OBJECTIVE To construct a predictive model for evaluating the efficacy of a triple antiemetic regimen （neurokinin- 1 receptor antagonist+5-hydroxytryptamine 3 receptor antagonist+dexamethasone） for preventing nausea and vomiting induced by highly emetogenic chemotherapy （HEC） based on interpretable deep learning algorithms. METHODS Clinical data of cancer patients who received HEC and were treated with the standard triple antiemetic regimen in the oncology department of Tianjin Medical University General Hospital from January 2018 to December 2022 were collected retrospectively. Demographic， clinical and metabolism-related variables were integrated. After data pre-processing， two deep learning algorithms （deep random forest and dense neural network） and four machine learning algorithms （support vector machine， categorical boosting， random forest and decision tree） were used to build predictive models. Subsequently， model performance evaluation and model interpretability analysis were conducted. RESULTS Among the six candidate models， the deep random forest model demonstrated the best predictive performance on the test set， with an area under the receiver operating characteristic curve of 0.850， an accuracy of 0.911， a precision of 0.805， a recall of 0.783， an F1 score of 0.793， and a Brier score of 0.075. Interpretability analysis revealed that creatinine clearance rate （Ccr） was the key predictive factor， and low Ccr levels， female gender， younger age， highly emetogenic drugs （particularly cisplatin-containing chemotherapy regimens）， and anticipatory nausea and vomiting were positively correlated with the risk of HEC-related nausea and vomiting. CONCLUSIONS The deep random forest model exhibits the best performance in predicting the efficacy of triple antiemetic regimen for preventing HEC-related nausea and vomiting. The key predictors in this model primarily include Ccr，anticipatory nausea and vomiting， gender， age， and highly emetogenic drugs.

The incidence rate of thyroid cancer has been rising in recent years. How to accurately distinguish malignant and benign thyroid nodules before surgery has become an important research direction. Ultrasound, as a non-invasive and fast examination method, has been widely used in clinical practice. Some typical ultrasound features, such as calcification, unclear boundaries, multiple lesions, low echo, and aspect ratio>1, can indicate the occurrence of thyroid cancer before surgery. Further analysis of these ultrasound features is still a focus of current research. This article will review the expression and distribution of calcification, a typical ultrasound feature, in benign and malignant thyroid nodules, in order to provide a basis for predicting the malignancy of thyroid nodules based on the characteristics of calcification under preoperative ultrasound.

Previous studies have shown that hepatitis E virus （HEV） infection in pregnancy can cause liver failure and adverse pregnancy outcomes such as miscarriage， stillbirth， and vertical transmission， especially in countries where HEV genotypes 1 and 2 are prevalent. In recent years， HEV infection in China is sporadic and is mainly caused by HEV genotype 4， and although studies have shown that most pregnant women with HEV infection in China have no signfinicant clinical symptoms， there is still a high incidence rate of adverse pregnancy outcomes. This article reviews the recent studies on HEV infection in pregnancy， including the advances in pathogenesis， epidemiology， prognosis， mechanism of severe exacerbation， treatment， and prognosis， and puts forward recommendations for the screening and evaluation of HEV infection in pregnancy.

Objective: To investigate the milk drinking behavior and bone mineral density level of pupils in Hainan Province, and to explore the correlation between bone mineral density and milk drinking behavior, in order to provide scientific basis for promoting the healthy development of bones in children and adolescents. Methods: In November 2021, a cross sectional survey including demographic characteristics, milk intake, unhealthy eating behavior, physical activity and sleep was conducted among 696 students from grades 3 to 5 in Sanya and Baisha, Hainan by stratified cluster random sampling, and bone mineral density at the distal 1/3 of the right forearm was measured by dual energy X-ray absorptiometry. t-test was used to compare the differences in bone mineral density among different milk drinking behaviors of pupils, and multiple linear regression was used to analyze the correlation between milk consumption and bone mineral density. Results: About 25.3% students consumed milk daily and 13.9% consumed ≥ 300 g of milk daily. The mean bone mineral density at the distal 1/3 of the right forearm was (0.237±0.041)g/cm 2. The bone mineral density was greater in the group with daily milk intake than in the group without daily milk intake [(0.250± 0.037 )(0.204±0.034) g/cm 2 , t=15.00, P <0.01], and the bone mineral density was greater in the group with daily average milk intake ≥300 g than in the group with daily average milk intake <300 g [(0.284±0.036)(0.229±0.037)g/cm 2, t=13.48, P < 0.01 ]. Multiple linear regression analysis showed that daily average milk intake was positively correlated with bone mineral density, with a correlation coefficient ( β=0.020, t=21.46, P <0.01). Conclusion Milk consumption among pupils is inadequate, and milk drinking behavior has a positive impact on bone mineral density, so effective milk drinking intervention should be carried out to promote children s bone development.