Top-ranked Features Research Articles

Prediction of pre-eclampsia with machine learning approaches: Leveraging important information from routinely collected data

BackgroundGlobally, pre-eclampsia (PE) is a leading cause of maternal and perinatal morbidity and mortality. PE prediction using routinely collected data has the advantage of being widely applicable, particularly in low-resource settings. Early intervention for high-risk women might reduce PE incidence and related complications. We aimed to replicate our machine learning (ML) published work predicting another maternal condition (gestational diabetes) to (1) predict PE using routine health data, (2) identify the optimal ML model, and (3) compare it with logistic regression approach. MethodsData were from a large health service network with 48,250 singleton pregnancies between January 2016 and June 2021. Supervised ML models were employed. Maternal clinical and medical characteristics were the feature variables (predictors), and a 70/30 data split was used for training and testing the model. Predictive performance was assessed using area under the curve (AUC) and calibration plots. Shapley value analysis assessed the contribution of feature variables. ResultsThe random forest approach provided excellent discrimination with an AUC of 0.84 (95% CI: 0.82–0.86) and highest prediction accuracy (0.79); however, the calibration curve (slope of 1.21, 95% CI 1.13–1.30) was acceptable only for a threshold of 0.3 or less. The next best approach was extreme gradient boosting, which provided an AUC of 0.77 (95% CI: 0.76–0.79) and well-calibrated (slope of 0.93, 95% CI 0.85–1.01). Logistic regression provided good discrimination performance with an AUC of 0.75 (95% CI: 0.74–0.76) and perfect calibration. Nulliparous, pre-pregnancy body mass index, previous pregnancy with prior PE, maternal age, family history of hypertension, and pre-existing hypertension and diabetes were the top-ranked features in Shapley value analysis. ConclusionTwo ML models created the highest-performing prediction using routinely collected data to identify women at high risk of PE, with acceptable discrimination. However, to confirm this result and also examine model generalisability, external validation studies are needed in other settings, utilising standardised prognostic factors.

Development and external validation of a machine-learning based model to predict pre-sarcopenia in MASLD population: Results from NHANES 2017–2018

Introduction and ObjectivesWith rising prevalence of pre-sarcopenia in metabolic dysfunction-associated steatotic liver disease (MASLD), this study aimed to develop and validate machine learning-based model to identify pre-sarcopenia in MASLD population. Materials and MethodsA total of 571 MASLD subjects were screened from the National Health and Nutrition Examination Survey 2017–2018. This cohort was randomly divided into training set and internal testing set with a ratio of 7:3. Sixty-six MASLD subjects were collected from our institution as external validation set. Four binary classifiers, including Random Forest (RF), support vector machine, and extreme gradient boosting and logistic regression, were fitted to identify pre-sarcopenia. The best-performing model was further validated in external validation set. Model performance was assessed in terms of discrimination and calibration. Shapley Additive explanations were used for model interpretability. ResultsThe pre-sarcopenia rate was 17.51 % and 15.16 % in NHANES cohort and external validation set, respectively. RF outperformed other models with area under receiver operating characteristic curve (AUROC) of 0.819(95 %CI: 0.749, 0.889). When six top-ranking features were retained as per variable importance, including weight-adjusted waist, sex, race, creatinine, education and alkaline phosphatase, a final RF model reached an AUROC being 0.824(0.737, 0.910) and 0.732(95 %CI: 0.529, 0.936) in internal and external validation sets, respectively. The model robustness was proved in sensitivity analysis. The calibration curve and decision curve analysis confirmed a good calibration capacity and good clinical usage. ConclusionsThis study proposed a user-friendly model using explainable machine learning algorithm to predict pre-sarcopenia in MASLD population. A web-based tool was provided to screening pre-sarcopenia in community and hospitalization settings.

Histopathological correlations of CT-based radiomics imaging biomarkers in native kidney biopsy

BackgroundKidney biopsy is the standard of care for the diagnosis of various kidney diseases. In particular, chronic histopathologic lesions, such as interstitial fibrosis and tubular atrophy, can provide prognostic information regarding chronic kidney disease progression. In this study, we aimed to evaluate historadiological correlations between CT-based radiomic features and chronic histologic changes in native kidney biopsies and to construct and validate a radiomics-based prediction model for chronicity grade.MethodsWe included patients aged ≥ 18 years who underwent kidney biopsy and abdominal CT scan within a week before kidney biopsy. Left kidneys were three-dimensionally segmented using a deep learning model based on the 3D Swin UNEt Transformers architecture. We additionally defined isovolumic cortical regions of interest near the lower pole of the left kidneys. Shape, first-order, and high-order texture features were extracted after resampling and kernel normalization. Correlations and diagnostic metrics between extracted features and chronic histologic lesions were examined. A machine learning-based radiomic prediction model for moderate chronicity was developed and compared according to the segmented regions of interest (ROI).ResultsOverall, moderate correlations with statistical significance (P < 0.05) were found between chronic histopathologic grade and top-ranked radiomic features. Total parenchymal features were more strongly correlated than cortical ROI features, and texture features were more highly ranked. However, conventional imaging markers, including kidney length, were poorly correlated. Top-ranked individual radiomic features had areas under receiver operating characteristic curves (AUCs) of 0.65 to 0.74. Developed radiomics models for moderate-to-severe chronicity achieved AUCs of 0.89 (95% confidence interval [CI] 0.75–0.99) and 0.74 (95% CI 0.52–0.93) for total parenchymal and cortical ROI features, respectively.ConclusionSignificant historadiological correlations were identified between CT-based radiomic features and chronic histologic changes in native kidney biopsies. Our findings underscore the potential of CT-based radiomic features and their prediction model for the non-invasive assessment of kidney fibrosis.

Investigating Acoustic and Psycholinguistic Predictors of Cognitive Impairment in Older Adults: Modeling Study.

About one-third of older adults aged 65 years and older often have mild cognitive impairment or dementia. Acoustic and psycho-linguistic features derived from conversation may be of great diagnostic value because speech involves verbal memory and cognitive and neuromuscular processes. The relative decline in these processes, however, may not be linear and remains understudied. This study aims to establish associations between cognitive abilities and various attributes of speech and natural language production. To date, the majority of research has been cross-sectional, relying mostly on data from structured interactions and restricted to textual versus acoustic analyses. In a sample of 71 older (mean age 83.3, SD 7.0 years) community-dwelling adults who completed qualitative interviews and cognitive testing, we investigated the performance of both acoustic and psycholinguistic features associated with cognitive deficits contemporaneously and at a 1-2 years follow up (mean follow-up time 512.3, SD 84.5 days). Combined acoustic and psycholinguistic features achieved high performance (F1-scores 0.73-0.86) and sensitivity (up to 0.90) in estimating cognitive deficits across multiple domains. Performance remained high when acoustic and psycholinguistic features were used to predict follow-up cognitive performance. The psycholinguistic features that were most successful at classifying high cognitive impairment reflected vocabulary richness, the quantity of speech produced, and the fragmentation of speech, whereas the analogous top-ranked acoustic features reflected breathing and nonverbal vocalizations such as giggles or laughter. These results suggest that both acoustic and psycholinguistic features extracted from qualitative interviews may be reliable markers of cognitive deficits in late life.

Prediction of early recurrence of adult-type diffuse gliomas following radiotherapy using multi-modal magnetic resonance images.

Adult-type diffuse gliomas are among the central nervous system's most aggressive malignant primary neoplasms. Despite advancements in systemic therapies and technological improvements in radiation oncology treatment delivery, the survival outcome for these patients remains poor. Fast and accurate assessment of tumor response to oncologic treatments is crucial, as it can enable the early detection of recurrent or refractory gliomas, thereby allowing timely intervention with life-prolonging salvage therapies. Radiomics is a developing field with great potential to improve medical image interpretation. This study aims to apply a radiomics-based predictive model for classifying response to radiotherapy within the first 3 months post-treatment. Ninety-five patients were selected from the Burdenko Glioblastoma Progression Dataset. Tumor regions were delineated in the axial plane on contrast-enhanced T1(CE T1W) and T2 fluid-attenuated inversion recovery (T2_FLAIR) magnetic resonance imaging (MRI). Hand-crafted radiomic (HCR) features, including first- and second-order features, were extracted using PyRadiomics (3.7.6) in Python (3.10). Then, recursive feature elimination with a random forest (RF) classifier was applied for feature dimensionality reduction. RF and support vector machine (SVM) classifiers were built to predict treatment outcomes using the selected features. Leave-one-out cross-validation was employed to tune hyperparameters and evaluate the models. For each segmented target, 186 HCR features were extracted from the MRI sequence. Using the top-ranked radiomic features from a combination of CE T1W and T2_FLAIR, an optimized classifier achieved the highest averaged area under the curve (AUC) of 0.829±0.075 using the RF classifier. The HCR features of CE T1W produced the worst outcomes among all models (0.603±0.024 and 0.615±0.075 for RF and SVM classifiers, respectively). We developed and evaluated a radiomics-based predictive model for early tumor response to radiotherapy, demonstrating excellent performance supported by high AUC values. This model, harnessing radiomic features from multi-modal MRI, showed superior predictive performance compared to single-modal MRI approaches. These results underscore the potential of radiomics in clinical decision support for this disease process.

Predictive modelling of metabolic syndrome in Ghanaian diabetic patients: an ensemble machine learning approach

Abstract Objectives The burgeoning prevalence of cardiometabolic disorders, including type 2 diabetes mellitus (T2DM) and metabolic syndrome (MetS) within Africa is concerning. Machine learning (ML) techniques offer a unique opportunity to leverage data-driven insights and construct predictive models for MetS risk, thereby enhancing the implementation of personalised prevention strategies. In this work, we employed ML techniques to develop predictive models for pre-MetS and MetS among diabetic patients. Methods This multi-centre cross-sectional study comprised of 919 T2DM patients. Age, gender, novel anthropometric indices along with biochemical measures were analysed using BORUTA feature selection and an ensemble majority voting classification model, which included logistic regression, k-nearest neighbour, Gaussian Naive Bayes, Gradient boosting classification, and support vector machine. Results Distinct metabolic profiles and phenotype clusters were associated with MetS progression. The BORUTA algorithm identified 10 and 16 significant features for pre-MetS and MetS prediction, respectively. For pre-MetS, the top-ranked features were lipid accumulation product (LAP), triglyceride-glucose index adjusted for waist-to-height ratio (TyG-WHtR), coronary risk (CR), visceral adiposity index (VAI) and abdominal volume index (AVI). For MetS prediction, the most influential features were VAI, LAP, waist triglyceride index (WTI), Very low-density cholesterol (VLDLC) and TyG-WHtR. Majority voting ensemble classifier demonstrated superior performance in predicting pre-MetS (AUC = 0.79) and MetS (AUC = 0.87). Conclusion Identifying these risk factors reveals the complex interplay between visceral adiposity and metabolic dysregulation in African populations, enabling early detection and treatment. Ethical integration of ML algorithms in clinical decision-making can streamline identification of high-risk individuals, optimize resource allocation, and enable precise, tailored interventions.

Mapping agricultural tile drainage in the US Midwest using explainable random forest machine learning and satellite imagery

There has been an increase in tile drained area across the US Midwest and other regions worldwide due to agricultural expansion, intensification, and climate variability. Despite this growth, spatially explicit tile drainage maps remain scarce, which limits the accuracy of hydrologic modeling and implementation of nutrient reduction strategies. Here, we developed a machine-learning model to provide a Spatially Explicit Estimate of Tile Drainage (SEETileDrain) across the US Midwest in 2017 at a 30-m resolution. This model used 31 satellite-derived and environmental features after removing less important and highly correlated features. It was trained with 60,938 tile and non-tile ground truth points within the Google Earth Engine cloud-computing platform. We also used multiple feature importance metrics and Accumulated Local Effects to interpret the machine learning model. The results show that our model achieved good accuracy, with 96 % of points classified correctly and an F1 score of 0.90. When tile drainage area is aggregated to the county scale, it agreed well (r2 = 0.69) with the reported area from the Ag Census. We found that Land Surface Temperature (LST) along with climate- and soil-related features were the most important factors for classification. The top-ranked feature is the median summer nighttime LST, followed by median summer soil moisture percent. This study demonstrates the potential of applying satellite remote sensing to map spatially explicit agricultural tile drainage across large regions. The results should be useful for land use change monitoring and hydrologic and nutrient models, including those designed to achieve cost-effective agricultural water and nutrient management strategies. The algorithms developed here should also be applicable for other remote sensing mapping applications.

Multi-Label Feature Selection with Graph-based Ant Colony Optimization and Generalized Jaccard Similarity

Multi-label learning is a technique that assigns multiple class labels to each data instance. The growth of digital technology resulted in the development of high-dimensional applications in real-world scenarios. Feature selection approaches are extensively used to reduce dimensionality in multi-label learning. The main problems of the recommender system are determining the best match of futures among users but have not engaged with previously. This paper proposes a strategy for selecting features using ant colony optimization (ACO) that incorporates mutual knowledge. The proposed method utilizes ACO to rank features based on their significance. Thus, the search space is mapped to a graph, and each ant traverses the graph, selecting a predetermined number of features. A new information-theoretical metric is introduced to evaluate the features chosen by each ant. Jaccard generalized similarity coefficient is used to select the most suitable communication target for efficient learning outcomes. Mutual information is employed to assess each features relevance to a set of labels and identify redundant features. Pheromones are assigned values based on the effectiveness of the ants in solving the problem. Finally, the features are ranked based on their pheromone values, and the top-ranked features are selected as the final set of attributes. The proposed method is evaluated using real-world datasets. The findings demonstrate that the proposed method outperforms most of existing and advanced approaches. This paper presents a novel feature selection approach for multi-label learning based on ACO. The experimental results confirm the effectiveness of the proposed method compared to existing techniques.

Machine Learning Approach to Metabolomic Data Predicts Type 2 Diabetes Mellitus Incidence.

Metabolomics, with its wealth of data, offers a valuable avenue for enhancing predictions and decision-making in diabetes. This observational study aimed to leverage machine learning (ML) algorithms to predict the 4-year risk of developing type 2 diabetes mellitus (T2DM) using targeted quantitative metabolomics data. A cohort of 279 cardiovascular risk patients who underwent coronary angiography and who were initially free of T2DM according to American Diabetes Association (ADA) criteria was analyzed at baseline, including anthropometric data and targeted metabolomics, using liquid chromatography (LC)-mass spectroscopy (MS) and flow injection analysis (FIA)-MS, respectively. All patients were followed for four years. During this time, 11.5% of the patients developed T2DM. After data preprocessing, 362 variables were used for ML, employing the Caret package in R. The dataset was divided into training and test sets (75:25 ratio) and we used an oversampling approach to address the classifier imbalance of T2DM incidence. After an additional recursive feature elimination step, identifying a set of 77 variables that were the most valuable for model generation, a Support Vector Machine (SVM) model with a linear kernel demonstrated the most promising predictive capabilities, exhibiting an F1 score of 50%, a specificity of 93%, and balanced and unbalanced accuracies of 72% and 88%, respectively. The top-ranked features were bile acids, ceramides, amino acids, and hexoses, whereas anthropometric features such as age, sex, waist circumference, or body mass index had no contribution. In conclusion, ML analysis of metabolomics data is a promising tool for identifying individuals at risk of developing T2DM and opens avenues for personalized and early intervention strategies.

Feature selection using non-parametric correlations and important features on recursive feature elimination for stock price prediction

Stock price prediction using machine learning is a rapidly growing area of research. However, the large number of features that can be used can complicate the learning process. The feature selection method that can be used to overcome this problem is recursive feature elimination. Standard recursive feature elimination carries the risk of producing inaccurate algorithms because the top-ranked features are not necessarily the most important features. This research proposes a feature selection method that combines important features and nonparametric correlation in recursive feature elimination for stock price prediction. The data features used are technical indicators and stock price history. The recursive feature elimination method is modified with important features and nonparametric correlation features. The strategy for combining important features and non-parametric features is average weight, 25:75% weight, 75:25% weight, maximum weight, and minimum weight. The performance evaluation results show that the proposed feature selection method succeeded in obtaining small error values. The proposed method for predicting PT Bank Rakyat Indonesia Tbk (BBRI) stock prices obtains mean squared error, root mean square error, mean absolute error, and mean absolute percentage error evaluation values of 0.0000336, 0.00577, 0.00459, and 1.78%, respectively. This shows that recursive feature elimination with feature selection that combines important features and non-parametric correlation works better than the original recursive feature elimination at predicting stock prices.

Comparative analysis of machine learning algorithms for Diabetes Mellitus prediction

Type II Diabetes Mellitus (T2DM) has become an increasingly prevalent disease due to the rising number of the obese population. Even though this disorder is the leading cause of more severe health complications, studies have shown that T2DM is largely preventable if detected in an early phase. To improve current diagnosis and prognosis procedures, this study aims to examine three machine learning algorithmsK-Nearest Neighbor (KNN), Random Forest (RF), and Support Vector Classification (SVC)and their potential in making accurate predictions on the outcomes of the Pima Indians Diabetes Dataset (PIDD). After training and 5-fold cross validation, the results show that the RF algorithm has the highest accuracy at 75.25%, followed by SVC at 74.91% and KNN at 71.01%. In addition, feature importances were evaluated for all three models, yet we observed a drastic difference in the top-ranked features across different models, which implies that more training and larger datasets are necessary before realizing these computational approaches into practice. Nevertheless, the potential of these approaches highlighted in this study demonstrated that machine learning is a burgeoning strategy in clinical use and in solving real-world problems.

Abstract 2582: Intra- and peri-tumoral radiomic features are predictive of pathologic response to multiple neoadjuvant therapy regimen in rectal cancers via pre-treatment MRI

Abstract Introduction: Rectal cancers undergo neoadjuvant chemoradiation prior to resection, with increasing evidence that neoadjuvant chemotherapy or immunotherapy can boost clinical or pathologic response rates. However, baseline clinical tumor staging and carcinoembryonic antigen levels are limited for identifying which patients will most benefit from a multimodal neoadjuvant regimen, and which will not. We evaluated whether radiomics (computational features from radiographic images) from pretreatment MRI could identify which rectal cancer patients will achieve clinical or pathologic response to different neoadjuvant treatment regimens. Methods: MRI scans were retrospectively obtained from 3 different institutions for rectal cancer patients who had either undergone neoadjuvant chemoradiation or an experimental immunotherapy + chemoradiation. After pre-processing all MRI scans, tumor was manually delineated with an automated annotation of a 10 mm peritumor region. 916 radiomic features were extracted from two planes of acquisition (axial, coronal) and two ROIs (tumor, peritumor). 5 top-ranked radiomic features were identified from each region and plane via multi-stage mutual information feature selection to train a linear discriminant machine classifier to assign a predicted likelihood of achieving complete response to each patient. Model performance was validated via ROC analysis against response groups defined via (i) tumor regression grade indicating no tumor present on surgical pathology, and (ii) 1-year clinical complete response for patients who underwent non-operative management. Clinical variables (CEA, clinical stage) were statistically compared between response groups. Results: Training cohort comprised 64 patients who underwent chemoradiation alone (2 institutions, median age 61 yrs, M:F:MtF = 36:27:1). Validation cohort included 37 patients who underwent experimental TGFß inhibitor therapy prior to chemotherapy + chemoradiation (1 institution, median age 51 yrs, M:F = 25:12). Area under the ROC curve for multi-plane tumor+peritumor radiomic features (0.765 ± 0.054) was significantly higher for distinguishing complete response vs non/partial response compared to tumor (AUC = 0.635 ± 0.057, p &amp;lt; 0.0001) or peritumor (AUC = 0.612 ± 0.064, p &amp;lt; 0.0001). In holdout validation, performance was maintained with AUCs of 0.742 (tumor) 0.596 (peritumor), and 0.700 (all), respectively. Baseline CEA levels (p=0.3385) and cT stage (p=0.3386) were found to lack statistical significance as a predictor of response. Conclusion: Radiomic features from tumor and peritumor regions on pre-treatment MRI scans in rectal cancer patients may enable robust and accurate identification of pathologic or near-complete response after multiple neoadjuvant treatment regimen, while outperforming baseline clinical variables. Citation Format: Leo Bao, Thomas DeSilvio, Benjamin N. Parker, Mohsen Hariri, Prathyush Chirra, Murad Labbad, Stephen Tang, Gregory M. O'Connor, Emily Steinhagen, Jennifer L. Miller-Ocuin, Amit Gupta, Eric L. Marderstein, Aaron Carroll, Marka Crittenden, Michael J. Gough, Smitha Krishnamurthi, Kristina H. Young, Satish E. Viswanath. Intra- and peri-tumoral radiomic features are predictive of pathologic response to multiple neoadjuvant therapy regimen in rectal cancers via pre-treatment MRI [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 2582.

Pro-cycling team cyclist assignment for an upcoming race.

Professional bicycle racing is a popular sport that has attracted significant attention in recent years. The evolution and ubiquitous use of sensors allow cyclists to measure many metrics including power, heart rate, speed, cadence, and more in training and racing. In this paper we explore for the first time assignment of a subset of a team's cyclists to an upcoming race. We introduce RaceFit, a model that recommends, based on recent workouts and past assignments, cyclists for participation in an upcoming race. RaceFit consists of binary classifiers that are trained on pairs of a cyclist and a race, described by their relevant properties (features) such as the cyclist's demographic properties, as well as features extracted from his workout data from recent weeks; as well additional properties of the race, such as its distance, elevation gain, and more. Two main approaches are introduced in recommending on each stage in a race and aggregate from it to the race, or on the entire race. The model training is based on binary label which represent participation of cyclist in a race (or in a stage) in past events. We evaluated RaceFit rigorously on a large dataset of three pro-cycling teams' cyclists and race data achieving up to 80% precision@i. The first experiment had shown that using TP or STRAVA data performs the same. Then the best-performing parameters of the framework are using 5 weeks time window, imputation was effective, and the CatBoost classifier performed best. However, the model with any of the parameters performed always better than the baselines, in which the cyclists are assigned based on their popularity in historical data. Additionally, we present the top-ranked predictive features.

Decoding bilingualism from resting-state oscillatory network organization.

Can lifelong bilingualism be robustly decoded from intrinsic brain connectivity? Can we determine, using a spectrally resolved approach, the oscillatory networks that better predict dual-language experience? We recorded resting-state magnetoencephalographic activity in highly proficient Spanish-Basque bilinguals and Spanish monolinguals, calculated functional connectivity at canonical frequency bands, and derived topological network properties using graph analysis. These features were fed into a machine learning classifier to establish how robustly they discriminated between the groups. The model showed excellent classification (AUC: 0.91 ± 0.12) between individuals in each group. The key drivers of classification were network strength in beta (15-30Hz) and delta (2-4Hz) rhythms. Further characterization of these networks revealed the involvement of temporal, cingulate, and fronto-parietal hubs likely underpinning the language and default-mode networks (DMNs). Complementary evidence from a correlation analysis showed that the top-ranked features that better discriminated individuals during rest also explained interindividual variability in second language (L2) proficiency within bilinguals, further supporting the robustness of the machine learning model in capturing trait-like markers of bilingualism. Overall, our results show that long-term experience with an L2 can be "brain-read" at a fine-grained level from resting-state oscillatory network organization, highlighting its pervasive impact, particularly within language and DMN networks.

Diagnosis of multiple sclerosis using optical coherence tomography supported by explainable artificial intelligence.

Study of retinal structure based on optical coherence tomography (OCT) data can facilitate early diagnosis of relapsing-remitting multiple sclerosis (RRMS). Although artificial intelligence can provide highly reliable diagnoses, the results obtained must be explainable. The study included 79 recently diagnosed RRMS patients and 69 age matched healthy control subjects. Thickness (Avg) and inter-eye difference (Diff) features are obtained in 4 retinal layers using the posterior pole protocol. Each layer is divided into six analysis zones. The Support Vector Machine plus Recursive Feature Elimination with Leave-One-Out Cross Validation (SVM-RFE-LOOCV) approach is used to find the subset of features that reduces dimensionality and optimises the performance of the classifier. SVM-RFE-LOOCV was used to identify OCT features with greatest capacity for early diagnosis, determining the area of the papillomacular bundle to be the most influential. A correlation was observed between loss of layer thickness and increase in functional disability. There was also greater functional deterioration in patients with greater asymmetry between left and right eyes. The classifier based on the top-ranked features obtained sensitivity = 0.86 and specificity = 0.90. There was consistency between the features identified as relevant by the SVM-RFE-LOOCV approach and the retinotopic distribution of the retinal nerve fibres and the optic nerve head. This simple method contributes to implementation of an assisted diagnosis system and its accuracy exceeds that achieved with magnetic resonance imaging of the central nervous system, the current gold standard. This paper provides novel insights into RRMS affectation of the neuroretina.

Development and validation of machine learning-augmented algorithm for insulin sensitivity assessment in the community and primary care settings: a population-based study in China.

Insulin plays a central role in the regulation of energy and glucose homeostasis, and insulin resistance (IR) is widely considered as the "common soil" of a cluster of cardiometabolic disorders. Assessment of insulin sensitivity is very important in preventing and treating IR-related disease. This study aims to develop and validate machine learning (ML)-augmented algorithms for insulin sensitivity assessment in the community and primary care settings. We analyzed the data of 9358 participants over 40 years old who participated in the population-based cohort of the Hubei center of the REACTION study (Risk Evaluation of Cancers in Chinese Diabetic Individuals). Three non-ensemble algorithms and four ensemble algorithms were used to develop the models with 70 non-laboratory variables for the community and 87 (70 non-laboratory and 17 laboratory) variables for the primary care settings to screen the classifier of the state-of-the-art. The models with the best performance were further streamlined using top-ranked 5, 8, 10, 13, 15, and 20 features. Performances of these ML models were evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPR), and the Brier score. The Shapley additive explanation (SHAP) analysis was employed to evaluate the importance of features and interpret the models. The LightGBM models developed for the community (AUROC 0.794, AUPR 0.575, Brier score 0.145) and primary care settings (AUROC 0.867, AUPR 0.705, Brier score 0.119) achieved higher performance than the models constructed by the other six algorithms. The streamlined LightGBM models for the community (AUROC 0.791, AUPR 0.563, Brier score 0.146) and primary care settings (AUROC 0.863, AUPR 0.692, Brier score 0.124) using the 20 top-ranked variables also showed excellent performance. SHAP analysis indicated that the top-ranked features included fasting plasma glucose (FPG), waist circumference (WC), body mass index (BMI), triglycerides (TG), gender, waist-to-height ratio (WHtR), the number of daughters born, resting pulse rate (RPR), etc. The ML models using the LightGBM algorithm are efficient to predict insulin sensitivity in the community and primary care settings accurately and might potentially become an efficient and practical tool for insulin sensitivity assessment in these settings.

Multiple and Optimal Screening Subset: a method selecting global characteristic congeners for robust foodomics analysis.

Metabolomics and foodomics shed light on the molecular processes within living organisms and the complex food composition by leveraging sophisticated analytical techniques to systematically analyze the vast array of molecular features. The traditional feature-picking method often results in arbitrary selections of the model, feature ranking, and cut-off, which may lead to suboptimal results. Thus, a Multiple and Optimal Screening Subset (MOSS) approach was developed in this study to achieve a balance between a minimal number of predictors and high predictive accuracy during statistical model setup. The MOSS approach compares five commonly used models in the context of food matrix analysis, specifically bourbons. These models include Student's t-test, receiver operating characteristic curve, partial least squares-discriminant analysis (PLS-DA), random forests, and support vector machines. The approach employs cross-validation to identify promising subset feature candidates that contribute to food characteristic classification. It then determines the optimal subset size by comparing it to the corresponding top-ranked features. Finally, it selects the optimal feature subset by traversing all possible feature candidate combinations. By utilizing MOSS approach to analyze 1406 mass spectral features from a collection of 122 bourbon samples, we were able to generate a subset of features for bourbon age prediction with 88% accuracy. Additionally, MOSS increased the area under the curve performance of sweetness prediction to 0.898 with only four predictors compared with the top-ranked four features at 0.681 based on the PLS-DA model. Overall, we demonstrated that MOSS provides an efficient and effective approach for selecting optimal features compared with other frequently utilized methods.

Development and validation of an individualized and weighted Myeloma Prognostic Score System (MPSS) in patients with newly diagnosed multiple myeloma.

Current standard predictive models of disease risk do not adequately account for the heterogeneity of survival outcomes in patients with new-diagnosed multiple myeloma (NDMM). In this retrospective, multicohort study, we collected clinical and genetic data from 1792 NDMM patients and identified the prognostic impact of all features. Using the top-ranked predictive features, a weighted Myeloma Prognostic Score System (MPSS) risk model was formulated and validated to predict overall survival (OS). In the training cohort, elevated lactate dehydrogenase level (LDH), International Staging System (ISS) Stage III, thrombocytopenia, and cumulative high-risk cytogenetic aberration (HRA) numbers were found to have independent prognostic significance. Each risk factor was defined as its weighted value respectively according to their hazard ratio for OS (thrombocytopenia 2, elevated LDH 1, ISS III 2, one HRA 1, and ≥2 HRA 2, points). Patients were further stratified into four risk groups: MPSS I (22.5%, 0 points), II (17.6%, 1 points), III (38.6%, 2-3 points), and IV (21.3%, 4-7 points). MPSS risk stratification showed optimal discrimination, as well as calibration, of four risk groups with median OS of 91.0, 69.8, 45.0, and 28.0 months, for patients in MPSS I to IV groups (p < .001), respectively. Importantly, the MPSS model retained its prognostic value in the internal validation cohort and an independent external validation cohort, and exhibited significant risk distribution compared with conventional prognostic models (R-ISS, R2-ISS, and MASS). Utilization of the MPSS model in clinical practice could improve risk estimation in NDMM patients, thus prompting individualized treatment strategies.

Utilizing predictive machine-learning modelling unveils feature-based risk assessment system for hyperinflammatory patterns and infectious outcomes in polytrauma.

Earlier research has identified several potentially predictive features including biomarkers associated with trauma, which can be used to assess the risk for harmful outcomes of polytraumatized patients. These features encompass various aspects such as the nature and severity of the injury, accompanying health conditions, immune and inflammatory markers, and blood parameters linked to organ functioning, however their applicability is limited. Numerous indicators relevant to the patients` outcome are routinely gathered in the intensive care unit (ICU) and recorded in electronic medical records, rendering them suitable predictors for risk assessment of polytraumatized patients. 317 polytraumatized patients were included, and the influence of 29 clinical and biological features on the complication patterns for systemic inflammatory response syndrome (SIRS), pneumonia and sepsis were analyzed with a machine learning workflow including clustering, classification and explainability using SHapley Additive exPlanations (SHAP) values. The predictive ability of the analyzed features within three days after admission to the hospital were compared based on patient-specific outcomes using receiver-operating characteristics. A correlation and clustering analysis revealed that distinct patterns of injury and biomarker patterns were observed for the major complication classes. A k-means clustering suggested four different clusters based on the major complications SIRS, pneumonia and sepsis as well as a patient subgroup that developed no complications. For classification of the outcome groups with no complications, pneumonia and sepsis based on boosting ensemble classification, 90% were correctly classified as low-risk group (no complications). For the high-risk groups associated with development of pneumonia and sepsis, 80% of the patients were correctly identified. The explainability analysis with SHAP values identified the top-ranking features that had the largest impact on the development of adverse outcome patterns. For both investigated risk scenarios (infectious complications and long ICU stay) the most important features are SOFA score, Glasgow Coma Scale, lactate, GGT and hemoglobin blood concentration. The machine learning-based identification of prognostic feature patterns in patients with traumatic injuries may improve tailoring personalized treatment modalities to mitigate the adverse outcomes in high-risk patient clusters.

Addressing agricultural challenges: An identification of best feature selection technique for dragon fruit disease recognition

Dragon fruit is a prominent substance in global agriculture. Despite this, it is gaining popularity and is a viable solution in resource-poor, environmentally degraded areas because of its many health benefits. Nevertheless, many dragon fruit plantations have been impacted by the disease, reducing their yield, and the detection system is still conventional. Farmers’ lack of disease identification and management expertise diminished crop quality and products. As a result, little research was carried out to assist those specific farmers requiring adequate agricultural support. This research has proposed an autonomous agro-based system to recognize dragon diseases using in-depth analysis of feature selection techniques. After the collection of real-time images of the dragon, the images are preprocessed using various image-processing techniques. The two important features are retrieved after segmentation. The analysis of variance (ANOVA) and the least absolute shrinkage and selection operator (LASSO) are used as feature selection techniques to assess the feature rank based on the mutual score. To analyze the effectiveness of the machine learning algorithms that were used, six distinct machine learning classifiers were applied to the top-ranked feature sets, and their performance was measured using seven distinct performance evaluation metrics. AdaBoost and Random Forest classifiers for the LASSO feature ranking approach got the maximum accuracy, which is 96.29%, based on a comparison of classifiers based on the ANOVA and LASSO feature set. Despite this, we have optimized the computational resources of each classifier for the LASSO feature set.