BACKGROUND: Bronchopulmonary dysplasia-associated pulmonary hypertension (BPD-PH) remains a devastating clinical complication seriously affecting the therapeutic outcome of preterm infants. Hence, early prevention and timely diagnosis prior to pathological change is the key to reducing morbidity and improving prognosis. Our primary objective is to utilize machine learning techniques to build predictive models that could accurately identify BPD infants at risk of developing PH.
METHODS: The data utilized in this study were collected from neonatology departments of four tertiary-level hospitals in China. To address the issue of imbalanced data, oversampling algorithms synthetic minority over-sampling technique (SMOTE) was applied to improve the model.
RESULTS: Seven hundred sixty one clinical records were collected in our study. Following data pre-processing and feature selection, 5 of the 46 features were used to build models, including duration of invasive respiratory support (day), the severity of BPD, ventilator-associated pneumonia, pulmonary hemorrhage, and early-onset PH. Four machine learning models were applied to predictive learning, and after comprehensive selection a model was ultimately selected. The model achieved 93.8% sensitivity, 85.0% accuracy, and 0.933 AUC. A score of the logistic regression formula greater than 0 was identified as a warning sign of BPD-PH.
CONCLUSIONS: We comprehensively compared different machine learning models and ultimately obtained a good prognosis model which was sufficient to support pediatric clinicians to make early diagnosis and formulate a better treatment plan for pediatric patients with BPD-PH.

BACKGROUND: Genome-wide association studies have successfully identified genetic variants associated with human disease. Various statistical approaches based on penalized and machine learning methods have recently been proposed for disease prediction. In this study, we evaluated the performance of several such methods for predicting asthma using the Korean Chip (KORV1.1) from the Korean Genome and Epidemiology Study (KoGES).
RESULTS: First, single-nucleotide polymorphisms were selected via single-variant tests using logistic regression with the adjustment of several epidemiological factors. Next, we evaluated the following methods for disease prediction: ridge, least absolute shrinkage and selection operator, elastic net, smoothly clipped absolute deviation, support vector machine, random forest, boosting, bagging, naïve Bayes, and k-nearest neighbor. Finally, we compared their predictive performance based on the area under the curve of the receiver operating characteristic curves, precision, recall, F1-score, Cohen\'s Kappa, balanced accuracy, error rate, Matthews correlation coefficient, and area under the precision-recall curve. Additionally, three oversampling algorithms are used to deal with imbalance problems.
CONCLUSIONS: Our results show that penalized methods exhibit better predictive performance for asthma than that achieved via machine learning methods. On the other hand, in the oversampling study, randomforest and boosting methods overall showed better prediction performance than penalized methods.

Machine learning offers new solutions for predicting life-threatening, unpredictable amiodarone-induced thyroid dysfunction. Traditional regression approaches for adverse-effect prediction without time-series consideration of features have yielded suboptimal predictions. Machine learning algorithms with multiple data sets at different time points may generate better performance in predicting adverse effects.
We aimed to develop and validate machine learning models for forecasting individualized amiodarone-induced thyroid dysfunction risk and to optimize a machine learning-based risk stratification scheme with a resampling method and readjustment of the clinically derived decision thresholds.
This study developed machine learning models using multicenter, delinked electronic health records. It included patients receiving amiodarone from January 2013 to December 2017. The training set was composed of data from Taipei Medical University Hospital and Wan Fang Hospital, while data from Taipei Medical University Shuang Ho Hospital were used as the external test set. The study collected stationary features at baseline and dynamic features at the first, second, third, sixth, ninth, 12th, 15th, 18th, and 21st months after amiodarone initiation. We used 16 machine learning models, including extreme gradient boosting, adaptive boosting, k-nearest neighbor, and logistic regression models, along with an original resampling method and 3 other resampling methods, including oversampling with the borderline-synthesized minority oversampling technique, undersampling-edited nearest neighbor, and over- and undersampling hybrid methods. The model performance was compared based on accuracy; Precision, recall, F1-score, geometric mean, area under the curve of the receiver operating characteristic curve (AUROC), and the area under the precision-recall curve (AUPRC). Feature importance was determined by the best model. The decision threshold was readjusted to identify the best cutoff value and a Kaplan-Meier survival analysis was performed.
The training set contained 4075 patients from Taipei Medical University Hospital and Wan Fang Hospital, of whom 583 (14.3%) developed amiodarone-induced thyroid dysfunction, while the external test set included 2422 patients from Taipei Medical University Shuang Ho Hospital, of whom 275 (11.4%) developed amiodarone-induced thyroid dysfunction. The extreme gradient boosting oversampling machine learning model demonstrated the best predictive outcomes among all 16 models. The accuracy; Precision, recall, F1-score, G-mean, AUPRC, and AUROC were 0.923, 0.632, 0.756, 0.688, 0.845, 0.751, and 0.934, respectively. After readjusting the cutoff, the best value was 0.627, and the F1-score reached 0.699. The best threshold was able to classify 286 of 2422 patients (11.8%) as high-risk subjects, among which 275 were true-positive patients in the testing set. A shorter treatment duration; higher levels of thyroid-stimulating hormone and high-density lipoprotein cholesterol; and lower levels of free thyroxin, alkaline phosphatase, and low-density lipoprotein were the most important features.
Machine learning models combined with resampling methods can predict amiodarone-induced thyroid dysfunction and serve as a support tool for individualized risk prediction and clinical decision support.

Accelerometer data collected from wearable devices have recently been used to monitor physical activities (PAs) in daily life. While the intensity of PAs can be distinguished with a cut-off approach, it is important to discriminate different behaviors with similar accelerometry patterns to estimate energy expenditure. We aim to overcome the data imbalance problem that negatively affects machine learning-based PA classification by extracting well-defined features and applying undersampling and oversampling methods. We extracted various temporal, spectral, and nonlinear features from wrist-, hip-, and ankle-worn accelerometer data. Then, the influences of undersampilng and oversampling were compared using various ML and DL approaches. Among various ML and DL models, ensemble methods including random forest (RF) and adaptive boosting (AdaBoost) exhibited great performance in differentiating sedentary behavior (driving) and three walking types (walking on level ground, ascending stairs, and descending stairs) even in a cross-subject paradigm. The undersampling approach, which has a low computational cost, exhibited classification results unbiased to the majority class. In addition, we found that RF could automatically select relevant features for PA classification depending on the sensor location by examining the importance of each node in multiple decision trees (DTs). This study proposes that ensemble learning using well-defined feature sets combined with the undersampling approach is robust for imbalanced datasets in PA classification. This approach will be useful for PA classification in the free-living situation, where data imbalance problems between classes are common.

BACKGROUND: As a major health hazard, the incidence of coronary heart disease has been increasing year by year. Although coronary revascularization, mainly percutaneous coronary intervention, has played an important role in the treatment of coronary heart disease, major adverse cardiovascular events (MACE) such as recurrent or persistent angina pectoris after coronary revascularization remain a very difficult problem in clinical practice.
OBJECTIVE: Given the high probability of MACE after coronary revascularization, the aim of this study was to develop and validate a predictive model for MACE occurrence within 6 months based on machine learning algorithms.
METHODS: A retrospective study was performed including 1004 patients who had undergone coronary revascularization at The People\'s Hospital of Liaoning Province and Affiliated Hospital of Liaoning University of Traditional Chinese Medicine from June 2019 to December 2020. According to the characteristics of available data, an oversampling strategy was adopted for initial preprocessing. We then employed six machine learning algorithms, including decision tree, random forest, logistic regression, naïve Bayes, support vector machine, and extreme gradient boosting (XGBoost), to develop prediction models for MACE depending on clinical information and 6-month follow-up information. Among all samples, 70% were randomly selected for training and the remaining 30% were used for model validation. Model performance was assessed based on accuracy, precision, recall, F1-score, confusion matrix, area under the receiver operating characteristic (ROC) curve (AUC), and visualization of the ROC curve.
RESULTS: Univariate analysis showed that 21 patient characteristic variables were statistically significant (P<.05) between the groups without and with MACE. Coupled with these significant factors, among the six machine learning algorithms, XGBoost stood out with an accuracy of 0.7788, precision of 0.8058, recall of 0.7345, F1-score of 0.7685, and AUC of 0.8599. Further exploration of the models to identify factors affecting the occurrence of MACE revealed that use of anticoagulant drugs and course of the disease consistently ranked in the top two predictive factors in three developed models.
CONCLUSIONS: The machine learning risk models constructed in this study can achieve acceptable performance of MACE prediction, with XGBoost performing the best, providing a valuable reference for pointed intervention and clinical decision-making in MACE prevention.

BACKGROUND: COVID-19 has overwhelmed health systems worldwide. It is important to identify severe cases as early as possible, such that resources can be mobilized and treatment can be escalated.
OBJECTIVE: This study aims to develop a machine learning approach for automated severity assessment of COVID-19 based on clinical and imaging data.
METHODS: Clinical data-including demographics, signs, symptoms, comorbidities, and blood test results-and chest computed tomography scans of 346 patients from 2 hospitals in the Hubei Province, China, were used to develop machine learning models for automated severity assessment in diagnosed COVID-19 cases. We compared the predictive power of the clinical and imaging data from multiple machine learning models and further explored the use of four oversampling methods to address the imbalanced classification issue. Features with the highest predictive power were identified using the Shapley Additive Explanations framework.
RESULTS: Imaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with those reported previously. Although oversampling yielded mixed results, it achieved the best model performance in our study. Logistic regression models differentiating between mild and severe cases achieved the best performance for clinical features (area under the curve [AUC] 0.848; sensitivity 0.455; specificity 0.906), imaging features (AUC 0.926; sensitivity 0.818; specificity 0.901), and a combination of clinical and imaging features (AUC 0.950; sensitivity 0.764; specificity 0.919). The synthetic minority oversampling method further improved the performance of the model using combined features (AUC 0.960; sensitivity 0.845; specificity 0.929).
CONCLUSIONS: Clinical and imaging features can be used for automated severity assessment of COVID-19 and can potentially help triage patients with COVID-19 and prioritize care delivery to those at a higher risk of severe disease.

Driving daily through traffic congestion has been recognised as a major cause of stress. High levels of stress while driving negatively impact the driver\'s decisions which could potentially lead to accidents and other long-term health hazards. Accordingly, there is a great need to determine stress levels for drivers based on measuring and predicting the major causes (features or classes) that increase stress levels. In this paper, the problem of predicting automobile drivers\' stress levels, as experienced during actual driving, is investigated through the application of five different data mining algorithms, namely K-Nearest Neighbour (KNN), Decision Tree (J48), Random Forest (RF), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). An experiment was conducted on 14 drivers taking various routes in Amman - Jordan, with a wearable biomedical device attached to the driver to instantly collect physiological data. The collected data (dataset) is grouped into two different categories, namely \'Yes\' to signify the presence of stress and \'No\' to signify the absence of stress. In order to efficiently apply data mining algorithms to the data set, oversampling was used to avoid the negative effect of driver samples with a lesser class on the prediction of stress. The findings are evaluated in relation to stress prediction and accordingly contrasted alongside standard reference approaches that do not consider oversampling and/or feature selection using the Friedman rank test. The proposed approach, in combination with RF, was seen to surpass any others in terms of accuracy, AUC, specificity, and sensitivity. The accuracy, AUC, specificity, and sensitivity rates produced by RF utilising our proposed approach were 98.92%, 99.91%, 98.46%, and 99.36%, respectively.

Bar pattern phantoms are used to determine the maximum number of line-pairs per mm that an imaging system can resolve. In some cases, a numerical determination of the modulation transfer function (MTF) can also be carried out. However, calculations can only be performed in a relatively small number of frequencies because of the small number of bar groups in the phantom. In this work, a new bar pattern phantom has been simulated. This phantom consists of 66 pairs of lines of different periods and these periods vary exponentially with spatial position, like in a chirp wave. An oversampling procedure has been implemented to obtain the pre-sampled MTF of the system and the results obtained have been compared with those obtained with the edge method, recommended by the IEC. Monte Carlo simulations were carried out for three different levels of noise aimed at investigating the effect of noise on the uncertainties of the MTF determination. In addition, using the analytic expressions for the MTF calculation, statistical fluctuations of noise in phantom images were propagated to MTF values. Despite the smaller size of the chirp phantom, uncertainties in the chirp method are smaller than those of the edge method. For the edge image, the standard deviation of the MTF is proportional to the frequency f, whereas for the chirp method it is proportional to its square root. It is shown that applying an oversampling method allows the use of a single line pair per period without compromising the precision in noisy environments.

A clustering problem involving multivariate time series (MTS) requires the selection of similarity metrics. This paper shows the limitations of the PCA similarity factor (SPCA) as a single metric in nonlinear problems where there are differences in magnitude of the same process variables due to expected changes in operation conditions. A novel method for clustering MTS based on a combination between SPCA and the average-based Euclidean distance (AED) within a fuzzy clustering approach is proposed. Case studies involving either simulated or real industrial data collected from a large scale gas turbine are used to illustrate that the hybrid approach enhances the ability to recognize normal and fault operating patterns. This paper also proposes an oversampling procedure to create synthetic multivariate time series that can be useful in commonly occurring situations involving unbalanced data sets.

OBJECTIVE: Epidemiological research on lesbian, gay and bisexual populations raises concerns regarding self-selection and group sizes. The aim of this research was to present strategies used to overcome these challenges in a national population-based web survey of self-reported sexual orientation and living conditions-exemplified with a case of daily tobacco smoking.
METHODS: The sample was extracted from pre-established national web panels. Utilizing an oversampling strategy, we established a sample including 315 gay men, 217 bisexual men, 789 heterosexual men, 197 lesbian women, 405 bisexual women and 979 heterosexual women. We compared daily smoking, representing three levels of differentiation of sexual orientation for each gender.
RESULTS: The aggregation of all non-heterosexuals into one group yielded a higher odds ratio (OR) for non-heterosexuals being a daily smoker. The aggregation of lesbian and bisexual women indicated higher OR between this group and heterosexual women. The full differentiation yielded no differences between groups except for bisexual compared with heterosexual women.
CONCLUSIONS: The analyses demonstrated the advantage of differentiation of sexual orientation and gender, in this case bisexual women were the main source of group differences. We recommend an oversampling procedure, making it possible to avoid self-recruitment and to increase the transferability of findings.