Identifying diseases symptoms and general rules using supervised and unsupervised machine learning.

The symptoms of diseases can vary among individuals and may remain undetected in the early stages. Detecting these symptoms is crucial in the initial stage to effectively manage and treat cases of varying severity. Machine learning has made major advances in recent years, proving its effectiveness in various healthcare applications. This study aims to identify patterns of symptoms and general rules regarding symptoms among patients using supervised and unsupervised machine learning. The integration of a rule-based machine learning technique and classification methods is utilized to extend a prediction model. This study analyzes patient data that was available online through the Kaggle repository. After preprocessing the data and exploring descriptive statistics, the Apriori algorithm was applied to identify frequent symptoms and patterns in the discovered rules. Additionally, the study applied several machine learning models for predicting diseases, including stepwise regression, support vector machine, bootstrap forest, boosted trees, and neural-boosted methods. Several predictive machine learning models were applied to the dataset to predict diseases. It was discovered that the stepwise method for fitting outperformed all competitors in this study, as determined through cross-validation conducted for each model based on established criteria. Moreover, numerous significant decision rules were extracted in the study, which can streamline clinical applications without the need for additional expertise. These rules enable the prediction of relationships between symptoms and diseases, as well as between different diseases. Therefore, the results obtained in this study have the potential to improve the performance of prediction models. We can discover diseases symptoms and general rules using supervised and unsupervised machine learning for the dataset. Overall, the proposed algorithm can support not only healthcare professionals but also patients who face cost and time constraints in diagnosing and treating these diseases.

What could be the role of genetic tests and machine learning of AXIN2 variant dominance in non-syndromic hypodontia? A case-control study in orthodontically treated patients.

BACKGROUND: Hypodontia is the most prevalent dental anomaly in humans, and is primarily attributed to genetic factors. Although genome-wide association studies (GWAS) have identified single-nucleotide polymorphisms (SNP) associated with hypodontia, genetic risk assessment remains challenging due to population-specific SNP variants. Therefore, we aimed to conducted a genetic analysis and developed a machine-learning-based predictive model to examine the association between previously reported SNPs and hypodontia in the Saudi Arabian population. Our case-control study included 106 participants (aged 8-50 years; 64 females and 42 males), comprising 54 hypodontia cases and 52 controls. We utilized TaqManTM Real-Time Polymerase Chain Reaction and allelic genotyping to analyze three selected SNPs (AXIN2: rs2240308, PAX9: rs61754301, and MSX1: rs12532) in unstimulated whole saliva samples. The chi-square test, multinomial logistic regression, and machine-learning techniques were used to assess genetic risk by using odds ratios (ORs) for multiple target variables. RESULTS: Multivariate logistic regression indicated a significant association between homozygous AXIN2 rs2240308 and the hypodontia phenotype (ORs [95% confidence interval] 2.893 [1.28-6.53]). Machine-learning algorithms revealed that the AXIN2 homozygous (A/A) genotype is a genetic risk factor for hypodontia of teeth #12, #22, and #35, whereas the AXIN2 homozygous (G/G) genotype increases the risk for hypodontia of teeth #22, #35, and #45. The PAX9 homozygous (C/C) genotype is associated with an increased risk for hypodontia of teeth #22 and #35. CONCLUSIONS: Our study confirms a link between AXIN2 and hypodontia in Saudi orthodontic patients and suggests that combining machine-learning models with SNP analysis of saliva samples can effectively identify individuals with non-syndromic hypodontia.

Development of machine learning-based personalized predictive models for risk evaluation of hepatocellular carcinoma in hepatitis B virus-related cirrhosis patients with low levels of serum alpha-fetoprotein.

INTRODUCTION AND OBJECTIVES: The increasing incidence of hepatocellular carcinoma (HCC) in China is an urgent issue, necessitating early diagnosis and treatment. This study aimed to develop personalized predictive models by combining machine learning (ML) technology with a demographic, medical history, and noninvasive biomarker data. These models can enhance the decision-making capabilities of physicians for HCC in hepatitis B virus (HBV)-related cirrhosis patients with low serum alpha-fetoprotein (AFP) levels. PATIENTS AND METHODS: A total of 6,980 patients treated between January 2012 and December 2018 were included. Pre-treatment laboratory tests and clinical data were obtained. The significant risk factors for HCC were identified, and the relative risk of each variable affecting its diagnosis was calculated using ML and univariate regression analysis. The data set was then randomly partitioned into validation (20%) and training sets (80%) to develop the ML models. RESULTS: Twelve independent risk factors for HCC were identified using Gaussian naïve Bayes, extreme gradient boosting (XGBoost), random forest, and least absolute shrinkage and selection operation regression models. Multivariate analysis revealed that male sex, age >60 years, alkaline phosphate >150 U/L, AFP >25 ng/mL, carcinoembryonic antigen >5 ng/mL, and fibrinogen >4 g/L were the risk factors, whereas hypertension, calcium <2.25 mmol/L, potassium ≤3.5 mmol/L, direct bilirubin >6.8 µmol/L, hemoglobin <110 g/L, and glutamic-pyruvic transaminase >40 U/L were the protective factors in HCC patients. Based on these factors, a nomogram was constructed, showing an area under the curve (AUC) of 0.746 (sensitivity=0.710, specificity=0.646), which was significantly higher than AFP AUC of 0.658 (sensitivity=0.462, specificity=0.766). Compared with several ML algorithms, the XGBoost model had an AUC of 0.832 (sensitivity=0.745, specificity=0.766) and an independent validation AUC of 0.829 (sensitivity=0.766, specificity=0.737), making it the top-performing model in both sets. The external validation results have proven the accuracy of the XGBoost model. CONCLUSIONS: The proposed XGBoost demonstrated a promising ability for individualized prediction of HCC in HBV-related cirrhosis patients with low-level AFP.

Development and evaluation of portable NIR technology for the identification and quantification of Australian illicit drugs.

The efficient and accurate analysis of illicit drugs remains a constant challenge in Australia given the high volume of drugs trafficked into and around the country. Portable drug testing technologies facilitate the decentralisation of the forensic laboratory and enable analytical data to be acted upon more efficiently. Near-infrared (NIR) spectroscopy combined with chemometric modelling (machine learning algorithms) has been highlighted as a portable drug testing technology that is rapid and accurate. However, its effectiveness depends upon a database of chemically relevant specimens that are representative of the market. There are chemical differences between drugs in different countries that need to be incorporated into the database to ensure accurate chemometric model prediction. This study aimed to optimise and assess the implementation of NIR spectroscopy combined with machine learning models to rapidly identify and quantify illicit drugs within an Australian context. The MicroNIR (Viavi Solutions Inc.) was used to scan 608 illicit drug specimens seized by the Australian Federal Police comprising of mainly crystalline methamphetamine hydrochloride (HCl), cocaine HCl, and heroin HCl. A number of other traditional drugs, new psychoactive substances and adulterants were also scanned to assess selectivity. The 3673 NIR scans were compared to the identity and quantification values obtained from a reference laboratory in order to assess the proficiency of the chemometric models. The identification of crystalline methamphetamine HCl, cocaine HCl, and heroin HCl specimens was highly accurate, with accuracy rates of 98.4 %, 97.5 %, and 99.2 %, respectively. The sensitivity of these three drugs was more varied with heroin HCl identification being the least sensitive (methamphetamine = 96.6 %, cocaine = 93.5 % and heroin = 91.3 %). For these three drugs, the NIR technology provided accurate quantification, with 99 % of values falling within the relative uncertainty of ±15 %. The MicroNIR with NIRLAB infrastructure has demonstrated to provide accurate results in real-time with clear operational applications. There is potential to improve informed decision-making, safety, efficiency and effectiveness of frontline and proactive policing within Australia.

The Impact of Information Relevancy and Interactivity on Intensivists' Trust in a Machine Learning-Based Bacteremia Prediction System: Simulation Study.

Background: The exponential growth in computing power and the increasing digitization of information have substantially advanced the machine learning (ML) research field. However, ML algorithms are often considered "black boxes," and this fosters distrust. In medical domains, in which mistakes can result in fatal outcomes, practitioners may be especially reluctant to trust ML algorithms. Objective: The aim of this study is to explore the effect of user-interface design features on intensivists' trust in an ML-based clinical decision support system. Methods: A total of 47 physicians from critical care specialties were presented with 3 patient cases of bacteremia in the setting of an ML-based simulation system. Three conditions of the simulation were tested according to combinations of information relevancy and interactivity. Participants' trust in the system was assessed by their agreement with the system's prediction and a postexperiment questionnaire. Linear regression models were applied to measure the effects. Results: Participants' agreement with the system's prediction did not differ according to the experimental conditions. However, in the postexperiment questionnaire, higher information relevancy ratings and interactivity ratings were associated with higher perceived trust in the system (P<.001 for both). The explicit visual presentation of the features of the ML algorithm on the user interface resulted in lower trust among the participants (P=.05). Conclusions: Information relevancy and interactivity features should be considered in the design of the user interface of ML-based clinical decision support systems to enhance intensivists' trust. This study sheds light on the connection between information relevancy, interactivity, and trust in human-ML interaction, specifically in the intensive care unit environment.

Predicting mortality amongst Jordanian men with heart attacks using the chi-square automatic interaction detection model.

Background: One of the most complicated cardiovascular diseases in the world is heart attack. Since men are the most likely to develop cardiac diseases, accurate prediction of these conditions can help save lives in this population. This study proposed the Chi-Squared Automated Interactive Detection (CHAID) model as a prediction algorithm to forecast death versus life among men who might experience heart attacks. Methods: Data were extracted from the electronic health solution system in Jordan using a retrospective, predictive study. Between 2015 and 2021, information on men admitted to public hospitals in Jordan was gathered. Results: The CHAID algorithm had a higher accuracy of 93.72% and an area under the curve of 0.792, making it the best top model created to predict mortality among Jordanian men. It was discovered that among Jordanian men, governorates, age, pulse oximetry, medical diagnosis, pulse pressure, heart rate, systolic blood pressure, and pulse pressure were the most significant predicted risk factors of mortality from heart attack. Conclusion: With heart attack complaints as the primary risk factors that were predicted using machine learning algorithms like the CHAID model, demographic characteristics and hemodynamic readings were presented.

Revealing the regulation of allergic asthma airway epithelial cell inflammation by STEAP4 targeting MIF through machine learning algorithms and single-cell sequencing analysis.

Asthma comprises one of the most common chronic inflammatory conditions, yet still lacks effective diagnostic markers and treatment targets. To gain deeper insights, we comprehensively analyzed microarray datasets of airway epithelial samples from asthmatic patients and healthy subjects in the Gene Expression Omnibus database using three machine learning algorithms. Our investigation identified a pivotal gene, STEAP4. The expression of STEAP4 in patients with allergic asthma was found to be reduced. Furthermore, it was found to negatively correlate with the severity of the disease and was subsequently validated in asthmatic mice in this study. A ROC analysis of STEAP4 showed the AUC value was greater than 0.75. Functional enrichment analysis of STEAP4 indicated a strong correlation with IL-17, steroid hormone biosynthesis, and ferroptosis signaling pathways. Subsequently, intercellular communication analysis was performed using single-cell RNA sequencing data obtained from airway epithelial cells. The results revealed that samples exhibiting low levels of STEAP4 expression had a richer MIF signaling pathway in comparison to samples with high STEAP4 expression. Through both in vitro and in vivo experiments, we further confirmed the overexpression of STEAP4 in airway epithelial cells resulted in decreased expression of MIF, which in turn caused a decrease in the levels of the cytokines IL-33, IL-25, and IL-4; In contrast, when the STEAP4 was suppressed in airway epithelial cells, there was an upregulation of MIF expression, resulting in elevated levels of the cytokines IL-33, IL-25, and IL-4. These findings suggest that STEAP4 in the airway epithelium reduces allergic asthma Th2-type inflammatory reactions by inhibiting the MIF signaling pathway.

Leveraging multi-site electronic health data for characterization of subtypes: a pilot study of dementia in the N3C Clinical Tenant.

Objectives: To provide a foundational methodology for differentiating comorbidity patterns in subphenotypes through investigation of a multi-site dementia patient dataset. Materials and Methods: Employing the National Clinical Cohort Collaborative Tenant Pilot (N3C Clinical) dataset, our approach integrates machine learning algorithms-logistic regression and eXtreme Gradient Boosting (XGBoost)-with a diagnostic hierarchical model for nuanced classification of dementia subtypes based on comorbidities and gender. The methodology is enhanced by multi-site EHR data, implementing a hybrid sampling strategy combining 65% Synthetic Minority Over-sampling Technique (SMOTE), 35% Random Under-Sampling (RUS), and Tomek Links for class imbalance. The hierarchical model further refines the analysis, allowing for layered understanding of disease patterns. Results: The study identified significant comorbidity patterns associated with diagnosis of Alzheimer's, Vascular, and Lewy Body dementia subtypes. The classification models achieved accuracies up to 69% for Alzheimer's/Vascular dementia and highlighted challenges in distinguishing Dementia with Lewy Bodies. The hierarchical model elucidates the complexity of diagnosing Dementia with Lewy Bodies and reveals the potential impact of regional clinical practices on dementia classification. Conclusion: Our methodology underscores the importance of leveraging multi-site datasets and tailored sampling techniques for dementia research. This framework holds promise for extending to other disease subtypes, offering a pathway to more nuanced and generalizable insights into dementia and its complex interplay with comorbid conditions. Discussion: This study underscores the critical role of multi-site data analyzes in understanding the relationship between comorbidities and disease subtypes. By utilizing diverse healthcare data, we emphasize the need to consider site-specific differences in clinical practices and patient demographics. Despite challenges like class imbalance and variability in EHR data, our findings highlight the essential contribution of multi-site data to developing accurate and generalizable models for disease classification.

Establishment of precise prevention strategies for the occurrence and progression of coronary atherosclerotic heart disease using machine learning.

Background: Coronary atherosclerotic heart disease (CHD) is highly prevalent in Northwest China; however, effective preventive measures are limited. This study aimed to develop metabolic risk models tailored for the primary and secondary prevention of CHD in Northwest China. Methods: This hospital-based cross-sectional study included 744 patients who underwent coronary angiography. Data on demographic characteristics, comorbidities, and serum biochemical indices of the participants were collected. Three machine learning algorithms-recursive feature elimination, random forest, and least absolute shrinkage and selection operator-were employed to construct risk models. Model validation was performed using receiver operating characteristic and calibration curves, and the optimal cutoff values for significant risk factors were determined. Results: The predictive model for CHD onset included sex, overweight/obesity, and hemoglobin A1c (HbA1c) levels. For CHD progression to multiple coronary artery disease, the model included age, total cholesterol (TC), low-density lipoprotein cholesterol (LDL-C), and HbA1c levels. The model predicting an increased coronary Gensini score included sex, overweight/obesity, TC, LDL-C, high-density lipoprotein cholesterol, lipoprotein(a), and HbA1c levels. Notably, the optimal cutoff values for HbA1c and lipoprotein(a) for determining CHD progression were 6 % and 298 mg/L, respectively. Conclusions: Robust metabolic risk models were established, offering significant value for both the primary and secondary prevention of CHD in Northwest China. Weight loss, strict hyperglycemic control, and improvement in dyslipidemia may help prevent or delay the occurrence and progression of CHD in this region.

A new attention-based CNN_GRU model for spatial-temporal PM2.5 prediction.

Accurately predicting the spatial-temporal distribution of PM2.5 is challenging due to missing data and selecting an appropriate modeling method. Effective imputation of missing data must consider the relationships between variables while preserving their inherent variability and uncertainty. In this study, we employed machine learning techniques to impute missing data by analyzing the relationships between meteorological variables and other pollutants. Subsequently, we introduced an innovative spatiotemporal hybrid model, AC_GRU, which integrates a one-dimensional convolutional neural network (CNN), GRU, and an attention-based network to predict PM2.5 concentrations in urban areas. The AC_GRU model utilizes meteorological variables, PM2.5 concentrations from nearby air quality monitoring stations, and concentrations of other pollutants as inputs. This approach allows the model to learn spatiotemporal correlations within the time-series data, enhancing the accuracy of PM2.5 predictions. Additionally, the attention mechanism improves prediction accuracy by automatically weighting the past input variables based on their importance for future PM2.5 predictions. The experimental results demonstrate that our AC_GRU model outperforms state-of-the-art methods, making it a valuable tool for urban air quality management and public health protection.

Artificial intelligence-assisted ultrasound-guided regional anaesthesia: An explorative scoping review.

Purpose: The present study reviews the available scientific literature on artificial intelligence (AI)-assisted ultrasound-guided regional anaesthesia (UGRA) and evaluates the reported intraprocedural parameters and postprocedural outcomes. Methods: A literature search was performed on 19 September 2023, using the Medline, EMBASE, CINAHL, Cochrane Library and Google Scholar databases by experts in electronic searching. All study designs were considered with no restrictions regarding patient characteristics or cohort size. Outcomes assessed included the accuracy of AI-model tracking, success at the first attempt, differences in outcomes between AI-assisted and unassisted UGRA, operator feedback and case-report data. Results: A joint adaptive median binary pattern (JAMBP) has been applied to improve the tracking procedure, while a particle filter (PF) is involved in feature extraction. JAMBP combined with PF was most accurate on all images for landmark identification, with accuracy scores of 0.83, 0.93 and 0.93 on original, preprocessed and filtered images, respectively. Evaluation of first-attempt success of spinal needle insertion revealed first-attempt success in most patients. When comparing AI application versus UGRA alone, a significant statistical difference (p < 0.05) was found for correct block view, correct structure identification and decrease in mean injection time, needle track adjustments and bone encounters in favour of having AI assistance. Assessment of operator feedback revealed that expert and nonexpert operator feedback was overall positive. Conclusion: AI appears promising to enhance UGRA as well as to positively influence operator training. AI application of UGRA may improve the identification of anatomical structures and provide guidance for needle placement, reducing the risk of complications and improving patient outcomes. Level of Evidence: Level IV.

Establishing a differential diagnosis model between primary membranous nephropathy and non-primary membranous nephropathy by machine learning algorithms.

CONTEXT: Four algorithms with relatively balanced complexity and accuracy in deep learning classification algorithm were selected for differential diagnosis of primary membranous nephropathy (PMN). OBJECTIVE: This study explored the most suitable classification algorithm for PMN identification, and to provide data reference for PMN diagnosis research. METHODS: A total of 500 patients were referred to Luo-he Central Hospital from 2019 to 2021. All patients were diagnosed with primary glomerular disease confirmed by renal biopsy, contained 322 cases of PMN, the 178 cases of non-PMN. Using the decision tree, random forest, support vector machine, and extreme gradient boosting (Xgboost) to establish a differential diagnosis model for PMN and non-PMN. Based on the true positive rate, true negative rate, false-positive rate, false-negative rate, accuracy, feature work area under the curve (AUC) of subjects, the best performance of the model was chosen. RESULTS: The efficiency of the Xgboost model based on the above evaluation indicators was the highest, which the diagnosis of PMN of the sensitivity and specificity, respectively 92% and 96%. CONCLUSIONS: The differential diagnosis model for PMN was established successfully and the efficiency performance of the Xgboost model was the best. It could be used for the clinical diagnosis of PMN.

Membranous nephropathy (MN) without obvious causes is called primary MN (PMN), This study utilized deep learning classification algorithms for differential diagnosis of PMN and explored the most suitable classification algorithm for PMN recognition, provided data reference for PMN diagnosis research.

Groundwater salinity modeling and mapping using machine learning approaches: a case study in Sidi Okba region, Algeria.

The groundwater salinization process complexity and the lack of data on its controlling factors are the main challenges for accurate predictions and mapping of aquifer salinity. For this purpose, effective machine learning (ML) methodologies are employed for effective modeling and mapping of groundwater salinity (GWS) in the Mio-Pliocene aquifer in the Sidi Okba region, Algeria, based on limited dataset of electrical conductivity (EC) measurements and readily available digital elevation model (DEM) derivatives. The dataset was randomly split into training (70%) and testing (30%) sets, and three wrapper selection methods, recursive feature elimination (RFE), forward feature selection (FFS), and backward feature selection (BFS) are applied to train the data. The resulting combinations are used as inputs for five ML models, namely random forest (RF), hybrid neuro-fuzzy inference system (HyFIS), K-nearest neighbors (KNN), cubist regression model (CRM), and support vector machine (SVM). The best-performing model is identified and applied to predict and map GWS across the entire study area. It is highlighted that the applied methods yield input variation combinations as critical factors that are often overlocked by many researchers, which substantially impacts the models' accuracy. Among different alternatives the RF model emerged as the most effective for predicting and mapping GWS in the study area, which led to the high performance in both the training (RMSE = 1.016, R = 0.854, and MAE = 0.759) and testing (RMSE = 1.069, R = 0.831, and MAE = 0.921) phases. The generated digital map highlighted the alarming situation regarding excessive GWS levels in the study area, particularly in zones of low elevations and far from the Foum Elgherza dam and Elbiraz wadi. Overall, this study represents a significant advancement over previous approaches, offering enhanced predictive performance for GWS with the minimum number of input variables.

Machine learning enables automated screening for systematic reviews and meta-analysis in urology.

PURPOSE: To investigate and implement semiautomated screening for meta-analyses (MA) in urology under consideration of class imbalance. METHODS: Machine learning algorithms were trained on data from three MA with detailed information of the screening process. Different methods to account for class imbalance (Sampling (up- and downsampling, weighting and cost-sensitive learning), thresholding) were implemented in different machine learning (ML) algorithms (Random Forest, Logistic Regression with Elastic Net Regularization, Support Vector Machines). Models were optimized for sensitivity. Besides metrics such as specificity, receiver operating curves, total missed studies, and work saved over sampling were calculated. RESULTS: During training, models trained after downsampling achieved the best results consistently among all algorithms. Computing time ranged between 251 and 5834 s. However, when evaluated on the final test data set, the weighting approach performed best. In addition, thresholding helped to improve results as compared to the standard of 0.5. However, due to heterogeneity of results no clear recommendation can be made for a universal sample size. Misses of relevant studies were 0 for the optimized models except for one review. CONCLUSION: It will be necessary to design a holistic methodology that implements the presented methods in a practical manner, but also takes into account other algorithms and the most sophisticated methods for text preprocessing. In addition, the different methods of a cost-sensitive learning approach can be the subject of further investigations.

Integrating bioinformatics and multiple machine learning to identify mitophagy-related targets for the diagnosis and treatment of diabetic foot ulcers: evidence from transcriptome analysis and drug docking.

Background: Diabetic foot ulcers are the most common and serious complication of diabetes mellitus, the high morbidity, mortality, and disability of which greatly diminish the quality of life of patients and impose a heavy socioeconomic burden. Thus, it is urgent to identify potential biomarkers and targeted drugs for diabetic foot ulcers. Methods: In this study, we downloaded datasets related to diabetic foot ulcers from gene expression omnibus. Dysregulation of mitophagy-related genes was identified by differential analysis and weighted gene co-expression network analysis. Multiple machine algorithms were utilized to identify hub mitophagy-related genes, and a novel artificial neural network model for assisting in the diagnosis of diabetic foot ulcers was constructed based on their transcriptome expression patterns. Finally, potential drugs that can target hub mitophagy-related genes were identified using the Enrichr platform and molecular docking methods. Results: In this study, we identified 702 differentially expressed genes related to diabetic foot ulcers, and enrichment analysis showed that these genes were associated with mitochondria and energy metabolism. Subsequently, we identified hexokinase-2, small ribosomal subunit protein us3, and l-lactate dehydrogenase A chain as hub mitophagy-related genes of diabetic foot ulcers using multiple machine learning algorithms and validated their diagnostic performance in a validation cohort independent of the present study (The areas under roc curve of hexokinase-2, small ribosomal subunit protein us3, and l-lactate dehydrogenase A chain are 0.671, 0.870, and 0.739, respectively). Next, we constructed a novel artificial neural network model for the molecular diagnosis of diabetic foot ulcers, and the diagnostic performance of the training cohort and validation cohort was good, with areas under roc curve of 0.924 and 0.840, respectively. Finally, we identified retinoic acid and estradiol as promising anti-diabetic foot ulcers by targeting hexokinase-2 (-6.6 and -7.2 kcal/mol), small ribosomal subunit protein us3 (-7.5 and -8.3 kcal/mol), and l-lactate dehydrogenase A chain (-7.6 and -8.5 kcal/mol). Conclusion: The present study identified hexokinase-2, small ribosomal subunit protein us3 and l-lactate dehydrogenase A chain, and emphasized their critical roles in the diagnosis and treatment of diabetic foot ulcers through multiple dimensions, providing promising diagnostic biomarkers and targeted drugs for diabetic foot ulcers.

Development and validation of machine-learning algorithms predicting retention, overdoses, and all-cause mortality among US military veterans treated with buprenorphine for opioid use disorder.

BACKGROUND: Buprenorphine for opioid use disorder (B-MOUD) is essential to improving patient outcomes; however, retention is essential. OBJECTIVE: To develop and validate machine-learning algorithms predicting retention, overdoses, and all-cause mortality among US military veterans initiating B-MOUD. METHODS: Veterans initiating B-MOUD from fiscal years 2006-2020 were identified. Veterans' B-MOUD episodes were randomly divided into training (80%;n = 45,238) and testing samples (20%;n = 11,309). Candidate algorithms [multiple logistic regression, least absolute shrinkage and selection operator regression, random forest (RF), gradient boosting machine (GBM), and deep neural network (DNN)] were used to build and validate classification models to predict six binary outcomes: 1) B-MOUD retention, 2) any overdose, 3) opioid-related overdose, 4) overdose death, 5) opioid overdose death, and 6) all-cause mortality. Model performance was assessed using standard classification statistics [e.g., area under the receiver operating characteristic curve (AUC-ROC)]. RESULTS: Episodes in the training sample were 93.0% male, 78.0% White, 72.3% unemployed, and 48.3% had a concurrent drug use disorder. The GBM model slightly outperformed others in predicting B-MOUD retention (AUC-ROC = 0.72). RF models outperformed others in predicting any overdose (AUC-ROC = 0.77) and opioid overdose (AUC-ROC = 0.77). RF and GBM outperformed other models for overdose death (AUC-ROC = 0.74 for both), and RF and DNN outperformed other models for opioid overdose death (RF AUC-ROC = 0.79; DNN AUC-ROC = 0.78). RF and GBM also outperformed other models for all-cause mortality (AUC-ROC = 0.76 for both). No single predictor accounted for >3% of the model's variance. CONCLUSIONS: Machine-learning algorithms can accurately predict OUD-related outcomes with moderate predictive performance; however, prediction of these outcomes is driven by many characteristics.

Application of Proteomics and Machine Learning Methods to Study the Pathogenesis of Diabetic Nephropathy and Screen Urinary Biomarkers.

Diabetic nephropathy (DN) has become the main cause of end-stage renal disease worldwide, causing significant health problems. Early diagnosis of the disease is quite inadequate. To screen urine biomarkers of DN and explore its potential mechanism, this study collected urine from 87 patients with type 2 diabetes mellitus (which will be classified into normal albuminuria, microalbuminuria, and macroalbuminuria groups) and 38 healthy subjects. Twelve individuals from each group were then randomly selected as the screening cohort for proteomics analysis and the rest as the validation cohort. The results showed that humoral immune response, complement activation, complement and coagulation cascades, renin-angiotensin system, and cell adhesion molecules were closely related to the progression of DN. Five overlapping proteins (KLK1, CSPG4, PLAU, SERPINA3, and ALB) were identified as potential biomarkers by machine learning methods. Among them, KLK1 and CSPG4 were positively correlated with the urinary albumin to creatinine ratio (UACR), and SERPINA3 was negatively correlated with the UACR, which were validated by enzyme-linked immunosorbent assay (ELISA). This study provides new insights into disease mechanisms and biomarkers for early diagnosis of DN.

The role of morphometric characteristics in predicting 20-meter sprint performance through machine learning.

The aim of this study was to test the morphometric features affecting 20-m sprint performance in children at the first level of primary education using machine learning (ML) algorithms. In this study, 130 male and 152 female volunteers aged between 6 and 11 years were included. After obtaining demographic information of the participants, skinfold thickness, diameter and circumference measurements, and 20-m sprint performance were determined. The study conducted three distinct experiments to determine the optimal ML technique for predicting outcomes. Initially, the entire feature space was utilized for training the ML models to establish a baseline performance. In the second experiment, only significant features identified through correlation analysis were used for training and testing the models, enhancing the focus on relevant predictors. Lastly, Principal Component Analysis (PCA) was employed to reduce the feature space, aiming to streamline model complexity while retaining data variance. These experiments collectively aimed to evaluate different feature selection and dimensionality reduction techniques, providing insights into the most effective strategies for optimizing predictive performance in the given context. The correlation-based selected features (Age, Height, waist circumference, hip circumference, leg length, thigh length, foot length) has produced a minimum Mean Squared Error (MSE) value of 0.012 for predicting the sprint performance in children. The effective utilization of correlation analysis in the selection of relevant features for our regression model suggests that the features selected exhibit robust linear associations with the target variable and can be relied upon as predictors.

Association of volatile organic compound levels with chronic obstructive pulmonary diseases in NHANES 2013-2016.

Volatile organic compounds (VOCs) represent a significant component of air pollution. However, studies evaluating the impact of VOC exposure on chronic obstructive pulmonary disease (COPD) have predominantly focused on single pollutant models. This study aims to comprehensively assess the relationship between multiple VOC exposures and COPD. A large cross-sectional study was conducted on 4983 participants from the National Health and Nutrition Examination Survey. Four models, including weighted logistic regression, restricted cubic splines (RCS), weighted quantile sum regression (WQS), and the dual-pollution model, were used to explore the association between blood VOC levels and the prevalence of COPD in the U.S. general population. Additionally, six machine learning algorithms were employed to develop a predictive model for COPD risk, with the model's predictive capacity assessed using the area under the curve (AUC) indices. Elevated blood concentrations of benzene, toluene, ortho-xylene, and para-xylene were significantly associated with the incidence of COPD. RCS analysis further revealed a non-linear and non-monotonic relationship between blood levels of toluene and m-p-xylene with COPD prevalence. WQS regression indicated that different VOCs had varying effects on COPD, with benzene and ortho-xylene having the greatest weights. Among the six models, the Extreme Gradient Boosting (XGBoost) model demonstrated the strongest predictive power, with an AUC value of 0.781. Increased blood concentrations of benzene and toluene are significantly correlated with a higher prevalence of COPD in the U.S. population, demonstrating a non-linear relationship. Exposure to environmental VOCs may represent a new risk factor in the etiology of COPD.

Elucidating the role of angiogenesis-related genes in colorectal cancer: a multi-omics analysis.

Background: Angiogenesis plays a pivotal role in colorectal cancer (CRC), yet its underlying mechanisms demand further exploration. This study aimed to elucidate the significance of angiogenesis-related genes (ARGs) in CRC through comprehensive multi-omics analysis. Methods: CRC patients were categorized according to ARGs expression to form angiogenesis-related clusters (ARCs). We investigated the correlation between ARCs and patient survival, clinical features, consensus molecular subtypes (CMS), cancer stem cell (CSC) index, tumor microenvironment (TME), gene mutations, and response to immunotherapy. Utilizing three machine learning algorithms (LASSO, Xgboost, and Decision Tree), we screen key ARGs associated with ARCs, further validated in independent cohorts. A prognostic signature based on key ARGs was developed and analyzed at the scRNA-seq level. Validation of gene expression in external cohorts, clinical tissues, and blood samples was conducted via RT-PCR assay. Results: Two distinct ARC subtypes were identified and were significantly associated with patient survival, clinical features, CMS, CSC index, and TME, but not with gene mutations. Four genes (S100A4, COL3A1, TIMP1, and APP) were identified as key ARCs, capable of distinguishing ARC subtypes. The prognostic signature based on these genes effectively stratified patients into high- or low-risk categories. scRNA-seq analysis showed that these genes were predominantly expressed in immune cells rather than in cancer cells. Validation in two external cohorts and through clinical samples confirmed significant expression differences between CRC and controls. Conclusion: This study identified two ARG subtypes in CRC and highlighted four key genes associated with these subtypes, offering new insights into personalized CRC treatment strategies.