ObjectiveTo assess the outcomes of laparoscopy-assisted surgery for treatment of advanced gastric cancer.MethodsA total of 115 patients with advanced gastric cancer were included between January 2014 and December 2018 were analyzed retroprospectively, the patients were divided into two groups: open surgery group (OS group, n=63) and laparoscopy-assisted surgery group (LAS group, n=52). Baseline characteristics, intraoperative parameters and postoperative items, and long-term efficacy were compared between the two groups.ResultsThere was no significant difference in preoperative baseline data including gender, age and preoperative serum parameters between the two groups (P>0.05). Intraoperative blood loss in the LAS group was significantly less than that in the OS group (P<0.05). In addition, the first feeding time after operation and postoperative hospital stay in the LAS group were significantly shorter than the OS group (P<0.05). Furthermore, numbers of white blood cells and neutrophils in the LAS group were fewer than that in the OS group at postoperative 2 days (P<0.05); the level of serum albumin in the LAS group was higher than that OS group (P<0.05). The number of lymph nodes detected during operation in the LAS group was more than that in the OS group (P<0.05). Operative time and occurrence of postoperative complications were not statistically significant between the two groups (P>0.05). One hundred and ten of 115 patients were followed- up, the follow-up rate was 95.7%. The follow-up time ranged from 6 to 48 months, with a median follow-up time of 12.4 months. The disease-free survival time of the OS group was 12.2±6.5 months, while that of the LAS group was 13.5±7.4 months. There was no significant difference between the two groups (P>0.05).ConclusionsLaparoscopic technique in treatment of advanced gastric cancer has the minimally invasive advantage, less intraoperative blood loss, less surgical trauma, and faster postoperative recovery in comparing to the traditional open surgery. Also the lymph node dissection is superior to open surgery. The curative effect is comparable to that of open surgery.
Objective To explore an AI-based method for automated hand hygiene monitoring and to compare the effectiveness of three algorithms (Uniformer-V2, TDN, C3D) in recognizing hand hygiene steps in surgical settings, thereby aiding hospital infection control. Methods From April to October 2024, we non-invasively collected 641 video recordings of healthcare staff performing hand hygiene at four-bay scrub sinks in two tertiary hospitals using overhead HD cameras. The dataset was annotated by five trained experts for model training and validation. Results Following training on 385 samples, internal validation (n=119) showed the C3D model achieved 81% accuracy, 87% recall, and an 83% F1-score. The TDN model achieved 93%, 91%, and 92% for the same metrics. The Uniformer-V2 model outperformed both, with an accuracy, recall, and F1-score of 93%—an improvement of over 10 percentage points compared to traditional CNNs (e.g., C3D). It also achieved an 84% accuracy in external validation, demonstrating strong generalization. Conclusion The Uniformer-V2 model is more accurate than CNN-based models for hand hygiene step recognition and shows robust performance in external validation. It presents a viable tool for healthcare facilities to enhance hand hygiene management, ultimately improving medical quality and patient safety.