Catheter tips are a possible resource for biological study on catheter failure

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

OBJECTIVES

Complications 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.

DESIGN

Pilot study.

SETTING

The University of Tokyo Hospital, Japan.

PRIMARY AND SECONDARY OUTCOME MEASURES

First, 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.

RESULTS

Through 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.

CONCLUSIONS

Our 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.

Preventing peripheral intravenous catheter failure by reducing mechanical irritation

Peripheral intravenous catheter failure is a significant concern in the clinical setting. We investigated the effectiveness of care protocols, including an ultrasonographic “pre-scan” for selecting a large-diameter vein before catheterization, a “post-scan” for confirming the catheter tip position after catheterization with ultrasonography, and the use of a flexible polyurethane catheter to reduce the mechanical irritation that contributes to the incidence of catheter failure. This intervention study was a non-randomized controlled trial to investigate the effectiveness of the abovementioned care protocols, the effects of which were compared to the outcomes in the control group, which received conventional care. For both groups, participants were selected from patients in two wards at the University of Tokyo in Japan between July and November 2017. Inverse probability score-based weighted methods (IPW) using propensity score were used to estimate the effectiveness of care protocols. The primary outcome was catheter failure, which was defined as accidental and unplanned catheter removal. We used Kaplan-Meier survival curves to compare rates of time until catheter failure. We analysed 189 and 233 catheters in the intervention and control groups, respectively. In the control group, 68 catheters (29.2%) were determined to have failed, whereas, in the intervention group, only 21 catheters (11.1%) failed. There was a significant difference between each group regarding the ratio of catheter failure adjusted according to IPW (p = 0.003). The relative risk reduction of the intervention for catheter failure was 0.60 (95% CI: 0.47–0.71). Care protocols, including assessment of vein diameter, vein depth, and catheter tip location using ultrasound examination for reducing mechanical irritation is a promising method to reduce catheter failure incidence.