Bayesian Classifier Research Articles

Machine learning-assisted cancer diagnosis in patients with paraneoplastic autoantibodies.

Paraneoplastic syndromes (PNS) are a group of rare disorders triggered by an immune response to malignancy, characterized by diverse neurological, muscular, and systemic symptoms. This study aims to leverage machine learning to develop a predictive model for cancer diagnosis in patients with paraneoplastic autoantibodies. Demographic data included age and sex, and presenting symptoms were recorded. Laboratory data comprised serum or cerebrospinal fluid (CSF) paraneoplastic autoantibody panels. The study included participants who tested positive for at least one autoantibody. Naive Bayes model was used to predict cancer presence. Model performance was evaluated using sensitivity, specificity, likelihood ratios, predictive values, AUC-ROC, Brier score, and overall accuracy. Feature importance was assessed using SHapley Additive exPlanations (SHAP) values. A graphical user interface (GUI)-based application was developed to facilitate model use. The study included 116 participants, with an average age of 57.1years and a higher proportion of females (53.4%). The most common presenting symptom was ''Motor'' (40.5%), followed by ''Cognitive'' (17.2%) and ''Bulbar'' (15.5%) symptoms. Cancer was present in 23 participants (19.8%). The Naive Bayes model demonstrated high performance with a sensitivity of 85.71% and specificity of 100.00%. The AUC-ROC was 0.9795, indicating excellent diagnostic capability. Age and the presence or absence of specific autoantibodies were significant predictors of cancer. Machine learning models, such as the Naive Bayes classifier developed in this study, can accurately stratify cancer risk in patients with positive paraneoplastic autoantibodies.

Detecting B-cell lymphoma-6 overexpression status in primary central nervous system lymphoma using multiparametric MRI-based machine learning.

In primary central nervous system lymphoma (PCNSL), B-cell lymphoma-6 (BCL-6) is an unfavorable prognostic biomarker. We aim to non-invasively detect BCL-6 overexpression in PCNSL patients using multiparametric MRI and machine learning techniques. 65 patients (101 lesions) with primary central nervous system lymphoma (PCNSL) diagnosed from January 2013 to July 2023, and all patients were randomly divided into a training set and a validation set according to a ratio of 8 to 2. ADC map derived from DWI (b = 0/1000 s/mm2), fast spin echo T2WI, T2FLAIR, were collected at 3.0 T. A total of 2234 radiomics features from the tumor segmentation area were extracted and LASSO were used to select features. Logistic regression (LR), Naive bayes (NB), Support vector machine (SVM), K-nearest Neighbor, (KNN) and Multilayer Perceptron (MLP), were used for machine learning, and sensitivity, specificity, accuracy F1-score, and area under the curve (AUC) was used to evaluate the detection performance of five classifiers, 6 groups with combinations of different sequences were fitted to 5 classifiers, and optimal classifier was obtained. BCL-6 status could be identified to varying degrees with 30 models based on radiomics, and model performance could be improved by combining different sequences and classifiers. Support vector machine (SVM) combined with three sequence group had the largest AUC (0.95) in training set and satisfactory AUC (0.87) in validation set. Multiparametric MRI based machine learning is promising in detecting BCL-6 overexpression.

Prognosis modelling of adverse events for post-PCI treated AMI patients based on inflammation and nutrition indexes.

This study aimed to evaluate the predictive performance of inflammatory and nutritional indices for adverse cardiovascular events (ACE) in patients with acute myocardial infarction (AMI) after percutaneous coronary intervention (PCI) using a machine learning (ML) algorithm. AMI patients who underwent PCI were recruited and randomly divided into non/ACE groups. Inflammatory and nutritional indices were graded according to the laboratory examination reports. Logistic Regression was used to screen for factors that were significant for ML model establishment. The performances of the algorithms were evaluated in terms of accuracy, kappa, F1, receiver operating characteristic, precision recall curve, etc. RESULTS: Age, LVEF%, Killip Grade, heart rate, creatinine, albumin, neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), and prognostic nutritional index (PNI) were significantly correlated with ACE by Logistic regression analysis (P < 0.05). These nine factors were employed to establish stepwise regression (SR), random forest (RF), naïve Bayes (NB), decision trees (DT), and artificial neutron network (ANN), whose performances were evaluated in terms of accuracy, kappa, F1, receiver operating characteristic, precision recall curve, etc. The accuracy of the decision tree was greater than that of other trees. The area under the curves was the highest in the ANN model compared with the other models. ANN predictive performance had an advantage over other ML algorithms based on age, LVEF%, Killip Grade, heart rate, creatinine, albumin, NLR, PLR, and PNI.

Monkeypox diagnosis based on probabilistic K-nearest neighbors (PKNN) algorithm.

Although it is not a new illness and has been around since the previous century, monkeypox later resurgence is fraught with difficulties. This study presents a novel approach of diagnosing monkeypox using artificial intelligence, which is called Effective Monkeypox Diagnosis Strategy (EMDS). The proposed EMDS is established through two sequential stages, namely; (i) Pre-Processing Phase (PP) and (ii) Monkeypox Diagnosing phase (MDP). During PP the input image dataset is prepared through three processes, which are; feature extraction, feature selection, and anomaly rejection, while the actual diagnosis performed in the MDP. Features are extracted from input images using GoogleNet as an effective pre-trained deep learning model, while Leopard Seal Optimization (LSO) is employed to select the most instructive features. The major contribution of this paper is focused in two issues, which are; (i) introducing a new methodology for rejecting anomalies from the input image dataset based on interquartile range (IQR), and (ii) proposing a new instance of K-Nearest Neighbor classifier for monkeypox diagnosis, which is called; Probabilistic K-Nearest Neighbors (PKNN) Algorithm. The proposed PKNN combines evidence from distance based traditional KNN as well as the Naïve probabilistic theorem used by Naïve Bayes (NB) algorithm in an integrated way. Numerous experiments have been conducted considering the proposed EMDS as well as recent competitive strategies on two public monkeypox datasets, which are; the Monkeypox Skin Image and Lesion Datasets (MSID and MSLD, respectively). Initially, the performance of the basic contributions of the proposed EMDS, which are the outlier rejection methodology (ORM) and PKNN, are evaluated individually. Then, EMSD as a whole is evaluated. Moreover, an ablation study has also been conducted to evaluate the effect of ORM and PKNN on the performance of EMSD. Based on the experimental results, it is shown that EMDS outperforms recent monkeypox identification strategies as it achieves 99% diagnosis accuracy. Moreover, it indicates the maximum precision and recall with the minimum diagnosis time.

Erlang Spectrogram and Residual Network-Based Features for Fake Audio Detection

Advancements in deep learning and other approaches are making synthetic speech more natural-sounding. These advancements enable people to train a speech synthesizer with a target voice, resulting in a model that can imitate someone's voice with excellent accuracy. To overcome these challenges, in this work, we are presenting a fusion of Spectrogram and Deep Convolutional Neural Network (DeepCNN) for detecting fake audio. The work has been implemented in three phases: Spectrogram generation, feature extraction & reduction, and classification. In the first step, Erlang spectrograms have been generated using the proposed Erlang filter bank. These generated spectrograms are then passed to the Residual Network (ResNet11) for feature extraction, and later these extracted features are fed to the Linear Discriminant Analysis (LDA) for dimensionality reduction. In the last phase, LDA-optimized features were used to train the four machine learning classifiers, one by one, eXtreme Gradient Boosting (XGboost), Naïve Bayes (NB), KNN (K-Nearest Neighbor), and Random Forest (RF). The proposed work has been evaluated on the complete Fake or Real (FoR) dataset for detecting fake audio in different scenarios. The combination of Erlang spectrogram-ResNet11-LDA with XGBoost has achieved a minimum 0% and 1.4% EER for FoR original and FoR 2sec.

A novel microsatellite instability test of sebaceous tumours to facilitate low cost universal screening for Lynch syndrome.

One in five sebaceous tumour (ST) patients may have Lynch syndrome (LS), a hereditary cancer predisposition. LS patients benefit from cancer surveillance and prevention programmes and immunotherapy. Whilst universal tumour mismatch repair (MMR) deficiency testing is recommended in colorectal and endometrial cancers to screen for LS, there is no consensus screening strategy for ST, leading to low testing rates and inequity of care. To assess a low cost and scalable, sequencing-based, microsatellite instability (MSI) assay, previously shown to enhance LS screening of colorectal cancers, for MMR deficiency detection in ST against the current clinical standard of immunohistochemistry (IHC). One-hundred-and-seven consecutive ST cases were identified from a single pathology department. MMR protein IHC staining was interpreted by a consultant histopathologist. MSI analysis used amplicon-sequencing of 14 microsatellites and a naïve Bayesian classifier to calculate sample MSI score. Loss of MMR protein expression was observed in 49/104 ST with interpretable IHC (47.1%; 95% CI: 37.3-57.2%). MMR deficiency was less frequent in carcinoma than adenoma and sebaceoma (P = 4.74x10-3). The majority of MMR deficient ST had concurrent loss of MSH2 and MSH6 expression. The MSI score achieved a receiver operator characteristic area under curve of 0.944 relative to IHC. Lower MSI scores were associated with MSH6 deficiency. These data support MSI testing as an adjunct or alternative to MMR IHC in ST. Integration of ST into established LS screening pathways using this high throughput methodology could increase testing and reduce costs.

Bowerbird courtship-inspired feature selection for efficient high-dimensional data analysis using a novel meta-heuristic

The challenge of feature selection in high-dimensional datasets is critical in enhancing machine learning model performance and interpretability while reducing computational costs. This paper introduces a novel feature selection method inspired by the unique courtship behaviors of bowerbirds, termed Bowerbird Courtship-Inspired Feature Selection (BBFS). Mimicking the decorative strategies and selective adaptation of bowerbirds, BBFS optimizes the selection of feature subsets through a meta-heuristic approach that efficiently balances exploration and exploitation. We compare the effectiveness of BBFS with established algorithms like Binary Cuckoo Search Optimization (BCSO) and Binary Grey Wolf Optimization (BGWO) across seven diverse datasets. Our results demonstrate that BBFS consistently selects fewer features and maintains or enhances classification accuracy using Decision Trees and Naive Bayes classifiers. This study underscores the potential of BBFS as a scalable and robust tool for high-dimensional data analysis, offering significant improvements over traditional and contemporary feature selection methods.Graphical

Efficient recognition of Parkinson’s disease mice on stepping characters with CNN

Parkinson’s disease (PD), as the second most prevalent neurodegenerative disorder worldwide, impacts the quality of life for over 12 million patients. This study aims to enhance the accuracy of early diagnosis of PD through non-invasive methods, with the goal of enabling earlier intervention in the disease process. To this end, we constructed an open-field environment using flexible sensors under dark conditions, conducting experiments on a mouse model of Parkinson’s disease alongside a normal control group. By processing footprint images collected in the absence of light—employing numerical area summation for noise reduction, adaptive enhancement algorithms based on pixel values, and a high-accuracy Convolutional Neural Network algorithm. And integrating motion data analysis, we achieved effective fusion of footprint images and behavioral data. After comprehensive analysis using decision-level fusion techniques and a Naive Bayes classifier, the results showed that the average classification accuracy for PD mice reached 96.56% when employing a multimodal data fusion strategy, demonstrating a significant advantage over using a single image recognition technique. This research not only highlights the substantial potential of applying multimodal data fusion strategies in the early detection of Parkinson’s disease but also proves that such an approach can significantly improve diagnostic accuracy. The findings provide new insights into the early diagnosis of Parkinson’s disease and other neurodegenerative disorders.

Advancing COVID-19 Treatment: The Role of Non-covalent Inhibitors Unveiled by Integrated Machine Learning and Network Pharmacology.

The COVID-19 pandemic has necessitated rapid advancements in therapeutic discovery. This study presents an integrated approach combining machine learning (ML) and network pharmacology to identify potential non-covalent inhibitors against pivotal proteins in COVID-19 pathogenesis, specifically B-cell lymphoma 2 (BCL2) and Epidermal Growth Factor Receptor (EGFR). Employing a dataset of 13,107 compounds, ML algorithms such as k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Random Forest (RF), and Naïve Bayes (NB) were utilized for screening and predicting active inhibitors based on molecular features. Molecular docking and molecular dynamics simulations, conducted over a 100 nanosecond period, enhanced the ML-based screening by providing insights into the binding affinities and interaction dynamics with BCL2 and EGFR. Network pharmacology analysis identified these proteins as hub targets within the COVID-19 protein-protein interaction network, highlighting their roles in apoptosis regulation and cellular signaling. The identified inhibitors exhibited strong binding affinities, suggesting potential efficacy in disrupting viral life cycles and impeding disease progression. Comparative analysis with existing literature affirmed the relevance of BCL2 and EGFR in COVID-19 therapy and underscored the novelty of integrating network pharmacology with ML. This multidisciplinary approach establishes a framework for emerging pathogen treatments and advocates for subsequent in vitro and in vivo validation, emphasizing a multi-targeted drug design strategy against viral adaptability. This study's findings are crucial for the ongoing development of therapeutic agents against COVID-19, leveraging computational and network-based strategies.

A cross-sectional study of parental perspectives on children about COVID-19 and classification using machine learning models

Background and objectiveThis study delves into the parenting cognition perspectives on COVID-19 in children, exploring symptoms, transmission modes, and protective measures. It aims to correlate these perspectives with sociodemographic factors and employ advanced machine-learning techniques for comprehensive analysis.MethodData collection involved a semi-structured questionnaire covering parental knowledge and attitude on COVID-19 symptoms, transmission, protective measures, and government satisfaction. The analysis utilised the Generalised Linear Regression Model (GLM), K-Nearest Neighbours (KNN), Support Vector Machine (SVM), Random Forest (RF), Naive Bayes (NB), and AdaBoost (AB).ResultsThe study revealed an average knowledge score of 18.02 ± 2.9, with 43.2 and 52.9% of parents demonstrating excellent and good knowledge, respectively. News channels (85%) emerged as the primary information source. Commonly reported symptoms included cough (96.47%) and fever (95.6%). GLM analysis indicated lower awareness in rural areas (β = −0.137, p &amp;lt; 0.001), lower attitude scores in males compared to females (β = −0.64, p = 0.025), and a correlation between lower socioeconomic status and attitude scores (β = −0.048, p = 0.009). The SVM classifier achieved the highest performance (66.70%) in classification tasks.ConclusionThis study offers valuable insights into parental attitudes towards COVID-19 in children, highlighting symptom recognition, transmission awareness, and preventive practices. Correlating these insights with sociodemographic factors underscores the need for tailored educational initiatives, particularly in rural areas, and for addressing gender and socioeconomic disparities. The efficacy of advanced analytics, exemplified by the SVM classifier, underscores the potential for informed decision-making in public health communication and targeted interventions, ultimately empowering parents to safeguard their children’s well-being amidst the ongoing pandemic.

Sentiment Analysis for Movie Database Management System Using Naive Bayes Algorithm

Abstract: According to F. Furtado and A. Singh (2021), movie recommendation systems aim to assist viewers by suggesting movies to watch, thereby avoiding the time-consuming and complex process of selecting from a vast library of movies, which can number in the thousands or even millions. This article seeks to reduce human effort by recommending movies based on user interests. To address these challenges, we propose a technique that combines content-based and collaborative approaches. This method produces more precise results than systems that rely solely on content-based methods. Content-based recommendation systems are limited to individual preferences and do not recommend items outside the user’s immediate interests, restricting exploration. To overcome these limitations, we developed a system that addresses these concerns. The proposed movie recommendation system uses Cosine Similarity to suggest movies like the one chosen by the user. While existing algorithms generate recommendations, they often fail to answer the critical question, “Is this a film worth watching?” To enhance the overall experience, our system incorporates sentiment analysis of selected movie reviews using machine learning techniques. This study employs two supervised learning approaches, Naïve Bayes (NB) and Support Vector Machine (SVM), to improve accuracy and efficacy. A comparison of the two methods reveals that SVM achieved an accuracy score of 98.63%, while NB scored 97.33%, as reported by N. Pavitha et al. (2022). The project integrates a sentiment analysis module into the movie management system to enhance decision-making and user experience. The Naïve Bayes approach is used to classify and evaluate user reviews and feedback into positive, negative, and neutral categories. This analysis provides insights into audience preferences, overall satisfaction, and movie reception. The system utilizes this information to refine movie recommendations, analyze trends, and enhance content selection, all of which contribute to a more personalized user experience. The system is evaluated using the ISO 25010 framework, focusing on functionality, reliability, usability, effectiveness, and robustness. Findings show that respondents actively participated in the review process across multiple domains. Key results indicate high satisfaction levels in terms of ease of use, interface design, and system performance. Feedback also highlighted areas for improvement, such as optimizing loading times and enhancing specific features for a smoother user experience. Overall, the findings reflect positive engagement with the system, demonstrating its effectiveness in meeting user needs while identifying opportunities for future enhancements.

Machine learning for predicting neoadjuvant chemotherapy effectiveness using ultrasound radiomics features and routine clinical data of patients with breast cancer

BackgroundThis study explores the clinical value of a machine learning (ML) model based on ultrasound radiomics features of primary foci, combined with clinicopathologic factors to predict the pathological complete response (pCR) of neoadjuvant chemotherapy (NAC) for patients with breast cancer (BC).MethodWe retrospectively analyzed ultrasound images and clinical information from 231 participants with BC who received NAC. These patients were randomly assigned to training and validation cohorts. Tumor regions of interest (ROI) were delineated, and radiomics features were extracted. Z-score normalization, Pearson correlation analysis, and the least absolute shrinkage selection operator (LASSO) were utilized for further screening ultrasound radiomics and clinical features. Univariate and multivariate logistic regression analysis were performed to identify the CFs that were independently associated with pCR. We compared 10 ML models based on radiomics features: support vector machine (SVM), logistic regression (LR), random forest, extra trees (ET), naïve Bayes (NB), k-nearest neighbor (KNN), multilayer perceptron (MLP), gradient boosting ML (GBM), light GBM (LGBM), and adaptive boost (AB). Diagnostic performance was evaluated using the receiver operating characteristic (ROC) area under the curve (AUC), accuracy, sensitivity, and specificity, and the Rad score was calculated. Subsequently, construction of clinical predictive models and Rad score joint clinical predictive models using ML algorithms for optimal diagnostic performance. The diagnostic process of the ML model was visualized and analyzed using SHapley Additive exPlanation (SHAP).ResultsOut of 231 participants with BC, 98 (42.42%) achieved pCR, and 133 (57.58%) did not. Twelve radiomics features were identified, with the GBM model demonstrating the best predictive performance (AUC of 0.851, accuracy of 0.75, sensitivity of 0.821, and specificity of 0.698). The clinical feature prediction model using the GBM algorithm had an AUC of 0.819 and an accuracy of 0.739. Combining the Rad score with clinical features in the GBM model resulted in superior predictive performance (AUC of 0.939 and an accuracy of 0.87). SHAP analysis indicated that participants with a high Rad score, PR-negative, ER-negative and human epidermal growth factor receptor-2 (HER-2) positive were more possibly to reach pCR. Based on the decision curve analysis, it was shown that the combined model of GBM provided higher clinical benefits.ConclusionThe GBM model based on ultrasound radiomics features and routine clinical date of BC patients had high performance in predicting pCR. SHAP analysis provided a clear explanation for the prediction results of the GBM model, revealing that patients with a high Rad score, PR-negative status, ER-negative status and HER-2-positive status are more likely to achieve pCR.

Phylotypr: an R package for classifying DNA sequences.

The phylotypr R package implements the popular naive Bayesian classification algorithm that is frequently used to classify 16S rRNA and other gene sequences to taxonomic lineages. A companion data package, phylotyprrefdata, also provides numerous versions of taxonomic databases from the Ribosomal Database Project, SILVA, and greengenes.

Identification of biomarkers for knee osteoarthritis through clinical data and machine learning models

Knee osteoarthritis (KOA) represents a progressive degenerative disorder characterized by the gradual erosion of articular cartilage. This study aimed to develop and validate biomarker-based predictive models for KOA diagnosis using machine learning techniques. Clinical data from 2594 samples were obtained and stratified into training and validation datasets in a 7:3 ratio. Key clinical features were identified through differential analysis between KOA and control groups, combined with least absolute shrinkage and selection operator (LASSO) regression. The SHapley Additive Planning (SHAP) method was employed to rank feature importance quantitatively. Based on these rankings, predictive models were constructed using Logistic Regression (LR), Random Forest (RF), eXtreme Gradient Boosting (xGBoost), Naive Bayes (NB), Support Vector Machine (SVM), and Decision Tree (DT) algorithms. Models were developed for subsets of variables, including the top 5, top 10, top 15, and all identified features. Receiver operating characteristic (ROC) curves were applied to compare diagnostic performance across models. Additionally, a risk stratification framework for KOA prediction was designed using recursive partitioning analysis (RPA). Using difference analysis and LASSO, 44 critical clinical features were identified. Among these, age, plasma prothrombin time, gender, body mass index (BMI), and prothrombin time and international normalized ratio (PTINR) emerged as the top five features, with SHAP values of 0.1990, 0.0981, 0.0471, 0.0433, and 0.0422, respectively. Machine learning analysis demonstrated that these variables provided robust diagnostic performance for KOA. In the training set, area under the curve (AUC) values for LR, RF, xGBoost, NB, SVM, and DT models were 0.947, 0.961, 0.892, 0.952, 0.885, and 0.779, respectively. Similarly, in the validation dataset, these models achieved AUC values of 0.961, 0.943, 0.789, 0.957, 0.824, and 0.76. Among them, RF consistently exhibited superior diagnostic accuracy for KOA. Additionally, RPA analysis indicated a higher prevalence of KOA among individuals aged 54 years and older. The integration of the top five clinical variables significantly enhanced the diagnostic accuracy for KOA, particularly when employing the RF model. Moreover, the RPA model offered valuable insights to assist clinicians in refining prognostic assessments and optimizing clinical decision-making processes.

Modeling suction of unsaturated granular soil treated with biochar in plant microbial fuel cell bioelectricity system

There is an initiative driven by the carbon-neutrality nature of biochar in recent times, where various countries across Europe and North America have introduced perks to encourage the production of biochar for construction purposes. This objective aligns with the zero greenhouse emission targets set by COP27 for 2050. This research work seeks to assess the effectiveness of biochar in soils with varying grain size distributions in enhancing the soil–water characteristic curve (SWCC). This work further explores the effect of different combinations of biochar content (0 to 15 mass %) on the bioelectricity generation from biochar-improved plant microbial fuel cells (BPMFC). Additionally, different machine learning models such as the “Gradient Boosting (GB)”, “CN2 Rule Induction (CN2)”, “Naive Bayes (NB)”, “Support vector machine (SVM), “Stochastic Gradient Descent (SGD)”, “K-Nearest Neighbors (KNN)”, “Tree Decision (Tree)”, “Random Forest (RF)”, and “Response Surface Methodology” (RSM), have been developed to predict SWCC based on soil suction, electric current, electrical potential, volumetric water content, temperature, and bulk density. The newly established model demonstrates a reasonable ability to predict SWCC and a cheaper technology in predicting the suction of unsaturated soils in relation to the studied bioelectric factors of the BPMFC. Overall, in this research paper, the GB, SVM and CN2 outclassed the other regression techniques in this order thereby proposing the cheapest technology with the highest performance index to predict the SWCC behavior of unsaturated soils in a BPMFC system.

Predicting Gestational Diabetes Mellitus in the first trimester using machine learning algorithms: a cross-sectional study at a hospital fertility health center in Iran

BackgroundGestational Diabetes Mellitus (GDM) is a common complication during pregnancy. Late diagnosis can have significant implications for both the mother and the fetus. This research aims to create an early prediction model for GDM in the first trimester of pregnancy. This model will help obstetricians and gynecologists make appropriate decisions for treating and preventing GDM complications.MethodsThis applied descriptive study was conducted at the fertility health center of Vali-e-Asr Hospital in Tehran, Iran. The dataset was collected from the records of pregnant women registered in the hospital’s system from 2020 to 2022. Risk factors for designing predictive models were identified through literature review, expert opinions, and clinical specialists’ input. The extracted information underwent preprocessing, and six machine learning (ML) methods were developed and evaluated for GDM prediction in the first trimester of pregnancy: decision tree (DT), multilayer perceptron (MLP), k-nearest neighbors (KNN), Naïve Bayes (NB), random forest (RF), and extreme gradient boosting (XGBoost).ResultsModels were evaluated using accuracy, precision, sensitivity, and the area under the receiver operating characteristic curve (AUC). Based on the glucose tolerance test (GTT) results, the RF model achieved the best performance in GDM prediction, with 89% accuracy, 86% precision, 92% recall, and 94% AUC, using demographic variables, medical history, and clinical findings. In modeling based on insulin consumption, the RF model achieved the best results with 62% accuracy, 60% precision, 63% recall, and 63% AUC in predicting GDM using demographic variables and medical history.ConclusionThe results of this study demonstrate that ML algorithms, especially RF, have acceptable accuracy in the early prediction of GDM during the first trimester of pregnancy.

Application of data mining for diagnosis of ENT diseases using the Naïve Bayes method with genetic algorithm feature selection

Ear, nose, and throat (ENT) disease is a disorder that occurs in the eustachian tube in one of the organs, be it the ear, nose, or throat. Early signs of ENT disease include sore throat, painful swallowing, swollen and red tonsils, runny nose, nosebleeds, blocked nose, discharge from the ears, and others. To determine the diagnosis, it is necessary to carry out a physical examination of the ears, nose, and throat as recommended by an expert, namely an ENT doctor. The research carried out was implementing data mining for the diagnosis of ENT diseases using the Naïve Bayes (NB) method. This method was chosen because it can increase the accuracy, efficiency, and accessibility of health services and is also easy to understand and apply to classify ENT disease symptom data. The NB method was used to build an ENT diagnosis classification model and the model performance was evaluated using accuracy, precision, and recall metrics. To increase the accuracy of the NB algorithm predictions, feature selection using a genetic algorithm can be used. Genetic algorithms can help select the most relevant and significant features, improving the accuracy of NB models by eliminating irrelevant or noisy features. By applying this method, predictions for ENT diseases can be produced with an accuracy of 95.67%.

Clinical Application of a Big Data Machine Learning Analysis Model for Osteoporotic Fracture Risk Assessment Built on Multicenter Clinical Data in Qingdao City.

Osteoporotic fractures (OPF) pose a public health issue, imposing significant burdens on families and societies worldwide. Currently, there is a lack of comprehensive and validated risk assessment models for OPF. This study aims to develop a model to assess and predict the risk of OPF in Qingdao City, China. From January 2021 to January 2023, we recruited 84 osteoporotic patients diagnosed with fractures from Qingdao University Affiliated Hospital, Qingdao Municipal Hospital, Qingdao Hiser Hospital Affiliated of Qingdao University, and Qingdao Central Hospital as the experimental group. In addition, 112 osteoporotic patients without fractures were recruited as the control group. In this study, we employed seven machine learning models, namely Adaboost, random forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), and Gradient Boosting Decision Trees (GBDT), to analyze the risk factors influencing the occurrence of OPF. Next, we plotted receiver operating characteristic (ROC), Precision-Recall (PR), and calibration curves to evaluate the predictive values of the different risk assessment models for OPF. Among the seven models built based on the training set data, the Adaboost model showed area under the curve (AUC), sensitivity, and specificity values close to 1, indicating the best classification performance. In the test set, the AUC values for the RF, SVM, LR, KNN, NB, AdaBoost, and GBDT models were 0.936, 0.905, 0.88, 0.93, 0.862, 0.939, and 0.859, respectively (p < 0.001). All sensitivity and specificity values for these models were higher than 0.8, with sensitivity and specificity values of the Adaboost model closest to 1. Additionally, six models had an area under the Precision-Recall curve (prAUC) values higher than 0.9, except KNN at 0.284 (p < 0.001). The calibration curves of the seven models did not significantly deviate from the ideal curve, indicating acceptable discriminative ability and predictive performance of the predictive model. All results showed that trabecular bone score (TBS) was the most important variable affecting the model, followed by osteocalcin (OST) and hunchback. Given the various clinical data from patients with OPF, we assessed and demonstrated the good predictive performance of our risk predictive models. This model will enable us to take timely intervention measures to reduce the incidence of OPF and improve patient prognosis.

A step towards quantifying, modeling and exploring uncertainty in biomedical knowledge graphs

Objective:This study aims at automatically quantifying and modelling the uncertainty of facts in biomedical knowledge graphs (BKGs) based on their textual supporting evidence using deep learning techniques. Materials and Methods:A sentence transformer is employed to extract deep features of sentences used to classify sentence factuality using a naive Bayes classifier. For each fact and its supporting evidence in a source KG, the deep feature extractor and the classifier are used to quantify the factuality of each sentence which are then transformed to numerical values in [0,1] before being averaged to get the confidence score of the fact. Results:The fact classification feature extractor enhances the separability of classes in the embedding space. This helped the fact classification model to achieve a better performance than existing factuality classification with hand-crafted features. Uncertainty quantification and modelling were demonstrated on SemMedDB by creating USemMedDB, showing KGB2U’s ability to process large BKGs. A subset of USemMedDB facts is modelled to demonstrate the correlation between the structure of the uncertain BKG and the confidence scores. The best-trained model is used to predict confidence scores of existing and unseen facts. The top-ranked unseen facts were grounded using scientific evidence showing KGB2U’s ability to discover new knowledge. Conclusion:Supporting literature of BKG facts can be used to automatically quantify their uncertainty. Additionally, the resulting uncertain biomedical KGs can be used for knowledge discovery. BKG2U interface and source code are available at http://biofunk.datanets.org/ and https://github.com/BahajAdil/KBG2U respectively.

Anxiety in aquatics: Leveraging machine learning models to predict adult zebrafish behavior.

Accurate analysis of anxiety behaviors in animal models is pivotal for advancing neuroscience research and drug discovery. This study compares the potential of DeepLabCut, ZebraLab, and machine learning models to analyze anxiety-related behaviors in adult zebrafish. Using a dataset comprising video recordings of unstressed and pre-stressed zebrafish, we extracted features such as total inactivity duration/immobility, time spent at the bottom, time spent at the top and turn angles (large and small). We observed that the data obtained using DeepLabCut and ZebraLab were highly correlated. Using this data, we annotated behaviors as anxious and not anxious and trained several machine learning models, including Logistic Regression, Decision Tree, K-Nearest Neighbours (KNN), Random Forests, Naive Bayes Classifiers, and Support Vector Machines (SVMs). The effectiveness of these machine learning models was validated and tested on independent datasets. We found that some machine learning models, such as Decision Tree and Random Forests, performed excellently to differentiate between anxious and non-anxious behavior, even in the control group, where the differences between subjects were more subtle. Our findings show that upcoming technologies, such as machine learning models, are able to effectively and accurately analyze anxiety behaviors in zebrafish and provide a cost-effective method to analyze animal behavior.