Objectives: . The prognostic value of the pretreatment albumin-to-alkaline phosphatase ratio (AAPR) in head and neck cancer (HNC) remains uncertain. This meta-analysis aimed to evaluate the predictive role of AAPR for survival outcomes in patients with HNC. Methods: . A comprehensive search of the Cochrane Library, PubMed, and Embase databases was conducted to identify relevant studies published up to July 30, 2024. We included studies on AAPR and survival outcomes in HNC patients. Results: . Eight studies comprising 1,737 HNC patients were analyzed using random-effects models. Lower AAPR values were significantly correlated with worse overall survival (hazard ratio [HR], 2.08), progression-free survival (HR, 2.00), and disease-free survival (HR, 2.18). Sensitivity analyses confirmed the robustness of these results, with no significant publication bias detected. Conclusion . Our findings suggest that pretreatment AAPR could serve as a valuable and cost-effective prognostic indicator in HNC, potentially aiding clinicians in risk stratification and treatment decision-making. However, additional validation studies are warranted to confirm its clinical applicability.

Objective This study aimed to investigate the seasonal variation of mosquitoes in Yantai, Shandong Province, and provide a scientific basis for mosquito and mosquito-borne disease control. Methods From March to November for each of the years between 2020 and 2023, adult mosquitoes were collected from different habitats, including parks, hospitals, urban residential areas, rural households and livestock sheds, in 13 counties of Yantai City using a mosquito trap lamp method, among which, female mosquitoes were separated and identified, and the numbers were counted. We used the circular distribution method to analyze the temporal distribution characteristics of mosquito density. Results The γ values obtained for mosquitoes in Yantai from 2020 to 2023, the distribution of mosquitoes in different habitats, and dominant mosquito species in different months showed strong seasonality, with values ranging from 0.7461 to 0.8531(P ＜ 0.05). The peak period of seasonal variation in mosquitoes occurred from June 28thto September 13th, with August 5thbeing identified as the peak day. The peak periods of seasonal variation in mosquitoes in residential areas, parks, hospitals, peasant households, and animals sheds were observed from June 24thto September 14th, June 25thto September 10th, June 22ndto September 12th, July 1stto September 9th, and July 2ndto September 17th, respectively, with corresponding peak days on August 4th,3rd, 2nd, 5th, and 9th, respectively. The peak periods of Culex pipiens pallens, Aedes albopictus, and Anopheles sinensis were from June 26thto September 11th, June 28thto September 17th, and July 12thto September 17th, respectively, with corresponding peak days on August 3rd,7th, and 14th, respectively. Conclusions Our findings in this study revealed that the peak of mosquito activity in Yantai was concentrated in early August, with a peak period extending from June 28thto September 13th, and there were differences between different habitats(with peak periods for rural households and livestock sheds occurring later than those in residential areas, parks, and hospitals). Moreover, with respect to the mosquito species, populations of Cx. pipiens pallens and Ae. albopictus peaked earlier than those of An. sinensis. Based on these findings, we recommend that city-wide mosquito control work should commence in late June, and include appropriate early prevention and control measures for key habitats, such as livestock sheds, and dominant mosquito species, such as Cx. pipiens pallens, to minimize the density of mosquito vectors and the risk of disease transmission.

Artificial intelligence(AI)has emerged as a cutting-edge technology leading the future and is a key engine for China's development.In the innovation and research of medical devices,AI has provided critical support in the areas of intelligent diagnostic assistance,intelligent therapeutic assis-tance,intelligent monitoring,life support,et al.Ma-chine learning-enabled device software functions(ML-DSFs)have become an essential component of many medical devices.Recently,the United States Food and Drug Administration(FDA)released a draft guidance titled"Marketing Submission Rec-ommendations for a Predetermined Change Con-trol Plan for Artificial Intelligence/Machine Learn-ing(AI/ML)-Enabled Device Software Functions(Draft)."that aimed to provide a forward-looking approach to foster the development of ML medical devices.By supporting iterative updates through modifications,this approach ensures the continu-ous safety and effectiveness of the devices.This guidance represents the latest in regulatory direc-tion and is especially beneficial for enhancing the quality and efficiency of clinical trials for AI prod-ucts.Therefore,we plan to provide a detailed intro-duction and interpretation of the guidance,with the aim of learning from international advanced regulatory concepts and experiences to promote the development of ML-DSFs with more profound international influence.

Objective To propose a novel identification algorithm based on ensemble learning for assessing the severity of acute respiratory distress syndrome(ARDS)to achieve continuous monitoring of the disease severity.Methods Firstly,leve-raging the open-source MIMIC-Ⅳ database,a variety of non-invasive physiological parameters of patients were extracted and subjected to preliminary preprocessing.A multivariate feature selection algorithm was employed to rank these parameters and calculate feature importance scores through weighted computation.Secondly,based on the feature importance scores,a subset search algorithm was utilized to identify the subset of features that could yield optimal performance across four machine learning algorithms:neural networks,logistic regression,AdaBoost and XGBoost.Finally,a soft voting ensemble method was designed using a generalized linear regression model to integrate the results of each single machine learning algorithm,and a multivariate ensemble learning algorithm was proposed by combining the optimal feature subsets.The algorithm proposed when used to identify the severity of ADRS was evaluated with MIMIC-Ⅳ database,and compared with the traditional algorithms.Results The sensitivity,specificity,accuracy and AUC of the algorithm were 87.15％,89.23％,88.34％and 0.923 4,respectively,all of which outperformed those of the traditional algorithms.Conclusion The ARDS severity identification algorithm based on ensemble learning is capable of achieving continuous and real-time monitoring of the severity of ARDS,thereby offering robust support for the early identification and warning of ARDS in patients.[Chinese Medical Equipment Journal,2025,46(2):1-9]

Artificial intelligence(AI)has emerged as a cutting-edge technology leading the future and is a key engine for China's development.In the innovation and research of medical devices,AI has provided critical support in the areas of intelligent diagnostic assistance,intelligent therapeutic assis-tance,intelligent monitoring,life support,et al.Ma-chine learning-enabled device software functions(ML-DSFs)have become an essential component of many medical devices.Recently,the United States Food and Drug Administration(FDA)released a draft guidance titled"Marketing Submission Rec-ommendations for a Predetermined Change Con-trol Plan for Artificial Intelligence/Machine Learn-ing(AI/ML)-Enabled Device Software Functions(Draft)."that aimed to provide a forward-looking approach to foster the development of ML medical devices.By supporting iterative updates through modifications,this approach ensures the continu-ous safety and effectiveness of the devices.This guidance represents the latest in regulatory direc-tion and is especially beneficial for enhancing the quality and efficiency of clinical trials for AI prod-ucts.Therefore,we plan to provide a detailed intro-duction and interpretation of the guidance,with the aim of learning from international advanced regulatory concepts and experiences to promote the development of ML-DSFs with more profound international influence.

With the rapid development of generative artificial intelligence(GAI)technologies,their widespread application in academic research and writing is continuously expanding the boundaries of sci-entific inquiry.However,this trend has also raised a series of ethical and regulatory challenges,inclu-ding issues related to authorship,content authenticity,citation accuracy,and accountability.In light of the growing involvement of AI in generating academic content,establishing an open,controllable,and trustworthy ethical governance framework has become a key task for safeguarding research integrity and maintaining trust within the academic community.This expert consensus outlines ethical requirements across key stages of AI-assisted academic writing-including topic selection,data management,citation practices,and authorship attribution.It aims to clarify the boundaries and ethical obligations surrounding AI use in academic writing,ensuring that technological tools enhance efficiency without compromising in-tegrity.The goal is to provide guidance and institutional support for building a responsible and sustainable research ecosystem.

Objective: To retrospectively compare the safety and efficacy of ultrasound-guided radiofrequency ablation (RFA) with parotidectomy for superficial pleomorphic adenoma (PA). Materials and Methods: From March 2022 to October 2023, 88 patients diagnosed with superficial parotid PA underwent either RFA (n = 12; mean age, 47.1 years) or parotidectomy (n = 76; mean age, 47.8 years). Patients in the RFA group were matched to those in the surgery group in a 1:1 ratio using propensity scores based on age, sex, tumor volume, diameter, location, and comorbidities. Ultrasound characteristics, cosmetic scores (0–4), numerical rating scale scores (0–10), and complications were assessed before the procedures and at 1-, 3-, and 6-month follow-ups. Outcomes were compared between baseline and follow-up in the RFA group and between the RFA and surgery groups. Results: In the RFA group, significant reductions in tumor volume were observed between baseline (median, 2.02 cm 3 ) and the 1-month follow-up (median, 1.21 cm 3 ; P = 0.015), between the 1-month and 3-month follow-ups (median, 0.53 cm 3 ; P= 0.002), and between the 3- and 6-month follow-ups (median, 0.23 cm 3 ; P = 0.003). The volume reduction ratios at 1, 3, and 6 months were 39.7%, 79.9%, and 88.0%, respectively. The cosmetic score was significantly lower at 3- and 6-month followup compared to baseline (median 1 and 1 vs. 4, P = 0.04). The numerical rating scale scores did not differ significantly from baseline throughout follow-up. In the propensity score-matched analysis (12 patients per group), RFA was associated with a shorter median procedure time (61.5 vs. 253.3 minutes; P < 0.001), shorter hospital stay (0 vs. 4 days; P < 0.001), and lower cost (1859.9 vs. 3512.4 USD; P < 0.001) than parotidectomy, with no significant difference in overall complication rates (33.3% [4/12] vs. 41.7% [5/12]; P = 1.000). Conclusion RFA may be a safe and effective alternative to surgery for superficial parotid PA, offering a shorter median procedure time, shorter hospital stay, and lower costs.

Objective: To retrospectively compare the safety and efficacy of ultrasound-guided radiofrequency ablation (RFA) with parotidectomy for superficial pleomorphic adenoma (PA). Materials and Methods: From March 2022 to October 2023, 88 patients diagnosed with superficial parotid PA underwent either RFA (n = 12; mean age, 47.1 years) or parotidectomy (n = 76; mean age, 47.8 years). Patients in the RFA group were matched to those in the surgery group in a 1:1 ratio using propensity scores based on age, sex, tumor volume, diameter, location, and comorbidities. Ultrasound characteristics, cosmetic scores (0–4), numerical rating scale scores (0–10), and complications were assessed before the procedures and at 1-, 3-, and 6-month follow-ups. Outcomes were compared between baseline and follow-up in the RFA group and between the RFA and surgery groups. Results: In the RFA group, significant reductions in tumor volume were observed between baseline (median, 2.02 cm 3 ) and the 1-month follow-up (median, 1.21 cm 3 ; P = 0.015), between the 1-month and 3-month follow-ups (median, 0.53 cm 3 ; P= 0.002), and between the 3- and 6-month follow-ups (median, 0.23 cm 3 ; P = 0.003). The volume reduction ratios at 1, 3, and 6 months were 39.7%, 79.9%, and 88.0%, respectively. The cosmetic score was significantly lower at 3- and 6-month followup compared to baseline (median 1 and 1 vs. 4, P = 0.04). The numerical rating scale scores did not differ significantly from baseline throughout follow-up. In the propensity score-matched analysis (12 patients per group), RFA was associated with a shorter median procedure time (61.5 vs. 253.3 minutes; P < 0.001), shorter hospital stay (0 vs. 4 days; P < 0.001), and lower cost (1859.9 vs. 3512.4 USD; P < 0.001) than parotidectomy, with no significant difference in overall complication rates (33.3% [4/12] vs. 41.7% [5/12]; P = 1.000). Conclusion RFA may be a safe and effective alternative to surgery for superficial parotid PA, offering a shorter median procedure time, shorter hospital stay, and lower costs.