Background: Central lymph node metastasis (CLNM) occurs frequently in patients with papillary thyroid cancer (PTC), but performing prophylactic central lymph node dissection is still controversial. There are no reliable models for predicting CLNM. This study aimed to develop predictive models for CLNM by machine learning (ML) algorithms. Methods: Patients with PTC who underwent initial thyroid resection at our hospital between January 2018 and December 2019 were enrolled. A total of 22 variables, including clinical characteristics and ultrasonography (US) features, were used for conventional univariate and multivariate analysis and to construct ML-based models. A 5-fold cross validation strategy was used for validation and a feature selection approach was applied to identify risk factors. Results: The areas under the receiver operating characteristic curve (AUC) of 7 models ranged from 0.680 to 0.731. All models performed significantly better than US (AUC=0.623) in predicting CLNM (P<0.05). In decision curve, most of the models also performed better than US. The gradient boosting decision tree model with 7 variables was identified as the best model because of its best performance in both ROC (AUC=0.731) and decision curves. Based on multivariate analysis and feature selection, young age, male sex, low serum thyroid peroxidase antibody and US features such as suspected lymph nodes, microcalcification and tumor size > 1.1 cm were the most contributing predictors for CLNM. Conclusions: It is feasible to develop predictive models of CLNM in PTC patients by incorporating clinical characteristics and US features. The ML algorithm may be a useful tool for the prediction of lymph node metastasis in thyroid cancer.

BACKGROUND The outbreak of coronavirus disease 2019 (COVID-19) happened in early December and it has affected China in more ways than one. The societal response to the pandemic restricted medical students to their homes. Although students cannot learn about COVID-19 through clinical practice, they can still pay attention to news of COVID-19 through various channels. Although, as suggested by previous studies, some medical students have already volunteered to serve during the COVID-19 pandemic, the overall willingness of Chinese medical students to volunteer for such has not been systematically examined. AIM To study Chinese medical students’ interest in the relevant knowledge on COVID-19 and what roles they want to play in the pandemic. METHODS Medical students at Peking Union Medical College were surveyed via a web-based questionnaire to obtain data on the extent of interest in the relevant knowledge on COVID-19, attitude towards volunteerism in the pandemic, and career preference. Logistic regression modeling was used to investigate possible factors that could encourage volunteerism among this group in a pandemic. RESULTS A total of 552 medical students responded. Most medical students showed a huge interest in COVID-19. The extent of students’ interest in COVID-19 varied among different student-classes ( P < 0.05). Senior students had higher scores than the other two classes. The number of people who were ‘glad to volunteer’ in COVID-19 represented 85.6% of the respondents. What these students expressed willingness to undertake involved direct, indirect, and administrative job activities. Logistic regression analysis identified two factors that negatively influenced volunteering in the pandemic: Student-class and hazards of the voluntary job. Factors that positively influenced volunteering were time to watch COVID-19 news, predictable impact on China, and moral responsibility. CONCLUSION More innovative methods can be explored to increase Chinese medical students’ interest in reading about the relevant knowledge on COVID-19 and doing voluntary jobs during the pandemic.

Background: Three-dimensional (3D) photography plays an important role in surgical planning and postoperative evaluation. Commercial 3D facial scanners are expensive, and they require patients to come to the clinics for 3D photography. To solve this problem, we developed an iPad/iPhone application to enable patients to capture 3D images of themselves on their own. This study aimed to evaluate the validity and reproducibility of this novel imaging system. Methods: 3D images were taken on 20 volunteers using the novel imaging system. Twenty-one anthropometric parameters were measured using calipers (direct measurement) and 3D photographs (3D photogrammetry). The results were compared to assess the accuracy and bias of 3D photogrammetry. The reproducibility was evaluated by testing intra-and interobserver reliabilities. Furthermore, 3D virtual models obtained by the novel imaging system and Vectra H1 camera were compared by performing heat map analysis. Results: The 3D photogrammetric results showed excellent correlations with direct measurements. Most anthropometric parameters did not show statistically significant differences between the two methods. The 95% limits of agreement exceeded 2 mm in some parameters, especially those with large numbers, although their relative error measurements were very small. Intra-and interobserver reliabilities were high enough to ensure good reproducibility. The comparison of 3D models obtained by the novel imaging system and Vectra H1 camera showed that the mean distance and the mean RMS were 0.08 and 0.67 mm, respectively. Conclusions: The novel 3D facial scanning system is validated to enable patients to take 3D images on their own. The imaging quality of the subnasale region needs further improvement. Future clinical applications include surgical planning, postoperative evaluation, and early diagnosis of diseases that affect facial appearance.

Background and Objectives: Total knee arthroplasty (TKA) is widely performed to improve mobility and quality of life for symptomatic knee osteoarthritis patients. The accurate prediction of patients' length of hospital stay (LOS) can help clinicians for rehabilitation decision-making and bed assignment planning, which thus makes full use of medical resources.Methods: Clinical characteristics were retrospectively collected from 1,298 patients who received TKA. A total of 36 variables were included to develop predictive models for LOS by multiple machine learning (ML) algorithms. The models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance and decision curve analysis (DCA) for clinical values. A feature selection approach was used to identify optimal predictive factors.Results: The areas under the ROC curve (AUCs) of the nine models ranged from 0.710 to 0.766. All the ML-based models performed better than models using conventional statistical methods in both ROC curves and decision curves. The random forest classifier (RFC) model with 10 variables introduced was identified as the best predictive model. The feature selection indicated the top five predictors: tourniquet time, distal femoral osteotomy thickness, osteoporosis, tibia component size, and post-operative values of Hb within 24 h.Conclusions: By analyzing clinical characteristics, it is feasible to develop ML-based models for the preoperative prediction of LOS for patients who received TKA, and the RFC model performed the best.

Background: Lymph node metastasis (LNM) is difficult to precisely predict before surgery in patients with early-T-stage non-small cell lung cancer (NSCLC). This study aimed to develop machine learning (ML)-based predictive models for LNM. Methods: Clinical characteristics and imaging features were retrospectively collected from 1,102 NSCLC ≤ 2 cm patients. A total of 23 variables were included to develop predictive models for LNM by multiple ML algorithms. The models were evaluated by the receiver operating characteristic (ROC) curve for predictive performance and decision curve analysis (DCA) for clinical values. A feature selection approach was used to identify optimal predictive factors. Results: The areas under the ROC curve (AUCs) of the 8 models ranged from 0.784 to 0.899. Some ML-based models performed better than models using conventional statistical methods in both ROC curves and decision curves. The random forest classifier (RFC) model with 9 variables introduced was identified as the best predictive model. The feature selection indicated the top five predictors were tumor size, imaging density, carcinoembryonic antigen (CEA), maximal standardized uptake value (SUV max), and age. Conclusions: By incorporating clinical characteristics and radiographical features, it is feasible to develop ML-based models for the preoperative prediction of LNM in early-T-stage NSCLC, and the RFC model performed best.

Background The lip is of important aesthetic value and highly subjected to aging. Collecting anthropometric baseline data and understanding age‐related changes of labial morphology can help with diagnosis of deformity, assessment of aging, and planning of cosmetic procedures. Many studies have focused on Caucasians, while there is a lack of anthropometric data on Chinese women. Methods A total of 169 women were enrolled in this cross‐sectional study and divided into four consecutive age groups. Linear distances, angles, and surface area data were obtained via stereophotogrammetry. Intergroup comparisons between different age groups were performed to find age‐related differences. Results Lip width significantly increased with age while philtrum width seemed to show no obvious change. Cutaneous upper and lower lip height increased, lengthening the lip in the vertical dimension. Decrease of upper vermilion height and changes in angles indicated that aging process shortened the upper vermilion and flattened the vermilion border. Surface area also showed age‐related changes. Intergroup comparison showed no statistical significance in most variables between 20s and 30s or 30s and 40s, while age‐related changes in some variables were significant between 40s and 50s. Conclusion This study provided anthropometric data of labial morphology across a wide age range. Aging process affected a variety of labial anthropometric variables. Age‐related changes accelerated after 40 among Chinese women.

Background: Eyelid morphology is highly susceptible to aging. Previous studies have described the process of eyelid aging in Caucasians; however, anthropometric data describing aging in Chinese eyelids are lacking. Therefore, this study aimed to quantitatively analyze the effect of aging on the eyelids of Chinese women through a three-dimensional (3D) anthropometry. Methods: In this prospective, cross-sectional study, 3D photos were captured from 188 healthy Chinese Han women, who were categorized into four age groups. Anthropometric landmarks were identified for the measurement of eyelid parameters, and a unified coordinate system was built into each subject. Linear and angular measurements were computed from the coordinates and were compared between the groups. Results: An age-related decrease was observed in the ocular width, outer canthal width, palpebral fissure height, and multiple angular measurements. This indicated upper eyelid ptosis, which reduced the lateral and superior visual field. Lateral shift of the upper eyelid arc was not observed. The lower eyelid underwent slight elevation with increasing age. Aging rendered the periorbital region esthetically less pleasing, as shown by changes in the multiple proportion indices computed. Furthermore, an intergroup comparison indicated that eyelid aging was accelerated after the age of 40 years among Chinese women. Conclusion: This study used 3D photography to quantitatively analyze how eyelids in Chinese women changed with age. The anthropometric data collected could help with antiaging cosmetic surgery planning and postoperative assessment.

A plump lip is the symbol of youth and glamorousness. Influenced by sun damage, genetic factors, and smoking, aging will cause volume loss and perioral wrinkles to the lip. 1 Lip augmentation with dermal filler is frequently performed to offset the age-related changes and provides a more attractive appearance. 2 Botulinum toxin A (BTA) is a naturally occurring polypeptide chain molecule derived from the Clostridium botulinum bacterium. By blocking the release of acetylcholine at the myoneural junction, BTA inhibits the contraction of orbicularis oris muscle and improves perioral wrinkles. 3 The paralyzed effect that BTA has on the orbicularis oris muscle results in the eversion of the lips and achieves an augmented outcome. 4 This study presents three cases of BTA injection to the lip and evaluates the possible changes in the labial morphology and surface area. 2 | C A S E REP ORT Three individuals (two females and one male) with no previous BTA treatment, with a mean age of 28.7 ± 5.5, received a total of 4U BTA (BOTOX ® , Allergan; 40 U/mL) with 1 unit at each site. The injection sites were located symmetrically at the vermilion border of the upper lip at the dermis level (Figure 1). Vectra ® H1 3D imaging system (Vectra M3, Canfield Scientific Inc) was used to capture 3D photographs of the patients with mouth gently closed in a neutral