Trial Outcomes & Findings for CADDIE Trial - Computer Aided Diagnosis and Detection for Intelligent Endoscopy (NCT NCT04325815)

NCT ID: NCT04325815

Last Updated: 2025-02-19

Results Overview

The difference in endoscopist ADR between the intervention (CADDIE system) and non-intervention arm.

• Recruitment status: COMPLETED
• Target enrollment: 739 participants
• Primary outcome timeframe: 30 days
• Results posted on: 2025-02-19

Participant Flow

Participant milestones

Measure	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	Standard Procedure In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
Overall Study STARTED	368	371
Overall Study COMPLETED	306	309
Overall Study NOT COMPLETED	62	62

Reasons for withdrawal

Withdrawal data not reported

Baseline Characteristics

CADDIE Trial - Computer Aided Diagnosis and Detection for Intelligent Endoscopy

Baseline characteristics by cohort

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.	Total n=615 Participants Total of all reporting groups
Age, Categorical <=18 years	0 Participants n=5 Participants	0 Participants n=7 Participants	0 Participants n=5 Participants
Age, Categorical Between 18 and 65 years	176 Participants n=5 Participants	201 Participants n=7 Participants	377 Participants n=5 Participants
Age, Categorical >=65 years	130 Participants n=5 Participants	108 Participants n=7 Participants	238 Participants n=5 Participants
Age, Continuous	59.4 years STANDARD_DEVIATION 14.7 • n=5 Participants	58.0 years STANDARD_DEVIATION 14.8 • n=7 Participants	58.7 years STANDARD_DEVIATION 14.7 • n=5 Participants
Sex: Female, Male Female	159 Participants n=5 Participants	156 Participants n=7 Participants	315 Participants n=5 Participants
Sex: Female, Male Male	147 Participants n=5 Participants	153 Participants n=7 Participants	300 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · White British/Irish	226 Participants n=5 Participants	247 Participants n=7 Participants	473 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · White European	21 Participants n=5 Participants	16 Participants n=7 Participants	37 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Mixed race	3 Participants n=5 Participants	2 Participants n=7 Participants	5 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · South East Asian	24 Participants n=5 Participants	11 Participants n=7 Participants	35 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Asian Chinese	3 Participants n=5 Participants	2 Participants n=7 Participants	5 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Asian Other	6 Participants n=5 Participants	3 Participants n=7 Participants	9 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Black	4 Participants n=5 Participants	11 Participants n=7 Participants	15 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Jewish	1 Participants n=5 Participants	1 Participants n=7 Participants	2 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Arab	5 Participants n=5 Participants	6 Participants n=7 Participants	11 Participants n=5 Participants
Race/Ethnicity, Customized Ethnicity/Race · Other	13 Participants n=5 Participants	10 Participants n=7 Participants	23 Participants n=5 Participants
Region of Enrollment United Kingdom	306 participants n=5 Participants	309 participants n=7 Participants	615 participants n=5 Participants

PRIMARY outcome

Timeframe: 30 days

The difference in endoscopist ADR between the intervention (CADDIE system) and non-intervention arm.

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
To Evaluate Whether Using the CADDIE System Improves Endoscopist Detection of Adenomas During Colonoscopy.	33.30 ADR (% of participants)	25.20 ADR (% of participants)

SECONDARY outcome

Timeframe: 30 days

Compare the difference in the number of adenomas detected per colonoscopy between the intervention and non-intervention arm

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the 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	0.42 Adenomas per colonoscopy Standard Deviation 0.98

SECONDARY outcome

Timeframe: 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.

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
To Determine Whether the CADDIE Artificial Intelligence System Improves Endoscopic Detection of All Polyps During Colonoscopy	0.87 PPC Standard Deviation 1.59	0.63 PPC Standard Deviation 1.24

SECONDARY outcome

Timeframe: 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.

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the 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 Interval 77.6 to 94.1	76.7 % of adenomas correctly diagnosed Interval 64.3 to 86.2

SECONDARY outcome

Timeframe: 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.

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the 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	87.2 % pts with correct surveillance interval

SECONDARY outcome

Timeframe: 30 days

Compare the accuracy of CADDIE against human endoscopist (high confidence diagnoses) for the optical diagnosis of diminutive rectal polyps.

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the 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 Interval 44.9 to 92.2	53.3 % of adenomas correctly diagnosed Interval 26.6 to 78.7

SECONDARY outcome

Timeframe: 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.

Outcome measures

Measure	CADDIE n=368 Participants 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	Standard Procedure n=371 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
Evaluate the Safety of the CADDIE by Recording Occurrence and Severity of Adverse Events.	15 AE/SAE	14 AE/SAE

SECONDARY outcome

Timeframe: 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).

Outcome measures

Measure	CADDIE n=306 Participants 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	Standard Procedure n=309 Participants In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
Assess Patient Anxiety During the Colonoscopy	2.989 score on a scale Standard Deviation 1.193	3.061 score on a scale Standard Deviation 1.241

Adverse Events

CADDIE

Serious events: 5 serious events

Other events: 10 other events

Deaths: 2 deaths

Standard Procedure

Serious events: 1 serious events

Other events: 13 other events

Deaths: 0 deaths

Serious adverse events

Measure	CADDIE n=368 participants at risk 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	Standard Procedure n=371 participants at risk In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
Musculoskeletal and connective tissue disorders Re-admission due to fall, mechnical injury	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.27% 1/371 • Adverse events were recorded for 30 days post-procedure
Surgical and medical procedures Operation unrelated to study design/study device	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Gastrointestinal disorders Gastrointestinal disorder unrelated to study device	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Cardiac disorders Death due to underlying cardiovascular disease	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
General disorders Death due to index diagnosis of malignancy unrelated to study design/ study device	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure

Other adverse events

Measure	CADDIE n=368 participants at risk 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	Standard Procedure n=371 participants at risk In addition to routine colonoscopy the endoscopist will perform optical diagnosis of detected polyps without the assistance of the CADDIE.
Gastrointestinal disorders Gastrointestinal disorder unrelated to study device	0.54% 2/368 • Adverse events were recorded for 30 days post-procedure	1.9% 7/371 • Adverse events were recorded for 30 days post-procedure
Musculoskeletal and connective tissue disorders Mechanical Injury unrelated to study design/ study device	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.54% 2/371 • Adverse events were recorded for 30 days post-procedure
Renal and urinary disorders New diagnosis Prostate cancer	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Respiratory, thoracic and mediastinal disorders Shortness of Breath	0.54% 2/368 • Adverse events were recorded for 30 days post-procedure	0.27% 1/371 • Adverse events were recorded for 30 days post-procedure
Nervous system disorders Headache	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Investigations Electrolyte abnormality	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Cardiac disorders Irregular heart beat	0.00% 0/368 • Adverse events were recorded for 30 days post-procedure	0.27% 1/371 • Adverse events were recorded for 30 days post-procedure
Nervous system disorders Dizziness	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Nervous system disorders Facial pain	0.00% 0/368 • Adverse events were recorded for 30 days post-procedure	0.27% 1/371 • Adverse events were recorded for 30 days post-procedure
Renal and urinary disorders Pyelonephritis	0.27% 1/368 • Adverse events were recorded for 30 days post-procedure	0.00% 0/371 • Adverse events were recorded for 30 days post-procedure
Renal and urinary disorders AKI	0.00% 0/368 • Adverse events were recorded for 30 days post-procedure	0.27% 1/371 • Adverse events were recorded for 30 days post-procedure

Additional Information

Professor Laurence B Lovat

University College London

Phone: 020-7679-9060

Email: l.lovat@ucl.ac.uk

Results disclosure agreements

• Principal investigator is a sponsor employee
• Publication restrictions are in place