Predicting the number of new suspected or confirmed cases of novel coronavirus disease 2019 (COVID-19) is crucial in the prevention and control of the COVID-19 outbreak. Social media search indexes (SMSI) for dry cough, fever, chest distress, coronavirus, and pneumonia were collected from 31 December 2019 to 9 February 2020. The new suspected cases of COVID-19 data were collected from 20 January 2020 to 9 February 2020. We used the lagged series of SMSI to predict new suspected COVID-19 case numbers during this period. To avoid overfitting, five methods, namely subset selection, forward selection, lasso regression, ridge regression, and elastic net, were used to estimate coefficients. We selected the optimal method to predict new suspected COVID-19 case numbers from 20 January 2020 to 9 February 2020. We further validated the optimal method for new confirmed cases of COVID-19 from 31 December 2019 to 17 February 2020. The new suspected COVID-19 case numbers correlated significantly with the lagged series of SMSI. SMSI could be detected 6–9 days earlier than new suspected cases of COVID-19. The optimal method was the subset selection method, which had the lowest estimation error and a moderate number of predictors. The subset selection method also significantly correlated with the new confirmed COVID-19 cases after validation. SMSI findings on lag day 10 were significantly correlated with new confirmed COVID-19 cases. SMSI could be a significant predictor of the number of COVID-19 infections. SMSI could be an effective early predictor, which would enable governments’ health departments to locate potential and high-risk outbreak areas.

Background: The use of social media in communications regarding cancer prevention is rapidly growing. However, less is known about the general population’s social media use related to cancer screening awareness and behavior for different cancers. Objective: We aimed to examine the relationship between social media use and cancer screening awareness and behavior among people without a cancer diagnosis. Methods: Data were collected from the Health Information National Trends Survey 5 Cycle 1 to 3 in the United States (n=12,227). Our study included 10,124 participants without a cancer diagnosis and 3 measures of screening awareness (those who had heard of hepatitis C virus [HCV], human papillomavirus [HPV], and the HPV vaccine) and 4 measures of behavior (those who had prostate-specific antigen tests, Papanicolaou tests for cervical cancer, as well as breast cancer and colon cancer tests). Propensity-score matching was conducted to adjust for the sociodemographic variables between the social media user and nonuser participants. Multivariable logistic regression was used to assess the association of social media use by gender. Jackknife replicate weights were incorporated into the analyses. Results: Of the 3794 matched participants, 1861 (57.6% weighted) were male, and the mean age was 55.5 (SD 0.42) years. Compared to social media nonusers, users were more likely to have heard of HCV (adjusted odds ratio [aOR]=2.27, 95% CI, 1.29-3.98 and aOR=2.86, 95% CI, 1.51-5.40, for male and female users, respectively) and HPV (aOR=1.82, 95% CI, 1.29-2.58 and aOR=2.35, 95% CI, 1.65-3.33, for male and female users, respectively). In addition, female users were more likely to have heard of the HPV vaccine (aOR=2.06, 95% CI, 1.41-3.00). No significant associations were found between social media use and prostate-specific antigen tests in males, Papanicolaou tests and breast cancer tests in females, or colon cancer tests in both male and female users. Conclusions: While social media services can potentially promote cancer screening awareness in the general population, but they did not improve screening behavior after adjusting for socioeconomic status. These findings strengthened our understanding of social media use in targeting health communications for different cancers.

Purpose: Although clinicians encounter patients aged ≥70 years with locally advanced oral cavity squamous cell carcinoma (LA-OCSCC), no evidence is available to facilitate decision making regarding treatment for this elderly population. Methods: We selected elderly (≥70 years) patients from the Taiwan Cancer Registry database who had received a diagnosis of LA-OCSCC. Propensity score matching was performed. Cox proportional hazards model curves were used to analyze all-cause mortality in patients in different age groups receiving different treatments. Results: The matching process yielded a final cohort of 976 patients in concurrent chemoradiotherapy (CCRT), non-treatment, radiotherapy (RT) alone, and surgery cohorts who were eligible for further analysis. After stratified analysis, the adjusted hazard ratios (aHRs) (95% confidence intervals [CIs]) derived for surgery, RT alone, and non-treatment compared with CCRT were 0.66 (0.52 to 0.83), 1.02 (0.81 to 1.28), and 1.52 (1.21 to 1.91), respectively, in patients aged 70 to 80 years. In the oldest patients (aged >80 years), multivariate analysis indicated that the results of surgery or RT alone were nonsignificant compared with those of CCRT. The aHR (95% CI) derived for the highest mortality was 1.81 (1.11 to 2.40) for non-treatment compared with CCRT. Conclusions: Surgery for elderly patients with LA-OCSCC is associated with a significant survival benefit, but the association is nonsignificant in the oldest elderly patients. No survival differences were observed between RT alone and CCRT in these elderly patients. Non-treatment should not be an option for these patients.

The Shapley value is a fundamental concept in data science, providing a principled framework for fair resource allocation, feature importance quantification, and improved interpretability of complex models. Its fundamental theory is based on four axiomatic proper ties, which underpin its widespread application. To address the inherent computational challenges of exact calculation, we discuss model-agnostic approximation techniques, such as Random Order Value, Least Squares Value, and Multilinear Extension Sampling, as well as specialized fast algorithms for linear, tree-based, and deep learning models. Recent extensions, such as Distributional Shapley and Weighted Shapley, have broadened the applications to data valuation, reinforcement learning, feature interaction analysis, and multi-party cooperation. Practical effectiveness has been demonstrated in health care, finance, industry, and the digital economy, with promising future directions for incorporating these techniques into emerging fields, such as data asset pricing and trading.

Purpose: To propose a risk classification scheme for locoregionally advanced (Stages III and IV) head and neck squamous cell carcinoma (LA-HNSCC) by using the Wu comorbidity score (WCS) to quantify the risk of curative surgeries, including tumor resection and radical neck dissection. Methods: This study included 55,080 patients with LA-HNSCC receiving curative surgery between 2006 and 2015 who were identified from the Taiwan Cancer Registry database; the patients were classified into two groups, mortality (n = 1287, mortality rate = 2.34%) and survival (n = 53,793, survival rate = 97.66%), according to the event of mortality within 90 days of surgery. Significant risk factors for mortality were identified using a stepwise multivariate Cox proportional hazards model. The WCS was calculated using the relative risk of each risk factor. The accuracy of the WCS was assessed using mortality rates in different risk strata. Results: Fifteen comorbidities significantly increased mortality risk after curative surgery. The patients were divided into low-risk (WCS, 0–6; 90-day mortality rate, 0–1.57%), intermediate-risk (7–11; 2.71–9.99%), high-risk (12–16; 17.30–20.00%), and very-high-risk (17–18 and >18; 46.15–50.00%) strata. The 90-day survival rates were 98.97, 95.85, 81.20, and 53.13% in the low-, intermediate-, high-, and very-high-risk patients, respectively (log-rank p < 0.0001). The five-year overall survival rates after surgery were 70.86, 48.62, 22.99, and 18.75% in the low-, intermediate-, high-, and very-high-risk patients, respectively (log-rank p < 0.0001). Conclusion: The WCS is an accurate tool for assessing curative-surgery-related 90-day mortality risk and overall survival in patients with LA-HNSCC.

Purpose: To predict the fundus tessellation (FT) severity with machine learning methods.Methods: A population-based cross-sectional study with 3,468 individuals (mean age of 64.6 ± 9.8 years) based on Beijing Eye Study 2011. Participants underwent detailed ophthalmic examinations including fundus images. Five machine learning methods including ordinal logistic regression, ordinal probit regression, ordinal log-gamma regression, ordinal forest and neural network were used.Main Outcome Measure: FT precision, recall, F1-score, weighted-average F1-score and AUC value.Results: Observed from the in-sample fitting performance, the optimal model was ordinal forest, which had correct classification rate (precision) of 81.28%, while 34.75, 93.73, 70.03, and 24.82% in each classified group by FT severity. The AUC value was 0.7249. And the F1-score was 65.05%, weighted-average F1-score was 79.64% on the whole dataset. For out-of-sample prediction performance, the optimal model was ordinal logistic regression, which had precision of 77.12% on the validation dataset, while 19.57, 92.68, 64.74, and 6.76% in each classified group by FT severity. The AUC value was 0.7187. The classification accuracy of light FT group was the highest, while that of severe FT group was the lowest. And the F1-score was 54.46%, weighted-average F1-score was 74.19% on the whole dataset.Conclusions: The ordinal forest and ordinal logistic regression model had the strong prediction in-sample and out-sample performance, respectively. The threshold ranges of the ordinal forest model for no FT and light, moderate, severe FT were [0, 0.3078], [0.3078, 0.3347], [0.3347, 0.4048], [0.4048, 1], respectively. Likewise, the threshold ranges of ordinal logistic regression model were ≤ 3.7389, [3.7389, 10.5053], [10.5053, 13.9323], > 13.9323. These results can be applied to guide clinical fundus disease screening and FT severity assessment.