Early Prediction Model Research Articles

A hybrid optimized model for predicting evapotranspiration in early and late rice based on a categorical regression tree combination of key influencing factors

Crop evapotranspiration (ETC) is an important component of the agricultural hydrological cycle, and its accurate estimation is important for assessing the hydrological environment of farmlands and guiding crop irrigation. To improve the prediction accuracy of ETC for early and late rice, this study analyzed the importance of the influencing factors based on a categorical regression tree (CART) machine learning algorithm. Based on the importance results of the influencing factors obtained from CART analysis, different combinations of input factors were constructed, and daily ETC prediction models were developed for early and late rice using the least squares support vector machine (LSSVM). A three-element heuristic optimization algorithm, Sine Cosine Algorithm (SCA), Slime Mold Algorithm (SMA), and Sparrow Search Algorithm (SSA), were used to optimize the ETC model to improve the performance of the early and late rice ETC prediction models. The results of this study revealed that the strongest correlation between early and late rice ETC was net solar radiation (Rn), with importance of 0.830 and 0.802, respectively. The next strongest correlations were temperature (T), wind speed (u), soil moisture (SM) and u, leaf area index (LAI), SM (0.092, 0.02, 0.014 and 0.058, 0.049, 0.034), respectively. The accuracy of the model tended to increase as the number of influencing factors in the input combinations constructed based on the importance results increased. The accuracy of the model increased more rapidly when the input factors were one to four and the accuracy of the model increased slightly when the input factors were more than four. The SSA-LSSVM model with four-factor combinations of inputs was the least-factor combination with guaranteed model accuracy of RMSE = 0.514 mm/d, R2 = 0.924, KGE = 0.565, WI = 0.978,and MAE = 0.414 mm/d; RMSE = 0.468 mm/d, R2 = 0.910, KGE = 0.670, WI = 0.985, and MAE = 0.368 mm/d. This study may provide a reference for the prediction of evapotranspiration as a key factor in the study of the agricultural hydrological environment of early and late rice.

Predicting academic performance in a course by universal features of LMS Moodle digital footprint

Student retention prediction is one of the most important problems of learning analytics. In the global scope research on the topic for higher education is rather extensive, there are cases of successful implementation of education support services in universities. The literature analysis shows of the growing interest in this problem in the Russian scientific and pedagogical community. At the same time, the specifics of Russian education does not allow direct transfer of foreign experience into the domestic educational system.The study reveals that a significant contribution to predicting student retention can be made by models for predicting academic performance in educational courses of the curriculum. The authors propose a structural model of a system for predicting academic performance, which includes a universal model based on generalized indicators of the digital footprint, a course-based model that takes into account the specifics of learning in a particular discipline, and a model based on the student’s educational profile.In the empirical study we trained 5 models for early prediction of interim assessment grades based on the universal indicators of the LMS Moodle student digital footprint. The most accurate model, especially in the first half of the semester, turned out to be ensemble-averaging models of logistic regression, random forest and gradient boosting. It was found that universal models are effective for detection of at-risk students in the discipline, the directions for further improvement of the universal model of performance prediction were determined and conditions for scaling the proposed approach to create a prognostic system for student retention to other educational institutions were formulated.

Google and Apple mobility data as predictors for European tourism during the COVID-19 pandemic: A neural network approach

Research background: The COVID-19 pandemic has caused unprecedented disruptions to the global tourism industry, resulting in significant impacts on both human and economic activities. Travel restrictions, border closures, and quarantine measures have led to a sharp decline in tourism demand, causing businesses to shut down, jobs to be lost, and economies to suffer. Purpose of the article: This study aims to examine the correlation and causal relationship between real-time mobility data and statistical data on tourism, specifically tourism overnights, across eleven European countries during the first 14 months of the pandemic. We analyzed the short longitudinal connections between two dimensions of tourism and related activities. Methods: Our method is to use Google and Apple's observational data to link with tourism statistical data, enabling the development of early predictive models and econometric models for tourism overnights (or other tourism indices). This approach leverages the more timely and more reliable mobility data from Google and Apple, which is published with less delay than tourism statistical data. Findings & value added: Our findings indicate statistically significant correlations between specific mobility dimensions, such as recreation and retail, parks, and tourism statistical data, but poor or insignificant relations with workplace and transit dimensions. We have identified that leisure and recreation have a much stronger influence on tourism than the domestic and routine-named dimensions. Additionally, our neural network analysis revealed that Google Mobility Parks and Google Mobility Retail & Recreation are the best predictors for tourism, while Apple Driving and Apple Walking also show significant correlations with tourism data. The main added value of our research is that it combines observational data with statistical data, demonstrates that Google and Apple location data can be used to model tourism phenomena, and identifies specific methods to determine the extent, direction, and intensity of the relationship between mobility and tourism flows.

Prediction of early improvement of major depressive disorder to antidepressant medication in adolescents with radiomics analysis after ComBat harmonization based on multiscale structural MRI

BackgroundDue to individual differences and lack of objective biomarkers, only 30-40% patients with major depressive disorder (MDD) achieve remission after initial antidepressant medication (ADM). We aimed to employ radiomics analysis after ComBat harmonization to predict early improvement to ADM in adolescents with MDD by using brain multiscale structural MRI (sMRI) and identify the radiomics features with high prediction power for selection of selective serotonin reuptake inhibitors (SSRIs) and serotonin norepinephrine reuptake inhibitors (SNRIs).Methods121 MDD patients were recruited for brain sMRI, including three-dimensional T1 weighted imaging (3D-T1WI)and diffusion tensor imaging (DTI). After receiving SSRIs or SNRIs for 2 weeks, the subjects were divided into ADM improvers (SSRIs improvers and SNRIs improvers) and non-improvers according to reduction rate of the Hamilton Depression Rating Scale, 17 item (HAM-D17) score. Then, sMRI data were preprocessed, and conventional imaging indicators and radiomics features of gray matter (GM) based on surface-based morphology (SBM) and voxel-based morphology (VBM) and diffusion properties of white matter (WM) were extracted and harmonized with ComBat harmonization. Two-level reduction strategy with analysis of variance (ANOVA) and recursive feature elimination (RFE) was utilized sequentially to decrease high-dimensional features. Support vector machine with radial basis function kernel (RBF-SVM) was used to integrate multiscale sMRI features to construct models for early improvement prediction. Area under the curve (AUC), accuracy, sensitivity, and specificity based on the leave-one-out cross-validation (LOO-CV) and receiver operating characteristic (ROC) curve analysis were calculated to evaluate the model performance. Permutation tests were used for assessing the generalization rate.ResultsAfter 2-week ADM, 121 patients were divided into 67 ADM improvers (31 SSRIs improvers and 36 SNRIs improvers) and 54 ADM non-improvers. After two-level dimensionality reduction, 8 conventional indicators (2 VBM-based features and 6 diffusion features) and 49 radiomics features (16 VBM-based features and 33 diffusion features) were selected. The overall accuracy of RBF-SVM models based on conventional indicators and radiomics features was 74.80% and 88.19%. The radiomics model achieved the AUC, sensitivity, specificity, and accuracy of 0.889, 91.2%, 80.1% and 85.1%, 0.954, 89.2%, 87.4% and 88.5%, 0.942, 91.9%, 82.5% and 86.8% for predicting ADM improvers, SSRIs improvers and SNRIs improvers, respectively. P value of permutation tests were less than 0.001. The radiomics features predicting ADM improver were mainly located in the hippocampus, medial orbitofrontal gyrus, anterior cingulate gyrus, cerebellum (lobule vii-b), body of corpus callosum, etc. The radiomics features predicting SSRIs improver were primarily distributed in hippocampus, amygdala, inferior temporal gyrus, thalamus, cerebellum (lobule vi), fornix, cerebellar peduncle, etc. The radiomics features predicting SNRIs improver were primarily located in the medial orbitofrontal cortex, anterior cingulate gyrus, ventral striatum, corpus callosum, etc.ConclusionsThese findings suggest the radiomics analysis based on brain multiscale sMRI after ComBat harmonization could effectively predict the early improvement of ADM in adolescent MDD patients with a high accuracy, which was superior to the model based on the conventional indicators. The radiomics features with high prediction power may help for the individual selection of SSRIs and SNRIs.

Hidden Markov Model for early prediction of the elderly’s dependency evolution in ambient assisted living

Hidden Markov Model for early prediction of the elderly’s dependency evolution in ambient assisted living

FFN-XGB- design of a hybrid feed forward neural network and extreme gradient boosting model for early prediction of chronic kidney disease

FFN-XGB- design of a hybrid feed forward neural network and extreme gradient boosting model for early prediction of chronic kidney disease

Development of a blood proteins-based model for bronchopulmonary dysplasia prediction in premature infants

BackgroundBronchopulmonary dysplasia (BPD) is the most common chronic pulmonary disease in premature infants. Blood proteins may be early predictors of the development of this disease.MethodsIn this study, protein expression profiles (blood samples during their first week of life) and clinical data of the GSE121097 was downloaded from the Gene Expression Omnibus. Weighted gene co-expression network analysis (WGCNA) and differential protein analysis were carried out for variable dimensionality reduction and feature selection. Least absolute shrinkage and selection operator (LASSO) were conducted for BPD prediction model development. The performance of the model was evaluated by the receiver operating characteristic (ROC) curve, calibration curve, and decision curve.ResultsThe results showed that black module, magenta module and turquoise module, which included 270 proteins, were significantly correlated with the occurrence of BPD. 59 proteins overlapped between differential analysis results and above three modules. These proteins were significantly enriched in 253 GO terms and 11 KEGG signaling pathways. Then, 59 proteins were reduced to 8 proteins by LASSO analysis in the training cohort. The proteins model showed good BPD predictive performance, with an AUC of 1.00 (95% CI 0.99-1.00) and 0.96 (95% CI 0.90-1.00) in training cohort and test cohort, respectively.ConclusionOur study established a reliable blood-protein based model for early prediction of BPD in premature infants. This may help elucidate pathways to target in lessening the burden or severity of BPD.

Development and clinical impact assessment of a machine-learning model for early prediction of late-onset sepsis

Background and aimPreterm infants are prone to neonatal infections such as late-onset sepsis (LOS). The consequences of LOS can be severe and potentially life-threatening. Unfortunately, LOS often presents with unspecific symptoms, and early screening laboratory tests have limited diagnostic value and are often late. This study aimed to build a predictive algorithm to aid doctors in the early detection of LOS in very preterm infants. MethodsIn a retrospective cohort study, all consecutively admitted preterm infants (GA ≤ 32 weeks) from 2008 until 2019 were included. They were classified as LOS or control according to blood culture results, currently the gold standard. To generate features, routine and continuously measured oxygen saturation and heart rate data with a minute-by-minute sampling rate were extracted from electronic medical records. Care was taken not to include variables indicative of existing LOS suspicion. The timing of a positive blood culture served as a proxy for LOS-onset. An equivalent timestamp was generated in gestational-age-matched control patients without a positive blood culture. Three machine learning (ML) techniques (generalized additive models, logistic regression, and XGBoost) were used to build a classification algorithm. To simulate the performance of the algorithm in clinical practice, a simulation using multiple alarm thresholds was performed on hourly predictions for the total hospitalization period. Results292 infants with LOS were matched to 1497 controls. The median gestational age before matching was 28.1 and 30.3 weeks, respectively. Evaluation of the overall discriminative power of the LR algorithm yielded an AUC of 0.73 (p < 0.05) at the moment of clinical suspicion (t = 0). In the longitudinal simulation, our algorithm detects LOS in at least 47% of the patients before clinical suspicion without exceeding the alarm fatigue threshold of 3 alarms per day. Furthermore, medical experts evaluated the algorithm as clinically relevant regarding the feature contributions in the model explanations. ConclusionsAn ML algorithm was trained for the early detection of LOS. Performance was evaluated on both prediction horizons and in a clinical impact simulation. To the best of our knowledge, our assessment of clinical impact with a retrospective simulation on longitudinal data is the most extensive in the literature on LOS prediction to date. The clinically relevant algorithm, based on routinely collected data, can potentially accelerate clinical decisions in the early detection of LOS, even with limited inputs.

THE PROGNOSIS OF INTRAUTERINE GROWTH RETARDATION OF FETUS AT DIFFERENT TERMS OF PREGNANCY IN THE CASE OF MICROELEMENTOSIS

Prediction of the development of intrauterine growth retardation (IUGR) – means to predict the possibility at the first prenatal visit of the pregnant woman.&#x0D; The aim of the study is to create an adequate, informative and stable model for early prediction of IUGR in pregnant women.&#x0D; Materials and methods: Predictions of IUGR were carried out by regression analysis. The software packages «Statistica» («StatSoft Inc.», USA). Model was grounded on data inspection of 30 women who gave birth to babies with IUGR and their new-borns. The checking of the created model was made on data holding on tracking 30 babies of the studied groups.&#x0D; Results: with the help of method of multiple linear regressions it got right to create a mathematical model for prediction of IUGR in pregnant women at different stages of pregnancy. The created method of forecasting with the using advanced methods of researching content of microelements in biological environments has been proposed for the first time and deserves attention.&#x0D; Conclusion: using the proposed method of prediction will allow the clinical practice of Obstetricians and Gynaecologists, Perinatologists to carry out the complex treatment-preventive maintenance measures to reduce maternal and perinatal morbidity and mortality.

Construction of the XGBoost model for early lung cancer prediction based on metabolic indices

BackgroundLung cancer is a malignant tumour, and early diagnosis has been shown to improve the survival rate of lung cancer patients. In this study, we assessed the use of plasma metabolites as biomarkers for lung cancer diagnosis. In this work, we used a novel interdisciplinary mechanism, applied for the first time to lung cancer, to detect biomarkers for early lung cancer diagnosis by combining metabolomics and machine learning approaches.ResultsIn total, 478 lung cancer patients and 370 subjects with benign lung nodules were enrolled from a hospital in Dalian, Liaoning Province. We selected 47 serum amino acid and carnitine indicators from targeted metabolomics studies using LC‒MS/MS and age and sex demographic indicators of the subjects. After screening by a stepwise regression algorithm, 16 metrics were included. The XGBoost model in the machine learning algorithm showed superior predictive power (AUC = 0.81, accuracy = 75.29%, sensitivity = 74%), with the metabolic biomarkers ornithine and palmitoylcarnitine being potential biomarkers to screen for lung cancer. The machine learning model XGBoost is proposed as an tool for early lung cancer prediction. This study provides strong support for the feasibility of blood-based screening for metabolites and provide a safer, faster and more accurate tool for early diagnosis of lung cancer.ConclusionsThis study proposes an interdisciplinary approach combining metabolomics with a machine learning model (XGBoost) to predict early the occurrence of lung cancer. The metabolic biomarkers ornithine and palmitoylcarnitine showed significant power for early lung cancer diagnosis.

A hybrid machine learning approach for early cost estimation of pile foundations

Purpose This study aims at proposing a hybrid model for early cost prediction of a construction project. Early cost prediction for a construction project is the basic approach to procure a project within a predefined budget. However, most of the projects routinely face the impact of cost overruns. Furthermore, conventional and manual cost computing techniques are hectic, time-consuming and error-prone. To deal with such challenges, soft computing techniques such as artificial neural networks (ANNs), fuzzy logic and genetic algorithms are applied in construction management. Each technique has its own constraints not only in terms of efficiency but also in terms of feasibility, practicability, reliability and environmental impacts. However, appropriate combination of the techniques improves the model owing to their inherent nature. Design/methodology/approach This paper proposes a hybrid model by combining machine learning (ML) techniques with ANN to accurately predict the cost of pile foundations. The parameters contributing toward the cost of pile foundations were collected from five different projects in India. Out of 180 collected data entries, 176 entries were finally used after data cleaning. About 70% of the final data were used for building the model and the remaining 30% were used for validation. Findings The proposed model is capable of predicting the pile foundation costs with an accuracy of 97.42%. Originality/value Although various cost estimation techniques are available, appropriate use and combination of various ML techniques aid in improving the prediction accuracy. The proposed model will be a value addition to cost estimation of pile foundations.

Comprehensive analyses of brain cell communications based on multiple scRNA-seq and snRNA-seq datasets for revealing novel mechanism in neurodegenerative diseases.

Complex cellular communications between glial cells and neurons are critical for brain normal function and disorders, and single-cell level RNA-sequencing datasets display more advantages for analyzing cell communications. Therefore, it is necessary to systematically explore brain cell communications when considering factors such as sex and brain region. We extracted a total of 1,039,459 cells derived from 28 brain single-cell RNA-sequencing (scRNA-seq) or single-nucleus RNA-sequencing (snRNA-seq) datasets from the GEO database, including 12 human and 16 mouse datasets. These datasets were further divided into 71 new sub-datasets when considering disease, sex, and region conditions. In the meanwhile, we integrated four methods to evaluate ligand-receptor interaction score among six major brain cell types (microglia, neuron, astrocyte, oligodendrocyte, OPC, and endothelial cell). For Alzheimer's disease (AD), disease-specific ligand-receptor pairs when compared with normal sub-datasets, such as SEMA4A-NRP1, were identified. Furthermore, we explored the sex- and region-specific cell communications and identified that WNT5A-ROR1 among microglia cells displayed close communications in male, and SPP1-ITGAV displayed close communications in the meninges region from microglia to neurons. Furthermore, based on the AD-specific cell communications, we constructed a model for AD early prediction and confirmed the predictive performance using multiple independent datasets. Finally, we developed an online platform for researchers to explore brain condition-specific cell communications. This research provided a comprehensive study to explore brain cell communications, which could reveal novel biological mechanisms involved in normal brain function and neurodegenerative diseases such as AD.

Predicting SARS-CoV-2 infection among hemodialysis patients using multimodal data.

The coronavirus disease 2019 (COVID-19) pandemic has created more devastation among dialysis patients than among the general population. Patient-level prediction models for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection are crucial for the early identification of patients to prevent and mitigate outbreaks within dialysis clinics. As the COVID-19 pandemic evolves, it is unclear whether or not previously built prediction models are still sufficiently effective. We developed a machine learning (XGBoost) model to predict during the incubation period a SARS-CoV-2 infection that is subsequently diagnosed after 3 or more days. We used data from multiple sources, including demographic, clinical, treatment, laboratory, and vaccination information from a national network of hemodialysis clinics, socioeconomic information from the Census Bureau, and county-level COVID-19 infection and mortality information from state and local health agencies. We created prediction models and evaluated their performances on a rolling basis to investigate the evolution of prediction power and risk factors. From April 2020 to August 2020, our machine learning model achieved an area under the receiver operating characteristic curve (AUROC) of 0.75, an improvement of over 0.07 from a previously developed machine learning model published by Kidney360 in 2021. As the pandemic evolved, the prediction performance deteriorated and fluctuated more, with the lowest AUROC of 0.6 in December 2021 and January 2022. Over the whole study period, that is, from April 2020 to February 2022, fixing the false-positive rate at 20%, our model was able to detect 40% of the positive patients. We found that features derived from local infection information reported by the Centers for Disease Control and Prevention (CDC) were the most important predictors, and vaccination status was a useful predictor as well. Whether or not a patient lives in a nursing home was an effective predictor before vaccination, but became less predictive after vaccination. As found in our study, the dynamics of the prediction model are frequently changing as the pandemic evolves. County-level infection information and vaccination information are crucial for the success of early COVID-19 prediction models. Our results show that the proposed model can effectively identify SARS-CoV-2 infections during the incubation period. Prospective studies are warranted to explore the application of such prediction models in daily clinical practice.

An early prediction model for gestational diabetes mellitus based on metabolomic biomarkers

BackgroundGestational diabetes mellitus (GDM) represents the main metabolic alteration during pregnancy. The available methods for diagnosing GDM identify women when the disease is established, and pancreatic beta-cell insufficiency has occurred.The present study aimed to generate an early prediction model (under 18 weeks of gestation) to identify those women who will later be diagnosed with GDM.MethodsA cohort of 75 pregnant women was followed during gestation, of which 62 underwent normal term pregnancy and 13 were diagnosed with GDM. Targeted metabolomics was used to select serum biomarkers with predictive power to identify women who will later be diagnosed with GDM.ResultsCandidate metabolites were selected to generate an early identification model employing a criterion used when performing Random Forest decision tree analysis. A model composed of two short-chain acylcarnitines was generated: isovalerylcarnitine (C5) and tiglylcarnitine (C5:1). An analysis by ROC curves was performed to determine the classification performance of the acylcarnitines identified in the study, obtaining an area under the curve (AUC) of 0.934 (0.873–0.995, 95% CI). The model correctly classified all cases with GDM, while it misclassified ten controls as in the GDM group. An analysis was also carried out to establish the concentrations of the acylcarnitines for the identification of the GDM group, obtaining concentrations of C5 in a range of 0.015–0.25 μmol/L and of C5:1 with a range of 0.015–0.19 μmol/L.ConclusionEarly pregnancy maternal metabolites can be used to screen and identify pregnant women who will later develop GDM. Regardless of their gestational body mass index, lipid metabolism is impaired even in the early stages of pregnancy in women who develop GDM.

Wavelet based ensemble models for early mortality prediction using imbalance ICU big data

Wavelet based ensemble models for early mortality prediction using imbalance ICU big data

Predicting the Risk of Alzheimer's Disease and Related Dementia in Patients with Mild Cognitive Impairment Using a Semi-Competing Risk Approach.

Alzheimer's disease (AD) and AD-related dementias (AD/ADRD) are a group of progressive neurodegenerative diseases. The progression of AD can be conceptualized as a continuum in which patients progress from normal cognition to preclinical AD (i.e., no symptoms but biological changes in the brain) to mild cognitive impairment (MCI) due to AD (i.e., mild symptoms but not interfere with daily activities), followed by increasing severity of dementia due to AD. Early detection and prediction models for the transition of MCI to AD/ADRD are needed, and efforts have been made to build predictions of MCI conversion to AD/ADRD. However, most existing studies developing such prediction models did not consider the competing risks of death, which may result in biased risk estimates. In this study, we aim to develop a prediction model for AD/ADRD among patients with MCI considering the competing risks of death using a semi-competing risk approach.

An Intelligent Model for early prediction of Type 2 diabetes likelihood using human behaviors and biometrics among adults in Saudi Arabia

An Intelligent Model for early prediction of Type 2 diabetes likelihood using human behaviors and biometrics among adults in Saudi Arabia

Development and verification of a combined diagnostic model for primary Sjögren's syndrome by integrated bioinformatics analysis and machine learning

Primary Sjögren’s syndrome (pSS) is a chronic, systemic autoimmune disease mostly affecting the exocrine glands. This debilitating condition is complex and specific treatments remain unavailable. There is a need for the development of novel diagnostic models for early screening. Four gene profiling datasets were downloaded from the Gene Expression Omnibus database. The ‘limma’ software package was used to identify differentially expressed genes (DEGs). A random forest-supervised classification algorithm was used to screen disease-specific genes, and three machine learning algorithms, including artificial neural networks (ANN), random forest (RF), and support vector machines (SVM), were used to build a pSS diagnostic model. The performance of the model was measured using its area under the receiver operating characteristic curve. Immune cell infiltration was investigated using the CIBERSORT algorithm. A total of 96 DEGs were identified. By utilizing a RF classifier, a set of 14 signature genes that are pivotal in transcription regulation and disease progression in pSS were identified. Through the utilization of training and testing datasets, diagnostic models for pSS were successfully designed using ANN, RF, and SVM, resulting in AUCs of 0.972, 1.00, and 0.9742, respectively. The validation set yielded AUCs of 0.766, 0.8321, and 0.8223. It was the RF model that produced the best prediction performance out of the three models tested. As a result, an early predictive model for pSS was successfully developed with high diagnostic performance, providing a valuable resource for the screening and early diagnosis of pSS.

Postoperative Relapse Prediction in Patients With Ewing Sarcoma Using Computed Tomography-Based Radiomics Models Covering Tumor Per Se and Peritumoral Signatures.

We aimed to develop and validate a computed tomography (CT)-based radiomics model for early relapse prediction in patients with Ewing sarcoma (ES). We recruited 104 patients in this study. Tumor areas and areas with a tumor expansion of 3 mm were used as regions of interest for radiomics analysis. Six different models were constructed: Pre-CT, CT enhancement (CTE), Pre-CT +3 mm , CTE +3 mm , Pre-CT and CTE combined (ComB), and Pre-CT +3 mm and CTE +3 mm combined (ComB +3 mm ). All 3 classifiers used a grid search with 5-fold cross-validation to identify their optimal parameters, followed by repeat 5-fold cross-validation to evaluate the model performance based on these parameters. The average performance of the 5-fold cross-validation and the best one-fold performance of each model were evaluated. The AUC (area under the receiver operating characteristic curve) and accuracy were calculated to evaluate the models. The 6 radiomics models performed well in predicting relapse in patients with ES using the 3 classifiers; the ComB and ComB +3 mm models performed better than the other models (AUC -best : 0.820-0.922/0.823-0.833 and 0.799-0.873/0.759-0.880 in the training and validation cohorts, respectively). Although the Pre-CT +3 mm , CTE +3 mm, and ComB +3 mm models covering tumor per se and peritumoral CT features preoperatively forecasted ES relapse, the model was not significantly improved. The radiomics model performed well for early recurrence prediction in patients with ES, and the ComB and ComB +3 mm models may be superior to the other models.

Performance Analysis and Assessment of Type 2 Diabetes Screening Scores in Patients with Non-Alcoholic Fatty Liver Disease

Type 2 diabetes (T2D) and non-alcoholic fatty liver disease (NAFLD) are worldwide chronic diseases that have strong relationships with one another and commonly exist together. Type 2 diabetes is considered one of the risk factors for NAFLD, so its occurrence in people with NAFLD is highly likely. As the high and increasing number of T2D and NAFLD, which potentially followed by existing together number, an analysis and assessment of T2D screening scores in people with NAFLD is necessary to be done. To prevent this potential case, an effective early prediction model is also required to be developed, which could help the patients avoid the dangers of both existing diseases. Therefore, in this study, analysis and assessment of T2D screening scores in people with NAFLD and the early prediction model utilizing a forward logistic regression-based feature selection method and multi-layer perceptrons are proposed. Our analysis and assessment results showed that the prevalence of T2D among patients with NAFLD was 8.13% (for prediabetes) and 37.19% (for diabetes) in two population-based NAFLD datasets. The variables related to clinical tests, such as alanine aminotransferase (ALT), aspartate aminotransferase (AST), alkaline phosphatase (ALP), gamma-glutamyl transferase (GGT), and systolic blood pressure (SBP), were found to be statistically significant predictors (p-values &lt; 0.001) that indicate a strong association with T2D among patients with NAFLD in both the prediabetes and diabetes NAFLD datasets. Finally, our proposed model showed the best performance in terms of all performance evaluation metrics compared to existing various machine learning models and also the models using variables recommended by WHO/CDC/ADA, with achieved accuracy as much as 92.11% and 83.05% and its improvement scores after feature selection of 1.35% and 5.35%, for the first and second dataset, respectively.