Automatic vein measurement by ultrasonography to prevent peripheral intravenous catheter failure for clinical practice using artificial intelligence: development and evaluation study of an automatic detection method based on deep learning

Abstract

ObjectivesComplications due to peripheral intravenous catheters (PIVC) can be assessed using ultrasound imaging; however, it is not routinely conducted due to the need for training in image reading techniques. This study aimed to develop and validate a system that automatically measures blood vessel diameters on ultrasound images using artificial intelligence (AI) and provide recommendations for selecting an implantation site.DesignPilot study.SettingThe University of Tokyo Hospital, Japan.Primary and secondary outcome measuresFirst, based on previous studies, the vessel diameter was calculated as the mean value of the maximum long diameter plus the maximum short diameter orthogonal to it. Second, the size of the PIVC to be recommended was evaluated based on previous studies. For the development and validation of an automatic detection tool, we used a fully convoluted network for automatic estimation of vein location and diameter. The agreement between manually generated correct data and automatically estimated data was assessed using Pearson’s product correlation coefficient, systematic error was identified using the Bland-Altman plot, and agreement between catheter sizes recommended by the research nurse and those recommended by the system was evaluated.ResultsThrough supervised machine learning, automated determination was performed using 998 ultrasound images, of which 739 and 259 were used as the training and test data set, respectively. There were 24 false-negatives indicating no arteries detected and 178 true-positives indicating correct detection. Correlation of the results between the system and the nurse was calculated from the 178 images detected (r=0.843); no systematic error was identified. The agreement between the sizes of the PIVC recommended by the research nurse and the system was 70.2%; 7% were underestimated and 21.9% were overestimated.ConclusionsOur automated AI-based image processing system may aid nurses in assessing peripheral veins using ultrasound images for catheterisation; however, further studies are still warranted.t

Handheld Ultrasound Devices for Peripheral Intravenous Cannulation

“…One study reported a remotely supervised ultrasound training program 32. Other USG PIVC training strategies featured in the literature that hold promise include artificial intelligence vessel image interpretation,42 immersive virtual reality,43 peer-assisted learning,44 and clinician rotations to the hospital vascular access team 45…”

“…One study reported a remotely supervised ultrasound training program. 32 Other USG PIVC training strategies featured in the literature that hold promise include artificial intelligence vessel image interpretation, 42 immersive virtual reality, 43 peer-assisted learning, 44 and clinician rotations to the hospital vascular access team. 45 Achieving competence with USG PIVC insertion is an area that needs more research, particularly as the studies in this review reported a wide range of successful cannulations needed for minimal competency.…”

Evaluating Accuracy of Rectal Fecal Stool Assessment Using Transgluteal Cleft Approach Ultrasonography

“…Recently, POCUS educational programs have been developed for nurses [31][32][33], and US training on the transgluteal cleft approach will need to be developed and disseminated because it is already presented in expert consensus documents and guidelines to assess constipation [14,28]. In addition, the development of artificial intelligence (AI)-assisted functions would be an effective means of making the procedure easier for nurses, as has already been put to practical use in the observation of the bladder and rectum in transabdominal approaches [25,34], peripheral veins [35], etc.…”

Effects of ultrasound with an automatic vessel detection system using artificial intelligence on the selection of puncture points among ultrasound beginner clinical nurses

“…[14][15][16] We previously reported the application of an automated vessel detection system (AVDS) using AI to support ultrasound beginners. 17 In addition, AVDS was implemented in a commercially available smartphone ultrasound device. It detects areas in short-axis images that have the characteristics of a vessel (circular or elliptical anechoic area) and displays the vein size in the form of numbers and colors in real time (Figure 1).…”