On the enrichment of time series with textual data for forecasting agricultural commodity prices

Filho, Ivan J. Reis; Marcacini, Ricardo Marcondes; Rezende, Solange Oliveira

doi:10.1016/j.mex.2022.101758

Cited by 5 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Screening features to further reduce the number of features used to generate predictive models can help mitigate the risk of model overfitting [ 27 ]. Among several feature selection methods, we focus on the feature-based ranking method, which ranks each feature in descending order of importance, and we consider the following methods.…”

Section: Methodsmentioning

confidence: 99%

Machine learning methods for adult OSAHS risk prediction

Ge,

Wu,

et al. 2024

BMC Health Serv Res

View full text Add to dashboard Cite

Background Obstructive sleep apnea hypopnea syndrome (OSAHS) is a common disease that can cause multiple organ damage in the whole body. Our aim was to use machine learning (ML) to build an independent polysomnography (PSG) model to analyze risk factors and predict OSAHS. Materials and methods Clinical data of 2064 snoring patients who underwent physical examination in the Health Management Center of the First Affiliated Hospital of Shanxi Medical University from July 2018 to July 2023 were retrospectively collected, involving 24 characteristic variables. Then they were randomly divided into training group and verification group according to the ratio of 7:3. By analyzing the importance of these features, it was concluded that LDL-C, Cr, common carotid artery plaque, A1c and BMI made major contributions to OSAHS. Moreover, five kinds of machine learning algorithm models such as logistic regression, support vector machine, Boosting, Random Forest and MLP were further established, and cross validation was used to adjust the model hyperparameters to determine the final prediction model. We compared the accuracy, Precision, Recall rate, F1-score and AUC indexes of the model, and finally obtained that MLP was the optimal model with an accuracy of 85.80%, Precision of 0.89, Recall of 0.75, F1-score of 0.82, and AUC of 0.938. Conclusion We established the risk prediction model of OSAHS using ML method, and proved that the MLP model performed best among the five ML models. This predictive model helps to identify patients with OSAHS and provide early, personalized diagnosis and treatment options.

show abstract

Section: Methodsmentioning

confidence: 99%