Identification of most important features based on a fuzzy ensemble technique: Evaluation on joint space narrowing progression in knee osteoarthritis patients

A semi-supervised multiview-MRI network for the detection of Knee Osteoarthritis

Knee OsteoArthritis (OA) is a prevalent chronic condition, affecting a significant proportion of the global population. Detecting knee OA is crucial as the degeneration of the knee joint is irreversible. In this paper, we introduce a semi-supervised multi-view framework and a 3D CNN model for detecting knee OA using 3D Magnetic Resonance Imaging (MRI) scans. We introduce a semi-supervised learning approach combining labeled and unlabeled data to improve the performance and generalizability of the proposed model. Experimental results show the efficacy of our proposed approach in detecting knee OA from 3D MRI scans using a large cohort of 4297 subjects. An ablation study was conducted to investigate the contributions of various components of the proposed model, providing insights into the optimal design of the model. Our results indicate the potential of the proposed approach to improve the accuracy and efficiency of OA diagnosis. The proposed framework reported an AUC of 93.20% for the detection of knee OA.

Diagnostic plasma small extracellular vesicles miRNA signatures for pancreatic cancer using machine learning methods

BACKGROUND

Identifying biomarkers may lead to easier detection and a better understanding of pathogenesis of pancreatic ductal adenocarcinoma (PDAC).

METHODS

Plasma small extracellular vesicles (sEV) from 106 participants, including 20 healthy controls (HC), 12 chronic pancreatitis (CP) patients, 12 benign pancreatic tumour (BPT) patients, and 58 PDAC patients, were profiled for microRNA (miRNA) sequencing. Three machine learning methods were applied to establish and evaluate the diagnostic model.

RESULTS

The plasma sEV miRNA diagnostic signature (d-signature) selected using the three machine learning methods could distinguish PDAC patients from non-PDAC individuals, HC, and benign pancreatic disease (BPD, CP plus BPT) both in training and validation cohort. Combining the d-signature with carbohydrate antigen 19-9 (CA19-9) performed better than with each model alone. Plasma sEV miR-664a-3p was selected by all methods and used to predict PDAC diagnosis with high accuracy combined with CA19-9. Plasma sEV miR-664a-3p was significantly positively associated with the presence of vascular invasion, lower surgery ratio, and poor differentiation. MiR-664a-3p was mainly distributed in the PDAC cancer stroma, including fibers and vessels, and was accompanied by VEGFA expression. Overexpression of miR-664a-3p could promote the epithelial-mesenchymal transition (EMT) and angiogenesis.

CONCLUSION

In conclusion, our study demonstrated the potential utility of the sEV-miRNA d-signature in the diagnosis of PDAC via machine learning methods. A novel sEV biomarker, miR-664a-3p, was identified for the diagnosis of PDAC. It can also potentially promote angiogenesis and metastasis, provide insight into PDAC pathogenesis, and reveal novel regulators of this disease.

Explainable Machine Learning Techniques to Predict Muscle Injuries in Professional Soccer Players through Biomechanical Analysis

There is a significant risk of injury in sports and intense competition due to the demanding physical and psychological requirements. Hamstring strain injuries (HSIs) are the most prevalent type of injury among professional soccer players and are the leading cause of missed days in the sport. These injuries stem from a combination of factors, making it challenging to pinpoint the most crucial risk factors and their interactions, let alone find effective prevention strategies. Recently, there has been growing recognition of the potential of tools provided by artificial intelligence (AI). However, current studies primarily concentrate on enhancing the performance of complex machine learning models, often overlooking their explanatory capabilities. Consequently, medical teams have difficulty interpreting these models and are hesitant to trust them fully. In light of this, there is an increasing need for advanced injury detection and prediction models that can aid doctors in diagnosing or detecting injuries earlier and with greater accuracy. Accordingly, this study aims to identify the biomarkers of muscle injuries in professional soccer players through biomechanical analysis, employing several ML algorithms such as decision tree (DT) methods, discriminant methods, logistic regression, naive Bayes, support vector machine (SVM), K-nearest neighbor (KNN), ensemble methods, boosted and bagged trees, artificial neural networks (ANNs), and XGBoost. In particular, XGBoost is also used to obtain the most important features. The findings highlight that the variables that most effectively differentiate the groups and could serve as reliable predictors for injury prevention are the maximum muscle strength of the hamstrings and the stiffness of the same muscle. With regard to the 35 techniques employed, a precision of up to 78% was achieved with XGBoost, indicating that by considering scientific evidence, suggestions based on various data sources, and expert opinions, it is possible to attain good precision, thus enhancing the reliability of the results for doctors and trainers. Furthermore, the obtained results strongly align with the existing literature, although further specific studies about this sport are necessary to draw a definitive conclusion.

Glycosyltransferase-related prognostic and diagnostic biomarkers of uterine corpus endometrial carcinoma

Uterine corpus endometrial carcinoma (UCEC) has a strong ability of invasion and metastasis, high recurrence rate, and poor survival. Glycosyltransferases are one of the most important enzymes that coordinate the glycosylation process, and abnormal modification of proteins by glycosyltransferases is closely related to the occurrence and development of cancer. However, there were fewer reports on glycosyltransferase related biomarkers in UCEC. In this paper, based on the UCEC transcriptome data published on The Cancer Genome Atlas (TCGA), we predicted the relationship between the expression of glycosyltransferase-related genes (GTs) and the diagnosis and prognosis of UCEC using bioinformatics methods. And validation of model genes by clinical samples. We used 4 methods: generalized linear model (GLM), random forest (RF), support vector machine (SVM) and extreme gradient boosting (XGB) to screen biomarkers with diagnostic significance, and the binary logistic regression was used to establish a diagnostic model for the 2-GTs (AUC = 0.979). And the diagnostic model was validated using a GEO external database (AUC = 0.978). Moreover, a prognostic model for the 6-GTs was developed using univariate, Lasso, and multivariate Cox regression analyses, and the model was made more stable by internal validation using the bootstrap. In addition, risk score is closely related to immune microenvironment (TME), immune infiltration, mutation, immunotherapy and chemotherapy. Overall, this study provides novel biomarkers for the diagnosis and prognosis of UCEC, and the models established by these biomarkers can also provide a good reference for individualized and precision medicine in UCEC.

Test-retest precision and longitudinal cartilage thickness loss in the IMI-APPROACH cohort

OBJECTIVE

To investigate the test-retest precision and to report the longitudinal change in cartilage thickness, the percentage of knees with progression and the predictive value of the machine-learning-estimated structural progression score (s-score) for cartilage thickness loss in the IMI-APPROACH cohort - an exploratory, 5-center, 2-year prospective follow-up cohort.

DESIGN

Quantitative cartilage morphology at baseline and at least one follow-up visit was available for 270 of the 297 IMI-APPROACH participants (78% females, age: 66.4 ± 7.1 years, body mass index (BMI): 28.1 ± 5.3 kg/m², 55% with radiographic knee osteoarthritis (OA)) from 1.5T or 3T MRI. Test-retest precision (root mean square coefficient of variation) was assessed from 34 participants. To define progressor knees, smallest detectable change (SDC) thresholds were computed from 11 participants with longitudinal test-retest scans. Binary logistic regression was used to evaluate the odds of progression in femorotibial cartilage thickness (threshold: -211 μm) for the quartile with the highest vs the quartile with the lowest s-scores.

RESULTS

The test-retest precision was 69 μm for the entire femorotibial joint. Over 24 months, mean cartilage thickness loss in the entire femorotibial joint reached -174 μm (95% CI: [-207, -141] μm, 32.7% with progression). The s-score was not associated with 24-month progression rates by MRI (OR: 1.30, 95% CI: [0.52, 3.28]).

CONCLUSION

IMI-APPROACH successfully enrolled participants with substantial cartilage thickness loss, although the machine-learning-estimated s-score was not observed to be predictive of cartilage thickness loss. IMI-APPROACH data will be used in subsequent analyses to evaluate the impact of clinical, imaging, biomechanical and biochemical biomarkers on cartilage thickness loss and to refine the machine-learning-based s-score.

CLINICALTRIALS

GOV IDENTIFICATION

NCT03883568.

Development and Evaluation of a Machine Learning Prediction Model for Small-for-Gestational-Age Births in Women Exposed to Radiation before Pregnancy

Exposure to radiation has been associated with increased risk of delivering small-for-gestational-age (SGA) newborns. There are no tools to predict SGA newborns in pregnant women exposed to radiation before pregnancy. Here, we aimed to develop an array of machine learning (ML) models to predict SGA newborns in women exposed to radiation before pregnancy. Patients’ data was obtained from the National Free Preconception Health Examination Project from 2010 to 2012. The data were randomly divided into a training dataset (n = 364) and a testing dataset (n = 91). Eight various ML models were compared for solving the binary classification of SGA prediction, followed by a post hoc explainability based on the SHAP model to identify and interpret the most important features that contribute to the prediction outcome. A total of 455 newborns were included, with the occurrence of 60 SGA births (13.2%). Overall, the model obtained by extreme gradient boosting (XGBoost) achieved the highest area under the receiver-operating-characteristic curve (AUC) in the testing set (0.844, 95% confidence interval (CI): 0.713–0.974). All models showed satisfied AUCs, except for the logistic regression model (AUC: 0.561, 95% CI: 0.355–0.768). After feature selection by recursive feature elimination (RFE), 15 features were included in the final prediction model using the XGBoost algorithm, with an AUC of 0.821 (95% CI: 0.650–0.993). ML algorithms can generate robust models to predict SGA newborns in pregnant women exposed to radiation before pregnancy, which may thus be used as a prediction tool for SGA newborns in high-risk pregnant women.

Smartphone Sensor-Based Human Locomotion Surveillance System Using Multilayer Perceptron

Applied sensing technology has made it possible for human beings to experience a revolutionary aspect of the science and technology world. Along with many other fields in which this technology is working wonders, human locomotion activity recognition, which finds applications in healthcare, smart homes, life-logging, and many other fields, is also proving to be a landmark. The purpose of this study is to develop a novel model that can robustly handle divergent data that are acquired remotely from various sensors and make an accurate classification of human locomotion activities. The biggest support for remotely sensed human locomotion activity recognition (RS-HLAR) is provided by modern smartphones. In this paper, we propose a robust model for an RS-HLAR that is trained and tested on remotely extracted data from smartphone-embedded sensors. Initially, the system denoises the input data and then performs windowing and segmentation. Then, this preprocessed data goes to the feature extraction module where Parseval’s energy, skewness, kurtosis, Shannon entropy, and statistical features from the time domain and the frequency domain are extracted from it. Advancing further, by using Luca-measure fuzzy entropy (LFE) and Lukasiewicz similarity measure (LS)–based feature selection, the system drops the least-informative features and shrinks the feature set by 25%. In the next step, the Yeo–Johnson power transform is applied, which is a maximum-likelihood-based feature optimization algorithm. The optimized feature set is then forwarded to the multilayer perceptron (MLP) classifier that performs the classification. MLP uses the cross-validation technique for training and testing to generate reliable results. We designed our system while experimenting on three benchmark datasets namely, MobiAct_v2.0, Real-World HAR, and Real-Life HAR. The proposed model outperforms the existing state-of-the-art models by scoring a mean accuracy of 84.49% on MobiAct_v2.0, 94.16% on Real-World HAR, and 95.89% on Real-Life HAR. Although our system can accurately differentiate among similar activities, excessive noise in data and complex activities have shown an inverse effect on its performance.

An Explainable Machine Learning Approach for COVID-19’s Impact on Mood States of Children and Adolescents during the First Lockdown in Greece

The global spread of COVID-19 led the World Health Organization to declare a pandemic on 11 March 2020. To decelerate this spread, countries have taken strict measures that have affected the lifestyles and economies. Various studies have focused on the identification of COVID-19’s impact on the mental health of children and adolescents via traditional statistical approaches. However, a machine learning methodology must be developed to explain the main factors that contribute to the changes in the mood state of children and adolescents during the first lockdown. Therefore, in this study an explainable machine learning pipeline is presented focusing on children and adolescents in Greece, where a strict lockdown was imposed. The target group consists of children and adolescents, recruited from children and adolescent mental health services, who present mental health problems diagnosed before the pandemic. The proposed methodology imposes: (i) data collection via questionnaires; (ii) a clustering process to identify the groups of subjects with amelioration, deterioration and stability to their mood state; (iii) a feature selection process to identify the most informative features that contribute to mood state prediction; (iv) a decision-making process based on an experimental evaluation among classifiers; (v) calibration of the best-performing model; and (vi) a post hoc interpretation of the features’ impact on the best-performing model. The results showed that a blend of heterogeneous features from almost all feature categories is necessary to increase our understanding regarding the effect of the COVID-19 pandemic on the mood state of children and adolescents.