Combined interaction of fungicides binary mixtures: experimental study and machine learning-driven QSAR modeling.

Fungicide mixtures are an effective strategy in delaying the development of fungicide resistance. In this research, a fixed ratio ray design method was used to generate fifty binary mixtures of five fungicides with diverse modes of action. The interaction of these mixtures was then analyzed using CA and IA models. QSAR modeling was conducted to assess their fungicidal activity through multiple linear regression (MLR), support vector machine (SVM), and artificial neural network (ANN). Most mixtures exhibited additive interaction, with the CA model proving more accurate than the IA model in predicting fungicidal activity. The MLR model showed a good linear correlation between selected theoretical descriptors by the genetic algorithm and fungicidal activity. However, both ML-based models demonstrated better predictive performance than the MLR model. The ANN model showed slightly better predictability than the SVM model, with R2 and R2cv at 0.91 and 0.81, respectively. For external validation, the R2test value was 0.845. In contrast, the SVM model had values of 0.91, 0.78, and 0.77 for the same metrics. In conclusion, the proposed ML-based model can be a valuable tool for developing potent fungicidal mixtures to delay fungicidal resistance emergence.

Predictive modelling of transport decisions and resources optimisation in pre-hospital setting using machine learning techniques.

BACKGROUND: The global evolution of pre-hospital care systems faces dynamic challenges, particularly in multinational settings. Machine learning (ML) techniques enable the exploration of deeply embedded data patterns for improved patient care and resource optimisation. This study's objective was to accurately predict cases that necessitated transportation versus those that did not, using ML techniques, thereby facilitating efficient resource allocation. METHODS: ML algorithms were utilised to predict patient transport decisions in a Middle Eastern national pre-hospital emergency medical care provider. A comprehensive dataset comprising 93,712 emergency calls from the 999-call centre was analysed using R programming language. Demographic and clinical variables were incorporated to enhance predictive accuracy. Random Forest (RF), Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Adaptive Boosting (AdaBoost) algorithms were trained and validated. RESULTS: All the trained algorithm models, particularly XGBoost (Accuracy = 83.1%), correctly predicted patients' transportation decisions. Further, they indicated statistically significant patterns that could be leveraged for targeted resource deployment. Moreover, the specificity rates were high; 97.96% in RF and 95.39% in XGBoost, minimising the incidence of incorrectly identified "Transported" cases (False Positive). CONCLUSION: The study identified the transformative potential of ML algorithms in enhancing the quality of pre-hospital care in Qatar. The high predictive accuracy of the employed models suggested actionable avenues for day and time-specific resource planning and patient triaging, thereby having potential to contribute to pre-hospital quality, safety, and value improvement. These findings pave the way for more nuanced, data-driven quality improvement interventions with significant implications for future operational strategies.

Stacking with Recursive Feature Elimination-Isolation Forest for classification of diabetes mellitus.

Diabetes Mellitus is one of the oldest diseases known to humankind, dating back to ancient Egypt. The disease is a chronic metabolic disorder that heavily burdens healthcare providers worldwide due to the steady increment of patients yearly. Worryingly, diabetes affects not only the aging population but also children. It is prevalent to control this problem, as diabetes can lead to many health complications. As evolution happens, humankind starts integrating computer technology with the healthcare system. The utilization of artificial intelligence assists healthcare to be more efficient in diagnosing diabetes patients, better healthcare delivery, and more patient eccentric. Among the advanced data mining techniques in artificial intelligence, stacking is among the most prominent methods applied in the diabetes domain. Hence, this study opts to investigate the potential of stacking ensembles. The aim of this study is to reduce the high complexity inherent in stacking, as this problem contributes to longer training time and reduces the outliers in the diabetes data to improve the classification performance. In addressing this concern, a novel machine learning method called the Stacking Recursive Feature Elimination-Isolation Forest was introduced for diabetes prediction. The application of stacking with Recursive Feature Elimination is to design an efficient model for diabetes diagnosis while using fewer features as resources. This method also incorporates the utilization of Isolation Forest as an outlier removal method. The study uses accuracy, precision, recall, F1 measure, training time, and standard deviation metrics to identify the classification performances. The proposed method acquired an accuracy of 79.077% for PIMA Indians Diabetes and 97.446% for the Diabetes Prediction dataset, outperforming many existing methods and demonstrating effectiveness in the diabetes domain.

Maize leaf disease recognition using PRF-SVM integration: a breakthrough technique.

The difficulty of collecting maize leaf lesion characteristics in an environment that undergoes frequent changes, suffers varying illumination from lighting sources, and is influenced by a variety of other factors makes detecting diseases in maize leaves difficult. It is critical to monitor and identify plant leaf diseases during the initial growing period to take suitable preventative measures. In this work, we propose an automated maize leaf disease recognition system constructed using the PRF-SVM model. The PRFSVM model was constructed by combining three powerful components: PSPNet, ResNet50, and Fuzzy Support Vector Machine (Fuzzy SVM). The combination of PSPNet and ResNet50 not only assures that the model can capture delicate visual features but also allows for end-to-end training for smooth integration. Fuzzy SVM is included as a final classification layer to accommodate the inherent fuzziness and uncertainty in real-world image data. Five different maize crop diseases (common rust, southern rust, grey leaf spot, maydis leaf blight, and turcicum leaf blight along with healthy leaves) are selected from the Plant Village dataset for the algorithm's evaluation. The average accuracy achieved using the proposed method is approximately 96.67%. The PRFSVM model achieves an average accuracy rating of 96.67% and a mAP value of 0.81, demonstrating the efficacy of our approach for detecting and classifying various forms of maize leaf diseases.

Spatial functional reorganizations can serve as potential biomarkers of post facial palsy synkinesis.

Facial palsy can result in a serious complication known as facial synkinesis, causing both physical and psychological harm to the patients. There is growing evidence that patients with facial synkinesis have brain abnormalities, but the brain mechanisms and underlying imaging biomarkers remain unclear. Here, we employed functional magnetic resonance imaging (fMRI) to investigate brain function in 31 unilateral post facial palsy synkinesis patients and 25 healthy controls during different facial expression movements and at rest. Combining surface-based mass-univariate analysis and multivariate pattern analysis, we identified diffused activation and intrinsic connection patterns in the primary motor cortex and the somatosensory cortex on the patient's affected side. Further, we classified post facial palsy synkinesis patients from healthy subjects with favorable accuracy using the support vector machine based on both task-related and resting-state functional magnetic resonance imaging data. Together, these findings indicate the potential of the identified functional reorganizations to serve as neuroimaging biomarkers for facial synkinesis diagnosis.

Machine learning and weighted gene co-expression network analysis identify a three-gene signature to diagnose rheumatoid arthritis.

Background: Rheumatoid arthritis (RA) is a systemic immune-related disease characterized by synovial inflammation and destruction of joint cartilage. The pathogenesis of RA remains unclear, and diagnostic markers with high sensitivity and specificity are needed urgently. This study aims to identify potential biomarkers in the synovium for diagnosing RA and to investigate their association with immune infiltration. Methods: We downloaded four datasets containing 51 RA and 36 healthy synovium samples from the Gene Expression Omnibus database. Differentially expressed genes were identified using R. Then, various enrichment analyses were conducted. Subsequently, weighted gene co-expression network analysis (WGCNA), random forest (RF), support vector machine-recursive feature elimination (SVM-RFE), and least absolute shrinkage and selection operator (LASSO) were used to identify the hub genes for RA diagnosis. Receiver operating characteristic curves and nomogram models were used to validate the specificity and sensitivity of hub genes. Additionally, we analyzed the infiltration levels of 28 immune cells in the expression profile and their relationship with the hub genes using single-sample gene set enrichment analysis. Results: Three hub genes, namely, ribonucleotide reductase regulatory subunit M2 (RRM2), DLG-associated protein 5 (DLGAP5), and kinesin family member 11 (KIF11), were identified through WGCNA, LASSO, SVM-RFE, and RF algorithms. These hub genes correlated strongly with T cells, natural killer cells, and macrophage cells as indicated by immune cell infiltration analysis. Conclusion: RRM2, DLGAP5, and KIF11 could serve as potential diagnostic indicators and treatment targets for RA. The infiltration of immune cells offers additional insights into the underlying mechanisms involved in the progression of RA.

The role of the immune system in early-onset schizophrenia: identifying immune characteristic genes and cells from peripheral blood.

BACKGROUND: Early-onset schizophrenia (EOS) is a type of schizophrenia (SCZ) with an age of onset of < 18 years. An abnormal inflammatory immune system may be involved in the occurrence and development of SCZ. We aimed to identify the immune characteristic genes and cells involved in EOS and to further explore the pathogenesis of EOS from the perspective of immunology. METHODS: We obtained microarray data from a whole-genome mRNA expression in peripheral blood mononuclear cells (PBMCs); 19 patients with EOS (age range: 14.79 ± 1.90) and 18 healthy controls (HC) (age range: 15.67 ± 2.40) were involved. We screened for differentially expressed genes (DEGs) using the Limma software package and modular genes using weighted gene co-expression network analysis (WGCNA). In addition, to identify immune characteristic genes and cells, we performed enrichment analysis, immune infiltration analysis, and receiver operating characteristic (ROC) curve analysis; we also used a random forest (RF), a support vector machine (SVM), and the LASSO-Cox algorithm. RESULTS: We selected the following immune characteristic genes: CCL8, PSMD1, AVPR1B and SEMG1. We employed a RF, a SVM, and the LASSO-Cox algorithm. We identified the following immune characteristic cells: activated mast cells, CD4+ memory resting T cells, resting mast cells, neutrophils and CD4+ memory activated T cells. In addition, the AUC values of the immune characteristic genes and cells were all > 0.7. CONCLUSION: Our results indicate that immune system function is altered in SCZ. In addition, CCL8, PSMD1, AVPR1B and SEMG1 may regulate peripheral immune cells in EOS. Further, immune characteristic genes and cells are expected to be diagnostic markers and therapeutic targets of SCZ.

Structural- and DTI- MRI enable automated prediction of IDH Mutation Status in CNS WHO Grade 2-4 glioma patients: a deep Radiomics Approach.

BACKGROUND: The role of isocitrate dehydrogenase (IDH) mutation status for glioma stratification and prognosis is established. While structural magnetic resonance image (MRI) is a promising biomarker, it may not be sufficient for non-invasive characterisation of IDH mutation status. We investigated the diagnostic value of combined diffusion tensor imaging (DTI) and structural MRI enhanced by a deep radiomics approach based on convolutional neural networks (CNNs) and support vector machine (SVM), to determine the IDH mutation status in Central Nervous System World Health Organization (CNS WHO) grade 2-4 gliomas. METHODS: This retrospective study analyzed the DTI-derived fractional anisotropy (FA) and mean diffusivity (MD) images and structural images including fluid attenuated inversion recovery (FLAIR), non-enhanced T1-, and T2-weighted images of 206 treatment-naïve gliomas, including 146 IDH mutant and 60 IDH-wildtype ones. The lesions were manually segmented by experienced neuroradiologists and the masks were applied to the FA and MD maps. Deep radiomics features were extracted from each subject by applying a pre-trained CNN and statistical description. An SVM classifier was applied to predict IDH status using imaging features in combination with demographic data. RESULTS: We comparatively assessed the CNN-SVM classifier performance in predicting IDH mutation status using standalone and combined structural and DTI-based imaging features. Combined imaging features surpassed stand-alone modalities for the prediction of IDH mutation status [area under the curve (AUC) = 0.846; sensitivity = 0.925; and specificity = 0.567]. Importantly, optimal model performance was noted following the addition of demographic data (patients' age) to structural and DTI imaging features [area under the curve (AUC) = 0.847; sensitivity = 0.911; and specificity = 0.617]. CONCLUSIONS: Imaging features derived from DTI-based FA and MD maps combined with structural MRI, have superior diagnostic value to that provided by standalone structural or DTI sequences. In combination with demographic information, this CNN-SVM model offers a further enhanced non-invasive prediction of IDH mutation status in gliomas.

Detecting the symptoms of Parkinson's disease with non-standard video.

BACKGROUND: Neurodegenerative diseases, such as Parkinson's disease (PD), necessitate frequent clinical visits and monitoring to identify changes in motor symptoms and provide appropriate care. By applying machine learning techniques to video data, automated video analysis has emerged as a promising approach to track and analyze motor symptoms, which could facilitate more timely intervention. However, existing solutions often rely on specialized equipment and recording procedures, which limits their usability in unstructured settings like the home. In this study, we developed a method to detect PD symptoms from unstructured videos of clinical assessments, without the need for specialized equipment or recording procedures. METHODS: Twenty-eight individuals with Parkinson's disease completed a video-recorded motor examination that included the finger-to-nose and hand pronation-supination tasks. Clinical staff provided ground truth scores for the level of Parkinsonian symptoms present. For each video, we used a pre-existing model called PIXIE to measure the location of several joints on the person's body and quantify how they were moving. Features derived from the joint angles and trajectories, designed to be robust to recording angle, were then used to train two types of machine-learning classifiers (random forests and support vector machines) to detect the presence of PD symptoms. RESULTS: The support vector machine trained on the finger-to-nose task had an F1 score of 0.93 while the random forest trained on the same task yielded an F1 score of 0.85. The support vector machine and random forest trained on the hand pronation-supination task had F1 scores of 0.20 and 0.33, respectively. CONCLUSION: These results demonstrate the feasibility of developing video analysis tools to track motor symptoms across variable perspectives. These tools do not work equally well for all tasks, however. This technology has the potential to overcome barriers to access for many individuals with degenerative neurological diseases like PD, providing them with a more convenient and timely method to monitor symptom progression, without requiring a structured video recording procedure. Ultimately, more frequent and objective home assessments of motor function could enable more precise telehealth optimization of interventions to improve clinical outcomes inside and outside of the clinic.

Characterization and classification of ductal carcinoma tissue using four channel based stokes-mueller polarimetry and machine learning.

Interaction of polarized light with healthy and abnormal regions of tissue reveals structural information associated with its pathological condition. Even a slight variation in structural alignment can induce a change in polarization property, which can play a crucial role in the early detection of abnormal tissue morphology. We propose a transmission-based Stokes-Mueller microscope for quantitative analysis of the microstructural properties of the tissue specimen. The Stokes-Mueller based polarization microscopy provides significant structural information of tissue through various polarization parameters such as degree of polarization (DOP), degree of linear polarization (DOLP), and degree of circular polarization (DOCP), anisotropy (r) and Mueller decomposition parameters such as diattenuation, retardance and depolarization. Further, by applying a suitable image processing technique such as Machine learning (ML) output images were analysed effectively. The support vector machine image classification model achieved 95.78% validation accuracy and 94.81% testing accuracy with polarization parameter dataset. The study's findings demonstrate the potential of Stokes-Mueller polarimetry in tissue characterization and diagnosis, providing a valuable tool for biomedical applications.

Establishment and validation of multiclassification prediction models for pulmonary nodules based on machine learning.

BACKGROUND: Lung cancer is the leading cause of cancer-related death worldwide. This study aimed to establish novel multiclassification prediction models based on machine learning (ML) to predict the probability of malignancy in pulmonary nodules (PNs) and to compare with three published models. METHODS: Nine hundred fourteen patients with PNs were collected from four medical institutions (A, B, C and D), which were organized into tables containing clinical features, radiologic features and laboratory test features. Patients were divided into benign lesion (BL), precursor lesion (PL) and malignant lesion (ML) groups according to pathological diagnosis. Approximately 80% of patients in A (total/male: 632/269, age: 57.73 ± 11.06) were randomly selected as a training set; the remaining 20% were used as an internal test set; and the patients in B (total/male: 94/53, age: 60.04 ± 11.22), C (total/male: 94/47, age: 59.30 ± 9.86) and D (total/male: 94/61, age: 62.0 ± 11.09) were used as an external validation set. Logical regression (LR), decision tree (DT), random forest (RF) and support vector machine (SVM) were used to establish prediction models. Finally, the Mayo model, Peking University People's Hospital (PKUPH) model and Brock model were externally validated in our patients. RESULTS: The AUC values of RF model for MLs, PLs and BLs were 0.80 (95% CI: 0.73-0.88), 0.90 (95% CI: 0.82-0.99) and 0.75 (95% CI: 0.67-0.88), respectively. The weighted average AUC value of the RF model for the external validation set was 0.71 (95% CI: 0.67-0.73), and its AUC values for MLs, PLs and BLs were 0.71 (95% CI: 0.68-0.79), 0.98 (95% CI: 0.88-1.07) and 0.68 (95% CI: 0.61-0.74), respectively. The AUC values of the Mayo model, PKUPH model and Brock model were 0.68 (95% CI: 0.62-0.74), 0.64 (95% CI: 0.58-0.70) and 0.57 (95% CI: 0.49-0.65), respectively. CONCLUSIONS: The RF model performed best, and its predictive performance was better than that of the three published models, which may provide a new noninvasive method for the risk assessment of PNs.

Developing machine learning models to predict multi-class functional outcomes and death three months after stroke in Sweden.

Globally, stroke is the third-leading cause of mortality and disability combined, and one of the costliest diseases in society. More accurate predictions of stroke outcomes can guide healthcare organizations in allocating appropriate resources to improve care and reduce both the economic and social burden of the disease. We aim to develop and evaluate the performance and explainability of three supervised machine learning models and the traditional multinomial logistic regression (mLR) in predicting functional dependence and death three months after stroke, using routinely-collected data. This prognostic study included adult patients, registered in the Swedish Stroke Registry (Riksstroke) from 2015 to 2020. Riksstroke contains information on stroke care and outcomes among patients treated in hospitals in Sweden. Prognostic factors (features) included demographic characteristics, pre-stroke functional status, cardiovascular risk factors, medications, acute care, stroke type, and severity. The outcome was measured using the modified Rankin Scale at three months after stroke (a scale of 0-2 indicates independent, 3-5 dependent, and 6 dead). Outcome prediction models included support vector machines, artificial neural networks (ANN), eXtreme Gradient Boosting (XGBoost), and mLR. The models were trained and evaluated on 75% and 25% of the dataset, respectively. Model predictions were explained using SHAP values. The study included 102,135 patients (85.8% ischemic stroke, 53.3% male, mean age 75.8 years, and median NIHSS of 3). All models demonstrated similar overall accuracy (69%-70%). The ANN and XGBoost models performed significantly better than the mLR in classifying dependence with F1-scores of 0.603 (95% CI; 0.594-0.611) and 0.577 (95% CI; 0.568-0.586), versus 0.544 (95% CI; 0.545-0.563) for the mLR model. The factors that contributed most to the predictions were expectedly similar in the models, based on clinical knowledge. Our ANN and XGBoost models showed a modest improvement in prediction performance and explainability compared to mLR using routinely-collected data. Their improved ability to predict functional dependence may be of particular importance for the planning and organization of acute stroke care and rehabilitation.

Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning.

Heart failure (HF) encompasses a diverse clinical spectrum, including instances of transient HF or HF with recovered ejection fraction, alongside persistent cases. This dynamic condition exhibits a growing prevalence and entails substantial healthcare expenditures, with anticipated escalation in the future. It is essential to classify HF patients into three groups based on their ejection fraction: reduced (HFrEF), mid-range (HFmEF), and preserved (HFpEF), such as for diagnosis, risk assessment, treatment choice, and the ongoing monitoring of heart failure. Nevertheless, obtaining a definitive prediction poses challenges, requiring the reliance on echocardiography. On the contrary, an electrocardiogram (ECG) provides a straightforward, quick, continuous assessment of the patient's cardiac rhythm, serving as a cost-effective adjunct to echocardiography. In this research, we evaluate several machine learning (ML)-based classification models, such as K-nearest neighbors (KNN), neural networks (NN), support vector machines (SVM), and decision trees (TREE), to classify left ventricular ejection fraction (LVEF) for three categories of HF patients at hourly intervals, using 24-hour ECG recordings. Information from heterogeneous group of 303 heart failure patients, encompassing HFpEF, HFmEF, or HFrEF classes, was acquired from a multicenter dataset involving both American and Greek populations. Features extracted from ECG data were employed to train the aforementioned ML classification models, with the training occurring in one-hour intervals. To optimize the classification of LVEF levels in coronary artery disease (CAD) patients, a nested cross-validation approach was employed for hyperparameter tuning. HF patients were best classified using TREE and KNN models, with an overall accuracy of 91.2% and 90.9%, and average area under the curve of the receiver operating characteristics (AUROC) of 0.98, and 0.99, respectively. Furthermore, according to the experimental findings, the time periods of midnight-1 am, 8-9 am, and 10-11 pm were the ones that contributed to the highest classification accuracy. The results pave the way for creating an automated screening system tailored for patients with CAD, utilizing optimal measurement timings aligned with their circadian cycles.

Machine learning assisted 5-part tooth segmentation method for CBCT-based dental age estimation in adults.

BACKGROUND: The utilization of segmentation method using volumetric data in adults dental age estimation (DAE) from cone-beam computed tomography (CBCT) was further expanded by using current 5-Part Tooth Segmentation (SG) method. Additionally, supervised machine learning modelling -namely support vector regression (SVR) with linear and polynomial kernel, and regression tree - was tested and compared with the multiple linear regression model. MATERIAL AND METHODS: CBCT scans from 99 patients aged between 20 to 59.99 was collected. Eighty eligible teeth including maxillary canine, lateral incisor, and central incisor were used in this study. Enamel to dentine volume ratio, pulp to dentine volume ratio, lower tooth volume ratio, and sex was utilized as independent variable to predict chronological age. RESULTS: No multicollinearity was detected in the models. The best performing model comes from maxillary lateral incisor using SVR with polynomial kernel ( = 0.73). The lowest error rate achieved by the model was given also by maxillary lateral incisor, with 4.86 years of mean average error and 6.05 years of root means squared error. However, demands a complex approach to segment the enamel volume in the crown section and a lengthier labour time of 45 minutes per tooth.

Exploration of a machine learning approach for diagnosing sarcopenia among Chinese community-dwelling older adults using sEMG-based data.

BACKGROUND: In the practical application of sarcopenia screening, there is a need for faster, time-saving, and community-friendly detection methods. The primary purpose of this study was to perform sarcopenia screening in community-dwelling older adults and investigate whether surface electromyogram (sEMG) from hand grip could potentially be used to detect sarcopenia using machine learning (ML) methods with reasonable features extracted from sEMG signals. The secondary aim was to provide the interpretability of the obtained ML models using a novel feature importance estimation method. METHODS: A total of 158 community-dwelling older residents (≥ 60 years old) were recruited. After screening through the diagnostic criteria of the Asian Working Group for Sarcopenia in 2019 (AWGS 2019) and data quality check, participants were assigned to the healthy group (n = 45) and the sarcopenic group (n = 48). sEMG signals from six forearm muscles were recorded during the hand grip task at 20% maximal voluntary contraction (MVC) and 50% MVC. After filtering recorded signals, nine representative features were extracted, including six time-domain features plus three time-frequency domain features. Then, a voting classifier ensembled by a support vector machine (SVM), a random forest (RF), and a gradient boosting machine (GBM) was implemented to classify healthy versus sarcopenic participants. Finally, the SHapley Additive exPlanations (SHAP) method was utilized to investigate feature importance during classification. RESULTS: Seven out of the nine features exhibited statistically significant differences between healthy and sarcopenic participants in both 20% and 50% MVC tests. Using these features, the voting classifier achieved 80% sensitivity and 73% accuracy through a five-fold cross-validation. Such performance was better than each of the SVM, RF, and GBM models alone. Lastly, SHAP results revealed that the wavelength (WL) and the kurtosis of continuous wavelet transform coefficients (CWT_kurtosis) had the highest feature impact scores. CONCLUSION: This study proposed a method for community-based sarcopenia screening using sEMG signals of forearm muscles. Using a voting classifier with nine representative features, the accuracy exceeds 70% and the sensitivity exceeds 75%, indicating moderate classification performance. Interpretable results obtained from the SHAP model suggest that motor unit (MU) activation mode may be a key factor affecting sarcopenia.

Explainable machine learning approach for cancer prediction through binarilization of RNA sequencing data.

In recent years, researchers have proven the effectiveness and speediness of machine learning-based cancer diagnosis models. However, it is difficult to explain the results generated by machine learning models, especially ones that utilized complex high-dimensional data like RNA sequencing data. In this study, we propose the binarilization technique as a novel way to treat RNA sequencing data and used it to construct explainable cancer prediction models. We tested our proposed data processing technique on five different models, namely neural network, random forest, xgboost, support vector machine, and decision tree, using four cancer datasets collected from the National Cancer Institute Genomic Data Commons. Since our datasets are imbalanced, we evaluated the performance of all models using metrics designed for imbalance performance like geometric mean, Matthews correlation coefficient, F-Measure, and area under the receiver operating characteristic curve. Our approach showed comparative performance while relying on less features. Additionally, we demonstrated that data binarilization offers higher explainability by revealing how each feature affects the prediction. These results demonstrate the potential of data binarilization technique in improving the performance and explainability of RNA sequencing based cancer prediction models.

Identification of disease-specific genes related to immune infiltration in nonalcoholic steatohepatitis using machine learning algorithms.

To identify disease signature genes associated with immune infiltration in nonalcoholic steatohepatitis (NASH), we downloaded 2 publicly available gene expression profiles, GSE164760 and GSE37031, from the gene expression omnibus database. These profiles represent human NASH and control samples and were used for differential genes (DEGs) expression screening. Two machine learning methods, the Least Absolute Shrinkage and Selection Operator regression model and Support Vector Machine Recursive Feature Elimination, were used to identify candidate disease signature genes. The CIBERSORT deconvolution algorithm was employed to analyze the infiltration of 22 immune cell types in NASH. Additionally, we constructed a NASH cell model using HepG2 cells treated with oleic acid and free fatty acids. The construction of the cell model was verified using oil red O staining, and Western blotting was used to detect the protein expression of the disease signature genes in both control and model groups. As a result, a total of 262 DEGs were identified. These DEGs were primarily associated with metal ion transmembrane transporter activity, sodium ion transmembrane transporter protein activity, calcium ion, and neuroactive ligand-receptor interactions. FOS, IGFBP2, dual-specificity phosphatase 1 (DUSP1), and IKZF3 were identified as disease signature genes of NASH by the least absolute shrinkage and selection operator and Support Vector Machine Recursive Feature Elimination algorithms for DEGs analysis. The receiver operating characteristic curves showed that FOS, IGFBP2, DUSP1, and IKZF3 had good diagnostic value (area under receiver operating characteristic curve > 0.8). These findings were validated in the GSE89632 dataset and through cellular assays. Immunocyte infiltration analysis revealed that NASH was associated with CD8 T cells, CD4 T cells, follicular helper T cells, resting NK cells, eosinophils, regulatory T cells, and γδ T cells. The FOS, IGFBP2, DUSP1, and IKZF3 genes were specifically associated with follicular helper T cells. Lipid droplet aggregation significantly increased in HepG2 cells treated with oleic acid and free fatty acids, indicating successful construction of the cell model. In this model, the expression of FOS, IGFBP2, and DUSP1 was significantly decreased, while that of IKZF3 was significantly elevated (P < .01, P < .001) compared with the control group. Therefore, FOS, IGFBP2, DUSP1, and IKZF3 can be considered as disease signature genes associated with immune infiltration in NASH.

Identifying potential (re)hemorrhage among sporadic cerebral cavernous malformations using machine learning.

The (re)hemorrhage in patients with sporadic cerebral cavernous malformations (CCM) was the primary aim for CCM management. However, accurately identifying the potential (re)hemorrhage among sporadic CCM patients in advance remains a challenge. This study aims to develop machine learning models to detect potential (re)hemorrhage in sporadic CCM patients. This study was based on a dataset of 731 sporadic CCM patients in open data platform Dryad. Sporadic CCM patients were followed up 5 years from January 2003 to December 2018. Support vector machine (SVM), stacked generalization, and extreme gradient boosting (XGBoost) were used to construct models. The performance of models was evaluated by area under receiver operating characteristic curves (AUROC), area under the precision-recall curve (PR-AUC) and other metrics. A total of 517 patients with sporadic CCM were included (330 female [63.8%], mean [SD] age at diagnosis, 42.1 [15.5] years). 76 (re)hemorrhage (14.7%) occurred during follow-up. Among 3 machine learning models, XGBoost model yielded the highest mean (SD) AUROC (0.87 [0.06]) in cross-validation. The top 4 features of XGBoost model were ranked with SHAP (SHapley Additive exPlanations). All-Elements XGBoost model achieved an AUROCs of 0.84 and PR-AUC of 0.49 in testing set, with a sensitivity of 0.86 and a specificity of 0.76. Importantly, 4-Elements XGBoost model developed using top 4 features got a AUROCs of 0.83 and PR-AUC of 0.40, a sensitivity of 0.79, and a specificity of 0.72 in testing set. Two machine learning-based models achieved accurate performance in identifying potential (re)hemorrhages within 5 years in sporadic CCM patients. These models may provide insights for clinical decision-making.

Decoding predicted musical notes from omitted stimulus potentials.

Electrophysiological studies have investigated predictive processing in music by examining event-related potentials (ERPs) elicited by the violation of musical expectations. While several studies have reported that the predictability of stimuli can modulate the amplitude of ERPs, it is unclear how specific the representation of the expected note is. The present study addressed this issue by recording the omitted stimulus potentials (OSPs) to avoid contamination of bottom-up sensory processing with top-down predictive processing. Decoding of the omitted content was attempted using a support vector machine, which is a type of machine learning. ERP responses to the omission of four target notes (E, F, A, and C) at the same position in familiar and unfamiliar melodies were recorded from 25 participants. The results showed that the omission N1 were larger in the familiar melody condition than in the unfamiliar melody condition. The decoding accuracy of the four omitted notes was significantly higher in the familiar melody condition than in the unfamiliar melody condition. These results suggest that the OSPs contain discriminable predictive information, and the higher the predictability, the more the specific representation of the expected note is generated.

Machine learning-based classification of petrofacies in fine laminated limestones.

Characterization and development of hydrocarbon reservoirs depends on the classification of lithological patterns from well log data. In thin reservoir units, limited vertical data impedes the efficient classification of lithologies. We present a test case of petrofacies classification using machine learning models in a thin interval of finely laminated limestones using pseudo-well data created over outcrops (radiometric and unconfined compressive strength logs). We tested Gaussian naïve Bayes (GNB) and support vector machine (SVM) techniques to classify eight petrofacies types, divided into two groups. The objective was to observe the capacity of some well-known models to classify petrofacies with a high-frequency vertical variation of diagenetic heterogeneities in an extreme scenario within a thin sedimentary interval. The GNB was less effective (F 1 score of 0.29), and the SVM achieved the best results in classifying the main facies patterns (F 1 = 0.47). However, the GNB performed better when the analysis was focused on distinguishing the two main groups of petrofacies. The results demonstrate that high-frequency facies variations present a challenge to the automatic identification of lithofacies, mainly due to local variations in horizontal heterogeneities (on the mm- to cm-scale) created by depositional and diagenetic processes, which impact the flow in porous media.