Summary: Objective: This study aimed to clarify the effect of statins on preventing the risk of postradiation epilepsy.Methods: We performed a retrospective analysis of neurological nasopharyngeal carcinoma patients with a history of radiotherapy. Patients with a history of epilepsy before radiation and those who received prophylactically antiepileptic treatment were excluded. The demographic and clinical data of these patients were collected through chart review. We used Kaplan–Meier analysis (log‐rank test) to examine the effect of statins on epilepsy‐free survival. Cox regression analysis was utilized to identify independent predictive variables.Results: Our study included 532 patients (405 males and 127 females) with a mean follow‐up of 28.1 months. During follow‐up, 471 (88.5%) patients developed radiation‐induced brain necrosis (RN). Within a mean latency of 24.1 months, 88 (16.5%) patients experienced epilepsy, of whom 27 (27 of 88, 30.7%) patients suffered from epilepsy before the diagnosis of RN. Thirty‐six (36 of 88, 40.9%) cases of epilepsy occurred after RN onset, and in 22 cases (22 of 88, 25.0%) epilepsy was the first presentation of RN. Three patients suffered from epilepsy but did not have RN. Eighty‐eight patients in our cohort were treated with statins because of hyperlipidemia or prevention of cardiocerebrovascular diseases, of whom six (6.8%) developed epilepsy, whereas in those without statin, the epileptic rate was 18.5%. Log‐rank test found that there was a significant difference in epilepsy‐free survival between patients who used statins and those who did not (p = 0.016). After adjusting for confounding variables, multivariate Cox regression analysis revealed that statin use could still significantly reduce the risk of epilepsy after radiation (hazard ratio = 0.36, 95% confidence interval = 0.15–0.82, p = 0.015). However, for the patients who already suffered from RN, statin treatment did not lower the risk of post‐RN epilepsy.Significance: Early statin use may reduce the risk of postradiotherapy epilepsy in patients with nasopharyngeal carcinoma.

A passive forensics method for detecting copy-move attacks was proposed. In the proposed method, tested image was segmented into non-overlapping blocks, DCT and DWT are applied to each image block to extract features, and then compare the statistics of each image block to detection replication regions. Our method was robust to compression up to JPEG quality level 20 and against additive noise. The time complexity of our approach for sorting is O(k 1g k).

Since the COVID-19 pandemic, the use of mobile health apps has been increasing significantly. Many have started using mobile health apps to manage their health and well-being. People need to develop healthy habits that will increase their job productivity, life expectancy and improve their social relationships. This study tests the Health Belief Model with adults in China in influencing health motivation and in turn improving their health behavior. A mobile and online survey was developed, and 120 usable responses were collected. A structural equation modeling was used to test the relationships between perceived benefits, perceived susceptibility, perceived barriers, health motivation, and health behavior. We found perceived self-efficacy, perceived benefits, and perceived susceptibility predicts health motivation, and health motivation predicts health behavior. We did not find that perceived barrier is a predictor for health motivation. We conclude that to encourage behavioral change, it is important to enhance self-efficacy and address the benefits; in the meantime, educating people on susceptibility is also important.

The popularity of ChatGPT has raised questions surrounding AI’s potential for health use cases. Since the release of ChatGPT in 2022, social media users have shared their prompts and ChatGPT responses on different topics such as health. Despite editorials and opinion articles discussing the potential uses of ChatGPT, there is a lack of a systematic approach to identify and analyze the use cases of ChatGPT in health. This study establishes a framework for gathering and identifying tweets (i.e., posts on social media site “X”, formerly known as Twitter) that discuss health use cases of ChatGPT, integrating topic modeling with constructivist grounded theory (CGT) to organize these topics into common categories. Using this framework, nine topics were identified, which were further grouped into four categories: (1) Clinical Workflow, (2) Wellness, (3), Diseases, and (4) Gender Identity. The Clinical Workflow category was the most popular category, and included four topics: (1) Seeking Advice, (2) Clinical Documentation, (3) Medical Diagnosis, and (4) Medical Treatment. Among the identified topics, “Diet and Workout Plans” was the most popular topic. This research highlights the potential of social media to identify the health use cases and potential health applications of an AI-based chatbot such as ChatGPT. The identified topics and categories can be beneficial for researchers, professionals, companies, and policymakers working on health use cases of AI chatbots.