Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Patients in acute myocardial infarction (AMI) with serious complications such as malignant ventricular arrhythmia and cardiogenic shock couldn't receive emergency percutaneous coronary intervention (PCI) procedures and had high perioperative mortality. A case of AMI patients who suffered cardiac arrest and long-term cardiopulmonary resuscitation (CPR) was admitted to the department of critical care medicine of the First People's Hospital of Foshan. With the assistance of extracorporeal membrane oxygenation (ECMO), PCI and intra-aortic balloon counterpulsation (IABP) were performed. ECMO and ventilator were successfully weaned after anti-shock, mechanical ventilation, organ support treatment. The patient was successfully treated and discharged. After 6 months of follow-up, the patient recovered well in heart function.
Extracorporeal Membrane Oxygenation ; Heart Arrest ; Humans ; Intra-Aortic Balloon Pumping ; Myocardial Infarction ; Percutaneous Coronary Intervention ; Shock, Cardiogenic ; Treatment Outcome

Patients in acute myocardial infarction (AMI) with serious complications such as malignant ventricular arrhythmia and cardiogenic shock couldn't receive emergency percutaneous coronary intervention (PCI) procedures and had high perioperative mortality. A case of AMI patients who suffered cardiac arrest and long-term cardiopulmonary resuscitation (CPR) was admitted to the department of critical care medicine of the First People's Hospital of Foshan. With the assistance of extracorporeal membrane oxygenation (ECMO), PCI and intra-aortic balloon counterpulsation (IABP) were performed. ECMO and ventilator were successfully weaned after anti-shock, mechanical ventilation, organ support treatment. The patient was successfully treated and discharged. After 6 months of follow-up, the patient recovered well in heart function.

ObjectiveTo explore the clinical feature of severe hand, foot and mouth disease (HFMD) in pediatric patients, and to observe the hemodynamic changes in those with acute pulmonary edema.Methods A prospective observation study was conducted. Thirty-five severe HFMD pediatric patients with acute pulmonary edema admitted to the intensive care unit (ICU) and Department of Pediatric of First People's Hospital of Foshan from May 2008 to September 2014 were enrolled. The clinical features were thoroughly investigated. Hemodynamic data were monitored by pulse-indicated continuous cardiac output (PiCCO) in 5 cases, and the changes in PiCCO parameters were observed at ICU admission (0 hour), and 24, 48, 96 hours after treatment.Results Thirty-five patients who met the diagnostic standard of severe HFMD were enrolled, including 22 male and 13 female, aged from 7 months to 4 years. Six patients were younger than 1 year, 13 1-2 years, 12 2-3 years, and 4 patients 3-4 years old. The most common time of occurrence of pulmonary edema was 3-4 days after the onset of the disease. Fever and central nervous system symptoms were found in all the patients, and examination of the cerebral spinal fluid (CSF) revealed non-bacterial inflammatory changes. PiCCO results showed a tendency of lowering of heart rate (HR), systemic vascular resistance index (SVRI), and extravascular lung water index (EVLWI) after the treatment, and the values obtained at 96 hours were significantly lower than those at 0 hour [HR (bpm): 119.0±14.7 vs. 200.8±19.7, SVRI (kPa·s·L-1·m-2):148.9±14.6 vs. 209.6±58.7, EVLWI (mL/kg): 10.5±1.9 vs. 34.8±10.8,P< 0.05 orP< 0.01], global end-diastolic volume index (GEDVI) was also gradually decreased without significant differences among all the time points, together with a tendency of increase in stroke volume index (SI) and cardiac index (CI). The values of the parameters at 96 hours were significantly higher than those at 0 hour [SI (mL/m2): 38.5±6.5 vs. 17.4±2.8, CI (mL·s-1·m-2): 75.0±8.0 vs. 55.5±8.5, bothP< 0.01]. Left atrium was found to be enlarged, and left ventricular systolic function decreased in two patients by cardiac ultrasonic. Four out of 35 patients died, and functional disability of extremities was found in 1 patient. Other patients were cured and discharged without any sequelae.Conclusions Severe HFMD complicated by acute pulmonary edema is a perilous condition in children, accompanied commonly by pathologic changes in central nervous system and systolic dysfunction of left ventricle. According to the results with PiCCO monitoring, HFMD patients suffering from acute pulmonary edema may be of cardiac origin in addition to neurogenic origin.

Objectives To evaluate the effects of enteral nutrition(EN)and parenteral nutrition(PN)support in critically ill surgical patients. Methods 80 patients who could not eat were randomized into two groups:one group receivedEN,the other group received PN. The nutrition parameters including nitrogen balance, serum levels of albumin, prealbumin, transferrin and retinal-binding protein,immunity function parameters including immunoglobulin A, immunoglobulin G,immunoglobulin M,and natural kill cell activity, and patients'tolerability parameters including glutamic-oxalacetic transaminase, glutarmic-pyruvic transaminase, blood urea nitrogen and creatinine,and plasma glucose were compared. Results After 10 days'therapy,the two groups all turned from negative nitrogen balance to positive nitrogen balance. The nutrition parameters and immunity function parameters increased significantly in both groups and the latter in group EN increased more. For tolerability parameters, blood sugar in group PN increased obviously and no change in EN group. ConclusionsBoth EN and PN play a rde in nutrition support and elevation of immunity function. Patients tolerate well. EN has better effects on elevation of immunity function and patients tolerate better compared with PN.