Coping with complications that occur after ureteral stent insertion for satisfactory evaluation of call service using artificial intelligence: A randomized controlled trial (Preprint)

Abstract

Ureteral stent, represented by double-J stent, have become indispensable in urologic procedures, but also has several complications such as hematuria and pain. While the advancement of AI technology has led to its increasing application in the health sector, there has been no utilization of AI to provide information on potential complications and to facilitate subsequent measures in the event of such complications.

This RCT was conducted to assess the effectiveness of an AI-based prediction tool in providing patients with information about potential complications from ureteroscopy and ureteric stent placement, and indicating the need for early additional therapy.

A total of 28 patients, aged between 20 and 70, who underwent ureteral stent insertion for the first time without history of psychological illness, were consecutively included in the study. A service known as ‘Ansim-call’ was set up to equip patients with details about the procedure and post-procedure care, to monitor for complications and their severity. Patients were randomly allocated into 2 groups, Ansim-call by AI (Group 1) and Ansim-call by human (Group 2). The primary outcome was the level of satisfaction with the Ansim-call service itself, measured using a Likert scale. Secondary outcomes included satisfaction with the AI-assisted Ansim-call service, also measured using a Likert scale, and the level of satisfaction and anxiety related to managing complications for both groups. Satisfaction in managing complications was evaluated using both a Likert scale and a VAS, while anxiety was assessed using the STAI and VAS.

Total 28 patients, 14 in each group, were recruited, but 1 patient in Group 2 dropped out due to a change of mind. Baseline characteristics of patients showed no significant differences. Satisfaction with Ansim-call averaged 4.14 (SD 0.66) and 4.54 (SD 0.52) in each group, with no significant difference between AI and human. AI-assisted Ansim-call satisfaction averaged 3.43 (SD 0.94). Satisfaction about management of complications using Likert scale averaged 3.79 (SD 0.70) and 4.23 (SD 0.83), respectively, showing no significant difference, but a significant difference was observed when using VAS, with averages of 6.64 (SD 2.13) in Group 1 and 8.69 (SD 1.80) in Group 2. Anxiety about complications using STAI averaged 36.43 (SD 9.17) and 39.23 (SD 8.51), while anxiety assessed with VAS averaged 4.86 (SD 2.28) and 3.46 (SD 3.38), respectively, showing no significant difference. Multiple regression analysis was performed on all outcomes, and human showed superior satisfaction for management of complications than AI. Otherwise, most of other variables showed no significant differences.

This is the first study to use AI for patient reassurance regarding complications after ureteric stent placement. The study found patients satisfied similarly for reassurance call conducted by AI or humans. Further research in larger populations is warranted to confirm these findings.

CRIS No. KCT0008062