Tree-based Pipeline Optimization Tool Research Articles

Optimized machine learning models for predicting crown convergence of plateau mountain tunnels

The precise prediction of tunnel convergence holds significant importance in ensuring the safety and efficiency of tunnel construction. This study involves the construction of seven machine learning (ML) models that are deemed reliable for predicting crown convergence (CC) of plateau mountain tunnels. These models include K-nearest neighbour (KNN), support vector regression (SVR), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and automated machine learning model (Auto-ML). The Bayesian optimization (BO) technique and the Tree-based pipeline optimization tool (TPOT) were employed to optimize the hyperparameters of non-automated machine learning models and the automated machine learning model, separately. A total of 2,734 samples of crown convergence monitoring data were collected for training and testing the models. The evaluation metrics employed to assess the performance of the models’ predictions included the determination coefficient (R2), mean absolute percentage error (MAPE), mean absolute error (MAE), and root mean square error (RMSE). The XGBoost model demonstrated the best prediction performance with the R2, MAPE, MAE, and RMSE of 0.9887, 0.1271, 0.7759, and 1.1845 on test set. The XGBoost, CatBoost, and Auto-ML models were utilized to predict the crown convergence monitoring curves of four sections of Huzhubeishan Tunnel in Qinghai Province, China. Notably, the predicted curves exhibited a significant level of concordance with the actual monitoring curves. The results of Shapley Additive Explanations (SHAP) suggested that time, tunnel depth ratio and groundwater table were more important than other input variables. The XGBoost model showed the best robustness of prediction performance across varying dataset sizes for seven distinct machine learning models.

Diffusion-weighted imaging-based radiomics model using automatic machine learning to differentiate cerebral cystic metastases from brain abscesses

ObjectivesTo develop a radiomics model based on diffusion-weighted imaging (DWI) utilizing automated machine learning method to differentiate cerebral cystic metastases from brain abscesses.Materials and methodsA total of 186 patients with cerebral cystic metastases (n = 98) and brain abscesses (n = 88) from two clinical institutions were retrospectively included. The datasets (129 from institution A) were randomly portioned into separate 75% training and 25% internal testing sets. Radiomics features were extracted from DWI images using two subregions of the lesion (cystic core and solid wall). A thorough image preprocessing method was applied to DWI images to ensure the robustness of radiomics features before feature extraction. Then the Tree-based Pipeline Optimization Tool (TPOT) was utilized to search for the best optimized machine learning pipeline, using a fivefold cross-validation in the training set. The external test set (57 from institution B) was used to evaluate the model’s performance.ResultsSeven distinct TPOT models were optimized to distinguish between cerebral cystic metastases and abscesses either based on different features combination or using wavelet transform. The optimal model demonstrated an AUC of 1.00, an accuracy of 0.97, sensitivity of 1.00, and specificity of 0.93 in the internal test set, based on the combination of cystic core and solid wall radiomics signature using wavelet transform. In the external test set, this model reached 1.00 AUC, 0.96 accuracy, 1.00 sensitivity, and 0.93 specificity.ConclusionThe DWI-based radiomics model established by TPOT exhibits a promising predictive capacity in distinguishing cerebral cystic metastases from abscesses.

Creating optimized machine learning pipelines for PV power generation forecasting using the grid search and tree-based pipeline optimization tool

Creating optimized machine learning pipelines for PV power generation forecasting using the grid search and tree-based pipeline optimization tool

An AutoML-based approach for automatic traffic incident detection in smart cities

In the realm of modern urban mobility, automatic incident detection is a critical element of intelligent transportation systems (ITS), since the ability to promptly identify unexpected events allows for quick implementation of preventive measures and efficient response to the situations as they arise. With the growing availability of traffic data, Machine Learning (ML) has become a vital tool for enhancing traditional incident detection methods. Automated machine-learning (AutoML) techniques present a promising solution by streamlining the machine-learning process; however the application of AutoML for incident detection has not been widely explored in scientific research In this paper, we propose and apply an AutoML-based methodology for traffic incident detection and compare it with state-ofthe-art ML approaches. Our approach integrates data preprocessing with AutoML, and uses Tree-based Pipeline Optimization Tool (TPOT) to refine the process from raw data to prediction. We have tested the efficiency of our approach in two major European cities, Athens and Antwerp. Finally, we present the limitations of our work and outline recommendations for application of AutoML in the incident detection task and potentially in other domains.

Inference of social cognition in schizophrenia patients with neurocognitive domains and neurocognitive tests using automated machine learning

AimIt has been suggested that single neurocognitive domain or neurocognitive test can be used to determine the overall cognitive function in schizophrenia using machine learning algorithms. It is unknown whether social cognition in schizophrenia patients can be estimated with machine learning based on neurocognitive domains or neurocognitive tests. MethodsTo predict social cognition in schizophrenia, we applied an automated machine learning (AutoML) framework resulting from the analysis of predictive factors such as six neurocognitive domain scores and nine neurocognitive test scores of 380 schizophrenia patients in the Taiwanese population. Four clinical parameters (i.e., age, gender, subgroup, and education) were also used as predictive factors. We utilized an AutoML framework called Tree-based Pipeline Optimization Tool (TPOT) to generate predictive pipelines automatically. ResultsThe analysis revealed that all neurocognitive domains and tests except the reasoning and problem solving domain/test showed significant associations with social cognition. In addition, a TPOT-generated pipeline can best predict social cognition in schizophrenia using seven predictive factors, including five neurocognitive domains (i.e., speed of processing, sustained attention, working memory, verbal learning and memory, and visual learning and memory) and two clinical parameters (i.e., age and gender). This predictive pipeline consists of machine learning algorithms such as function transformers, an approximate feature map, independent component analysis, and linear regression. ConclusionThe study indicates that an AutoML framework such as TPOT may provide a promising way to produce truly effective machine learning pipelines for predicting social cognition in schizophrenia using neurocognitive domains and/or neurocognitive tests.

Machine learning approaches to predict and detect early-onset of digital dermatitis in dairy cows using sensor data.

The present study aimed to employ machine learning algorithms based on sensor behavior data for (1) early-onset detection of digital dermatitis (DD) and (2) DD prediction in dairy cows. Our machine learning model, which was based on the Tree-Based Pipeline Optimization Tool (TPOT) automatic machine learning method, for DD detection on day 0 of the appearance of the clinical signs has reached an accuracy of 79% on the test set, while the model for the prediction of DD 2 days prior to the appearance of the first clinical signs, which was a combination of K-means and TPOT, has reached an accuracy of 64%. The proposed machine learning models have the potential to help achieve a real-time automated tool for monitoring and diagnosing DD in lactating dairy cows based on sensor data in conventional dairy barn environments. Our results suggest that alterations in behavioral patterns can be used as inputs in an early warning system for herd management in order to detect variances in the health and wellbeing of individual cows.

The possibility of rainfall nowcasting using atmospheric electric field

The possibility of rainfall nowcasting using a new parameter — atmospheric electric field (potential gradient, PG) — is investigated. The temporal behavior of the PG measured by a ground-based electric field mill before rainfall was analyzed at the University of Reading Atmospheric Observatory (51.441°N, 0.938°W, 66 m) in 2007–2021 and the Nor Amberd research station (40.367°N, 45.258°E, 2000 m) in 2013–2018. The PG tend to show abnormal oscillations before the precipitation cloud arrived at the PG measuring site. Several rules were applied to determine rainfall and PG oscillation events. Statistical analysis was conducted, and the results showed that PG oscillations occurred before and overlap with 48% (54%) of rainfall events, and PG oscillations occurred in one hour before 68% (77%) of rainfall events started at the University of Reading Atmospheric Observatory site (Nor Amberd research station site). A PG-based rainfall nowcasting model is proposed, which is constructed using machine learning techniques Fully Connected Neural Network and Tree-based Pipeline Optimization Tool. The hit rate, false alarm rate, missed detection rate, TS score of the model reached 93.8% (94.6%), 36% (37.4%), 37.7% (39.3%), 46.1% (44.5%) respectively, which is comparable to that of the state-of-the-art rainfall nowcasting methods. And the heavy rainfall hit rate reached 41.5% (36.4%). PG show a great potential to be used as a new parameter for rainfall nowcasting. And the effect of rainfall nowcasting method that proposed in this paper is barely affected by the weather conditions and the PG measuring range of different sites. Moreover, PG stands out among many other parameters because long-term and stable PG measurements can be obtained at a very low cost using an electric field mill.

Novel Functional Radiomics for Prediction of Cardiac PET Avidity in Lung Cancer Radiotherapy

Traditional methods of evaluating cardiotoxicity focus solely on radiation doses to the heart and do not incorporate functional imaging information. Functional imaging has great potential to improve the ability to provide early prediction for cardiotoxicity for lung cancer patients undergoing radiotherapy. FDG-based PET/CT imaging is routinely obtained as part of standard staging work up for lung cancer patients. Although FDG PET/CT scans are typically used to evaluate the tumor, imaging guidelines note that FDG PET/CT scans are an FDA-approved method to image for cardiac inflammation, and studies have noted that the PET cardiac signal can be predictive of clinical outcomes. The purpose of this work was to develop a radiomics model to predict clinical cardiac assessment of standard of care FDG PET/CT scans. The study included 100 consecutive lung cancer patients treated with radiotherapy who underwent standard pre-treatment FDG-PET/CT staging scans. A clinician reviewed the PET/CT scans per clinical cardiac assessment guidelines and classified the cardiac uptake as: 0 = uniform diffuse, 1 = absent, 2 = heterogeneous, with event rates of 20%, 44%, and 35%, respectively. The heart was delineated and 200 novel functional radiomics features were selected to classify cardiac FDG uptake patterns. We divided the data into an 80% training set and a 20% test set to train and evaluate the classification models. Feature reduction was carried out using the Wilcoxon test (with Bonferroni adjusted p<0.05), hierarchical clustering, and Recursive Feature Elimination. Two automatic machine learning (AutoML) frameworks were used to determine classification models: a Random Forest Classifier (Tree-based Pipeline Optimization Tool, TPOT) and Linear Discriminant Analysis (AutoSklearn). 10-fold cross validation was carried out for training and the accuracy of the ability of the models to predict for clinical cardiac assessment is reported. Fifty-one independent radiomics features were reduced to 3 clinically pertinent features (PET 2D Skewness, PET Grey Level Co-occurrence Matrix Correlation, and PET Median) using feature reduction techniques. The model selected by TPOT showed 89.8% predictive accuracy in the cross validation of the training set and 85% predictive accuracy on the test set. The model selected by AutoSklearn showed 89.7% predictive accuracy in the cross validation of the training set and 80% predictive accuracy on the test set. The novelty of this work is that it is the first study to develop and evaluate functional cardiac radiomic features from standard of care FDG PET/CT scans with the data showing good predictive accuracy with clinical imaging evaluation. If validated, the current work provides automated methods to provide functional cardiac information using standard of care imaging that can be used as an imaging biomarker for early clinical toxicity prediction for lung cancer patients.

Unveiling the Transparency of Prediction Models for Spatial PM2.5 over Singapore: Comparison of Different Machine Learning Approaches with eXplainable Artificial Intelligence

Aerosols play a crucial role in the climate system due to direct and indirect effects, such as scattering and absorbing radiant energy. They also have adverse effects on visibility and human health. Humans are exposed to fine PM2.5, which has adverse health impacts related to cardiovascular and respiratory-related diseases. Long-term trends in PM concentrations are influenced by emissions and meteorological variations, while meteorological factors primarily drive short-term variations. Factors such as vegetation cover, relative humidity, temperature, and wind speed impact the divergence in the PM2.5 concentrations on the surface. Machine learning proved to be a good predictor of air quality. This study focuses on predicting PM2.5 with these parameters as input for spatial and temporal information. The work analyzes the in situ observations for PM2.5 over Singapore for seven years (2014–2021) at five locations, and these datasets are used for spatial prediction of PM2.5. The study aims to provide a novel framework based on temporal-based prediction using Random Forest (RF), Gradient Boosting (GB) regression, and Tree-based Pipeline Optimization Tool (TP) Auto ML works based on meta-heuristic via genetic algorithm. TP produced reasonable Global Performance Index values; 7.4 was the highest GPI value in August 2016, and the lowest was −0.6 in June 2019. This indicates the positive performance of the TP model; even the negative values are less than other models, denoting less pessimistic predictions. The outcomes are explained with the eXplainable Artificial Intelligence (XAI) techniques which help to investigate the fidelity of feature importance of the machine learning models to extract information regarding the rhythmic shift of the PM2.5 pattern.

Comparisons of automated machine learning (AutoML) in predicting whistleblowing of academic dishonesty with demographic and theory of planned behavior

Machine learning has been very promising in solving real problems, but the implementation involved difficulties mainly for the inexpert data scientists. Therefore, this paper presents an automated machine learning (AutoML) to simplify and accelerate the modeling tasks. Focused on Python and RapidMiner rapid modeling tools, Tree-based Pipeline Optimization Tool (TPOT) and AutoModel were used. This paper presents a comprehensive comparison between these tools with regard to the prediction accuracy and Area Under Curve (AUC) in classifying real cases of whistleblowing academic dishonesty among undergraduate students of two universities in Indonesia. Additionally, the correlations weight from demographic and Theory of Planned Behavior (TOB) attributes in the different machine learning models are also discussed. All the machine learning algorithms from TPOT and AutoModel are considerable powerful to generate good accuracy level (between 70–93% of AUC) in classifying both cases of whistleblowing and non-whistleblowing on the hold-out samples from the testing process. Generally, based on the validation results of the prediction models, demographic attributes presented more importance than the TBP attributes. The findings of this study will be a great interest of many research scholars to conduct a more in-depth analysis on AutoML for many domains mainly in education and academic misconduct fields.•AutoML is the first of its kind to be empirically compared between TPOT and AutoModel in an application to predict academic dishonesty whistleblowing.•Besides accuracy performances of the AutoML, the proportion of the variance of each attribute from demographic and Theory of Planned Behavior (TPB) is also presented in the prediction models of academic dishonesty whistleblowing.•AutoML is a convenient and reproducible rapid modeling method of machine learning to be used in many kinds of prediction problem.

An automated machine learning model for diagnosing coronavirus disease 2019 (COVID-19) infection

The coronavirus disease 2019 (COVID-19) epidemic still impacts every facet of life and necessitates a fast and accurate diagnosis. The need for an effective, rapid, and precise way to reduce radiologists' workload in diagnosing suspected cases has emerged. This study used the tree-based pipeline optimization tool (TPOT) and many machine learning (ML) algorithms. TPOT is an open-source genetic programming-based AutoML system that optimizes a set of feature preprocessors and ML models to maximize classification accuracy on a supervised classification problem. A series of trials and comparisons with the results of ML and earlier studies discovered that most of the AutoML beat traditional ML in terms of accuracy. A blood test dataset that has 111 variables and 5644 cases were used. In TPOT, 450 pipelines were used, and the best pipeline selected consisted of radial basis function (RBF) Sampler preprocessing and Gradient boosting classifier as the best algorithm with a 99% accuracy rate.

Applying machine learning methods to quantify emotional experience in installation art

Aesthetic experience is original, dynamic and ever-changing. This article covers three research questions (RQs) concerning how immersive installation artworks can elicit emotions that may contribute to their popularity. Based on Yayoi Kusama’s and Peter Kogler’s kaleidoscopic rooms, this study aims to predict the emotions of visitors of immersive installation art based on their Twitter activity. As indicators, we employed the total number of likes, comments, retweets, followers, followings, the average of tweets per user, and emotional response. According to our evaluation of emotions, panic obtained the highest scores. Furthermore, compared to traditional machine learning algorithms, Tree-based Pipeline Optimization Tool (TPOT) Automated Machine Learning used in this research yielded slightly lower performance. We forecast that our findings will stimulate future research in the fields of data analysis, cultural heritage management and marketing, aesthetics and cultural analytics.

Early detection of paediatric and adolescent obsessive–compulsive, separation anxiety and attention deficit hyperactivity disorder using machine learning algorithms

PurposeMental health issues of young minds are at the threshold of all development and possibilities. Obsessive–compulsive disorder (OCD), separation anxiety disorder (SAD), and attention deficit hyperactivity disorder (ADHD) are three of the most common mental illness affecting children and adolescents. Several studies have been conducted on approaches for recognising OCD, SAD and ADHD, but their accuracy is inadequate due to limited features and participants. Therefore, the purpose of this study is to investigate the approach using machine learning (ML) algorithms with 1474 features from Australia's nationally representative mental health survey of children and adolescents.MethodsBased on the internal cross-validation (CV) score of the Tree-based Pipeline Optimization Tool (TPOTClassifier), the dataset has been examined using three of the most optimal algorithms, including Random Forest (RF), Decision Tree (DT), and Gaussian Naïve Bayes (GaussianNB).ResultsGaussianNB performs well in classifying OCD with 91% accuracy, 76% precision, and 96% specificity as well as in detecting SAD with 79% accuracy, 62% precision, 91% specificity. RF outperformed all other methods in identifying ADHD with 91% accuracy, 94% precision, and 99% specificity.ConclusionUsing Streamlit and Python a web application was developed based on the findings of the analysis. The application will assist parents/guardians and school officials in detecting mental illnesses early in their children and adolescents using signs and symptoms to start the treatment at the earliest convenience.

Screening of Breast Cancer from Sweat Samples Analyzed by 2-Dimensional Gas Chromatography-Mass Spectrometry: A Preliminary Study.

Breast cancer (BC) remains one of the most commonly diagnosed malignancies in women. There is increasing interest in the development of non-invasive screening methods. Volatile organic compounds (VOCs) emitted through the metabolism of cancer cells are possible novel cancer biomarkers. This study aims to identify the existence of BC-specific VOCs in the sweat of BC patients. Sweat samples from the breast and hand area were collected from 21 BC participants before and after breast tumor ablation. Thermal desorption coupled with two-dimensional gas chromatography and mass spectrometry was used to analyze VOCs. A total of 761 volatiles from a homemade human odor library were screened on each chromatogram. From those 761 VOCs, a minimum of 77 VOCs were detected within the BC samples. Principal component analysis showed that VOCs differ between the pre- and post-surgery status of the BC patients. The Tree-based Pipeline Optimization Tool identified logistic regression as the best-performing machine learning model. Logistic regression modeling identified VOCs that distinguish the pre-and post-surgery state in BC patients on both the breast and hand area with sensitivities close to 1. Further, Shapley additive explanations and the probe variable method identified the most important and pertinent VOCs distinguishing pre- and post-operative status which are mostly of distinct origin for the hand and breast region. Results suggest the possibility to identify endogenous metabolites linked to BC, hence proposing this innovative pipeline as a stepstone to discovering potential BC biomarkers. Large-scale studies in a multi-centered VOC analysis setting must be carried out to validate obtained findings.

Evaluating a New Auto-ML Approach for Sentiment Analysis and Intent Recognition Tasks

Automated Machine Learning (AutoML) is a research area that aims to help humans solve Machine Learning (ML) problems by automatically discovering good ML pipelines (algorithms and their hyperparameters for every stage of a machine learning process) for a given dataset. Since we have a combinatorial optimization problem for which it is impossible to evaluate all possible pipelines, most AutoML systems use a Genetic Algorithm (GA) or Bayesian Optimization (BO) to find a good solution. These systems usually evaluate the performance of the pipelines using the K-fold cross-validation method, for which the more pipelines are evaluated, the higher the chance of finding an overfitted solution. To avoid the aforementioned issue, we propose a system named Auto-ML System for Text Classification (ASTeC), that uses the Bootstrap Bias Corrected CV (BBC-CV) method to evaluate the performance of the pipelines. More specifically, the proposed system combines GA, BO, and BBC-CV to find a good ML pipeline for the text classification task. We evaluated our approach by comparing it with state-of-the-art systems: in the the Sentiment Analysis (SA) task, we compared our approach to TPOT (Tree-based Pipeline Optimization Tool) and Google Cloud AutoML service, and for the Intent Recognition (IR) task, we compared with TPOT and MLJAR AutoML. Concerning the data, we analysed seven public datasets from the SA domain and sixteen from the IR domain. Four out of those sixteen are composed by written English text, while all of the others are in Brazilian Portuguese. Statistical tests show that, in 21 out of 23 datasets, our system's performance is equivalent to or better than the others.

Mapping variation of extracellular matrix in human keloid scar by label-free multiphoton imaging and machine learning.

Rapid diagnosis and analysis of human keloid scar tissues in an automated manner are essential for understanding pathogenesis and formulating treatment solutions. Our aim is to resolve the features of the extracellular matrix in human keloid scar tissues automatically for accurate diagnosis with the aid of machine learning. Multiphoton microscopy was utilized to acquire images of collagen and elastin fibers. Morphological features, histogram, and gray-level co-occurrence matrix-based texture features were obtained to produce a total of 28 features. The minimum redundancy maximum relevancy feature selection approach was implemented to rank these features and establish feature subsets, each of which was employed to build a machine learning model through the tree-based pipeline optimization tool (TPOT). The feature importance ranking was obtained, and 28 feature subsets were acquired by incremental feature selection. The subset with the top 23 features was identified as the most accurate. Then stochastic gradient descent classifier optimized by the TPOT was generated with an accuracy of 96.15% in classifying normal, scar, and adjacent tissues. The area under curve of the classification results (scar versus normal and adjacent, normal versus scar and adjacent, and adjacent versus normal and scar) was 1.0, 1.0, and 0.99, respectively. The proposed approach has great potential for future dermatological clinical diagnosis and analysis and holds promise for the development of computer-aided systems to assist dermatologists in diagnosis and treatment.

Predicting Hepatotoxicity Associated with Low-Dose Methotrexate Using Machine Learning

An accurate prediction of the hepatotoxicity associated with low-dose methotrexate can provide evidence for a reasonable treatment choice. This study aimed to develop a machine learning-based prediction model to predict hepatotoxicity associated with low-dose methotrexate and explore the associated risk factors. Eligible patients with immune system disorders, who received low-dose methotrexate at West China Hospital between 1 January 2018, and 31 December 2019, were enrolled. A retrospective review of the included patients was conducted. Risk factors were selected from multiple patient characteristics, including demographics, admissions, and treatments. Eight algorithms, including eXtreme Gradient Boosting (XGBoost), AdaBoost, CatBoost, Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LightGBM), Tree-based Pipeline Optimization Tool (TPOT), Random Forest (RF), and Artificial Neural Network (ANN), were used to establish the prediction model. A total of 782 patients were included, and hepatotoxicity was detected in 35.68% (279/782) of the patients. The Random Forest model with the best predictive capacity was chosen to establish the prediction model (receiver operating characteristic curve 0.97, accuracy 64.33%, precision 50.00%, recall 32.14%, and F1 39.13%). Among the 15 risk factors, the highest score was a body mass index of 0.237, followed by age (0.198), the number of drugs (0.151), and the number of comorbidities (0.144). These factors demonstrated their importance in predicting hepatotoxicity associated with low-dose methotrexate. Using machine learning, this novel study established a predictive model for low-dose methotrexate-related hepatotoxicity. The model can improve medication safety in patients taking methotrexate in clinical practice.

A novel automated SuperLearner using a genetic algorithm-based hyperparameter optimization

Industrial revolution 4.0 has pushed industries worldwide to use machine learning (ML) models to address real-world engineering problems. The industry generally faces two main challenges in ML applications: the lack of skilled data scientists and the cost of obtaining large labeled datasets. These challenges need to be addressed to unlock the full potential of ML. In this work, a novel automated SuperLearner (SL) model using a genetic algorithm (AutoSL-GA) based hyperparameter optimization (HPO) is introduced to address the aforementioned challenges and assist scientists and engineers. Detailed comparisons are performed between AutoSL-GA, SuperLearner using Bayesian-based HPO (AutoSL-BO), and another well-known automated machine learning (AutoML) algorithm called Tree-based pipeline optimization tool (TPOT). Six different benchmark datasets were used to compare the performance and computational times of the models. AutoSL-GA resulted in higher performance with lower computational time than other models for all six benchmark datasets. Finally, a sensitivity analysis for dataset size was performed, in which AutoSL-GA also outperformed the other models across the dataset sizes while consuming the least computational resources.

Data-driven compressive strength prediction of steel fiber reinforced concrete (SFRC) subjected to elevated temperatures using stacked machine learning algorithms

Experimental studies using a substantial number of datasets can be avoided by employing efficient methods to predict the mechanical properties of construction materials. The correlation between the mechanical attributes and structural performance of these structures can be determined using an efficient mathematical model. In this study, a large data-rich framework is constructed with data from 307 experiments conducted between 2000 and 2022 and reported in the literature to predict the compressive strength (CS) of steel fiber-reinforced concrete (SFRC) subjected to high temperatures. The collected data are utilized for training the proposed models using the SciKit, Tree-based Pipeline Optimization Tool (TPOT), and AutoKeras libraries in Python, followed by hyperparameter tuning and k-fold cross-validation. After performing the feature selection analysis, several machine learning (ML) algorithms are developed and compared. Out of 7 different leaderboard combinations, the best stacked pipeline including support vector machine, random forest, gradient boosting machine, extra tree regression, and K-nearest neighbors, is found to provide the most accurate solution. In addition, the results obtained using the stacked ML are compared with those obtained using an artificial neural network algorithm. Moreover, the accuracy of each method is determined through a comparative study. The stacked ML pipeline with optimum hyperparameters yields the highest accuracy (R2 = 0.92). The proposed stacked technique serves as an accurate and adaptable attribute evaluation tool for researchers to predict the CS of SFRCs subjected to elevated temperatures in construction applications.

Radiomic study on preoperative multi-modal magnetic resonance images identifies IDH-mutant TERT promoter-mutant gliomas.

Gliomas with comutations of isocitrate dehydrogenase (IDH) genes and telomerase reverse transcriptase (TERT) gene promoter (IDHmut pTERTmut) show distinct biological features and respond to first-line treatment differently in comparison with other gliomas. This study aimed to characterize the IDHmut pTERTmut gliomas in multimodal MRI using the radiomic method and establish a precise diagnostic model identifying this group of gliomas. A total of 140 patients with untreated primary gliomas were admitted between 2016 and 2020 to West China Hospital as a discovery cohort, including 22 IDHmut pTERTmut patients. Thirty-four additional cases from a different hospital were included in the study as an independent validation cohort. A total of 3654 radiomic features were extracted from the preoperative multimodal MRI images (T1c, FLAIR, and ADC maps) and filtered in a data-driven approach. The discovery cohort was split into training and test sets by a 4:1 ratio. A diagnostic model (multilayer perceptron classifier) for detecting the IDHmut pTERTmut gliomas was trained using an automatic machine-learning algorithm named tree-based pipeline optimization tool (TPOT). The most critical radiomic features in the model were identified and visualized. The model achieved an area under the receiver-operating curve (AUROC) of 0.971 (95% CI, 0.902-1.000), the sensitivity of 0.833 (95% CI, 0.333-1.000), and the specificity of 0.966 (95% CI, 0.931-1.000) in the test set. The area under the precision-recall curve (AUCPR) was 0.754 (95% CI, 0.572-0.833) and the F1 score was 0.833 (95% CI, 0.500-1.000). In the independent validation set, the model reached 0.952 AUROC, 0.714 sensitivity, 0.963 specificity, 0.841 AUCPR, and 0.769 F1 score. MR radiomic features of the IDHmut pTERTmut gliomas represented homogenous low-complexity texture in three modalities. An accurate diagnostic model was constructed for detecting IDHmut pTERTmut gliomas using multimodal radiomic features. The most important features were associated with the homogenous simple texture of IDHmut pTERTmut gliomas in MRI images transformed using Laplacian of Gaussian and wavelet filters.