A multi-granularity convolutional neural network model with temporal information and attention mechanism for efficient diabetes medical cost prediction

Luo, Min; Wang, Yiting; Wang, Xiaokang; Hou, Wenhua; Huang, Rui-lu; Liu, Ye; Wang, Jian‐qiang

doi:10.1016/j.compbiomed.2022.106246

Cited by 9 publications

(2 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The cross-validation set was evaluated by adjusting the hyperparameters to obtain a reliable and stable model. Feature selection plays an important role in choosing to predict time granularity [9]. For example, short-term fluctuations can be captured by adding the variables "is it a holiday" and "is it a promotion day".…”

Section: Characteristic Importance Predicted By Weekmentioning

confidence: 99%

Product order-demand prediction model based on random forest

Wang,

Zhang,

Zhao

et al. 2023

HBEM

View full text Add to dashboard Cite

This study aims to develop a decision support model based on product order data analysis and demand forecasting. By analyzing the shipment data of a large manufacturing enterprise from September 2015 to December 2018, we establish an accurate prediction model for the demand in the next three months of a large manufacturing enterprise. Quarterly and monthly variables capture trends and seasonal variation by adjusting hyperparameters and cross-validation using a random forest algorithm. The results show that the mean absolute error (MAE) on the test set is 8.965, the root mean square error (RMSE) is 11.369, the relative mean absolute error (MAPE) is 8.256%, and the coefficient of determination (R²) is 0.826. These indicators confirm that the model can accurately predict the target variable, with little difference from the true value, and show good predictive power and fit. The monthly model has high accuracy and stability and can effectively support production and supply chain planning to meet future needs. This study confirms the potential of product order data analysis and demand prediction models to improve the efficiency and competitiveness of enterprises and provides a valuable reference for the research and practice in related fields.

show abstract

Section: Characteristic Importance Predicted By Weekmentioning

confidence: 99%

Product order-demand prediction model based on random forest

Wang,

Zhang,

Zhao

et al. 2023

HBEM

View full text Add to dashboard Cite

show abstract

“…Recent studies have focused on improving the accuracy of hospital bill prediction using arti cial neural networks and deep neural network-based learning techniques, such as convolutional neural networks and recurrent neural networks. These techniques have been applied to large datasets to predict the cost of hospitalization for speci c diseases and conditions [18,19]. Moreover, literature suggests that various factors including patient demographics, medical history, and length of stay are strongly correlated with accurate estimates of hospital bills.…”

Section: Introductionmentioning

confidence: 99%

Enhancing Accuracy in Pediatric Inpatient Hospital Cost Estimation: A Machine Learning-Based Approach

Zafar,

Hajiani,

Affan

et al. 2023

Preprint

View full text Add to dashboard Cite

Purpose: Accurately estimating inpatient billing costs during admission is important for financial planning in healthcare. Traditional methods have limitations in capturing true cost; hence, data-driven approaches are needed to improve hospital cost estimation in complex and dynamic environments. The main objective of this study is to predict a deviation between the initial hospital bill estimate and the actual bill charged at the time of discharge. This study is also focused on identifying the major factors contributing towards the cost of hospital stay. Methods This study utilized dataset of approximately 22,000 pediatric patients (under 18 years of age). The main features of the dataset included medical conditions, hospital administration details, and socio-demographic information. The methodology utilizes named entity recognition techniques to extract structured data from unstructured textual data. Subsequently, a variety of machine learning classification models are trained and tested to predict deviations in hospital bill estimates. Results: The boosting ensemble and artificial neural network classifier models performed best in predicting the deviations in the billing cost, with best accuracy, AUC and F1-scores of 80%, 77% and 77% respectively. The analysis of the important features revealed that age, length of stay, financial status of patients as main features to predict deviation in hospital bill estimates. Conclusions: The results obtained from our study demonstrate that leveraging machine learning techniques provides a reliable and efficient means of improving the performance of hospital billing estimations. These findings have significant implications for healthcare practitioners, enabling them to make more informed decisions and allocate resources effectively.

show abstract