MiRNAs are a class of small non-coding RNAs,which regulate gene expression post-transcriptionally by partial complementary base pairing.Aberrant miRNA expressions have been reported in tumor tissues and peripheral blood of cancer patients.In recent years,artificial intelligence algorithms such as machine learning and deep learning have been widely used in bioinformatic research.Compared to traditional bioinformatic tools,miRNA target prediction tools based on artificial intelligence algorithms have higher accuracy,and can successfully predict subcellular localization and redistribution of miRNAs to deepen our understanding.Additionally,the construction of clinical models based on artificial intelligence algorithms could significantly improve the mining efficiency of miRNA used as biomarkers.In this article,we summarize recent development of bioinformatic miRNA tools based on artificial intelligence algorithms,focusing on the potential of machine learning and deep learning in cancer-related miRNA research.

As the main body of the national healthcare service system,public hospitals play a crucial role in implemen-ting the Healthy China strategy.Therefore,promoting the deep integration of Party building and business operations has become an inevitable trend for public hospitals in the new era to strengthen Party work and achieve high-quality development.The Sun Yat-sen University Cancer Prevention and Treatment Center focuses on the requirements of grassroots Party building,emphasizing the top-level design and refined management of the comprehensive goal management system of Party branches.Through scientific and effective comprehensive goal management,it harnesses high-quality Party building to lead the high-quality development of public hospitals.This study actively explores effective pathways for the deep integration of Party building and business operations in public hospitals,providing insights and references for promoting high-quality development in these institutions.

With the rapid development of information technology and the advent of the big data era,promoting smart Par-ty building has gradually become an inevitable trend and important approach for strengthening the Party building effort in public hospitals in the new era.Sun Yat-sen University Cancer Center,focusing on the requirements of grassroots Party building and in-tegrating the characteristics of Party building work in university-affiliated hospitals,has innovatively developed a smart Party building information platform suitable for the ecosystem of public hospital Party building.The platform's functional modules are designed based on the closed-loop process of Party building work assessment,which includes"task issuance-execution-evalua-tion-rectification".It has been found that the orderly construction of the smart Party building information platform has signifi-cantly contributed to enhancing the standardization of Party branch construction,facilitating burden reduction and empowerment of grassroots organizations,and strengthening the leading role of Party building work.This initiative serves as a viable practical ex-ample for the intelligent operation of hospital Party building work and spurs continuous innovation and high-quality development in party building efforts in university-affiliated hospitals.

AIM: To investigate the relationship between objective ocular torsion and near stereopsis in patients with primary superior oblique overaction(PSOOA).METHODS: Retrospective study. A total of 59 strabismus patients with PSOOA who underwent strabismus surgery at Renmin Hospital of Wuhan University between January 2019 and November 2023 were collected. Based on the collected fundus photographs and the position of the fovea relative to the horizontal line through the optic disc, the eyes were categorized as incyclotorsion, excyclotorsion, or no cyclotorsion. Additionally, the fovea-disc angle(FDA)and the relationship between objective ocular torsion status, FDA, and near stereopsis function in the patients were further measured and analyzed.RESULTS: Totally 59 patients(92 eyes)showed superior oblique overaction. There were no cases of excyclotorsion, 32 cases with no cyclotorsion, and 27 cases with incyclotorsion. The total binocular FDA was significantly smaller in the no-cyclotorsion group compared with the incyclotorsion group(2.83°±2.89° vs 16.12°±5.74°, P<0.001). The preservation rates of near stereopsis were 66% and 15% in the no-cyclotorsion and incyclotorsion groups, respectively, with a significant statistical difference(P<0.001), and the preservation rates of fine near stereopsis were 38% and 11% in the no-cyclotorsion and incyclotorsion groups, respectively, with a significant statistical difference(P=0.02). Among all patients, near stereopsis was correlated with total binocular FDA(r=-0.526, P<0.001), with the strongest correlation observed with the FDA of the incyclotorsion(r=-0.546, P<0.001). In the incyclotorsion group, there was no correlation between near stereopsis and total binocular FDA(r=-0.366, P=0.060), with a negative correlation between near stereopsis and the FDA of both the incyclotorsion and the overaction(r=-0.424, P=0.028; r=-0.485, P=0.010). In the no-cyclotorsion group, near stereopsis was not correlated with total binocular FDA, incyclotorsion FDA, or overaction FDA.CONCLUSION:PSOOA patients with incyclotorsion have a lower preservation rate of near stereopsis than those without cyclotorsion. Near stereopsis function of patients with PSOOA is negatively correlated with total binocular FDA, especially the greater the FDA of the incyclotorsion and overaction, the worse the near-stereoscopic function.