ABSTRACT
Artificial intelligence has been gradually applied in medical image diagnosis, showing good efficiency and diagnostic accuracy. As a recent innovation in artificial intelligence, convolutional neural network (CNN) displayed the ability to interpret medical images with accuracy at or near that of skilled clinicians for some applications, indicating overwhelming clinical application prospects. The research progresses of CNN in musculoskeletal radiology were reviewed in this article.
ABSTRACT
Objective To investigate the application of the cross-sectional area ratio of internal jugular vein and common carotid artery (IJV/CCA) in the evaluating the volume responsiveness of critically ill patients. Methods The capacity of critically ill patients were prospectively assessed. The diameter and sectional area of the IJV and CCA were measured by bedside ultrasonography. The cross-sectional area ratio of IJV/CCA was calculated and compared with the variety of cardiac output (ΔCO) after passive leg raising (PLR). Then the correlation index between the cross-sectional area ratio of IJV/CCA and ΔCO was evaluated, and the sensitivity and specificity parameters of capacity status were assessed by the cross-sectional area ratio of IJV/CCA. Results Of 55 critically ill patients in this study, 34 cases had positive volume responsiveness, and 21 case negative volume responsiveness.The general clinical data of the two groups had no statistically significant difference. The cross-sectional area ratio of IJV/CCA in the positive group was significantly less than that of the negative group (1.38±0.55 vs. 2.16±0.68, P<0.01). There was a significant correlation between the IJV/CCA cross-sectional area ratio and the ΔCO value of PLR (r=-0.67, P<0.01). When the ratio of the cross-sectional area of IJV/CCA was 1.65, the sensitivity of the assessment capacity was 86.4％ and the specificity was 78.8％. Conclusions The use of portable bedside ultrasonography is a noninvasive, convenient and reliable method to evaluate the capacity state of the critically ill patients.
ABSTRACT
Based on analyzing the problems existed in hostital informatization, the paper proposes using shared-database to realize data sharing among various departments.It mainly introduces shared-database and its function module and customer display module. The introduction of shared-database is conducive to comprehensive management of hospital data, providing basis for future data mining.