Objective:To evaluate the diagnostic performance of artificial intelligence-assisted diagnostic systems in cervical cytopathological examination.Methods:Cervical cytology slide data were retrospectively collected from four hospitals for the external validation of the developed artificial intelligence-assisted diagnostic system. Subsequently, prospective data collection was conducted for human-machine assisted studies.Results:In the retrospective study, a total of 3 162 valid samples were collected as external validation data. The system showed an area under the curve (AUC) of 0.890 (95% CI: 0.878-0.902), accuracy of 0.885 (95% CI: 0.873-0.896), sensitivity of 0.928 (95% CI: 0.914-0.941), and specificity of 0.852 (95% CI: 0.834-0.867). In the prospective study, 212 valid samples were collected, and five junior cytologists participated in the human-machine assisted study. Without artificial intelligence assistance, the average AUC for the five cytologists was 0.686 (95% CI: 0.650-0.722), the accuracy was 0.699 (95% CI: 0.671-0.727), the sensitivity was 0.653 (95% CI: 0.599-0.703), the specificity was 0.719 (95% CI: 0.685-0.750), the Fleiss κ value was 0.510, and the reading time was 223 seconds. With artificial intelligence assistance, the AUC, accuracy, sensitivity, and specificity increased by 0.166, 0.143, 0.225, and 0.107, respectively. Additionally, Fleiss κ was 0.730 and the reading time decreased by 188 seconds. All differences were statistically significant (all P<0.001). Conclusions:Artificial intelligence-assisted diagnosis system shows excellent performance and good generalizability, significantly improving the diagnostic accuracy, consistency, and efficiency of junior cytologists. It can be an effective auxiliary tool for junior cytologists in clinical practice.

Objective:To evaluate the diagnostic performance of artificial intelligence-assisted diagnostic systems in cervical cytopathological examination.Methods:Cervical cytology slide data were retrospectively collected from four hospitals for the external validation of the developed artificial intelligence-assisted diagnostic system. Subsequently, prospective data collection was conducted for human-machine assisted studies.Results:In the retrospective study, a total of 3 162 valid samples were collected as external validation data. The system showed an area under the curve (AUC) of 0.890 (95% CI: 0.878-0.902), accuracy of 0.885 (95% CI: 0.873-0.896), sensitivity of 0.928 (95% CI: 0.914-0.941), and specificity of 0.852 (95% CI: 0.834-0.867). In the prospective study, 212 valid samples were collected, and five junior cytologists participated in the human-machine assisted study. Without artificial intelligence assistance, the average AUC for the five cytologists was 0.686 (95% CI: 0.650-0.722), the accuracy was 0.699 (95% CI: 0.671-0.727), the sensitivity was 0.653 (95% CI: 0.599-0.703), the specificity was 0.719 (95% CI: 0.685-0.750), the Fleiss κ value was 0.510, and the reading time was 223 seconds. With artificial intelligence assistance, the AUC, accuracy, sensitivity, and specificity increased by 0.166, 0.143, 0.225, and 0.107, respectively. Additionally, Fleiss κ was 0.730 and the reading time decreased by 188 seconds. All differences were statistically significant (all P<0.001). Conclusions:Artificial intelligence-assisted diagnosis system shows excellent performance and good generalizability, significantly improving the diagnostic accuracy, consistency, and efficiency of junior cytologists. It can be an effective auxiliary tool for junior cytologists in clinical practice.

The rapid development of artificial intelligence in the field of healthcare has greatly improved diagnosis accuracy, disease prediction, personalized treatment and healthcare resource management. However, with the widespread application of medical artificial intelligence, challenges has emerged in the aspects of medical data, model development and evaluation, and societal considerations. Therefore, this study aims to explore challenges in the application of artificial intelligence in healthcare and suggest a series of feasible solutions to improve medical professional and researchers' understanding of medical artificial intelligence and enhance the quality of healthcare in clinical practice

Objective     To systematically evaluate the safety, efficacy, and economics of intracardiac echocardiography (ICE) versus transesophageal echocardiography (TEE) in left atrial appendage occlusion (LAAO). Methods     PubMed, EMbase, The Cochrane Library, CBM, CNKI, VIP and WanFang Database were systematically  searched to collect relevant studies on comparing ICE and TEE-guided LAAO from inception to June 15th, 2022. Two reviewers independently screened the literatures, extracted the data, and assessed the risk of bias of the included studies. Meta-analyses were performed using RevMan 5.3 and R 4.0.3. Retrospective cohort studies were excluded for sensitivity analysis. Subgroup analyses were performed based on the types of occluder and ICE catheter. Results     A total of 14 studies with 6 599 patients were included. Meta-analyses showed no statistical differences in technical success rate, overall complications, device embolization, peri-device leakage, device-related thrombus, stroke, vascular complications, bleeding, operation time, fluoroscopy time, or contrast agent volume between the ICE and TEE-guided LAAO. The total in-room time (MD=–33.47 min, 95%CI –41.20 to –25.73, P<0.000 01) and radiation dosage (MD=–170.20 mGy, 95%CI –309.79 to –30.62, P=0.02) were lower in the ICE group than those in the TEE group, whereas the incidence of pericardial effusion/tamponade was higher than the TEE group (RR=1.57, 95%CI 1.01 to 2.45, P=0.048). Except for pericardial effusion/tamponade, subgroup analyses and sensitivity analysis showed similar results. The analysis based on the cost data from the United States showed comparable or even lower total costs for ICE versus TEE, but comparative domestic cost studies were lacking. Conclusion     Current evidence suggests that ICE-guided LAAO can reduce radiation dosage and total in-room time, and there is no statistical difference in the overall complication rate between the two groups. Owing to the limitations of sample size and quality of the included studies, the conclusion still needs to be verified by large sample size and high-quality randomized controlled trials.

Objective:To explore the current status and influencing factors of knowledge, attitude and practice of drug clinical trials among ovarian cancer patients.Methods:From July 2017 to December 2018, we selected 90 families of asthma children in Observation Room of Hangzhou Children's Hospital. All families were divided into observation group ( n=44) and control group ( n=46) with the method of random number table. In control group, pediatric specialist nurses provided regular self-management guidance and health education to children's families. Observation group received the intervention of asthma family empowerment program. Before intervention (when asthma children and their family members entered the Observation Room for treatment) and after intervention (the sixth week after intervention) , we evaluated the outcome indicators with the Parenting Stress Index (PSI) , Family Environment Scale (FES) and the Asthma Severity Scale. Results:The total score of PSI and scores of asthma status of observation group were lower than those of control group, and dimension scores of FES of observation group were better than those of control group, and the differences were statistically significant ( P<0.05) . Conclusions:Asthma family empowerment program is beneficial to reduce parents' stress index, improve functional status and children's asthma symptoms.

Objective: To explore the effect of Wenrun-Xinjin-Peiben paste on the nutrition status, quality of life and pulmonary function in the stable COPD patients. Methods: A total of 94 malnutrition patients with stable COPD were randomly divided into treatment group (47 cases) and control group (47 cases). The patients in the control group took Symbicort 1 suction/time, bid, and the patients were given oxygen therapy, health and diet nutrition education. The patients in the treatment group were given Wenrun-Xinjin-Peiben paste 6 months as well as the control group treatment. The nutritional status (body mass index, triceps skinfold thickness, upper arm circumference, hemoglobin, albumin, prealbumin), quality of life and pulmonary function in the two groups were compared. Results: The curative effect of TCM syndromes was 90.48% in the treatment group, which is significantly higher than 61.90 % in the control group (Z=3.173, P=0.002). The hemoglobin in the treatment group was superior to the control group (135.69 ± 16.42 g/L vs. 122.75 ± 14.99 g/L; t=12.346, P<0.001). The Albumin in the treatment group was superior to the control group (35.89 ± 6.14 g/L vs. 33.01 ± 6.20 g/L; t=2.139, P=0.035). The disease impacts domain of ST George's respiratory questionnaire in the treatment group was superior to the control group (24.9 ± 16.1 vs. 36.6 ± 16.9; t=3.252, P=0.002). Total score of ST George's respiratory questionnaire in the treatment group was superior to the control group (41.4 ± 14.9 vs. 48.0 ± 14.9; t=2.006, P=0.048). The FEV₁ predicted value in the treatment group was superior to the control group (65.22% ± 4.01% vs. 60.17% ± 4.34%; t=5.538, P=0.000). Conclusions The Wenrun-Xinjin-Peiben paste combined with western medicine could help to improve the nutritional status and quality of life of patients in stable COPD.

Objective: To evaluate the clinical performance of HPV genotyping with cytology for detecting cervical precancer among women attending co-testing. Methods: A total of 2 883 females who participated in cervical cancer screening program were recruited from Erdos in 2016. All the participants were tested by cytology and HPV genotyping. In 2017, women with abnormal cytology results or HPV positive were followed up. Pathological cervical intraepithelial neoplasia (CIN) 2+ was the study end-point. Clinical performance indexes were calculated, including sensitivity, specificity, positive predictive value, negative predictive value, referral rate and missed cases. Results: INNO-LiPA resulted in a detection rate of 18.87%(544/2 883) for the 14-type high risk HPV. HPV16 was the most common infectious genotype (4.06%), followed by HPV52 (3.61%), HPV51 (2.50%), HPV58 (1.98%), and HPV18 (1.56%). With more HPV genotypes added into the group, sensitivity increased and the specificity decreased. Addition of HPV16, 58, 33, 39, 52, 18, 31 for detection lead to the maximun value of area under the curve (AUC)=0.913 (95%CI: 0.882-0.944). Compared with traditional screening method by cytology, cotesting decreased the number of missed diagnosis. Meanwhile, the fifth method (co-testing: triage of women with HPV16/18+ , cytological minor abnormalities and HPV58, 33, 39, 52, 31+ or cytological high grade abnormalities) did not increase referral rate (8.99% vs. 8.71%, P=0.525), with five cases of missed diagnosis (sensitivity of 92.1% and specificity of 93.2%). Conclusions Co-testing with triage of women with HPV16/18+ , cytological minor abnormalities and HPV58, 33, 39, 52, 31+ or cytological high grade abnormalities would provide better clinical performance. In co-testing, triage of HPV16/18 was used in women with normal cytology; triage of HPV58, 33, 39, 52 and 31 was used in women with low-grade abnormal cytology; referral colposcopy was used in women with high-grade abnormal cytology, which would provide better clinical performance.

Objective To study the clinical efficacy and safety of purse-string suture on the treatment of peptic ulcer bleeding. Methods Data of 42 patients with peptic ulcer bleeding treated by purse-string suture with hexiejia combined with endoloop in Dongguan Tung Wah Hospital from January 2016 to January 2017 were retrospectively analyzed. The immediate hemostasis rate, effective hemostasis rate, additional surgery rate, recurrence rate in two weeks and mortality were analyzed. Results Among 20 cases with active bleeding during operation, 19 were immediately arrested, and 1 case of failure was diagnosed as marginal ulcer after gastric resection. The overall effective hemostasis rate was 97. 6%(41/42), additional surgery rate was only 2. 4%( 1/42). The vital signs of 41 patients with successful endoscopic hemostasis were stable after operation, and no fever, hematemesis, black stool or other symptoms occurred. No recurrence of bleeding or death occurred within two weeks. The ulcers were healed well in follow-up of one month. Conclusion Endoscopic purse-string suture is a safe and feasible method for treatment of patients with peptic ulcer bleeding.

Through a brief overview of the origin and development of artificial intelligence, the research progress of artificial intelligence in digestive endoscopy, ophthalmoscopy and electronic colposcopy was summarized, and the importance of its application was clarified. This article induced the main problems and suggestions of artificial intelligence in the development of medical endoscopes, and prospected the future application of artificial intelligence in medical endoscopy diagnosis.

Objective: to investigate the clinical value of p16/Ki-67 immunocytochemical dual staining (abbreviated as p16/Ki-67 dual staining) in cervical intraepithelial neoplasia (CIN) and cervical cancer screening. Methods: From July to November 2015, a total of 980 women attending cervical cancer screening and receiving high-risk human papillomavirus (HR-HPV) test and thinprep cytologic test (TCT) were included in the study. p16/Ki-67 immunocytochemical dual staining was performed on residual cytologic specimens and compared with histopathology results. Results: The expression risks of p16/Ki-67 in HPV16/18 group and another HR-HPV group were higher than HPV negative group, with an odds ratio of 10.64 (95%CI: 5.66~20.02) and 5.40 (95%CI: 3.62~8.04), respectively. The positive rate of p16/Ki-67 increased with the grade of TCT and histologic diagnosis, and was higher in both CIN2 and CIN3 groups than normal group (P<0.05). The sensitivity of p16/Ki-67 to detect CIN2+ and CIN3+ lesions was 89.3% and 94.1%, respectively, and the specificity was 69.3% and 66.8%, respectively. The sensitivity of TCT to detect CIN2+ and CIN3+ lesions was 60.7% and 64.7%, respectively, and the specificity was 49.3% and 49.1%, respectively. Conclusions Compared with TCT, p16/Ki-67 dual staining has higher sensitivity and specificity. It can identify high-grade cervical lesions and guide the classification of CIN. p16/Ki-67 dual staining in conjunction with HPV test may be considered as an efficient method for cervical cancer screening.