Adenoma Colon, Colon Polyp, Colorectal Polyp, Polyps
Conditions
Keywords
Artificial Intelligence, Endoscopy, ADR
Brief summary
Background: Colonoscopy is accepted to be the gold standard for screening of colorectal cancer (CRC). Most CRCs develop from adenomatous polyps, with colonoscopy accepted to be the gold standard for screening of CRC. An endoscopist's ability to detect polyps is assessed in the form of an Adenoma Detection Rate (ADR). Each 1.0% increase in ADR is associated with a 3.0% decrease in the risk of the patient developing an interval CRC. There remains a wide variation in endoscopist ADR. More recently, the use of artificial intelligence (AI) and computer aided diagnosis in endoscopy has been gaining increasing attention for its role in automated lesion detection and characterisation. AI can potentially improve ADR, but previous AI related work has largely focused on retrospectively assessing still endoscopic images and selected video sequences which may be subject to bias and lack clinical utility. There are only limited clinical studies evaluating the effect of AI in improving ADR. The CADDIE device uses convolutional neural networks developed for computer assisted detection and computer assisted diagnosis of polyps. Primary objective: To determine whether the CADDIE artificial intelligence system improves endoscopic detection of adenomas during colonoscopy. Primary endpoint: The difference in adenoma detection rate (ADR) between the intervention (supported with the CADDIE system) and non-intervention arm Study design: Multi-Centre, open-label, randomised, prospective trial to assess efficacy and safety of the CADDIE artificial intelligence system for improving endoscopic detection of colonic polyps in real-time.
Interventions
DEVICECADDIE- Computer Aided (AI) Device used in Endoscopy
1. CADDIE assisted polyp detection 2. CADDIE assisted polyp characterisation
Sponsors
University College, London
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Patient's scheduled to undergo a surveillance or symptomatic colonoscopy with an endoscopist participating in the study phase of the trial. * Male and female participants aged 18 years or older at the time of informed consent. * Patient's able to comprehend, sign and date the written informed consent document to participate in the study.
Exclusion criteria
* Emergency colonoscopies and/or inpatient colonoscopies. * Patients with inflammatory bowel disease (IBD) * Patients with Colorectal Cancer (CRC) * Patients with previous CRC * Patients with previous colonic resection * Patients returning for a planned elective therapeutic colonoscopy. * Polyposis syndromes * Current or relevant history of a physical or psychiatric illness or any medical condition that in the opinion of the investigator could affect the patient's safety or interfere with the study assessments * Patients with a contraindication for biopsy or polypectomy. These include: * Patients who have not withheld medications pre-disposing to bleeding at time of colonoscopy as per local site /national guidelines 30. * Patients with a history of haemostasis disorders (Haemostasis disorders will include but will not be limited to: patients with haemophilia or other congenitally acquired clotting factor deficiencies, patients with cirrhosis with coagulopathy, patients known to have thrombocytopenia (\<80,000 platelet/ul) and individuals with Von Willebrand's disease or other known platelet malfunction disorders). * Patients is enrolled in another research study with an investigational medicinal product (IMP) or non-IMP that pre-disposes them to bleeding
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| To Evaluate Whether Using the CADDIE System Improves Endoscopist Detection of Adenomas During Colonoscopy. | 30 days | The difference in endoscopist ADR between the intervention (CADDIE system) and non-intervention arm. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| To Determine Whether the CADDIE Artificial Intelligence System Improves Endoscopic Detection of All Polyps During Colonoscopy | 30 days | Polyp Detection Rate (including proximal polyp detection rate) in the interventional group compared to the control group. \- Mean number of polyps detected per colonoscopy in the interventional group compared to the control group. |
| Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 30 days | Compare the accuracy of CADDIE against human endoscopist (high confidence diagnoses) for the optical diagnosis of diminutive polyps. Accuracy is defined as true positive and true negative divided by diagnoses total polyps that were optically diagnosed with high confidence. |
| Compare the Accuracy of Endoscopist Optical Diagnosis to Assign Colonoscopy Surveillance Intervals When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 30 days | Compare the accuracy of using CADDIE's optical diagnosis to assign surveillance colonoscopy intervals against using human endoscopist optical diagnosis (high confidence diagnoses) for assigning surveillance colonoscopy intervals. |
| Evaluate the Difference in Number of Adenomas Detected Per Colonoscopy Between Intervention and Non-intervention Arm | 30 days | Compare the difference in the number of adenomas detected per colonoscopy between the intervention and non-intervention arm |
| Evaluate the Safety of the CADDIE by Recording Occurrence and Severity of Adverse Events. | 30 days | Safety of the device will be assessed through monitoring of adverse events for 30 days' post-procedure. Adverse events are defined as: * Abdominal pain/discomfort. * Abdominal bloating. * Sedation related aspiration. * Bleeding risk. * Perforation. * Post polypectomy electrocoagulation syndrome. * Infection. |
| Assess Patient Anxiety During the Colonoscopy | 30 days | Patient response to the question 'How anxious or calm were you during the colonoscopy?' assessed by Likert Scale with 5 options - 1 (Very anxious), 2 (Somewhat anxious), 3 (Neither Anxious nor calm), 4 (Somewhat calm), 5 (Very calm). |
| Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Rectal Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 30 days | Compare the accuracy of CADDIE against human endoscopist (high confidence diagnoses) for the optical diagnosis of diminutive rectal polyps. |
Countries
United Kingdom
Participant flow
Participants by arm
| Arm | Count |
|---|---|
| CADDIE The endoscopist will be assisted with CADDIE system to detect polyps. The endoscopist will perform optical diagnosis of polyps with the assistance of the CADDIE's polyp characterisation function.
CADDIE- Computer Aided (AI) Device used in Endoscopy:
1. CADDIE assisted polyp detection
2. CADDIE assisted polyp characterisation | 306 |
| Standard Procedure In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE. | 309 |
| Total | 615 |
Baseline characteristics
| Characteristic | CADDIE | Standard Procedure | Total |
|---|---|---|---|
| Age, Categorical <=18 years | 0 Participants | 0 Participants | 0 Participants |
| Age, Categorical >=65 years | 130 Participants | 108 Participants | 238 Participants |
| Age, Categorical Between 18 and 65 years | 176 Participants | 201 Participants | 377 Participants |
| Age, Continuous | 59.4 years STANDARD_DEVIATION 14.7 | 58.0 years STANDARD_DEVIATION 14.8 | 58.7 years STANDARD_DEVIATION 14.7 |
| Race/Ethnicity, Customized Ethnicity/Race Arab | 5 Participants | 6 Participants | 11 Participants |
| Race/Ethnicity, Customized Ethnicity/Race Asian Chinese | 3 Participants | 2 Participants | 5 Participants |
| Race/Ethnicity, Customized Ethnicity/Race Asian Other | 6 Participants | 3 Participants | 9 Participants |
| Race/Ethnicity, Customized Ethnicity/Race Black | 4 Participants | 11 Participants | 15 Participants |
| Race/Ethnicity, Customized Ethnicity/Race Jewish | 1 Participants | 1 Participants | 2 Participants |
| Race/Ethnicity, Customized Ethnicity/Race Mixed race | 3 Participants | 2 Participants | 5 Participants |
| Race/Ethnicity, Customized Ethnicity/Race Other | 13 Participants | 10 Participants | 23 Participants |
| Race/Ethnicity, Customized Ethnicity/Race South East Asian | 24 Participants | 11 Participants | 35 Participants |
| Race/Ethnicity, Customized Ethnicity/Race White British/Irish | 226 Participants | 247 Participants | 473 Participants |
| Race/Ethnicity, Customized Ethnicity/Race White European | 21 Participants | 16 Participants | 37 Participants |
| Region of Enrollment United Kingdom | 306 participants | 309 participants | 615 participants |
| Sex: Female, Male Female | 159 Participants | 156 Participants | 315 Participants |
| Sex: Female, Male Male | 147 Participants | 153 Participants | 300 Participants |
Adverse events
| Event type | EG000 affected / at risk | EG001 affected / at risk |
|---|---|---|
| deaths Total, all-cause mortality | 2 / 368 | 0 / 371 |
| other Total, other adverse events | 10 / 368 | 13 / 371 |
| serious Total, serious adverse events | 5 / 368 | 1 / 371 |
Outcome results
Primary
To Evaluate Whether Using the CADDIE System Improves Endoscopist Detection of Adenomas During Colonoscopy.
The difference in endoscopist ADR between the intervention (CADDIE system) and non-intervention arm.
Time frame: 30 days
| Arm | Measure | Value (NUMBER) |
|---|---|---|
| CADDIE | To Evaluate Whether Using the CADDIE System Improves Endoscopist Detection of Adenomas During Colonoscopy. | 33.30 ADR (% of participants) |
| Standard Procedure | To Evaluate Whether Using the CADDIE System Improves Endoscopist Detection of Adenomas During Colonoscopy. | 25.20 ADR (% of participants) |
Secondary
Assess Patient Anxiety During the Colonoscopy
Patient response to the question 'How anxious or calm were you during the colonoscopy?' assessed by Likert Scale with 5 options - 1 (Very anxious), 2 (Somewhat anxious), 3 (Neither Anxious nor calm), 4 (Somewhat calm), 5 (Very calm).
Time frame: 30 days
| Arm | Measure | Value (MEAN) | Dispersion |
|---|---|---|---|
| CADDIE | Assess Patient Anxiety During the Colonoscopy | 2.989 score on a scale | Standard Deviation 1.193 |
| Standard Procedure | Assess Patient Anxiety During the Colonoscopy | 3.061 score on a scale | Standard Deviation 1.241 |
Secondary
Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm)
Compare the accuracy of CADDIE against human endoscopist (high confidence diagnoses) for the optical diagnosis of diminutive polyps. Accuracy is defined as true positive and true negative divided by diagnoses total polyps that were optically diagnosed with high confidence.
Time frame: 30 days
| Arm | Measure | Value (NUMBER) |
|---|---|---|
| CADDIE | Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 87.5 % of adenomas correctly diagnosed |
| Standard Procedure | Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 76.7 % of adenomas correctly diagnosed |
Secondary
Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Rectal Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm)
Compare the accuracy of CADDIE against human endoscopist (high confidence diagnoses) for the optical diagnosis of diminutive rectal polyps.
Time frame: 30 days
| Arm | Measure | Value (NUMBER) |
|---|---|---|
| CADDIE | Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Rectal Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 73.3 % of adenomas correctly diagnosed |
| Standard Procedure | Compare the Accuracy of Endoscopist Optical Diagnosis of Diminutive Rectal Polyps When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 53.3 % of adenomas correctly diagnosed |
Secondary
Compare the Accuracy of Endoscopist Optical Diagnosis to Assign Colonoscopy Surveillance Intervals When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm)
Compare the accuracy of using CADDIE's optical diagnosis to assign surveillance colonoscopy intervals against using human endoscopist optical diagnosis (high confidence diagnoses) for assigning surveillance colonoscopy intervals.
Time frame: 30 days
| Arm | Measure | Value (NUMBER) |
|---|---|---|
| CADDIE | Compare the Accuracy of Endoscopist Optical Diagnosis to Assign Colonoscopy Surveillance Intervals When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 90.9 % pts with correct surveillance interval |
| Standard Procedure | Compare the Accuracy of Endoscopist Optical Diagnosis to Assign Colonoscopy Surveillance Intervals When Using the CADDIE System (Intervention Arm) Compared to Without the CADDIE System (Control Arm) | 87.2 % pts with correct surveillance interval |
Secondary
Evaluate the Difference in Number of Adenomas Detected Per Colonoscopy Between Intervention and Non-intervention Arm
Compare the difference in the number of adenomas detected per colonoscopy between the intervention and non-intervention arm
Time frame: 30 days
| Arm | Measure | Value (MEAN) | Dispersion |
|---|---|---|---|
| CADDIE | Evaluate the Difference in Number of Adenomas Detected Per Colonoscopy Between Intervention and Non-intervention Arm | 0.66 Adenomas per colonoscopy | Standard Deviation 1.44 |
| Standard Procedure | Evaluate the Difference in Number of Adenomas Detected Per Colonoscopy Between Intervention and Non-intervention Arm | 0.42 Adenomas per colonoscopy | Standard Deviation 0.98 |
Secondary
Evaluate the Safety of the CADDIE by Recording Occurrence and Severity of Adverse Events.
Safety of the device will be assessed through monitoring of adverse events for 30 days' post-procedure. Adverse events are defined as: * Abdominal pain/discomfort. * Abdominal bloating. * Sedation related aspiration. * Bleeding risk. * Perforation. * Post polypectomy electrocoagulation syndrome. * Infection.
Time frame: 30 days
| Arm | Measure | Value (NUMBER) |
|---|---|---|
| CADDIE | Evaluate the Safety of the CADDIE by Recording Occurrence and Severity of Adverse Events. | 15 AE/SAE |
| Standard Procedure | Evaluate the Safety of the CADDIE by Recording Occurrence and Severity of Adverse Events. | 14 AE/SAE |
Secondary
To Determine Whether the CADDIE Artificial Intelligence System Improves Endoscopic Detection of All Polyps During Colonoscopy
Polyp Detection Rate (including proximal polyp detection rate) in the interventional group compared to the control group. \- Mean number of polyps detected per colonoscopy in the interventional group compared to the control group.
Time frame: 30 days
| Arm | Measure | Value (MEAN) | Dispersion |
|---|---|---|---|
| CADDIE | To Determine Whether the CADDIE Artificial Intelligence System Improves Endoscopic Detection of All Polyps During Colonoscopy | 0.87 PPC | Standard Deviation 1.59 |
| Standard Procedure | To Determine Whether the CADDIE Artificial Intelligence System Improves Endoscopic Detection of All Polyps During Colonoscopy | 0.63 PPC | Standard Deviation 1.24 |