The application of artificial intelligence(AI)in the medical field, particularly for predicting, diagnosing and treating retinal detachment(RD), has made remarkable achievements. This paper reviews the advancements in AI applications for RD across multiple dimensions, including predicting RD incidence, assessing surgical success rates, forecasting postoperative visual outcomes, and evaluating recurrence rates. In diagnostic support, AI technology has demonstrated significant value, especially in ophthalmic imaging, with applications in the intelligent analysis of ultra-wide-angle fundus photography, optical coherence tomography(OCT), ophthalmologic ultrasound images, and AI chatbots models. Furthermore, AI has proven uniquely beneficial in surgical decision-making, robotic-assisted surgical systems, and the assessment of surgical complications. This paper provides a comprehensive overview of the current state of AI applications in RD, underscoring its potential to address numerous challenges in clinical practice. It also explores existing limitations and offers insights into future directions for development in this field.

The application of artificial intelligence(AI)in the medical field, particularly for predicting, diagnosing and treating retinal detachment(RD), has made remarkable achievements. This paper reviews the advancements in AI applications for RD across multiple dimensions, including predicting RD incidence, assessing surgical success rates, forecasting postoperative visual outcomes, and evaluating recurrence rates. In diagnostic support, AI technology has demonstrated significant value, especially in ophthalmic imaging, with applications in the intelligent analysis of ultra-wide-angle fundus photography, optical coherence tomography(OCT), ophthalmologic ultrasound images, and AI chatbots models. Furthermore, AI has proven uniquely beneficial in surgical decision-making, robotic-assisted surgical systems, and the assessment of surgical complications. This paper provides a comprehensive overview of the current state of AI applications in RD, underscoring its potential to address numerous challenges in clinical practice. It also explores existing limitations and offers insights into future directions for development in this field.

OBJECTIVE To provide reference for strengthening the standardized management of off-label drug use in cancer hospitals. METHODS The evaluation system for off-label drug use was established to standardize the application， approval， and filing process for off-label drug use in our hospital. The changes in off-label drug application quantity， proportion， disease category and drug category in our hospital were compared before （October 1st， 2021-September 30th， 2022） and after （October 1st， 2022- September 30th， 2023） the establishment of the evaluation system； drug items supported by high-level evidence screened by pharmacy department were analyzed statistically. RESULTS The number of off-label drug use applications in our hospital had gradually increased， from 306 pieces in the fourth quarter of 2021 to 3 828 pieces in the third quarter of 2023. In the year before the construction of the evaluation system， there were a total of 4 482 applications for off-label drug use， and in the year after the construction of the evaluation system， there were 11 840 applications for off-label drug use. After the construction of the evaluation system， the proportion of unregistered off-label drug use significantly decreased， compared to the same period last year （P＜0.05）. Among them， there were no unregistered applications for off-label drug use for digestive system tumors， head and neck tumors， and radioactive drugs； lymphoma， breast tumors，urogenital system tumors， cytotoxic drugs and new anti-tumor drugs all had a decrease of over 70% in unregistered off-label drug applications. Twenty-seven off-label drug use items related to 19 drugs supported by high-level evidence were screened by the pharmacy department of our hospital， among which 25 items were drug use beyond indication. CONCLUSIONS The establishment of off-label drug use evaluation system in cancer hospital is helpful to the rational use and refined management of clinical anti-tumor drugs.

AIM:To explore the fundus vascular characteristics of healthy individuals based on deep learning techniques, with a view to discovering the range of normal values of the fundus arteries and veins, as well as the relationship between physiological factors, such as gender, age, body mass index(BMI), blood pressure, and fundus vasculature characteristics.METHODS:Fundus images of healthy people were taken from a professional fundus camera, and the subject's blood pressure and laboratory test was collected. Additionally, the fundus arteries and veins were segmented by the improved U-Net model, and the color, morphology and Haralick texture features of the vessels were extracted from computer vision technology.RESULTS:A total of 4 487 cases fundus images were taken and 326 cases with healthy and clear fundus images were screened, including 200 males and 126 females. There were differences in the morphology, color, and textural characteristics of the left and right eyes, as well as of the fundus arterioles and veins, with a mean vessel width(width)of 1.146 in the arteries and 1.430 in the veins, and an arteriovenous ratio about 4:5. Fundus artery and vein characteristics in healthy individuals of different ages(21-30, 31-40, 41-50): compared with the healthy population aged 21-30 and 31-40 years, arterial and venous inverse difference moment(idm), f12 and venous angular second moment(asm)values increased, and arterial and venous contrast(con), entropy(ent), difference entropy(den), and venous sum entropy(sen)values decreased in 41-50 years. Compared with the 21-30 years age group, arterial f12 values increased and venous con values decreased in 31-40 years(all P<0.05). Fundus vascular characteristics of healthy individuals of different sexes: compared with male, fundus arterial and venous sum average(sav), sum variance(sva)values, arterial curved values, and venous b mean, bsd, variance(var), sen, ent values increased in female, while venous area value of female decreased(all P<0.05). There were no statistically significant differences in fundus arteriosus and venous features in healthy subjects with different levels of BMI(all P>0.05). Fundus characteristics of healthy people with different degrees of blood pressure: there were statistically significant differences in fundus arteriosus area, width, and venous con, idm, dva, and den values between the normal blood pressure and high blood pressure groups(all P<0.05).CONCLUSION: The characteristics of the left and right eyes as well as the fundus arteries and veins differ in healthy individuals and correlate with physiological factors such as gender, age and blood pressure, which have the value of a potential microcirculation marker.

Background Blue light, as an occupational hazard, is widely present in welding and related work environments. However, China's occupational health standard system has not yet established any limit for blue light exposure in welding work environments. Objective To study and propose blue light exposure limits in welding operation environments, and provide a reference for evaluation of blue light hazard and maximum allowable exposure time in welding operations. Methods A function between retinal irradiance and welding arc radiance was introduced by studying arc light and blue light radiation generated in welding operation environments, analyzing the incoherent light radiation protection guidelines issued by the International Commission on Non-Ionizing Radiation Protection (ICNIRP), and combined with factors such as the size of arc light in welding operations, the distance between the welder's eyes and the arc light, and the diameter of the human eye pupil, as well as the geometric optics principle of human eye imaging and the conservation of energy. Then, the radiance limit (100 W·m⁻²·Sr⁻¹) issued by ICNIRP was input into the above function to calculate the blue light irradiance exposure limit in the welding operation environments. Results The blue light irradiance exposure limit in the welding operation environments (\begin{document}$ {E}_{{\rm{B}}}^{{\rm{EL}}} $\end{document}) was 3 W·m⁻². Considering the high repeatability of welding operations, the exposure limit for blue light radiant exposure (\begin{document}$ {H}_{{\rm{B}}}^{{\rm{EL}}} $\end{document}) was 60 J·m⁻². According to the definitions of radiant exposure and irradiance, the maximum allowable exposure time within one working day was calculated according to the formula \begin{document}$ {t}_{\mathrm{m}\mathrm{a}\mathrm{x}}={H}_{{\rm{B}}}^{{\rm{EL}}}{/E}_{{\rm{B}}} $\end{document}, in which \begin{document}$ {E}_{{\rm{B}}} $\end{document} was the measured blue light irradiance in a welding environment. Conclusion Exposure limits of radiant exposure for blue light are proposed to provide important references for evaluating the hazards and maximum allowable exposure time of blue light in welding operations, and for future development of occupational exposure limit standards for blue light in China.

Objective: To analyze the current situation, influencing factors and mechanism of knowledge-attitude-practice(KAP) regarding acquired immune deficiency syndrome(AIDS)/sexually transmitted diseases(STDs) among migrant workers in Chengdu's main urban area, so as to provide a basis for the development of effective prevention and control policies for this group. Methods: Convenience sampling and systematic sampling were used to collect demographic information and data on knowledge, attitudes, and sexual behavior characteristics of AIDS/STDs of the participants. The collected data were organized and statistically analyzed by EpiData 3.1 and SPSS 26.0 software. Additionally, a KAP path analysis model was constructed by using AMOS 24.0 software. Results: A total of 257 valid questionnaires were obtained. The AIDS awareness rate was 55.6%, with a mean scores of(5.59±1.61). The awareness rate of STDs was 37.4%, with a mean scores of(9.05±3.00). Discrimination attitudes towards AIDS and STDs were reported by 58 participants(22.6%) and 44 participants(17.1%) respectively. The prevalence of high-risk sexual behavior was 3.50%. Men(OR=0.500, 95%CI: 0.279-0.897) acted as deterrents to knowledge of AIDS. On the other hand, childlessness facilitated discrimination against AIDS(OR=2.748, 95%CI: 1.385-5.451) and STDs(OR=2.287, 95%CI: 1.084-4.825). There was lower likelihood of engaging in high-risk sexual behavior among migrant workers in Chengdu's main urban area who were older(OR=0.854, 95%CI: 0.785-0.929). The occurrence of high-risk sexual behaviors was influenced both directly and indirectly by attitudes towards AIDS and related knowledge. There was a positive correlation between knowledge about AIDS and STDs and attitudes towards them(r=0.15,0.24, bothP<0.05), as well as between attitudes towards AIDS and attitudes towards STDs(r=0.57,P<0.05). That is, the higher the scores of knowledge, the less likely one was to hold discrimination attitudes. Therefore, increasing the rate of knowledge awareness could reduce discrimination towards AIDS/STDs and the occurrence of high-risk sexual behaviors. Conclusion The level of AIDS/STDs knowledge among the migrant workers in Chengdu′s main urban area is concerning. Innovative interventions should be intensified in key areas and populations.

In the all-media era,online public opinion events are causing more and more trouble to the healthcare industry,and public hospitals in this situation are facing a severe test in terms of online public opinion management,which is generally problematic.It introduces the hospital network public opinion governance strategies and methods based on hazard vulnerability analysis of Peking University People's Hospital and explores a practical and feasible hos-pital online public opinion management model from the aspects of public opinion risk identification,public opinion management system construction,and improvement of departmental management level,to enhance the level of hospital public opinion governance,with a view to reducing and avoiding negative impacts on the hospital caused by online public opinion events,building a harmonious doctor-patient relationship,and improving the work of medical services.The aim is to reduce and avoid the negative impact of online public opinion events on the hospital,to build a harmonious doctor-patient relationship and improve medical services.

In the all-media era,online public opinion events are causing more and more trouble to the healthcare industry,and public hospitals in this situation are facing a severe test in terms of online public opinion management,which is generally problematic.It introduces the hospital network public opinion governance strategies and methods based on hazard vulnerability analysis of Peking University People's Hospital and explores a practical and feasible hos-pital online public opinion management model from the aspects of public opinion risk identification,public opinion management system construction,and improvement of departmental management level,to enhance the level of hospital public opinion governance,with a view to reducing and avoiding negative impacts on the hospital caused by online public opinion events,building a harmonious doctor-patient relationship,and improving the work of medical services.The aim is to reduce and avoid the negative impact of online public opinion events on the hospital,to build a harmonious doctor-patient relationship and improve medical services.

In the all-media era,online public opinion events are causing more and more trouble to the healthcare industry,and public hospitals in this situation are facing a severe test in terms of online public opinion management,which is generally problematic.It introduces the hospital network public opinion governance strategies and methods based on hazard vulnerability analysis of Peking University People's Hospital and explores a practical and feasible hos-pital online public opinion management model from the aspects of public opinion risk identification,public opinion management system construction,and improvement of departmental management level,to enhance the level of hospital public opinion governance,with a view to reducing and avoiding negative impacts on the hospital caused by online public opinion events,building a harmonious doctor-patient relationship,and improving the work of medical services.The aim is to reduce and avoid the negative impact of online public opinion events on the hospital,to build a harmonious doctor-patient relationship and improve medical services.

In the all-media era,online public opinion events are causing more and more trouble to the healthcare industry,and public hospitals in this situation are facing a severe test in terms of online public opinion management,which is generally problematic.It introduces the hospital network public opinion governance strategies and methods based on hazard vulnerability analysis of Peking University People's Hospital and explores a practical and feasible hos-pital online public opinion management model from the aspects of public opinion risk identification,public opinion management system construction,and improvement of departmental management level,to enhance the level of hospital public opinion governance,with a view to reducing and avoiding negative impacts on the hospital caused by online public opinion events,building a harmonious doctor-patient relationship,and improving the work of medical services.The aim is to reduce and avoid the negative impact of online public opinion events on the hospital,to build a harmonious doctor-patient relationship and improve medical services.