Alzheimer\'s disease is a type of neurodegenerative disorder that is characterized by the progressive degeneration of brain cells, leading to cognitive decline and memory loss. It is the most common cause of dementia and affects millions of people worldwide. While there is currently no cure for Alzheimer\'s disease, early detection and treatment can help to slow the progression of symptoms and improve quality of life. This research presents a diagnostic tool for classifying mild cognitive impairment and Alzheimer\'s diseases using feature-based machine learning applied to optical coherence tomographic angiography images (OCT-A). Several features are extracted from the OCT-A image, including vessel density in five sectors, the area of the foveal avascular zone, retinal thickness, and novel features based on the histogram of the range-filtered OCT-A image. To ensure effectiveness for a diverse population, a large local database for our study was collected. The promising results of our study, with the best accuracy of 92.17,% will provide an efficient diagnostic tool for early detection of Alzheimer\'s disease.

The histological grade of oral squamous cell carcinoma affects the prognosis. In the present study, we performed a radiomics analysis to extract features from 18F-FDG PET image data, created machine learning models from the features, and verified the accuracy of the prediction of the histological grade of oral squamous cell carcinoma. The subjects were 191 patients in whom an 18F-FDG-PET examination was performed preoperatively and a histopathological grade was confirmed after surgery, and their tumor sizes were sufficient for a radiomics analysis. These patients were split in a 70%/30% ratio for use as training data and testing data, respectively. We extracted 2993 radiomics features from the PET images of each patient. Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Naïve Bayes (NB), and K-Nearest Neighbor (KNN) machine learning models were created. The areas under the curve obtained from receiver operating characteristic curves for the prediction of the histological grade of oral squamous cell carcinoma were 0.72, 0.71, 0.84, 0.74, and 0.73 for LR, SVM, RF, NB, and KNN, respectively. We confirmed that a PET radiomics analysis is useful for the preoperative prediction of the histological grade of oral squamous cell carcinoma.

There is a complex high-dimensional nonlinear mapping relationship between the compressive strength of High-Performance Concrete (HPC) and its components, which has great influence on the accurate prediction of compressive strength. In this paper, an efficient robust software calculation strategy combining BP Neural Network (BPNN), Support Vector Machine (SVM) and Genetic Algorithm (GA) is proposed for the prediction of compressive strength of HPC. 8 features were extracted from the previous literature, and a compressive strength database containing 454 sets of data was constructed. The model was trained and tested, and the performance of 4 Machine Learning (ML) models, namely BPNN, SVM, GA-BPNN and GA-SVM, was compared. The results show that the coupled model is superior to the single model. Moreover, because GA-SVM has better generalization ability and theoretical basis, its convergence speed and prediction accuracy are better than GA-BPNN. Then Grey Relational Analysis (GRA) and Shapley analysis were used to verify the interpretability of the GA-SVM model, which showed that the water-binder ratio had the most significant influence on the compressive strength. Finally, the combination of multiple input variables to evaluate the compressive strength supplemented this research, and again verified the significant influence of water-binder ratio, providing reference value for subsequent research.

BACKGROUND: Preoperative evaluation is important, and this study explored the application of machine learning methods for anesthetic risk classification and the evaluation of the contributions of various factors. To minimize the effects of confounding variables during model training, we used a homogenous group with similar physiological states and ages undergoing similar pelvic organ-related procedures not involving malignancies.
OBJECTIVE: Data on women of reproductive age (age 20-50 years) who underwent gestational or gynecological surgery between January 1, 2017, and December 31, 2021, were obtained from the National Taiwan University Hospital Integrated Medical Database.
METHODS: We first performed an exploratory analysis and selected key features. We then performed data preprocessing to acquire relevant features related to preoperative examination. To further enhance predictive performance, we used the log-likelihood ratio algorithm to generate comorbidity patterns. Finally, we input the processed features into the light gradient boosting machine (LightGBM) model for training and subsequent prediction.
RESULTS: A total of 10,892 patients were included. Within this data set, 9893 patients were classified as having low anesthetic risk (American Society of Anesthesiologists physical status score of 1-2), and 999 patients were classified as having high anesthetic risk (American Society of Anesthesiologists physical status score of >2). The area under the receiver operating characteristic curve of the proposed model was 0.6831.
CONCLUSIONS: By combining comorbidity information and clinical laboratory data, our methodology based on the LightGBM model provides more accurate predictions for anesthetic risk classification.
BACKGROUND: Research Ethics Committee of the National Taiwan University Hospital 202204010RINB; https://www.ntuh.gov.tw/RECO/Index.action.

BACKGROUND: Identifying individuals with depressive symptomatology (DS) promptly and effectively is of paramount importance for providing timely treatment. Machine learning models have shown promise in this area; however, studies often fall short in demonstrating the practical benefits of using these models and fail to provide tangible real-world applications.
OBJECTIVE: This study aims to establish a novel methodology for identifying individuals likely to exhibit DS, identify the most influential features in a more explainable way via probabilistic measures, and propose tools that can be used in real-world applications.
METHODS: The study used 3 data sets: PROACTIVE, the Brazilian National Health Survey (Pesquisa Nacional de Saúde [PNS]) 2013, and PNS 2019, comprising sociodemographic and health-related features. A Bayesian network was used for feature selection. Selected features were then used to train machine learning models to predict DS, operationalized as a score of ≥10 on the 9-item Patient Health Questionnaire. The study also analyzed the impact of varying sensitivity rates on the reduction of screening interviews compared to a random approach.
RESULTS: The methodology allows the users to make an informed trade-off among sensitivity, specificity, and a reduction in the number of interviews. At the thresholds of 0.444, 0.412, and 0.472, determined by maximizing the Youden index, the models achieved sensitivities of 0.717, 0.741, and 0.718, and specificities of 0.644, 0.737, and 0.766 for PROACTIVE, PNS 2013, and PNS 2019, respectively. The area under the receiver operating characteristic curve was 0.736, 0.801, and 0.809 for these 3 data sets, respectively. For the PROACTIVE data set, the most influential features identified were postural balance, shortness of breath, and how old people feel they are. In the PNS 2013 data set, the features were the ability to do usual activities, chest pain, sleep problems, and chronic back problems. The PNS 2019 data set shared 3 of the most influential features with the PNS 2013 data set. However, the difference was the replacement of chronic back problems with verbal abuse. It is important to note that the features contained in the PNS data sets differ from those found in the PROACTIVE data set. An empirical analysis demonstrated that using the proposed model led to a potential reduction in screening interviews of up to 52% while maintaining a sensitivity of 0.80.
CONCLUSIONS: This study developed a novel methodology for identifying individuals with DS, demonstrating the utility of using Bayesian networks to identify the most significant features. Moreover, this approach has the potential to substantially reduce the number of screening interviews while maintaining high sensitivity, thereby facilitating improved early identification and intervention strategies for individuals experiencing DS.

The incidence of Alzheimer\'s disease (AD) is rising globally, yet its treatment and prediction of this condition remain challenging due to the complex pathophysiological mechanisms associated with it. Consequently, the objective of the present study was to analyze and characterize the molecular mechanisms underlying ferroptosis‑related genes (FEGs) in the pathogenesis of AD, as well as to construct a prognostic model. The findings will provide new insights for the future diagnosis and treatment of AD. First, the AD dataset GSE33000 from the Gene Expression Omnibus database and the FEGs from FerrDB were obtained. Next, unsupervised cluster analysis was used to obtain the FEGs that were most relevant to AD. Subsequently, enrichment analyses were performed on the FEGs to explore biological functions. Subsequently, the role of these genes in the immune microenvironment was elucidated through CIBERSORT. Then, the optimal machine learning was selected by comparing the performance of different machine learning models. To validate the prediction efficiency, the models were validated using nomograms, calibration curves, decision curve analysis and external datasets. Furthermore, the expression of FEGs between different groups was verified using reverse transcription quantitative PCR and western blot analysis. In AD, alterations in the expression of FEGs affect the aggregation and infiltration of certain immune cells. This indicated that the occurrence of AD is strongly associated with immune infiltration. Finally, the most appropriate machine learning models were selected, and AD diagnostic models and nomograms were built. The present study provided novel insights that enhance understanding with regard to the molecular mechanism of action of FEGs in AD. Moreover, the present study provided biomarkers that may facilitate the diagnosis of AD.

Pollen collected by pollinators can be used as a marker of the foraging behavior as well as indicate the botanical species present in each environment. Pollen intake is essential for pollinators\' health and survival. During the foraging activity, some pollinators, such as honeybees, manipulate the collected pollen mixing it with salivary secretions and nectar (corbicular pollen) changing the pollen chemical profile. Different tools have been developed for the identification of the botanical origin of pollen, based on microscopy, spectrometry, or molecular markers. However, up to date, corbicular pollen has never been investigated. In our work, corbicular pollen from 5 regions with different climate conditions was collected during spring. Pollens were identified with microscopy-based techniques, and then analyzed in MALDI-MS. Four different chemical extraction solutions and two physical disruption methods were tested to achieve a MALDI-MS effective protocol. The best performance was obtained using a sonication disruption method after extraction with acetic acid or trifluoroacetic acid. Therefore, we propose a new rapid and reliable methodology for the identification of the botanical origin of the corbicular pollens using MALDI-MS. This new approach opens to a wide range of environmental studies spanning from plant biodiversity to ecosystem trophic interactions.

The risk of cholangitis after ERCP implantation in malignant obstructive jaundice patients remains unknown. To develop models based on artificial intelligence methods to predict cholangitis risk more accurately, according to patients after stent implantation in patients\' MOJ clinical data. This retrospective study included 218 patients with MOJ undergoing ERCP surgery. A total of 27 clinical variables were collected as input variables. Seven models (including univariate analysis and six machine learning models) were trained and tested for classified prediction. The model\' performance was measured by AUROC. The RFT model demonstrated excellent performances with accuracies up to 0.86 and AUROC up to 0.87. Feature selection in RF and SHAP was similar, and the choice of the best variable subset produced a high performance with an AUROC up to 0.89. We have developed a hybrid machine learning model with better predictive performance than traditional LR prediction models, as well as other machine learning models for cholangitis based on simple clinical data. The model can assist doctors in clinical diagnosis, adopt reasonable treatment plans, and improve the survival rate of patients.

Reference evapotranspiration (ET0 ) is a significant parameter for efficient irrigation scheduling and groundwater conservation. Different machine learning models have been designed for ET0 estimation for specific combinations of available meteorological parameters. However, no single model has been suggested so far that can handle diverse combinations of available meteorological parameters for the estimation of ET0. This article suggests a novel architecture of an improved hybrid quasi-fuzzy artificial neural network (ANN) model (EvatCrop) for this purpose. EvatCrop yielded superior results when compared with the other three popular models, decision trees, artificial neural networks, and adaptive neuro-fuzzy inference systems, irrespective of study locations and the combinations of input parameters. For real-field case studies, it was applied in the groundwater-stressed area of the Terai agro-climatic region of North Bengal, India, and trained and tested with the daily meteorological data available from the National Centres for Environmental Prediction from 2000 to 2014. The precision of the model was compared with the standard Penman-Monteith model (FAO56PM). Empirical results depicted that the model performances remarkably varied under different data-limited situations. When the complete set of input parameters was available, EvatCrop resulted in the best values of coefficient of determination (R2 = 0.988), degree of agreement (d = 0.997), root mean square error (RMSE = 0.183), and root mean square relative error (RMSRE = 0.034).

UNASSIGNED: This study aimed to explore specific biochemical indicators and construct a risk prediction model for diabetic kidney disease (DKD) in patients with type 2 diabetes (T2D).
UNASSIGNED: This study included 234 T2D patients, of whom 166 had DKD, at the First Hospital of Jilin University from January 2021 to July 2022. Clinical characteristics, such as age, gender, and typical hematological parameters, were collected and used for modeling. Five machine learning algorithms [Extreme Gradient Boosting (XGBoost), Gradient Boosting Machine (GBM), Support Vector Machine (SVM), Logistic Regression (LR), and Random Forest (RF)] were used to identify critical clinical and pathological features and to build a risk prediction model for DKD. Additionally, clinical data from 70 patients (nT2D = 20, nDKD = 50) were collected for external validation from the Third Hospital of Jilin University.
UNASSIGNED: The RF algorithm demonstrated the best performance in predicting progression to DKD, identifying five major indicators: estimated glomerular filtration rate (eGFR), glycated albumin (GA), Uric acid, HbA1c, and Zinc (Zn). The prediction model showed sufficient predictive accuracy with area under the curve (AUC) values of 0.960 (95% CI: 0.936-0.984) and 0.9326 (95% CI: 0.8747-0.9885) in the internal validation set and external validation set, respectively. The diagnostic efficacy of the RF model (AUC = 0.960) was significantly higher than each of the five features screened with the highest feature importance in the RF model.
UNASSIGNED: The online DKD risk prediction model constructed using the RF algorithm was selected based on its strong performance in the internal validation.