AI Assistance in GI Endoscopy Recovery Assessment (AIVR2)

Effectiveness of Artificial Intelligence-assisted Recovery Assessment After Outpatient Gastrointestinal Endoscopy. A Pilot Double-blind Randomized Controlled Trial.

We have developed and validated an AI model to assess endoscopy recovery status based on 400 voice recordings from 200 patients. This model has a mean accuracy of 84.14% with a mean area under the curve (AUC) of 0.91.

To further enhance the performance of this AI model, we plan to collect additional voice recordings to retrain it. We also plan to develop a mobile application of this AI model for effectiveness evaluation in a pilot randomized controlled trial (RCT) setting. Endoscopy nurses in Hong Kong were invited to participate in a survey study. Therefore, we believe implementation of AI model in clinical practice will be well accepted by endoscopy nurses in Hong Kong.

Study Overview

• Status: Not yet recruiting
• Conditions: Artificial Intelligence Assistance in Endoscopy Recovery; AI Validation
• Intervention / Treatment: Other: AI-assisted endoscopy recovery assessment

Detailed Description

Globally, cancer is one of the leading causes of death. 70% of this global burden of cancer is attributed to premature mortality, of which 70% of these deaths are preventable and 30% are treatable Globally, cancer is one of the leading causes of death. 70% of this global burden of cancer is attributed to premature mortality, of which 70% of these deaths are preventable and 30% are treatable . Among the ten most common causes of cancer death worldwide, one third are digestive cancers. These can be diagnosed by outpatient gastrointestinal endoscopy. These include colorectal cancer (via colonoscopy), as well as esophageal and gastric cancer (via esophagogastroduodenoscopy). In addition to diagnosis, outpatient endoscopy is also widely used for cancer screening and surveillance. With the global increase in the aging population and heightened awareness of cancer screening, the demand for endoscopy services for cancer screening, diagnosis and surveillance is rapidly increasing to achieve the goal of early cancer detection and treatment.

To reduce patients' fear and anxiety regarding endoscopy and to relieve the associated pain and discomfort, most endoscopies are performed under sedation. It is known that the sedative effect lasts longer than needed for diagnostic or basic therapeutic colonoscopies, which can mostly be done within 30 minutes. Patients are closely monitored at the recovery room after the completion of the endoscopy, and the recovery nurse assesses the consciousness of the patient after a fixed period of time, typically 60 minutes, or every 10 minutes until the standardized discharge criteria are met. In an outpatient setting, it is important to determine if patients are fully recovered from the sedative effect and have reached a clinically stable state before discharging them from the hospital with the accompany of a responsible adult. The assessment of the standardized discharge criteria includes the followings: 1) return of consciousness to baseline level; 2) vital signs are within normal limits; 3) respiratory status is not compromised; and 4) pain and discomfort have been addressed. A standardized discharge assessment scoring, such as, the modified Aldrete's score, and the modified post-anaesthesia discharge scoring system (mPADSS), were recommended. The mean recovery time required by both systems was reported to be 60 minutes, which is quite time-consuming. International guidelines on sedation in gastrointestinal endoscopy recommend a 1:1 nursing ratio to closely monitor patients following moderate or deep sedation to enhance patient safety. With this 1:1 ratio, recovery nurses can assess the consciousness level of patient every 10 minutes by standardized discharge assessment scoring, which facilitates a shorter recovery time. However, assessment every 10 minutes is time-consuming and labour-intensive and such recovery nursing ratio may not be practicable in resource-limited countries. In Hong Kong, the usual recovery nursing ratio is 1:10, therefore, the current standard practice is to assess patient's consciousness after 60 minutes. As a result, the number of endoscopies arranged in each session is limited by the recovery time (i.e. patient turnover rate), the recovery space and nursing manpower. Moreover, the decision of the recovery nurse on whether a patient is dischargeable can be interfered by a series of contextual factors, such as heavy workload, the availability of recovery space and the demand of patient. A fast, convenient, and reliable assessment system is warranted to reduce the recovery time (i.e. to increase the turnover rate) because of the anticipated increasing demand of sedated endoscopy which leads to the requirement for space and nursing manpower for patient recovery. To our best knowledge, no interventional trial has been conducted to reduce the recovery time by AI technology without increasing the nursing manpower. In the past decade, artificial intelligence (AI) technology has emerged and been successfully implemented in various clinical settings, particularly in the field of gastrointestinal endoscopy. AI models trained from endoscopic images have been proven to be effective in detecting and diagnosing gastrointestinal diseases and cancers. Human voice can be transferred to image and used to train AI models to assist in disease diagnosis. For example, AI has been trained to effectively detect Alzheimer's disease and predict its severity solely based on patients' voice data. Another AI model has been developed based on voice analysis to distinguish major psychiatric disorders, including bipolar, depressive, anxiety and schizophrenia spectrum disorders. Given these promising results, we have developed and validated an AI model to assess endoscopy recovery status based on 400 voice recordings from 200 patients. This model has a mean accuracy of 84.14% with a mean area under the curve (AUC) of 0.91. To further enhance the performance of this AI model, we plan to collect additional voice recordings to retrain it. We also plan to develop a mobile application of this AI model for effectiveness evaluation in a pilot randomized controlled trial (RCT) setting. Endoscopy nurses in Hong Kong were invited to participate in a survey study. Therefore, we believe implementation of AI model in clinical practice will be well accepted by endoscopy nurses in Hong Kong.1). Among the ten most common causes of cancer death worldwide, one third are digestive cancers. These can be diagnosed by outpatient gastrointestinal endoscopy. These include colorectal cancer (via colonoscopy), as well as esophageal and gastric cancer (via esophagogastroduodenoscopy). In addition to diagnosis, outpatient endoscopy is also widely used for cancer screening and surveillance. With the global increase in the aging population and heightened awareness of cancer screening, the demand for endoscopy services for cancer screening, diagnosis and surveillance is rapidly increasing to achieve the goal of early cancer detection and treatment. To reduce patients' fear and anxiety regarding endoscopy and to relieve the associated pain and discomfort, most endoscopies are performed under sedation. It is known that the sedative effect lasts longer than needed for diagnostic or basic therapeutic colonoscopies, which can mostly be done within 30 minutes. Patients are closely monitored at the recovery room after the completion of the endoscopy, and the recovery nurse assesses the consciousness of the patient after a fixed period of time, typically 60 minutes, or every 10 minutes until the standardized discharge criteria are met. In an outpatient setting, it is important to determine if patients are fully recovered from the sedative effect and have reached a clinically stable state before discharging them from the hospital with the accompany of a responsible adult. The assessment of the standardized discharge criteria includes the followings: 1) return of consciousness to baseline level; 2) vital signs are within normal limits; 3) respiratory status is not compromised; and 4) pain and discomfort have been addressed (10). A standardized discharge assessment scoring, such as, the modified Aldrete's score, and the modified post-anaesthesia discharge scoring system (mPADSS), were recommended. The mean recovery time required by both systems was reported to be 60 minutes, which is quite time-consuming. International guidelines on sedation in gastrointestinal endoscopy recommend a 1:1 nursing ratio to closely monitor patients following moderate or deep sedation to enhance patient safety. With this 1:1 ratio, recovery nurses can assess the consciousness level of patient every 10 minutes by standardized discharge assessment scoring, which facilitates a shorter recovery time. However, assessment every 10 minutes is time-consuming and labour-intensive and such recovery nursing ratio may not be practicable in resource-limited countries. In Hong Kong, the usual recovery nursing ratio is 1:10, therefore, the current standard practice is to assess patient's consciousness after 60 minutes. As a result, the number of endoscopies arranged in each session is limited by the recovery time (i.e. patient turnover rate), the recovery space and nursing manpower. Moreover, the decision of the recovery nurse on whether a patient is dischargeable can be interfered by a series of contextual factors, such as heavy workload, the availability of recovery space and the demand of patient. A fast, convenient, and reliable assessment system is warranted to reduce the recovery time (i.e. to increase the turnover rate) because of the anticipated increasing demand of sedated endoscopy which leads to the requirement for space and nursing manpower for patient recovery. To our best knowledge, no interventional trial has been conducted to reduce the recovery time by AI technology without increasing the nursing manpower. In the past decade, artificial intelligence (AI) technology has emerged and been successfully implemented in various clinical settings, particularly in the field of gastrointestinal endoscopy. AI models trained from endoscopic images have been proven to be effective in detecting and diagnosing gastrointestinal diseases and cancers. Human voice can be transferred to image and used to train AI models to assist in disease diagnosis. For example, AI has been trained to effectively detect Alzheimer's disease and predict its severity solely based on patients' voice data. Another AI model has been developed based on voice analysis to distinguish major psychiatric disorders, including bipolar, depressive, anxiety and schizophrenia spectrum disorders.

• Study Type: Interventional
• Enrollment (Estimated): 460
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Felix SIA; Phone Number: 852-26370428; Email: felixsia@cuhk.edu.hk

Study Locations

• Hong Kong
  • New Territories, Hong Kong
    • Alice Ho Miu Ling Nethersole Hospital
    • Contact: Felix SIA; Phone Number: 852-26370428; Email: felixsia@cuhk.edu.hk

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• speak Cantonese;
• aged ≥18 years;
• undergoing outpatient sedated gastrointestinal endoscopy of any indication in Combined Endoscopy Unit at Alice Ho Miu Ling Nethersole Hospital

Exclusion Criteria:

• patients who are unable to provide consent or communicate verbally

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Double

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: AI-assisted endoscopy recovery assessment (AI) arm; The patients randomized to the AI arm will be assessed by the AI model regularly. A smartphone, with the mobile application of the AI model to assess for endoscopy recovery installed, will be attached to the head of the stretcher once the patient arrives at the recovery room. After the recovery nurse starts the AI application following the standard-of-care baseline assessment of vital signs, the AI application will prompt an automatic voice alarm to wake up the patient by asking if he/she is awake every 10 minutes. If the patient swipes the confirmation button, the AI application will ask them to read from 1 to 7. The patient's voice will be recorded and analyzed by the AI model. The assessment results of endoscopy recovery status will be uploaded to the cloud server and notify the recovery nurse. The recovery nurse will provide an early assessment of recovery if the AI analysis result suggests the patient is "conscious" before the pre-specified time point of standard-of-care.	Other: AI-assisted endoscopy recovery assessment; The intervention group will be assessed by the AI model regularly, which will be installed in a smartphone attached to the head of the stretcher once the patient in this group arrives at the recovery room. After the recovery nurse starts the AI application following the standard-of-care baseline assessment of vital signs, the AI application will prompt an automatic voice alarm to wake up the patient by asking if he/she is awake every 10 minutes.
No Intervention: Standard-of-care (SC) arm; The recovery nurse will perform baseline assessments of vital signs every 10 minutes once the patient arrives at the recovery room, and a smartphone will be attached to the head of the stretcher, which will prompt an automatic voice alarm to wake up the patient by asking if he/she is awake every 10 minutes. If the patient swipes the confirmation button, they will be asked to read from 1 to 7. The patient's voice will be recorded but without AI analysis. The recovery nurse will assess the consciousness of the patient by mPADSS at a pre-specified time point: 1) after 60 minutes; 2) on demand of patient; 3) by nurse's judgement; or 4) in shortage of recovery space. After the subjects have fully recovered from sedation and are able to perform the 100-7 subtraction test correctly for 3 times, they will be asked to rate their satisfaction in terms of bedside manner, endoscopy technique, level of explanation and overall experience, time of stay and the care provided at the recovery room.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Recovery time	Differences between the time of arrival at the recovery room and the time of discharge	Periprocedural

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Proportion of early discharge	Recovery time less than 60 minutes will be reported as early discharge, and the proportion will be recorded	Periprocedural
Manpower usage	A research assistant will record the patient contact time by the recovery nurse to calculate the manpower	Periprocedural
Patient's satisfaction	Patient's perceived satisfaction in terms of time of stay and the care provided at the recovery room will be assessed after he/she is fully recover from sedation	Periprocedural
Patient's enrollment rate	Number of participations divided by the total number of patients asked for consent	Periprocedural
Post-endoscopy adverse event rate	Post-endoscopy adverse events, including haemoptysis, abdominal pain, and per rectal bleeding, and their rates at discharge and within 7 days will be recorded	Periprocedural

Collaborators and Investigators

• Sponsor: Chinese University of Hong Kong

Study record dates

Study Major Dates

• Study Start (Estimated): April 1, 2025
• Primary Completion (Estimated): December 31, 2026
• Study Completion (Estimated): June 30, 2027

Study Registration Dates

• First Submitted: March 25, 2025
• First Submitted That Met QC Criteria: April 9, 2025
• First Posted (Actual): April 11, 2025

Study Record Updates

• Last Update Posted (Actual): April 11, 2025
• Last Update Submitted That Met QC Criteria: April 9, 2025
• Last Verified: April 1, 2025

More Information

Terms related to this study

• Keywords: randomized controlled trial; colonoscopy; Artificial intelligence; gastrointestinal; endoscopy recovery
• Other Study ID Numbers: 2024.637

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: There will be no plan to share Individual participant data

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No