Machine Learning Classification Models Research Articles

Data Transformation and Predictive Analytics of Cardiovascular Disease Using Machine and Ensemble Learning Techniques

About one person dies every minute from cardiovascular disease; consequently, it has almost surpassed war as the largest cause of death in the twenty-first century. In cardiology, early and accurate diagnosis of heart illness is a cornerstone of effective healthcare. Predictive analytics, which involves machine-learning algorithms, can be a great option for contributing towards the early detection of cardiovascular disease. This study evaluates the data preprocessing techniques involved in building machine learning models to predict cardiovascular disease and identify the features contributing to the cardio attack. A novel data transformation technique named the superlative boundary binning method was proposed to enhance machine learning and ensemble learning classification models for predicting cardiac illness based on independent physiological feature parameters. The results revealed that the ensemble learning classifier AdaBoost using the superlative boundary binning method has performed well with a classification accuracy of 93% when compared with the other data transformation and machine learning classifier models.

Comparing Scientific Machine Learning With Population Pharmacokinetic and Classical Machine Learning Approaches for Prediction of Drug Concentrations.

A variety of classical machine learning (ML) approaches has been developed over the past decade aiming to individualize drug dosages based on measured plasma concentrations. However, the interpretability of these models is challenging as they do not incorporate information on pharmacokinetic (PK) drug disposition. In this work we compare drug plasma concentraton predictions of well-known population PK (PopPK) modeling with classical machine learning models and a newly proposed scientific machine learning (MMPK-SciML) framework. MMPK-SciML allows to estimate PopPK parameters and their inter-individual variability (IIV) using multimodal covariate data of each patient and does not require assumptions about the underlying covariate relationships. A dataset of 541 fluorouracil (5FU) plasma concentrations as example for an intravenously administered drug and a dataset of 302 sunitinib and its active metabolite concentrations each as example for an orally administered drug were used for analysis. Whereas classical ML models were not able to describe the data sufficiently, MMPK-SciML allowed us to obtain accurate drug plasma concentration predictions for test patients. In case of 5FU, goodness-of-fit shows that the MMPK-SciML approach predicts drug plasma concentrations more accurately than PopPK models. For sunitinib, we observed slightly less accurate drug concentration predictions compared to PopPK. Overall, MMPK-SciML has shown promising results and should therefore be further investigated as a valuable alternative to classical PopPK modeling, provided there is sufficient training data.

Skin microbiome differences in pancreatic adenocarcinoma, other cancers, and healthy controls: a pilot study

IntroductionMany studies have reported the importance of the human microbiome in relationship to the overall health of its host. While recent studies have explored the microbiome’s role in various types of cancer compared to healthy patients, this pilot study is the first to investigate differences in the skin microbiome composition among pancreatic adenocarcinoma patients, individuals with other cancers, and cancer-free controls.MethodsThe study characterizes the skin microbiome’s potential associations with cancer status by analyzing skin swabs from the forehead and cheek of 58 participants using Next Generation Sequencing (NGS), differential abundance analysis, and machine learning techniques.ResultsThe study results indicated that the cancer group displayed a significantly higher mean alpha diversity compared to the control group. Additionally, a machine learning classification model achieved a mean F1 Score of 0.943 in predicting cancer status, indicating measurable differentiation in the skin microbiome between the study groups. This differentiation is supported by differential abundance methods, including ANCOM-BC and MaAsLin2.DiscussionThis pilot study suggests that skin microbiome profiling could serve as a non-invasive biomarker for cancer detection and monitoring, which warrants a larger, longitudinal study to validate these results.

Nutrient based classification of Phyllospora comosa biomasses using machine learning algorithms: Towards sustainable valorisation.

Sustainable seaweed value chains necessitate accurate biomass biochemical characterisation that leads to product development, geographical authentications and quality and sustainability assurances. Underutilised yet abundantly available seaweed species require a thorough investigation of biochemical characteristics prior to their valorisation. Abundantly available Australian seaweed species lack such comprehensive investigations within the global seaweed industrial value chains. Aiming to bridge this gap, this study characterises Phyllospora comosa thallus segments (blades, stipes, and vesicles) and unsegmented samples collected from separate locations in Victoria, Australia using high throughput characterisation techniques and machine learning classification models. Carbohydrate (64-68%), ash (27-31%), potassium (31.01 - 65.01mg/g), sodium (20.36 - 30.59mg/g), calcium (15.10 - 18.40mg/g), magnesium (7.71 - 11.81mg/g) and iodine (1.57 - 2.74mg/g) were the most abundant nutrients of the P. comosa biomasses, on a dry weight basis. Variations between segments showed that stipes were rich in carbohydrate, blades in glutamic acid, calcium, magnesium, and iodine and vesicles in potassium, suggesting differing valorisation paths. The "rpart" classification separated the collection sites based on cadmium: Bancoora < 84.9x10-6 mg/g (dw) ≤ Port Fairy with a 88% accuracy and segments, initially based on glutamic acid : blades ≥ 10.61mg/g (dw) or protein 45.25mg/g (dw) > stipes and vesicles and then by potassium : vesicles ≥ 44.88mg/g (dw) > stipes with a 100% accuracy. These highly accurate characterisation and classification methods, when applied to larger sample sizes will assist in the diversification and expansions of authentic and sustainable Australian seaweed value chains.

EEG microstate analysis and machine learning classification in patients with obsessive-compulsive disorder.

Microstate characterization of electroencephalogram (EEG) is a data-driven approach to explore the functional changes and interrelationships of multiple brain networks on a millisecond scale. This study aimed to explore the pathological changes of whole-brain functional networks in patients with obsessive-compulsive disorders (OCD) through microstate analysis and further to explore its potential value as an auxiliary diagnostic index. Forty-eight OCD patients (33 with more than moderate anxiety symptoms, 15 with mild anxiety symptoms) and 52 healthy controls (HCs) were recruited. Brain activities during eyes-closed period were collected using 64-channel electroencephalography. The differences in microstate features between OCD patients and HCs were compared, and the relationship between the microstate features and clinical symptoms were explored. Key microstate features were selected for machine learning modeling to achieve targeted classifications. The probability of transition from microstate B to C was significantly lower in OCD patients compared to HCs, and the obsessive thoughts factor scores were significantly correlated with the duration of microstate A, the occurrence of microstate B, and the transition probability from microstate C to B. The occurrence rate of microstate C was significantly negatively correlated with the Hamilton rating scale for anxiety (HAMA) scores. The AUC (Area Under the Receiver Operating Characteristic Curve) of the machine learning model in the test set classification between the above two groups and between OCD patients with more than moderate/mild anxiety symptoms could achieve 70.43% and 77.13%, respectively. EEG microstate characteristics were altered in OCD patients, and these changes were closely associated with obsessive thoughts and anxiety symptoms. Besides, the machine learning classification model based on microstate features has limited ability to identify OCD, and further optimization on this classification approach is still needed in the future.

P-1305. Identifying Animal Exposures from Clinical Documents Using Large Language Models

Abstract Background Information about animal exposure is crucial to understanding zoonotic infectious diseases; however, it is typically unavailable in structured clinical data. We evaluated the automated extraction of animal exposure mentions from clinical notes and summarized initial observations.Figure 1.Example snippets and labels assigned during annotation. While some mentions are Affirmed exposure, others be Denied or Negated. Other keywords may not be related to animals or exposure at all. Methods Clinical notes from the Department of Veterans Affairs (VA) data were extracted if associated with indicators for diseases which included CDC Nationally Notifiable Diseases (NND) as well as early cases of COVID-19 and mpox (i.e., positive labs, chart review, or diagnosis codes). These were then processed into text snippets containing animal keywords (e.g., cats, cattle, birds, etc.) and given to annotators who then assigned a category of: affirmed, denied/negated, or no exposure, including pets and farm animals. To augment the size of our training set, large language models (LLM) were also used to generate snippets for each category. A machine learning classification model was trained using a LLM and few-shot learning. After validation, this model was used to infer animal exposure mentions among infectious disease cases which were not part of annotation to examine the distribution of animals mentioned.Figure 2.Prevalence of Affirmed Animal Exposures by disease category among documents which had at least one animal keyword so that the model could perform a classification. Results The model’s accuracy on the held out test set of 115 (40%) text instances was 90% PPV and 91% sensitivity. Example snippets and annotations are shown in Figure 1. Following validation, the model was applied to 82,937 documents related to a selection of disease categories. The distribution of classified exposures among these documents was 2.7% affirmed, 0.1% denied/negated, and 97.2% no exposure. Figure 2 shows that prevalence of affirmed exposure varied by disease where non-zoonotic diseases such as COVID-19 were relatively lower. Some top animals terms in affirmed exposures are shown in Figure 3. Figure 4 is a distribution of top terms affirmed in tularemia cases.Figure 3.Top three animal terms associated with affirmed exposure according to inferences in the proposed model for each disease. A mention in text is simply an exposure and does not imply that the animal caused an infection. Since pets can be documented in notes along with other social history information, “dog” and “cat” may occur in any clinical note regardless of etiology. Conclusion Automated extraction of animal exposure is feasible with small, manually generated training sets and acceptable accuracy. Our approach summarized exposures documented among several categories of infectious disease. While this work was performed retrospectively, it has been used to enhance case-finding for the biosurveillance of zoonotic diseases.Figure 4.Percentages of animal terms associated with affirmed exposure according to inferences in the proposed model among tularemia cases. A mention in text is simply an exposure and does not imply that the animal caused an infection. Disclosures All Authors: No reported disclosures

Tunnel squeezing prediction based on partially missing dataset and optimized machine learning models

Accurate prediction of tunnel squeezing, one of the common geological hazards during tunnel construction, is of great significance for ensuring construction safety and reducing economic losses. To achieve precise prediction of tunnel squeezing, this study constructed six reliable machine learning (ML) classification models for this purpose, including Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), and K-Nearest Neighbors (KNN). The parameters of these 6 ML models were optimized using the Whale Optimization Algorithm (WOA) in conjunction with five-fold cross-validation. A total of 305 tunnel squeezing sample data were collected to train and test the models. KNN and Synthetic Minority Over-sampling Technique (SMOTE) methods were employed to handle the missing and imbalanced data sets. An input feature system for tunnel squeezing prediction was established, comprising tunnel burial depth (H), tunnel diameter (D), strength-to-stress ratio (SSR), and support stiffness (K). The XGBoost model optimized with WOA demonstrated the highest prediction accuracy of 0.9681. The SHAP method was utilized to interpret the XGBoost model, indicating that the contribution rank of the input features to tunnel squeezing prediction was SSR &amp;gt; K &amp;gt; D &amp;gt; H, with average SHAP values of 2.93, 1.49, 0.82, and 0.69, respectively. The XGBoost model was applied to predict tunnel squeezing in 10 sections of the Qinghai Huzhu Beishan Tunnel. The prediction results were highly consistent with the actual outcomes.

Data‐Driven Analysis of Ni‐Catalyzed Semihydrogenations of Alkynes

The semihydrogenation of alkynes to alkenes has historically been an essential technique in organic chemistry. In this context, researchers often employ transition metal complexes to achieve this conversion. Given the pronounced polarization of results, often yielding either very high or very low values, it remains challenging to discern the factors influencing reactivity and selectivity in many cases. In this work, we combine different sub‐disciplines of digital chemistry with experimental outcomes to rationalize the results of a model Ni‐catalyzed semihydrogenation that leads to E‐alkenes. First, we analyze the main factors behind successful reactions using a machine learning classification model. The descriptors are computed directly from the SMILES strings of the reacting alkynes using an automated protocol that relies on structural features, molecular mechanics, and semi‐empirical techniques. This workflow requires minimal human intervention and provides a fast yet useful approach. Next, we couple the same descriptors with activation barriers calculated with density functional theory, generating a regression model that explains reactivity based on the properties of the alkyne substrates. Overall, this study demonstrates the potential of using a combination of digital chemistry techniques to uncover reaction trends in Ni‐catalyzed semihydrogenations of alkynes, an area where human intuition proves limited in application.

Deterministic and Stochastic Machine Learning Classification Models: A Comparative Study Applied to Companies’ Capital Structures

Corporate financing decisions, particularly the choice between equity and debt, significantly impact a company’s financial health and value. This study predicts binary corporate debt levels (high or low) using supervised machine learning (ML) models and firms’ characteristics as predictive variables. Key features include companies’ size, tangibility, profitability, liquidity, growth opportunities, risk, and industry. Deterministic models, represented by logistic regression and multilevel logistic regression, and stochastic approaches that incorporate a certain degree of randomness or probability, including decision trees, random forests, Gradient Boosting, Support Vector Machines, and Artificial Neural Networks, were evaluated using usual metrics. The results indicate that decision trees, random forest, and XGBoost excelled in the training phase but showed higher overfitting when evaluated in the test sample. Deterministic models, in contrast, were less prone to overfitting. Notably, all models delivered statistically similar results in the test sample, emphasizing the need to balance performance, simplicity, and interpretability. These findings provide actionable insights for managers to benchmark their company’s debt level and improve financing strategies. Furthermore, this study contributes to ML applications in corporate finance by comparing deterministic and stochastic models in predicting capital structure, offering a robust tool to enhance managerial decision-making and optimize financial strategies.

Spray Quality Assessment on Water-Sensitive Paper Comparing AI and Classical Computer Vision Methods

Precision agriculture seeks to optimize crop yields while minimizing resource use. A key challenge is achieving uniform pesticide spraying to prevent crop damage and environmental contamination. Water-sensitive paper (WSP) is a common tool used for assessing spray quality, as it visually registers droplet impacts through color change. This work introduces a smartphone-based solution for capturing WSP images within vegetation, offering a tool for farmers to assess spray quality in real-world conditions. To achieve this, two approaches were explored: classical computer vision techniques and machine learning (ML) models (YOLOv8, Mask-RCNN, and Cellpose). Addressing the challenges of limited real-world data and the complexity of manual annotation, a programmatically generated synthetic dataset was employed to enable sim-to-real transfer learning. For the task of WSP segmentation within vegetation, YOLOv8 achieved an average Intersection over Union of 97.76%. In the droplet detection task, which involves identifying individual droplets on WSP, Cellpose achieved the highest precision of 96.18%, in the presence of overlapping droplets. While classical computer vision techniques provided a reliable baseline, they struggled with complex cases. Additionally, ML models, particularly Cellpose, demonstrated accurate droplet detection even without fine-tuning.

Predicting Drug Resistance in Mycobacterium tuberculosis: A Machine Learning Approach to Genomic Mutation Analysis

Background/Objectives: Tuberculosis (TB) is one of the leading causes of death by infectious disease in the world, caused by the bacterium Mycobacterium tuberculosis (M. tuberculosis). First- and second-line drugs are used to treat active tuberculosis. However, drug resistance presents a critical challenge in the global fight against tuberculosis. Materials and Methods: Drug resistance diagnosis is typically performed through drug susceptibility testing, either via culture-based methods or molecular rapid tests. In recent years, studies have utilized whole-genome sequencing of M. tuberculosis isolates combined with machine learning techniques to predict drug resistance. In this study, we evaluated four machine learning classification models: Extreme Gradient Boosting Classifier (XGBC), Logistic Gradient Boosting Classifier (LGBC), Gradient Boosting Classifier (GBC), and an Artificial Neural Network (ANN). These models were trained using a Variant Call Format (VCF) file preprocessed by the CRyPTIC consortium. We employed three datasets: the original dataset, a dataset reduced through principal component analysis, and a dataset that prioritized the most important features identified by the XGBC model. Results: The four models were utilized on the principal component analysis dataset, while the XGBC model was additionally implemented with an arbitrarily reduced dataset focusing on the most significant mutations identified during model training. All models were trained and tested across these datasets, and their performances were compared. The XGBC model trained on the original dataset outperformed the others, achieving sensitivity values of 0.97, 0.90, and 0.94, specificity values of 0.97, 0.99, and 0.96, and F1-scores of 0.93, 0.94, and 0.92 for ethambutol, isoniazid, and rifampicin, respectively. Discussion: This study highlights the effectiveness of a binary representation of mutations (indicating their presence or absence) as a robust approach for training XGBC models that accurately classify resistance and susceptibility to ethambutol, isoniazid, and rifampicin in M. tuberculosis. Conclusion: The XGBC model trained on the original dataset demonstrated superior performance compared to the other models, indicating its potential for improving drug resistance prediction in TB. This approach could be further explored for clinical applications in the fight against drug-resistant tuberculosis.

Monitoring Moso bamboo (Phyllostachys pubescens) forests damage caused by Pantana phyllostachysae Chao considering phenological differences between on-year and off-year using UAV hyperspectral images

ABSTRACT The on-year and off-year phenomenon is a distinctive phenological characteristic of Moso bamboo, reflecting variations in nutrient dynamics and endogenous hormonal rhythms during the transition from bamboo shoot to the culm. This phenomenon also influences pest resistance between the on-year and off-year cycles of Moso bamboo. Pantana phyllostachysae Chao is a leaf-feeding pest that affects Moso bamboo. However, monitoring P. phyllostachysae damage using remote sensing data is challenging because the off-year Moso bamboo has physiological characteristics similar to on-year Moso bamboo infested with P. phyllostachysae. This study utilizes the Recursive Feature Elimination (RFE) algorithm to investigate hyperspectral remote sensing characteristics of P. phyllostachysae in Moso bamboo forests. We analyzed the impact of on-year and off-year phenological characteristics on the accuracy of hazard extraction and developed detection models for P. phyllostachysae hazard levels in on-year and off-year Moso bamboo using Support Vector Machine (SVM), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and one-dimensional Convolutional Neural Network (1D-CNN). The results demonstrate that classical machine learning and deep learning models can effectively detect P. phyllostachysae damage, with the 1D-CNN algorithm achieving the best performance. Analyzing the impact of the phenological differences between on-year and off-year Moso bamboo on pest identification accuracy revealed that when four machine learning models accounted for these phenological characteristics, their accuracy in identifying pests was significantly higher than that of a model which did not take into account the bamboo phenology. This finding highlights that considering the phenological characteristics of on-year and off-year Moso bamboo can substantially improve the detection accuracy of UAV hyperspectral remote sensing in monitoring P. phyllostachysae damage. This provides more accurate technical support for the health management and resource protection of bamboo forests and offers a scientific basis for maximizing the ecological and economic benefits of bamboo forests.

Machine learning-based assessment of morphometric abnormalities distinguishes bipolar disorder and major depressive disorder.

Bipolar disorder (BD) and major depressive disorder (MDD) have overlapping clinical presentations which may make it difficult for clinicians to distinguish them potentially resulting in misdiagnosis. This study combined structural MRI and machine learning techniques to determine whether regional morphological differences could distinguish patients with BD and MDD. A total of 123 participants, including BD (n = 31), MDD (n = 48), and healthy controls (HC, n = 44), underwent high-resolution 3D T1-weighted imaging. Cortical thickness, surface area, and subcortical volumes were measured using FreeSurfer software. Common and classic machine learning models were utilized to identify distinct morphometric alterations between BD and MDD. Significant morphological differences were observed in both common and distinct brain regions between BD, MDD, and HC. Specifically, abnormalities in the amygdala, thalamus, medial orbitofrontal cortex and fusiform were observed in both BD and MDD compared with HC. Relative to HC, unique differences in BD were identified in the lateral occipital and inferior/middle temporal regions, whereas MDD exhibited differences in nucleus accumbens and middle temporal regions. BD exhibited larger surface area in right middle temporal gyrus and greater right nucleus accumbens volume compared to MDD. The integration of two-stage models, including deep neural network (DNN) and support vector machine (SVM), achieved an accuracy rate of 91.2% in discriminating individuals with BD from MDD. These findings demonstrate that structural MRI combined with machine learning techniques can accurately discriminate individuals with BD from MDD, and provide a foundation supporting the potential of this approach to improve diagnostic accuracy.

Integrating C-H Information to Improve Machine Learning Classification Models for Microplastic Identification from Raman Spectra.

Research has shown microplastic particles to be pervasive pollutants in the natural environment, but labor-intensive sample preparation, data acquisition, and analysis protocols continue to be necessary to navigate their diverse chemistry. Machine learning (ML) classification models have shown promise for identifying microplastics from their Raman spectra, but all attempts to date have focused on the lower energy "fingerprint" region of the spectrum. We explore strategies to improve ML classification models based on the k-nearest-neighbor algorithm by including other regions of the Raman spectra. The information content inherent in C-H bonds, which occur in the higher frequency region of 2500-3600 cm-1, is found to be particularly powerful in improving classification model performance. Variations in the relative intensity of peaks arising from C-H vibrations improve identification capabilities for plastics that the fingerprint region alone struggles with, such as resolving acrylonitrile butadiene styrene from polystyrene and identifying poly(vinyl chloride), polyurethane, and polyoxymethylene. Testing of strategies to both acquire and analyze data across the two regions is explored for their efficacy and their compatibility with real-world sampling restrictions. We find that localized normalization of spectra, independently acquired in the two regions, provides the most direct and effective route to improving the ML classification performance.

Enhancing supply chain resilience through supervised machine learning: supplier performance analysis and risk profiling for a multi-class classification problem

PurposeThis paper explores the application of supervised machine learning (ML) classification models to address supplier performance analysis and risk profiling as a multi-class classification problem. The research highlights that current applications of machine learning in supplier selection primarily focus on binary classification problems, underscoring a significant gap in the literature.Design/methodology/approachThis research paper opts for a structured approach to solve supplier selection and risk profiling using supervised machine learning multi-class classification models and prediction probabilities. The study involved a synthetic data set of 1,600 historical data points, creating a supplier selection framework that simulates current supply chain (SC) performance. The “Supplier Analysis and Selection ML Module” guided supplier selection recommendations based on ML analysis. Real-world variability is introduced through random seeds, impacting actual delivery dates, quantity delivered and quality performance. Supervised ML models, with hyperparameter tuning, enable multi-class classification of suppliers, considering past delivery performance and risk calculations.FindingsThe study demonstrates the effectiveness of the supervised ML-based approach in ensuring consistent supplier selection across multi-class classification problems. Beyond evaluating past delivery performance, it introduces a new dimension by predicting and assessing supplier risks through ML-generated prediction probabilities. This can enhance overall SC visibility and help organizations optimize strategies associated with risk mitigation, inventory management and customer service.Research limitations/implicationsThe findings highlight the adaptability of ML-based methodologies in dynamic SC environments, providing a proactive means to identify and manage risks. These insights are vital for organizations aiming to bolster SC resilience, particularly amid uncertainties.Practical implicationsThe practical implications of this study are significant for both commercial and humanitarian supply chain management (SCM). For commercial applications, the ML-based methodology allows businesses to make more informed supplier selection decisions, reducing risks and improving operational efficiency. In disaster and humanitarian SC contexts, the use of ML can improve preparedness and resource allocation, ensuring that critical supplies reach affected areas promptly.Social implicationsThe study’s implications extend to disaster and humanitarian SCM, where timely and efficient delivery is critical for saving lives and alleviating suffering. ML tools can improve preparedness, resource allocation and coordination in these contexts, enhancing the resilience and responsiveness of humanitarian supply chains.Originality/valueUnlike conventional methods focused on quality, cost and delivery performance aspects, the current study introduces supervised ML to identify and assess supplier risks through prediction probabilities for multi-class classification problems (delivery performance as late, on-time and ahead), offering a refined understanding of supplier selection in dynamic SC environments.

Process capability analysis of additive manufacturing process: a machine learning−based predictive model

Purpose Predicting dimensional and geometrical errors in 3D printing parts during the design stage can significantly enhance the product’s quality. This study aims to predict the form deviation and process capability in additive manufacturing (AM) specimens considering layer thickness, laser power and scan speed parameters in the laser powder bed fusion (LPBF) method. Various machine learning (ML) techniques are implemented to estimate the form deviation and process capability with the highest accuracy in 3D-printed cylindrical parts as a case study. Design/methodology/approach The workflow started by simulating the LPBF AM process using a finite element modeling approach. Then, different ML algorithms like artificial neural networks are used to predict the form deviation. The process capability value is forecasted using some classification ML models and process capability indices (PCIs) for cylindrical parts. Finally, concentricity tolerance classification is performed for cylindrical parts, which can ensure quality control issues in the production stage. Findings Results present an accuracy of about 93% for predicting form deviations and 95% accuracy for predicting PCI C_pm in PCI classification based on random forest model as an ML algorithm. Originality/value The noteworthy point of the research is accessing the form deviation due to AM and process capability evaluation in the AM process before the production stage, which has not been studied before based on the author’s knowledge. So that the product quality is evaluated based on the shape deviation and its tolerances in the AM process digital chain.

Identification of IGFBP3 and LGALS1 as potential secreted biomarkers for clear cell renal cell carcinoma based on bioinformatics analysis and machine learning.

Clear cell renal cell carcinoma (ccRCC) is the most common subtype of renal cell carcinoma (RCC). Due to the lack of symptoms until advanced stages, early diagnosis of ccRCC is challenging. Therefore, the identification of novel secreted biomarkers for the early detection of ccRCC is urgently needed. This study aimed to identify novel secreted biomarkers for diagnosing ccRCC using bioinformatics and machine learning techniques based on transcriptomics data. Differentially expressed genes (DEGs) in ccRCC compared to normal kidney tissues were identified using 3 transcriptomics datasets (GSE53757, GSE40435 and GSE11151) from the Gene Expression Omnibus (GEO). Potential secreted biomarkers were examined within these common DEGs using a list of human secretome proteins from The Human Protein Atlas. The recursive feature elimination (RFE) technique was used to determine the optimal number of features for building classification machine learning models. The expression levels and clinical associations of candidate biomarkers identified with RFE were validated using transcriptomics data from The Cancer Genome Atlas (TCGA). Classification models were then developed based on the expression levels of these candidate biomarkers. The performance of the models was evaluated based on accuracy, evaluation metrics, confusion matrices, and ROC-AUC (receiver operating characteristic-area under the ROC curve) curves. We identified 44 DEGs that encode potential secreted proteins from 274 common DEGs found across all datasets. Among these, insulin-like growth factor binding protein 3 (IGFBP3) and lectin, galactoside-binding, soluble, 1 (LGALS1) were selected for further analysis using the RFE technique. Both IGFBP3 and LGALS1 showed significant upregulation in ccRCC tissues compared to normal tissues in the GEO and TCGA datasets. The results of the survival analysis indicated that patients with higher expression levels of these genes exhibited shorter overall and disease-free survival times (OS and DFS). Decision tree and random forest models based on IGFBP3 and LGALS1 levels achieved an accuracy of 98.04% and an AUC of 0.98. This study identified IGFBP3 and LGALS1 as promising novel secreted biomarkers for ccRCC diagnosis.

Establishment and validation of predictive model of ARDS in critically ill patients

BackgroundAcute respiratory distress syndrome (ARDS) is a prevalent complication among critically ill patients, constituting around 10% of intensive care unit (ICU) admissions and mortality rates ranging from 35 to 46%. Hence, early recognition and prediction of ARDS are crucial for the timely administration of targeted treatment. However, ARDS is frequently underdiagnosed or delayed, and its heterogeneity diminishes the clinical utility of ARDS biomarkers. This study aimed to observe the incidence of ARDS among high-risk patients and develop and validate an ARDS prediction model using machine learning (ML) techniques based on clinical parameters.MethodsThis prospective cohort study in China was conducted on critically ill patients to derivate and validate the prediction model. The derivation cohort, consisting of 400 patients admitted to the ICU of the Peking University Third Hospital(PUTH) between December 2020 and August 2023, was separated for training and internal validation, and an external data set of 160 patients at the FU YANG People's Hospital from August 2022 to August 2023 was employed for external validation. Least absolute shrinkage and selection operator (LASSO) and multivariate logistic regression were used to screen predictor variables. Multiple ML classification models were integrated to analyze and identify the best models. Several evaluation indexes were used to compare the model performance, including the area under the receiver-operating-characteristic curve (AUC) and decision curve analysis (DCA). SHapley Additive ex Planations (SHAP) is used to interpret ML models.Results400 critically ill patients were included in the analysis, with 117 developing ARDS during follow-up. The final model included gender, Lung Injury Prediction Score (LIPS), Hepatic Disease, Shock, and combined Lung Contusion. Based on the AUC and DCA in the validation group, the logistic model demonstrated excellent performance, achieving an AUC of 0.836 (95% CI: 0.762–0.910). For external validation, comprising 160 patients, 44 of whom developed ARDS, the AUC was 0.799 (95% CI: 0.723–0.875), significantly outperforming the LIPS score alone.ConclusionCombining the LIPS score with other clinical parameters in a logistic regression model provides a more accurate, clinically applicable, and user-friendly ARDS prediction tool than the LIPS score alone.

Opportunities and Challenges for Clinical Practice in Detecting Depression Using EEG and Machine Learning.

Major depressive disorder (MDD) is associated with substantial morbidity and mortality, yet its diagnosis and treatment rates remain low due to its diverse and often overlapping clinical manifestations. In this context, electroencephalography (EEG) has gained attention as a potential objective tool for diagnosing depression. This study aimed to evaluate the effectiveness of EEG in identifying MDD by analyzing 140 EEG recordings from patients diagnosed with depression and healthy volunteers. Using various machine learning (ML) classification models, we achieved up to 80% accuracy in distinguishing individuals with MDD from healthy controls. Despite its promise, this approach has limitations. The variability in the clinical and biological presentations of depression, as well as patient-specific confounding factors, must be carefully considered when integrating ML technologies into clinical practice. Nevertheless, our findings suggest that an EEG-based ML model holds potential as a diagnostic aid for MDD, paving the way for further refinement and clinical application.

Distinct clinical phenotypes in gastric pathologies: a cluster analysis of demographic and biomarker profiles in a diverse patient population.

Understanding the heterogeneity of a population at risk is an important step in the early detection of gastric cancer. We aimed to cluster demographic, hematological, and biochemical markers of gastric cancer in a heterogeneous sample of patients. Data of 695 adult patients (50.0% women) who were diagnosed with histologically confirmed gastric cancer, benign gastric disease, or identified as healthy individuals (December 2018 to August 2019, Hangzhou, China) were analyzed. We conducted hierarchical clustering using a factorial analysis of mixed data. To assess the clustering scheme, we also developed a machine-learning classification model using the Extreme Gradient Boosting algorithm and subsequently ranked the variables for differentiating patient phenotypes. Three clusters were identified using patient characteristics. The classification model showed high performance (multi-class AUC = 0.921) for recognizing the clusters. The top five important variables in differentiating the clusters were sex, hemoglobin, albumin, creatinine, and high-density lipoprotein (all ANOVA P <0.001) in decreasing order of importance. The prevalence of gastric cancer in clusters I, II, and III was 95.8%, 53.8%, and 34%, respectively [χ2(2) = 164.050, P <0.001]. Cluster I (N = 167) predominantly had an inflammatory profile, Cluster II (N = 240) showed metabolic disturbances, and Cluster III (N = 288) presented a relatively favorable metabolic and inflammatory profile. There were distinct clinical phenotypes in the population, each with varying prevalence of gastric cancer. A combination of routine clinical data outperformed carbohydrate or carcinoembryonic antigens in capturing the heterogeneity of the population regarding gastric pathologies.