Mean parotid dose prediction model using machine learning regression method for intensity-modulated radiotherapy in head and neck cancer

Economic burden and influence factors among hospitalized children with bronchiolitis or pneumonia: a multiregional study in China

Background

Bronchiolitis and pneumonia are both significant lower respiratory tract infections with a profound impact on children's health. The purpose of this study is to explore the economic burden and related influence factors of pediatric patients with bronchiolitis and pneumonia in China.

Methods

A face-to-face interview was employed for the investigation of hospitalized patients (≤5 years old) with bronchiolitis and pneumonia, along with their guardians from January to October 2019. Demographic and costs were collected from Shanghai, Zhengzhou, and Kunming, representing three regions with different levels of economic development in China. Multiple linear regression analysis was used to explore factors associated with the economic burden of the diseases.

Results

A total of 338 patients with bronchiolitis and 529 patients with pneumonia were included in the analysis. The average hospitalization and total cost for patients with bronchiolitis are 4,162 CNY and 5,748 CNY, respectively, while those with pneumonia are 6,096 CNY and 7,783 CNY. Patients from Shanghai, both bronchiolitis and pneumonia, exhibited the lowest cost expenditures, with average total costs of 3,531 CNY and 3,488 CNY, respectively. Multiple regression analysis indicated that, among bronchiolitis patients, factors such as region, medical insurance, relationship, loss of work time, and length of stay were found to be significantly associated with both hospitalization cost and total cost (p < 0.05). For pneumonia patients, the hospitalization cost and total cost were significantly impacted by region, medical insurance, and length of stay (p < 0.05).

Conclusion

Bronchiolitis and pneumonia in children put substantial economic burden on families of affected children. The financial strain varies significantly across different regions, with families in underdeveloped areas and those dealing with pneumonia facing particularly daunting challenges. Targeted policies to reduce healthcare costs and improve insurance coverage, especially in economically disadvantaged regions are needed.

Application and progress of artificial intelligence in radiation therapy dose prediction

Radiation therapy (RT) nowadays is a main treatment modality of cancer. To ensure the therapeutic efficacy of patients, accurate dose distribution is often required, which is a time-consuming and labor-intensive process. In addition, due to the differences in knowledge and experience among participants and diverse institutions, the predicted dose are often inconsistent. In last several decades, artificial intelligence (AI) has been applied in various aspects of RT, several products have been implemented in clinical practice and confirmed superiority. In this paper, we will review the research of AI in dose prediction, focusing on the progress in deep learning (DL).

An artificial neural network based approach for predicting the proton beam spot dosimetric characteristics of a pencil beam scanning technique

Utilising Machine Learning (ML) models to predict dosimetric parameters in pencil beam scanning proton therapy presents a promising and practical approach. The study developed Artificial Neural Network (ANN) models to predict proton beam spot size and relative positional errors using 9000 proton spot data. The irradiation log files as input variables and corresponding scintillation detector measurements as the label values. The ANN models were developed to predict six variables: spot size in thex-axis,y-axis, major axis, minor axis, and relative positional errors in thex-axis andy-axis. All ANN models used a Multi-layer perception (MLP) network using one input layer, three hidden layers, and one output layer. Model performance was validated using various statistical tools. The log file recorded spot size and relative positional errors, which were compared with scintillator-measured data. The Root Mean Squared Error (RMSE) values for the x-spot and y-spot sizes were 0.356 mm and 0.362 mm, respectively. Additionally, the maximum variation for the x-spot relative positional error was 0.910 mm, while for the y-spot, it was 1.610 mm. The ANN models exhibit lower prediction errors. Specifically, the RMSE values for spot size prediction in the x, y, major, and minor axes are 0.053 mm, 0.049 mm, 0.053 mm, and 0.052 mm, respectively. Additionally, the relative spot positional error prediction model for the x and y axes yielded maximum errors of 0.160 mm and 0.170 mm, respectively. The normality of models was validated using the residual histogram and Q-Q plot. The data over fit, and bias were tested using K (k = 5) fold cross-validation, and the maximum RMSE value of the K fold cross-validation among all the six ML models was less than 0.150 mm (R-Square 0.960). All the models showed excellent prediction accuracy. Accurately predicting beam spot size and positional errors enhances efficiency in routine dosimetric checks.

Development of Prediction Model for Mean Parotid Dose of HNC Undergoing Radiotherapy - A Single Institutional Study

Aim

The aim of the study was to develop a simple prediction model based on previous treatment plans for head-and-neck cancer (HNC).

Materials and Methods

This study was conducted on 95 patients who underwent volumetric-modulated arc therapy (VMAT) with curative intent for HNC at our institute between January 2016 and December 2022 with intact bilateral parotid glands. Two simple prediction models were used: one linear regression model and one exponential model. Both models use fractional overlapping parotid volume with planning target volume (PTV) as a predictor of mean parotid dose. The fractional overlapping volume was calculated as the difference between the volume of the parotid gland minus the volume of the parotid gland outside the PTV plus a 2 mm margin, divided by the volume of the parotid gland. Statistical calculations were done using data analysis tools and Solver in Microsoft Excel (Microsoft Office 2013, Redmond, WA, USA). To enhance the accuracy of the results, outliers were excluded with residuals >2 standard deviations below and above the residuals. R2 and root-mean-square error were calculated for both models to evaluate the quality of the predictions. The normality of both models' residuals was validated using the Shapiro-Wilk test.

Results

Both linear and exponential prediction models exhibited strong correlation statistics, with r2 = 0.85 and 0.82, respectively. The authors found a fractional overlap of 16.4% and 18.9% in linear and exponential models that predict parotid mean dose 26 Gy. The implementation was carried out on a cohort of 12 prospective patients, demonstrating a remarkable improvement in minimizing the dose to the parotid glands.

Conclusion

In this single-institutional study, the authors successfully developed a prediction model for mean parotid dose in HNC patients undergoing radiotherapy. The model showed promising accuracy and has the potential to assist planners in optimizing treatment plans and minimizing radiation-related toxicity. It is possible to avoid under sparing the organs at risks in some cases and wasting time or effort on physically impossible goals in others using this prediction model. As a result, planning resources can be used much more efficiently. Future studies should focus on validating the model's performance using external datasets and exploring its integration into clinical practice.

Economic Burden and Influencing Factors of Acute Gastroenteritis in China: A Population-Based Face to Face Survey in 2018

Background

Acute gastroenteritis is an important and highly prevalent public health problem worldwide. The purpose of this study was to assess the economic burden of disease and its influencing factors in patients with acute gastroenteritis in Heilongjiang Province, China.

Methods

A multi-stage stratified random sampling method was used in a face-to-face household survey in 2018. Demographic and socioeconomic characteristics, clinical symptoms, suspicious dietary history, and disease treatment information were collected from 19,647 respondents. One-way analysis of variance and multiple stepwise regression analysis were used to investigate the factors associated with the economic burden of acute gastroenteritis. Quantitative risk analysis and sensitivity analysis were performed to estimate the uncertainty and risk factors of the economic burden of acute gastroenteritis.

Results

The total economic burden of patients with acute gastroenteritis was 63,969.22 CNY (Chinese Yuan), of which the direct economic burden accounted for 63.82%; the per capita economic burden was 131.35 CNY per month. Age, region, disease duration, and disease treatment were the main factors significantly associated with the economic burden of acute gastroenteritis (P &lt; 0.05). The average economic burden of patients with acute gastroenteritis was approximately 571.84 CNY/person (95% CI: 227–1,459). Sensitivity analysis showed that the greatest impact was from the indirect economic burden.

Conclusions

Acute gastroenteritis brings a substantial health burden to patients due to its high incidence. The economic burden of self-purchased drugs and the indirect economic burden of patients cannot be ignored. To better estimate the economic burden of acute gastroenteritis in China, further studies on the pathogen-specific economic burden of acute gastroenteritis are required.

The Clinical Outcomes, Prognostic Factors and Nomogram Models for Primary Lung Cancer Patients Treated With Stereotactic Body Radiation Therapy

PURPOSE

Stereotactic body radiation therapy (SBRT) is a standard treatment for early primary lung cancer patients. However, there are few simple models for predicting the clinical outcomes of these patients. Our study analyzed the clinical outcomes, identified the prognostic factors, and developed prediction nomogram models for these patients.

MATERIALS AND METHODS

We retrospectively analyzed 114 patients with primary lung cancer treated with SBRT from 2012 to 2020 at our institutions and assessed patient's clinical outcomes and levels of toxicity. Kaplan-Meier analysis with a log-rank test was used to generate the survival curve. The cut-off values of continuous factors were calculated with the X-tile tool. Potential independent prognostic factors for clinical outcomes were explored using cox regression analysis. Nomograms for clinical outcomes prediction were established with identified factors and assessed by calibration curves.

RESULTS

The median overall survival (OS) was 40.6 months, with 3-year OS, local recurrence free survival (LRFS), distant disease-free survival (DDFS) and progression free survival (PFS) of 56.3%, 61.3%, 72.9% and 35.8%, respectively, with grade 3 or higher toxicity rate of 7%. The cox regression analysis revealed that the clinical stage, immobilization device, and the prescription dose covering 95% of the target area (D95) were independent prognostic factors associated with OS. Moreover, the clinical stage, and immobilization device were independent prognostic factors of LRFS and PFS. The smoking status, hemoglobin (Hb) and immobilization device were significant prognostic factors for DDFS. The nomograms and calibration curves incorporating the above factors indicated good predictive accuracy.

CONCLUSIONS

SBRT is effective and safe for primary lung cancer. The prognostic factors associated with OS, LRFS, DDFS and PFS are proposed, and the nomograms we proposed are suitable for clinical outcomes prediction.

Multi-constraint generative adversarial network for dose prediction in radiotherapy

Radiation therapy (RT) is regarded as the primary treatment for cancer in the clinic, aiming to deliver an accurate dose to the planning target volume (PTV) while protecting the surrounding organs at risk (OARs). To improve the effectiveness of the treatment planning, deep learning methods are widely adopted to predict dose distribution maps for clinical treatment planning. In this paper, we present a novel multi-constraint dose prediction model based on generative adversarial network, named Mc-GAN, to automatically predict the dose distribution map from the computer tomography (CT) images and the masks of PTV and OARs. Specifically, the generator is an embedded UNet-like structure with dilated convolution to capture both the global and local information. During the feature extraction, a dual attention module (DAM) is embedded to force the generator to take more heed of internal semantic relevance. To improve the prediction accuracy, two additional losses, i.e., the locality-constrained loss (LCL) and the self-supervised perceptual loss (SPL), are introduced besides the conventional global pixel-level loss and adversarial loss. Concretely, the LCL tries to focus on the predictions of locally important areas while the SPL aims to prevent the predicted dose maps from the possible distortion at the feature level. Evaluated on two in-house datasets, our proposed Mc-GAN has been demonstrated to outperform other state-of-the-art methods in almost all PTV and OARs criteria.