SVM-CART for Disease Classification

Effects of environmental phenols on eGFR: machine learning modeling methods applied to cross-sectional studies

Purpose

Limited investigation is available on the correlation between environmental phenols' exposure and estimated glomerular filtration rate (eGFR). Our target is established a robust and explainable machine learning (ML) model that associates environmental phenols' exposure with eGFR.

Methods

Our datasets for constructing the associations between environmental phenols' and eGFR were collected from the National Health and Nutrition Examination Survey (NHANES, 2013-2016). Five ML models were contained and fine-tuned to eGFR regression by phenols' exposure. Regression evaluation metrics were used to extract the limitation of the models. The most effective model was then utilized for regression, with interpretation of its features carried out using shapley additive explanations (SHAP) and the game theory python package to represent the model's regression capacity.

Results

The study identified the top-performing random forest (RF) regressor with a mean absolute error of 0.621 and a coefficient of determination of 0.998 among 3,371 participants. Six environmental phenols with eGFR in linear regression models revealed that the concentrations of triclosan (TCS) and bisphenol S (BPS) in urine were positively correlated with eGFR, and the correlation coefficients were β = 0.010 (p = 0.026) and β = 0.007 (p = 0.004) respectively. SHAP values indicate that BPS (1.38), bisphenol F (BPF) (0.97), 2,5-dichlorophenol (0.87), TCS (0.78), BP3 (0.60), bisphenol A (BPA) (0.59) and 2,4-dichlorophenol (0.47) in urinary contributed to the model.

Conclusion

The RF model was efficient in identifying a correlation between phenols' exposure and eGFR among United States NHANES 2013-2016 participants. The findings indicate that BPA, BPF, and BPS are inversely associated with eGFR.

Strategies for overcoming data scarcity, imbalance, and feature selection challenges in machine learning models for predictive maintenance

Predictive maintenance harnesses statistical analysis to preemptively identify equipment and system faults, facilitating cost- effective preventive measures. Machine learning algorithms enable comprehensive analysis of historical data, revealing emerging patterns and accurate predictions of impending system failures. Common hurdles in applying ML algorithms to PdM include data scarcity, data imbalance due to few failure instances, and the temporal dependence nature of PdM data. This study proposes an ML-based approach that adapts to these hurdles through the generation of synthetic data, temporal feature extraction, and the creation of failure horizons. The approach employs Generative Adversarial Networks to generate synthetic data and LSTM layers to extract temporal features. ML algorithms trained on the generated data achieved high accuracies: ANN (88.98%), Random Forest (74.15%), Decision Tree (73.82%), KNN (74.02%), and XGBoost (73.93%).

Intelligent assistant diagnosis for pediatric inguinal hernia based on a multilayer and unbalanced classification model

As one of the most common diseases in pediatric surgery, an inguinal hernia is usually diagnosed by medical experts based on clinical data collected from magnetic resonance imaging (MRI), computed tomography (CT), or B-ultrasound. The parameters of blood routine examination, such as white blood cell count and platelet count, are often used as diagnostic indicators of intestinal necrosis. Based on the medical numerical data on blood routine examination parameters and liver and kidney function parameters, this paper used machine learning algorithm to assist the diagnosis of intestinal necrosis in children with inguinal hernia before operation. In the work, we used clinical data consisting of 3,807 children with inguinal hernia symptoms and 170 children with intestinal necrosis and perforation caused by the disease. Three different models were constructed according to the blood routine examination and liver and kidney function. Some missing values were replaced by using the RIN-3M (median, mean, or mode region random interpolation) method according to the actual necessity, and the ensemble learning based on the voting principle was used to deal with the imbalanced datasets. The model trained after feature selection yielded satisfactory results with an accuracy of 86.43%, sensitivity of 84.34%, specificity of 96.89%, and AUC value of 0.91. Therefore, the proposed methods may be a potential idea for auxiliary diagnosis of inguinal hernia in children.

Heptadecanoic acid and pentadecanoic acid crosstalk with fecal-derived gut microbiota are potential non-invasive biomarkers for chronic atrophic gastritis

Background

Chronic atrophic gastritis (CAG), premalignant lesions of gastric cancer (GC), greatly increases the risk of GC. Gastroscopy with tissue biopsy is the most commonly used technology for CAG diagnosis. However, due to the invasive nature, both ordinary gastroscope and painless gastroscope result in a certain degree of injury to the esophagus as well as inducing psychological pressure on patients. In addition, patients need fast for at least half a day and take laxatives.

Methods

In this study, fecal metabolites and microbiota profiles were detected by metabolomics and 16S rRNA V4-V5 region sequencing.

Results

Alteration of fecal metabolites and microbiota profiles was found in CAG patients, compared with healthy volunteers. To identify the most relevant features, 7 fecal metabolites and 4 microbiota were selected by random forest (RF), from A and B sample sets, respectively. Furthermore, we constructed support vector machines (SVM) classifification model using 7 fecal metabolites or 4 gut microbes, or 7 fecal metabolites with 4 gut microbes, respectively, on C sample set. The accuracy of classifification model was 0.714, 0.857, 0.857, respectively, and the AUC was 0.71, 0.88, 0.9, respectively. In C sample set, Spearman's rank correlation analysis demonstrated heptadecanoic acid and pentadecanoic acid were signifificantly negatively correlated to Erysipelotrichaceae_UCG-003 and Haemophilus, respectively. We constructed SVM classifification model using 2 correlated fecal metabolites and 2 correlated gut microbes on C sample set. The accuracy of classification model was 0.857, and the AUC was 0.88.

Conclusion

Therefore, heptadecanoic acid and pentadecanoic acid, crosstalk with fecal-derived gut microbiota namely Erysipelotrichaceae_UCG-003 and Haemophilus, are potential non-invasive biomarkers for CAG diagnosis.

Use of machine learning to predict medication adherence in individuals at risk for atherosclerotic cardiovascular disease

Background

Medication nonadherence is a critical problem with severe implications in individuals at risk for atherosclerotic cardiovascular disease. Many studies have attempted to predict medication adherence in this population, but few, if any, have been effective in prediction, sug-gesting that essential risk factors remain unidentified.

Objective

This study's objective was to (1) establish an accurate prediction model of medi-cation adherence in individuals at risk for atherosclerotic cardiovascular disease and (2) identify significant contributing factors to the predictive accuracy of medication adherence. In particular, we aimed to use only the baseline questionnaire data to assess medication adherence prediction feasibility.

Methods

A sample of 40 individuals at risk for atherosclerotic cardiovascular disease was recruited for an eight-week feasibility study. After collecting baseline data, we recorded data from a pillbox that sent events to a cloud-based server. Health measures and medication use events were analyzed using machine learning algorithms to identify variables that best predict medication adherence.

Results

Our adherence prediction model, based on only the ten most relevant variables, achieved an average error rate of 12.9%. Medication adherence was closely correlated with being encouraged to play an active role in their treatment, having confidence about what to do in an emergency, knowledge about their medications, and having a special person in their life.

Conclusions

Our results showed the significance of clinical and psychosocial factors for predicting medication adherence in people at risk for atherosclerotic cardiovascular diseases. Clini-cians and researchers can use these factors to stratify individuals to make evidence-based decisions to reduce the risks.

The Neuropeptide-Related HERC5/TAC1 Interactions May Be Associated with the Dysregulation of lncRNA GAS5 Expression in Gestational Diabetes Mellitus Exosomes

Objective

The goal of this work was to look at the expression and probable role of exosomal long noncoding RNA (lncRNA) GAS5 in gestational diabetes mellitus (GDM), as well as forecast the importance of its interaction with neuropeptides in the progression of the disease.

Methods

We divided 44 pregnant women visiting the obstetric outpatient clinics at the Affiliated Hospital of Guilin Medical College from January 2021 to December 2021 into healthy and GDM groups. We measured the expression levels of the lncRNA GAS5 in peripheral blood using PCR and compared the expression levels between the 2 groups. The Gene Expression Omnibus (GEO) database and the R software were used to analyse the differences in the genes expressed in the amniotic fluid cells in the GDM and normal groups. catRAPID was used to identify potential target proteins for GAS5. Key neuropeptide-related proteins and potential target proteins of GAS5 were extracted, and protein interaction networks were mapped. AlphaFold 2 was used to predict the structure of the target protein. The ClusPro tool was used to predict protein-protein interactions. ZDOCK was used to further confirm the protein–nucleic acid docking.

Results

The lncRNA GAS5 was downregulated in the peripheral blood of pregnant women with GDM compared with normal pregnant women. The subcellular localization sites of GAS5 were the nucleus, cytoplasm, and ribosome; in addition, GAS5 was present in exosomes. Intercellular interactions, including neuropeptide receptors, were increased in the amniotic fluid cells of patients with GDM. Venn diagram analysis yielded seven neuropeptide-related proteins and three GAS5 target proteins. Among them, HERC5/TAC1 interacted and GAS5 docked well with HERC5.

Conclusion

The lncRNA GAS5 in the peripheral blood exosomes in patients with GDM may be a new target for the detection of GDM, and the interaction between GAS5 and HERC5/TAC1 may be involved in the pathogenesis of GDM.

Machine Learning Methods to Identify Missed Cases of Bladder Cancer in Population-Based Registries

PURPOSE

Population-based cancer incidence rates of bladder cancer may be underestimated. Accurate estimates are needed for understanding the burden of bladder cancer in the United States. We developed and evaluated the feasibility of a machine learning–based classifier to identify bladder cancer cases missed by cancer registries, and estimated the rate of bladder cancer cases potentially missed.

METHODS

Data were from population-based cohort of 37,940 bladder cancer cases 65 years of age and older in the SEER cancer registries linked with Medicare claims (2007-2013). Cases with other urologic cancers, abdominal cancers, and unrelated cancers were included as control groups. A cohort of cancer-free controls was also selected using the Medicare 5% random sample. We used five supervised machine learning methods: classification and regression trees, random forest, logic regression, support vector machines, and logistic regression, for predicting bladder cancer.

RESULTS

Registry linkages yielded 37,940 bladder cancer cases and 766,303 cancer-free controls. Using health insurance claims, classification and regression trees distinguished bladder cancer cases from noncancer controls with very high accuracy (95%). Bacille Calmette-Guerin, cystectomy, and mitomycin were the most important predictors for identifying bladder cancer. From 2007 to 2013, we estimated that up to 3,300 bladder cancer cases in the United States may have been missed by the SEER registries. This would result in an average of 3.5% increase in the reported incidence rate.

CONCLUSION

SEER cancer registries may potentially miss bladder cancer cases during routine reporting. These missed cases can be identified leveraging Medicare claims and data analytics, leading to more accurate estimates of bladder cancer incidence.

Altered Fractional Amplitude of Low-Frequency Fluctuation in Major Depressive Disorder and Bipolar Disorder

Background: Discriminating between major depressive disorder (MDD) and bipolar disorder (BD) remains challenging and cognitive deficits in MDD and BD are generally recognized. In this study, the fractional amplitude of low-frequency fluctuation (fALFF) approach was performed to explore neural activity and cognition in first-episode, drug-naïve BD and MDD patients, as well as the relationship between altered fALFF values and clinical or psychometric variables. Methods: A total of 21 BD patients, 25 MDD patients, and 41 healthy controls (HCs) completed clinical assessments and resting-state functional magnetic resonance imaging (rs-fMRI) scans in this study. The rs-fMRI data were analyzed by fALFF method and Pearson correlation analyses were performed between altered fALFF values and clinical variables or cognition. Support vector machine (SVM) was adopted to identify the three groups from each other with abnormal fALFF values in the brain regions obtained by group comparisons. Results: (1) The fALFF values were significantly different in the frontal lobe, temporal lobe, and left precuneus among three groups. In comparison to HCs, BD showed increased fALFF values in the right inferior temporal gyrus (ITG) and decreased fALFF values in the right middle temporal gyrus, while MDD showed decreased fALFF values in the right cerebellar lobule IV/V. In comparison to MDD, BD showed decreased fALFF values in bilateral posterior cingulate gyrus and the right cerebellar lobule VIII/IX. (2) In the BD group, a negative correlation was found between increased fALFF values in the right ITG and years of education, and a positive correlation was found between decreased fALFF values in the right cerebellar lobule VIII/IX and visuospatial abilities. (3) The fALFF values in the right cerebellar lobule VIII/IX may have the ability to discriminate BD patients from MDD patients, with sensitivity, specificity, and accuracy all over 0.70. Conclusions: Abnormal brain activities were observed in BD and MDD and were related with cognition in BD patients. The abnormality in the cerebellum can be potentially used to identify BD from MDD patients.