Objective:To explore the clinical application value of artificial intelligence models in identifying bleeding events and hemorrhagic points during laparoscopic pancreatic surgery.Methods:This single-center retrospective cohort study collected surgical videos of 25 patients undergoing laparoscopic pancreatic surgery at the Department of General Surgery, Peking Union Medical College Hospital from January 2022 to December 2024. Videos within 5 seconds before and after representative bleeding events were captured at 30 frames/s, with 11 666 hemorrhagic-related video frames annotated. Two algorithm models were developed: a pigment-based model and a pigment+optical flow-based model for classification and target recognition of bleeding frames. The training and test sets for the pigment-based algorithm contained 4 692 hemorrhagic and 4 309 non-hemorrhagic frames, while those for the pigment+optical flow model included 1 339 hemorrhagic and 1 326 non-hemorrhagic frames. Performance evaluation was conducted using overlap thresholds, with accuracy and recall rates as key metrics.Results:The pigment-based model achieved 93.8% accuracy (134/143) and 43.3% recall (134/310) in hemorrhagic frame classification. At an overlap threshold of 0.3, the pigment-based model showed 84.1% accuracy (433/515) and 85.4% recall (433/507) in target recognition. When the threshold was increased to 0.5, the pigment+optical flow model demonstrated 88.1% accuracy (354/402) and 89.2% recall (354/397) in hemorrhagic target recognition.Conclusions:It is difficult to distinguish active bleeding from old bleeding completely by pigment information alone. The spatio-temporal features can be effectively extracted by combining pigment and optical flow information, and the bleeding can be accurately identified and located, which has potential clinical application value.

Objective:To explore the efficacy of Qingjin Huatan Decoction combined with conventional Western medicine for the treatment of acute exacerbation of chronic obstructive pulmonary disease (AECOPD) with phlegm-heat obstructing lung syndrome.Methods:A randomized controlled trial was conducted. Totally 90 hospitalized patients with AECOPD phlegm-heat obstructing lung syndrome in the respiratory department of Shunyi Hospital, Beijing Traditional Chinese Medicine Hospital from January 2023 to June 2024 were selected as the observation subjects. According to the simplified randomization method (single-double number method), the patients were divided into two groups, with 45 cases in each group. The conventional Western medicine group was given conventional Western medicine treatment, and the combined Chinese materia medica group was given Qingjin Huatan Decoction on the basis of the conventional Western medicine group. The treatment for both groups lasted for 7 d. TCM symptoms were scored before and after treatment; FEV 1 and FVC were detected by pulmonary function analyzer, PaO 2, PaCO 2, PaO 2/FiO 2 were detected by blood gas biochemical analyzer, CRP and PCT were detected by ELISA, and white blood cell count (WBC) was detected by automatic blood cell analyzer. Adverse reactions were recorded, and the clinical efficacy was evaluated. Results:The total effective rate was 93.33% (42/45) in the combined Chinese materia medica group and 77.78% (35/45) in the conventional Western medicine group, with statistical significance ( χ2=4.41, P=0.036). After treatment, the scores of cough, wheezing, chest tightness and shortness of breath and fever and the total score in the combined Chinese materia medica group were lower than those in the conventional Western medicine group ( t=4.83, 2.26, 5.36, 10.43, 5.27,respectively, P<0.01 or P<0.05); the levels of FEV 1 and FVC in the combined Chinese materia medica group were higher than those in the conventional Western medicine group ( t=3.03, 2.64, respectively, P<0.01); the levels of PaO 2 and PaO 2/FiO 2 in the combined Chinese materia medica group were higher than those in the conventional Western medicine group ( t=4.83, 5.36, P<0.01), while the level of PaCO 2 in the combined Chinese materia medica group was lower than that in the conventional Western medicine group ( t=2.26, P<0.05); the levels of CRP, PCT and WBC in the combined Chinese materia medica group were lower than those in the conventional western medicine group ( t=10.53, 11.29 and 2.59, respectively, P<0.01 or P<0.05). During the treatment, the incidence of adverse reactions was 6.67% (3/45) in the combined Chinese materia medica and 8.89% (4/45) in the conventional Western medicine group, without statistical significance ( χ2=0.16, P=0.694). Conclusion:Qingjin Huatan Decoction can effectively improve the lung function and blood gas indicators of AECOPD with phlegm-heat obstructing lung syndrome, and relieve the inflammation, with safety and effectiveness.

Objective:To explore the clinical application value of artificial intelligence models in identifying bleeding events and hemorrhagic points during laparoscopic pancreatic surgery.Methods:This single-center retrospective cohort study collected surgical videos of 25 patients undergoing laparoscopic pancreatic surgery at the Department of General Surgery, Peking Union Medical College Hospital from January 2022 to December 2024. Videos within 5 seconds before and after representative bleeding events were captured at 30 frames/s, with 11 666 hemorrhagic-related video frames annotated. Two algorithm models were developed: a pigment-based model and a pigment+optical flow-based model for classification and target recognition of bleeding frames. The training and test sets for the pigment-based algorithm contained 4 692 hemorrhagic and 4 309 non-hemorrhagic frames, while those for the pigment+optical flow model included 1 339 hemorrhagic and 1 326 non-hemorrhagic frames. Performance evaluation was conducted using overlap thresholds, with accuracy and recall rates as key metrics.Results:The pigment-based model achieved 93.8% accuracy (134/143) and 43.3% recall (134/310) in hemorrhagic frame classification. At an overlap threshold of 0.3, the pigment-based model showed 84.1% accuracy (433/515) and 85.4% recall (433/507) in target recognition. When the threshold was increased to 0.5, the pigment+optical flow model demonstrated 88.1% accuracy (354/402) and 89.2% recall (354/397) in hemorrhagic target recognition.Conclusions:It is difficult to distinguish active bleeding from old bleeding completely by pigment information alone. The spatio-temporal features can be effectively extracted by combining pigment and optical flow information, and the bleeding can be accurately identified and located, which has potential clinical application value.

Objective: To identify problems and demands for antenatal care (ANC) among pregnant women in different trimesters of pregnancy in Shanghai for optimizing ANC service during the epidemic of coronavirus disease 2019 (COVID-19). Methods: Organized by Maternal and Child Health Care institute in the 16 districts of Shanghai, a cross sectional study was conducted among pregnant women who came to pregnancy registration in the community health centers or attended ANC in maternity hospitals from February 7 to February 12, 2020. Consented participating women completed a semi-structured online questionnaire voluntarily. Data was analyzed using frequency and scoring, chi-square test. Results: A total of 2 002 valid questionnaires were collected from 183 community health centers and 67 midwifery hospitals. About 94.6% of the pregnant women worried about being infected during the COVID-19 epidemic, and 14.7% demanded for psychological consultation. Appointment ANC services were requested by 87.7% of the participants for avoiding presenting themselves in people-density places. Compared with other pregnancy trimesters, pregnant women in the second trimester were more willing to reduce the frequency of ANC (48.1% VS. 39.5% VS. 35.2%, P<0.01). Compared with multiparas, primiparas were more willing to have online consultation and guidance (63.8% VS. 49.2%, P<0.01). Regarding the needs for health knowledge on COVID-19, personal protection against 2019-nCoV was the most concerned for pregnant women, and 71.0% of them preferred to obtain knowledge through health applications, official Weibo and WeChat. Conclusions Pregnant women in Shanghai critically concern about the risk of 2019-nCoV infections, and highly demand knowledge and measures on prevention and protection from COVID-19. They ask for having time-lapse appointments for ANC and online access to health information and services. Maternal and Child Care institutes should understand the demands of pregnant women, optimize the means of ANC service, and provide tailored and accessible health education and service for the safety of mother and child.