ObjectiveTo study the application of artificial intelligence based on neural network in breast cancer screening and diagnosis, and to summarize its current situation and clinical application value.MethodThe combined studies of neural network and artificial intelligence in the directions of breast mammography, breast ultrasound, breast magnetic resonance, and breast pathology diagnosis in CNKI and PubMed database were reviewed.ResultsPublic databases of mammography, such as Digital Database for Screening Mammography (DDSM), provided raw materials for the research of neural network in the field of mammography. Mammography was the most widely used data for screening and diagnosis of breast diseases by neural network. In the field of mammography and color doppler ultrasound, neural network could segment, measure, and analyze the characteristics, judge the benign or malignant, and issue a structured report. The application of neural network in the field of breast ultrasound focused on the diagnosis and treatment of benign and malignant breast diseases. Samsung Madison Group taken the lead in grafting research results into ultrasound instruments. Breast MRI had a lot of high-throughput information, which had became the breakthrough point for the joint study of artificial neural network and imaging omics. Pathological images had more data information to be measured, and quantitative analysis of data was the advantage of neural network. The combination of the two kinds of methods could significantly improve the diagnosis time of pathologists.ConclusionsTo study the application of artificial intelligence in breast cancer screening and diagnosis is to analyze the application of neural network in breast imaging and pathology. At present, artificial intelligence screening can be used as a physician assistant and an objective diagnostic reference assistant, to improve the diagnosis of breast disease. With the development of medical image histology and neural network, the application of artificial intelligence in medical field can be extended to surgical method design, efficacy evaluation, prognosis analysis, and so on.
Objective To assess the effectiveness and safety of traditional Chinese medicinal herbs for subfertility. Method Databases used including MEDLINE, EMBASE, CBM and the Cochrane Controlled Trial Register (CCTR). Potentially related trials in reference lists of studies were hand searched. Published RCTs in any languages and length whether they were blind or unblind, were included. Treatments were Chinese medicinal herbs (single or compound), and controls were placebo, standard medical intervention, or no intervention. Data were extracted independently by two reviewers and analyzed with Revman 4.2 softeware. Results 7 randomized trials, including 1 042 patients met inclusion criteria. Methodological quality of all trials was poor. Chinese medicinal herbs were effective compared with routine antibiotics [RR 1.49, 95％CI (1.37 to1.62), Plt;0.000 01] and resulted in higher pregnancy rate [RR 1.46, 95%CI (1.09 to,1.96), P=0.01]. There were no adverse events reported in treatment group. Conclusions Some Chinese medicinal herbs may be effective for subfertility. However, the evidence is too weak to draw a conclusion. More strictly designed, randomized, double-blind, placebo-controlled trials are required.
ObjectiveTo investigate the evening outpatient service demand in West China Hospital, in order to provide better service. MethodsUsing self-questionnaire, we investigated 1 734 outpatients and the data were analyzed with SPSS 16.0 software. ResultsA total of 90.7% of the surveyed patients reported that it was necessary to have evening outpatient service, 53.1% of the patients were willing to come to the hospital in the morning, and 4.2% prefer to come to the hospital in the evening. ConclusionEvening outpatient service in large general hospitals is getting high social affirmation. It is helpful to those who are inconvenient or unwilling to come to the hospital during day time, and is a complement for day-time outpatient and emergency outpatient service. Consultation time and resource arrangement in the evening outpatient service should conform to the principle of rational allocation for hospital resources.
ObjectiveTo investigate the efficacy and safety of intravenous diltiazem in controlling ventricular rate in elderly patients with atrial fibrillation. MethodWe retrospectively analyzed the clinical data of patients suffering from atrial fibrillation with rapid ventricular rate presented to the Emergency Department between January 2014 and January 2015, and found that 57 elderly patients aged over 70 were treated with intravenous diltiazem for ventricular rate controlling. We analyzed the general situation of this group of patients, the changes of heart rate and mean arterial pressure before and after the treatment, and the adverse reactions to the treatment. ResultsThe total effective rate was 92.9%, and the mean onset time was (13.3±7.3) minutes. The mean arterial pressure showed no significant difference after treatment, and the heart function showed no significant deterioration. Only 4 patients (7.0%) had symptoms of transient hypotension. ConclusionsFor elderly patients with atrial fibrillation with rapid ventricular rate, intravenous diltiazem can control the ventricular rate rapidly, efficiently, safely, and sustainably.
ObjectiveTo explore the effect of continuous improvement of quality control system on the emergency treatment efficiency for patients with acute ST segment elevation myocardial infarction (STEMI) after the establishment of Chest Pain Center. MethodsWe retrospectively analyzed the differences of theory examination scores acquired by the Chest Pain Center staff one month before and after they got the system training. Moreover, we designated the STEMI patients treated between May and August 2015 after the establishment of Chest Pain Center but before optimization of process to group A (n=70), and patients treated from September to December 2015 after optimization of process to group B (n=55). Then we analyzed the differences between these two groups in terms of the time from patients' arriving to registration, the time from arriving to first order, the length of stay in Emergency Department, and even the time from door to balloon (D2B). ResultsThe scores acquired by Chest Pain Center staff before and after system training were 69.89±6.34 and 87.09±4.39 respectively, with a significant difference (P＜0.05). All the time indicators of both group A and group B were shown as median and quartile. The time from patients' arriving to registration of group A and group B was 6.0 (0.0, 11.0) minutes and 1.0 (0.0, 3.0) minutes (P＜0.05); the time from arriving to first order was 12.8 (9.0, 18.0) minutes and 5.0 (3.0, 9.0) minutes (P＜0.05); the length of stay in Emergency Department was 54.0 (44.0,77.0) minutes and 33.0 (20.0, 61.0) minutes (P＜0.05); and the time of D2B was 107.5 (89.0, 130.0) minutes and 79.0 (63.0, 108.0) minutes (P＜0.05). ConclusionAfter taking measures such as drawing lessons from the past, training staff and optimizing process continuously, we have significantly shortened the acute STEMI patients' length of stay in the Emergency Department, which has saved more time for the following rescue of STEMI patients.
ObjectiveTo develop mobile phone terminal application software using artificial intelligence (AI) model of breast ultrasound so as to provide an opportunity for early diagnosis of patients with breast cancer irrespective of time and space. MethodsThe ultrasonic electronic images of patients underwent operation in the Department of Breast Surgery of West China Hospital of Sichuan University from January 2018 to April 2019 were collected. The neural network deep learning algorithm was used to train and test the breast ultrasonic electronic images at a ratio of 4∶1 to establish DeepBC model, and a mobile phone terminal application software was developed according to the trained DeepBC model, which included image reconstruction module, image classification module, and missed diagnosis module to identify and diagnose the uploaded ultrasonic electronic images. Results A total of 4 128 ultrasonic electronic images were collected in this study, including 3 302 in the training set and 826 in the test set. The accuracy, sensitivity, specificity, false positive rate, and false negative rate of the DeepBC model for the identification of malignant and non-malignant lesions in the breast ultrasound images were 93.70%, 93.10%, 94.08%, 5.92%, and 6.90%, respectively. The optimal cut-off value was 92.31% by receiver operating characteristic curve of DeepBC model and the area of receiver operating characteristic curve was 0.987. The DeepBC mobile phone terminal application software was developed according to the DeepBC model, and the web page was released in the mobile wechat. So far, more than 10 000 people had uploaded ultrasonic electronic images on the wechat web page, and the diagnosis had exceeded 30 000 times. ConclusionsIn this study, an AI DeepBC model is established successfully based on ultrasonic electronic images, each module of mobile phone terminal application software runs well and independently. And web page is simple and contents are easy to be comprehended.