), which enable automated and continuous water consumption measurement. However, challenges persist in efficiently managing and transmitting the vast amount of data generated by these networks. To address this, researchers have proposed anomaly detection techniques to identify and detect anomalies within SWMNs. In the realm of anomaly detection, a substantial body of research has emerged. However, there is a notable gap in the literature on a comprehensive synthesis of Machine Learning (ML) applications for anomaly detection in SWMNs. To bridge this knowledge gap, this study evaluated thirty-two research papers written between 2016 and 2023, focusing on ML applications for anomaly detection in smart water systems, smart water grids, water distribution networks, and water networks. From an initial pool of 725 research papers, those directly related to ML-based anomaly detection techniques were selected and analysed using both quantitative and qualitative data analysis. The study revealed that ML techniques such as k-Nearest Neighbors (kNN), Autoencoders, Density-Based Spatial Clustering of Applications with Noise (DBSCAN), Random Forest, Decision Trees, and Support Vector Machines (SVM) have made significant contributions to anomaly detection within these networks. Notably, researchers frequently employed multiple ML techniques to enhance accuracy. Performance metrics analysis demonstrated that F1 score, precision, accuracy, and recall were commonly used to assess the quality of ML anomaly detection techniques. This review aims to provide researchers with recommendations for selecting suitable ML anomaly detection techniques in SWMNs. The findings underscore the promising nature of ML applications for anomaly detection in SWMNs and highlight the need for further research in this area.

PPSNO: A Feature-Rich SNO Sites Predictor by Stacking Ensemble Strategy from Protein Sequence-Derived Information.

The protein S-nitrosylation (SNO) is a significant post-translational modification that affects the stability, activity, cellular localization, and function of proteins. Therefore, highly accurate prediction of SNO sites aids in grasping biological function mechanisms. In this document, we have constructed a predictor, named PPSNO, forecasting protein SNO sites using stacked integrated learning. PPSNO integrates multiple machine learning techniques into an ensemble model, enhancing its predictive accuracy. First, we established benchmark datasets by collecting SNO sites from various sources, including literature, databases, and other predictors. Second, various techniques for feature extraction are applied to derive characteristics from protein sequences, which are subsequently amalgamated into the PPSNO predictor for training. Five-fold cross-validation experiments show that PPSNO outperformed existing predictors, such as PSNO, PreSNO, pCysMod, DeepNitro, RecSNO, and Mul-SNO. The PPSNO predictor achieved an impressive accuracy of 92.8%, an area under the curve (AUC) of 96.1%, a Matthews correlation coefficient (MCC) of 81.3%, an F1-score of 85.6%, an SN of 79.3%, an SP of 97.7%, and an average precision (AP) of 92.2%. We also employed ROC curves, PR curves, and radar plots to show the superior performance of PPSNO. Our study shows that fused protein sequence features and two-layer stacked ensemble models can improve the accuracy of predicting SNO sites, which can aid in comprehending cellular processes and disease mechanisms. The codes and data are available at https://github.com/serendipity-wly/PPSNO .

Pyroptosis-Related Gene Signature Predicts Prognosis and Response to Immunotherapy and Medication in Pediatric and Young Adult Osteosarcoma Patients.

Pyroptosis, a new form of inflammatory programmed cell death, has recently gained attention. However, the impact of the expression levels of pyroptosis-related genes (PRGs) on the overall survival (OS) of osteosarcoma patients remains unclear. This study aims to investigate the impact of the expression levels of PRGs on the OS of pediatric and young adult patients with osteosarcoma. Transcriptome matrix datasets of normal muscle or skeletal tissues from the Genotype-Tissue Expression (GTEx) project and osteosarcoma specimen the National Cancer Institute's (NCI) Therapeutically Applicable Research to Generate Effective Treatments (TARGET) database were used to identify pyroptosis-related genes (PRGs) associated with prognosis. The National Center for Biotechnology Information's (NCBI) GSE21257 dataset was employed to validate the predictive value of the pyroptosis-related signature (PRS). Additionally, reverse transcription polymerase chain reaction (RT-qPCR) experiment was performed in normal and osteosarcoma cell lines. The study identified 18 differentially expressed PRGs (DEPRGs) between normal muscle or skeletal tissues and tumor samples. Multiple machine learning techniques were used to select PRGs, resulting in the identification of four hub PRGs. A PRS-score was calculated for each sample based on the expression of these four hub PRGs, and samples were categorized into low and high PRS-score level groups. It was confirmed that metastatic status and PRS-score level are independent prognostic predictors. A nomogram model for predicting OS of osteosarcoma patients was constructed. Single-cell RNA-sequencing data display the expression patterns of the hub PRGs. RT-qPCR data results were found to be consistent with the differential expression analysis performed on TARGET and GTEx samples. The study developed a novel pyroptosis-related gene signature that can stratify pediatric and young adult osteosarcoma patients into different risk groups, thus predicting their response to immunotherapy and chemotherapy.

Binary Classification of Diabetes in Pima Indian Dataset: A Deep Learning Perspective

Abstract: In this study, we develop into the application of deep learning methodologies for diabetes prediction utilizing the Pima Indian dataset. Employing Keras with Theano as the backend, we establish a binary classification model to effectively forecast the presence or absence of diabetes in individuals. Our research aims to enhance the precision and reliability of diabetes diagnosis, ultimately contributing to improved healthcare decision-making. Our investigation leverages Keras, a high-level neural networks API, in conjunction with Theano, to conduct binary classification on the Pima Indian diabetes dataset. Our study provides valuable insights into the field of medical data analysis, showcasing the effectiveness of deep learning techniques in advancing diagnostic tools for proactive healthcare management. Diabetes mellitus, a prevalent chronic disease globally, necessitates the development of a system for early type 2 diabetes mellitus (T2DM) diagnosis. Multiple machine learning and data mining techniques, including ANN, SVM, KNN, decision trees, and Extreme Learning Machines, have emerged and been employed as aids in diabetes detection. Consequently, we introduce Deep Learning, a subfield of machine learning, which can effectively handle smaller datasets through efficient data processing techniques. This paper presents an in-depth review of Diabetic Retinopathy, covering its features, causes, various ML models, DL models, challenges, comparisons, and future directions for early DR detection. Diabetes mellitus is a global health concern with a rapidly increasing prevalence. In this context, machine learning technologies prove invaluable for early disease identification and diagnosis. The focus of this study is to identify the most effective ML algorithm for diabetes prediction.

Unravelling the Drought Variance Using Machine Learning Methods in Six Capital Cities of Australia

Understanding and projecting drought, especially in the face of climate change, is crucial for assessing its impending risks. However, the causes of drought are multifaceted. As the environmental research paradigm pivots towards machine learning (ML) for predictions, our investigation contrasted multiple ML techniques to simulate the Standardized Precipitation Evapotranspiration Index (SPEI) from 2009 to 2022, utilizing various potential evapotranspiration (PET) methods. Our primary focus was Australia, the world’s driest inhabited continent. Given the challenges with ML model interpretation, SHAP (SHapley Additive exPlanations) values were employed to decipher SPEI variations and to gauge the relative importance of precipitation (Prec) and PET in six key Australian cities. Our findings revealed that while different PET methods resulted in distinct mean values, their trends remained consistent. Post the Millennium Drought, Australia experienced several drought events. SPEI discrepancies based on PET methods were minimal in humid regions like Brisbane and Darwin. However, for arid cities, the Priestley–Taylor equation-driven SPEI differed notably from other methods. Ridge regression was the most adept at mirroring SPEI changes among the assessed ML models. Furthermore, the SHAP explainer discerned that PET-related climate variables had a greater impact on SPEI in drier cities, whereas in humid cities, Prec was more influential. Notably, the research emphasised CO2′s role in influencing drought dynamics in humid cities. These insights are invaluable for enhancing drought mitigation strategies and refining predictive models. Such revelations are crucial for stakeholders aiming to improve drought prediction and management, especially in drought-prone regions like Australia.

Lightweight Techniques to Improve Generalization and Robustness of U-Net Based Networks for Pulmonary Lobe Segmentation.

Lung lobe segmentation in chest CT is relevant to a wide range of clinical applications. However, existing segmentation pipelines often exhibit vulnerabilities and performance degradations when applied to external datasets. This is usually attributed to the size of the available dataset or model. We show that it is possible to enhance generalizability without huge resources by carefully curating the dataset and combining machine learning with medical expertise. Multiple machine learning techniques (self-supervision (SSL), attention (A), and data augmentation (DA)) are used to train a fast and fully-automated lung lobe segmentation model based on 2D U-Net. Our study involved evaluating these techniques on a diverse dataset collected under the RACOON project, encompassing 100 CT chest scans from patients with bacterial, viral, or SARS-CoV2 infections. We compare our model to a baseline U-Net trained on the same dataset. Our approach significantly improved segmentation accuracy (Dice score of 92.8% vs. 82.3%, p < 0.001). Moreover, our model achieved state-of-the-art performance (Dice score of 92.8% vs. 90.8% for the literature's state-of-the-art, p = 0.102) with reduced training examples (69 vs. 231 CT Scans). Among the techniques, data augmentation with expert knowledge displayed the most significant impact, enhancing the Dice score by +0.056. Notably, these enhancements are not limited to lobe segmentation but can be seamlessly integrated into various medical imaging segmentation tasks, demonstrating their versatility and potential for broader applications.

Novel graph-based machine-learning technique for viral infectious diseases: application to influenza and hepatitis diseases

Background Most infectious diseases are caused by viruses, fungi, bacteria and parasites. Their ability to easily infect humans and trigger large-scale epidemics makes them a public health concern. Methods for early detection of these diseases have been developed; however, they are hindered by the absence of a unified, interoperable and reusable model. This study seeks to create a holistic and real-time model for swift, preliminary detection of infectious diseases using symptoms and additional clinical data. Materials and methods In this study, we present a medical knowledge graph (MKG) that leverages multiple data sources to analyse connections between different nodes. Medical ontologies were used to enhance the MKG. We applied various graph algorithms to extract key features. The performance of multiple machine-learning (ML) techniques for influenza and hepatitis detection was assessed, selecting multi-layer perceptron (MLP) and random forest (RF) models due to their superior outcomes. The hyperparameters of both graph-based ML models were automatically fine-tuned. Results Both the graph-based MLP and RF models showcased the least loss and error rates, along with the most specific, accurate recall, precision and F1 scores. Their Matthews correlation coefficients were also optimal. When compared with existing ML techniques and findings from the literature, these graph-based ML models manifested superior detection accuracy. Conclusions The graph-based MLP and RF models effectively diagnosed influenza and hepatitis, respectively. This underlines the potential of graph data science in enhancing ML model performance and uncovering concealed relationships in the MKG.