CADDIE

{0}  September 12, 2026 Odin Medical Limited Luke Sampson COO 74 Rivington St. London, EC2A 3AY United Kingdom Re: K260133 Trade/Device Name: CADDIE Regulation Number: 21 CFR 876.1520 Regulation Name: Gastrointestinal lesion software detection system Regulatory Class: Class II Product Code: QNP, SBX Dated: August 14, 2026 Received: August 14, 2026 Dear Luke Sampson: We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmn/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading. If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register. Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" U.S. Food & Drug Administration 10903 New Hampshire Avenue Silver Spring, MD 20993 www.fda.gov {1} K260133 - Luke Sampson Page 2 (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download). Your device is also subject to, among other requirements, the Quality Management System Regulation (QMSR) (21 CFR Part 820), which includes, but is not limited to, ISO 13485 clause 7.3 (Design controls), ISO 13485 clause 8.3 (Nonconforming product), ISO 13485 clause 8.5.2 (Corrective action), and ISO 13485 clause 8.5.3 (Preventative action). Please note that regardless of whether a change requires premarket review, the QMSR requires device manufacturers to review and approve changes to device design and production (ISO 13485 clause 7.3 and ISO 13485 clause 7.5) and document changes and approvals in the Medical Device File (ISO 13485 clause 4.2.3). Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting (reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reporting-combination-products); good manufacturing practice requirements as set forth in the Quality Management System Regulation (QMSR) (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050. All medical devices, including Class I and unclassified devices and combination product device constituent parts are required to be in compliance with the final Unique Device Identification System rule ("UDI Rule"). The UDI Rule requires, among other things, that a device bear a unique device identifier (UDI) on its label and package (21 CFR 801.20(a)) unless an exception or alternative applies (21 CFR 801.20(b)) and that the dates on the device label be formatted in accordance with 21 CFR 801.18. The UDI Rule (21 CFR 830.300(a) and 830.320(b)) also requires that certain information be submitted to the Global Unique Device Identification Database (GUDID) (21 CFR Part 830 Subpart E). For additional information on these requirements, please see the UDI System webpage at https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/unique-device-identification-system-udi-system. Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-devices/medical-device-safety/medical-device-reporting-mdr-how-report-medical-device-problems. For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-devices/device-advice-comprehensive-regulatory-assistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100). {2} K260133 - Luke Sampson Page 3 Sincerely, # SHANIL P. HAUGEN -S Shanil P. Haugen, Ph.D. Assistant Director DHT3A: Division of Renal, Gastrointestinal, Obesity, and Transplant Devices OHT3: Office of Gastrorenal, ObGyn, General Hospital, and Urology Devices Office of Product Evaluation and Quality Center for Devices and Radiological Health Enclosure {3} DEPARTMENT OF HEALTH AND HUMAN SERVICES Food and Drug Administration # Indications for Use Form Approved: OMB No. 0910-0120 Expiration Date: 07/31/2026 See PRA Statement below. 510(k) Number (if known) K260133 Device Name CADDIE Indications for Use (Describe) The CADDIE computer-assisted detection device is intended to assist the gastroenterologist in detecting suspected colorectal polyps only. The gastroenterologist is responsible for reviewing CADDIE suspected polyp areas and confirming the presence or absence of a polyp based on their own medical judgment. CADDIE is not intended to replace a full patient evaluation, nor is it intended to be relied upon to make a primary interpretation of endoscopic procedures, medical diagnosis, or recommendations of treatment/course of action for patients. The CADDIE computer-assisted detection device is limited for use with standard white-light endoscopy imaging only. Type of Use (Select one or both, as applicable) ☑ Prescription Use (Part 21 CFR 801 Subpart D) ☐ Over-The-Counter Use (21 CFR 801 Subpart C) # CONTINUE ON A SEPARATE PAGE IF NEEDED. This section applies only to requirements of the Paperwork Reduction Act of 1995. # *DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.* The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to: Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov "An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number." FORM FDA 3881 (8/23) Page 1 of 1 PSC Publishing Services (301) 443-6740 EF {4} K260133 K260133 Page 1 of 14 Odin Vision ## 510(k) Summary | **510(k) Number:** | K260133 | | --- | --- | | **510(k) Type:** | Special | | **Date Prepared:** | 14-Aug-2026 | | **510(k) Owner:** | Odin Medical Ltd, 74 Rivington Street, London EC2A 3AY United Kingdom Tel - +44 (0)7957 948411 | | **Official Contact:** | Luke Sampson - COO | | **Submission Correspondent:** | Luke Sampson - COO | | **Proprietary or Trade Name:** | CADDIE | | **Common/ Usual Name:** | Gastrointestinal Lesion Software Detection System | | **Classification CFR:** | 21 CFR 876.1520 | | **Classification Code:** | QNP, SBX | | **Classification Name:** | Gastrointestinal Lesion Software Detection System | | **Class:** | Class II | | **Predicate Device:** | K252586 CADDIE – Odin Medical LTD | Page 1 of 14 {5} K260133 K260133 Page 2 of 14 Odin Vision ### Device Description: CADDIE is cloud based artificial intelligence medical device software. CADDIE interfaces with the video feed generated by an endoscopic video processor during a colonoscopy procedure. CADDIE also includes a Cecum AI feature as an additional convenience function that prompts the user to verify that the CADDIE detection mode is enabled before inspection begins. The software is intended to be used by trained and qualified healthcare professionals as an accompaniment to video endoscopy for the purpose of drawing attention to regions with visual characteristics consistent with colonic mucosal lesions (such as polyps and adenomas). CADDIE analyses the data from the endoscopic video processor in real-time and provides information to aid the endoscopist in detecting suspected colorectal polyps, if they are in the field of view of the endoscope. The areas highlighted by CADDIE are not to be interpreted as definite polyps or adenomas. The responsibility to make a decision as to whether or not a highlighted region contains a polyp or is an adenoma lies with the user. The endoscopist is responsible for reviewing CADDIE suspected polyp areas and confirming the presence or absence of a polyp and its classification based on their own medical judgement. ### Indications for Use: The CADDIE computer-assisted detection device is intended to assist the gastroenterologist in detecting suspected colorectal polyps only. The gastroenterologist is responsible for reviewing CADDIE suspected polyp areas and confirming the presence or absence of a polyp based on their own medical judgment. CADDIE is not intended to replace a full patient evaluation, nor is it intended to be relied upon to make a primary interpretation of endoscopic procedures, medical diagnosis, or recommendations of treatment/course of action for patients. The CADDIE computer-assisted detection device is limited for use with standard white-light endoscopy imaging only. ### Patient Population: CADDIE is intended to be used on patients aged 45 and over referred for screening and surveillance endoscopic mucosal evaluations. This does not include pregnant women, for which no clinical evaluation has been carried out. ### Environments of use: Hospitals and clinics or in other secure endoscopy units where colonoscopies are performed. ### Summary of Technological Characteristics: At a high level we present the technological comparison of the subject device and the predicate in the Table below. Page 2 of 14 {6} K260133 Odin Vision K260133 Page 3 of 14 # Summary of Technological Characteristics | Characteristics | Subject Device: CADDIE (Software version 1.6.0) | Predicate Device: CADDIE K252586 (Software version 1.5.0) | Comparison | | --- | --- | --- | --- | | Manufacturer | Odin Medical Ltd | Odin Medical Ltd | Same | | Regulation Number | 21 CFR 876.1520 | 21 CFR 876.1520 | Same | | Regulation Title | Gastrointestinal lesion software detection system | Gastrointestinal lesion software detection system | Same | | Classification | Class II | Class II | Same | | Classification Product Code | QNP, SBX | QNP, SBX | Same | | Intended Use - definition | A gastrointestinal lesion software detection system is a computer-assisted detection device used in conjunction with endoscopy for the detection of abnormal lesions in the gastrointestinal tract. This device with advanced software algorithms brings attention to images to aid in the detection of lesions. The device may contain hardware to support interfacing with an endoscope. | A gastrointestinal lesion software detection system is a computer-assisted detection device used in conjunction with endoscopy for the detection of abnormal lesions in the gastrointestinal tract. This device with advanced software algorithms brings attention to images to aid in the detection of lesions. The device may contain hardware to support interfacing with an endoscope. | Same | | Indications for Use | The CADDIE computer-assisted detection device is intended to assist the gastroenterologist in detecting suspected colorectal polyps only. The gastroenterologist is responsible for reviewing CADDIE suspected polyp areas and confirming the presence or absence of a polyp based on their own medical judgment. CADDIE is not intended to replace a full patient evaluation, nor is it intended to be relied upon to make a primary interpretation of endoscopic | The CADDIE computer-assisted detection device is intended to assist the gastroenterologist in detecting suspected colorectal polyps only. The gastroenterologist is responsible for reviewing CADDIE suspected polyp areas and confirming the presence or absence of a polyp based on their own medical judgment. CADDIE is not intended to replace a full patient evaluation, nor is it intended to be relied upon to make a primary interpretation of endoscopic | Same | Page 3 of 14 {7} K260133 Odin Vision K260133 Page 4 of 14 | Characteristics | Subject Device: CADDIE (Software version 1.6.0) | Predicate Device: CADDIE K252586 (Software version 1.5.0) | Comparison | | --- | --- | --- | --- | | | procedures, medical diagnosis, or recommendations of treatment/course of action for patients. The CADDIE computer-assisted detection device is limited for use with standard white-light endoscopy imaging only. | procedures, medical diagnosis, or recommendations of treatment/course of action for patients. The CADDIE computer-assisted detection device is limited for use with standard white-light endoscopy imaging only. | | | **Patient Population** | CADDIE is intended to be used on patients aged 45 and over referred for screening and surveillance endoscopic mucosal evaluations. This does not include pregnant women, for which no clinical evaluation has been carried out. | CADDIE is intended to be used on patients aged 45 and over referred for screening and surveillance endoscopic mucosal evaluations. This does not include pregnant women, for which no clinical evaluation has been carried out. | Same | | **Technological Characteristics** | CADDIE is standalone software that is deployed on the cloud and accessed via a web browser. The device is designed to highlight portions of the colon where the device detects potential colorectal polyps. CADDIE requires a network connection unless deployed locally. | CADDIE is standalone software that is deployed on the cloud and accessed via a web browser. The device is designed to highlight portions of the colon where the device detects potential colorectal polyps. CADDIE requires a network connection unless deployed locally. | Same | | **Convenience Features** | When the clinician confirms the cecum and photo documents the cecal landmarks in standard clinical workflow, Cecum AI is triggered, and the image is sent for analysis. If the cecal landmarks are confirmed in the image, by the AI, the user will be given a reminder to check the status of Polyp detection. If polyp detection is turned off, the cross icon will flash three times along with the cecum icon. If detection is on, the cecum icon will flash three times next to the tick icon. This is a convenience feature that provides a check to the user that the CADDIE polyp detection function is on and in use. | When the clinician confirms the cecum and photo documents the cecal landmarks in standard clinical workflow, Cecum AI is triggered, and the image is sent for analysis. If the cecal landmarks are confirmed in the image, by the AI, the user will be given a reminder to check the status of Polyp detection. If polyp detection is turned off, the cross icon will flash three times along with the cecum icon. If detection is on, the cecum icon will flash three times next to the tick icon. This is a convenience feature that provides a check to the user that the CADDIE polyp detection function is on and in use. | Same | Page 4 of 14 {8} K260133 Odin Vision K260133 Page 5 of 14 | Characteristics | Subject Device: CADDIE (Software version 1.6.0) | Predicate Device: CADDIE K252586 (Software version 1.5.0) | Comparison | | --- | --- | --- | --- | | **Software Algorithms** | CADDIE utilizes an artificial intelligence-based algorithms to perform the polyp detection and cecum AI functions. | CADDIE utilizes an artificial intelligence-based algorithms to perform the polyp detection and cecum AI functions. | Same | | **Device Output** | Polyp Detection: During a colonoscopy, CADDIE generates markers, which look like green squares and are accompanied by a short, low-volume sound, and superimposes them on the video from the endoscope camera when it identifies a potential lesion. Cecum AI: When the clinician photo documents cecum, Cecum AI is triggered. If cecal landmarks are confirmed in the image, by the AI, the user will be given a reminder to check the on/ off status of Polyp detection. | Polyp Detection: During a colonoscopy, CADDIE generates markers, which look like green squares and are accompanied by a short, low-volume sound, and superimposes them on the video from the endoscope camera when it identifies a potential lesion. Cecum AI: When the clinician photo documents cecum, Cecum AI is triggered. If cecal landmarks are confirmed in the image, by the AI, the user will be given a reminder to check the on/ off status of Polyp detection. | Same | | **Additional compatible accessory** | Arc Endocuff Vision (K162205) | N/A | Different; compatibility does not affect device design or performance as supported by performance testing | Page 5 of 14 {9} K260133 K260133 Page 6 of 14 Odin Vision ## Discussion of Differences The Indications for Use for both devices are identical; the subject device is an upgrade to the predicate device, without altering its Indications for Use. Both the subject device and CADDIE (K252586) are identical in polyp detection. Both devices take a colonoscopy video as an input from an endoscopy image processor and provide an output of a green bounding box that highlights the detected polyps. Both devices are used in real-time to aid the clinician in detecting abnormal lesions live during a colonoscopy. There is an introduction to a new compatible medical device, Arc Endocuff Vision (K162205), as an optional tool that can be used with CADDIE during procedures. The subject and predicate device (CADDIE) shared identical indications for use, principles of operation as well as technological characteristics. The introduction of new compatible device has been assessed through identical standalone non-clinical performance testing, and the results demonstrated that the performance of the subject device is non inferior to that of the predicate device. As a result, the subject device can be considered substantially equivalent to the predicate. ## Performance Testing This Special 510(k) addresses the introduction of new compatible medical device, Arc Endocuff Vision. Performance testing was conducted to evaluate the additional compatible device and is summarized below. The addition of compatible device does not alter the safety or performance characteristics previously cleared under K252586. Changes to other aspects of the device that are not the subject of this submission have been evaluated through Odin's risk management process and FDA's guidance on deciding when to submit a 510(k) and determined not to require a new 510(k). For all changes, design and development activities were performed in compliance with Odin's Quality Management System and FDA Design Control requirements (21 CFR 820.30), using the same methods and acceptance criteria described in the cleared submission (K252586). All performance characteristics continue to meet their established requirements and do not raise any additional questions associated with the safety and effectiveness of the device. Special controls per 21 CFR 876.1520 have been addressed as follows: Page 6 of 14 {10} K260133 K260133 Page 7 of 14 Odin Vision ### Software controls Special control (4) Software verification, validation, and hazard analysis must be provided. Software description must include a detailed, technical description including the impact of any software and hardware on the device's functions, the associated capabilities and limitations of each part, the associated inputs and outputs, mapping of the software architecture, and a description of the video signal pipeline. Relevant documented evidence was generated through adherence to Odin's Quality Management System and FDA Design Control requirements and form part of the documentation associated with this 510(k). ### Human Factors and Usability Testing Special Control (3) Usability assessment must demonstrate that the intended user(s) can safely and correctly use the device. Human Factors and Usability Testing was conducted and reviewed in K240044 and is still applicable to the version of the device that is the subject of this 510(k). ### Non-clinical Performance Testing Special Control (2) Non-clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, which include: (i) Standalone algorithm performance testing; (ii) Pixel-level comparison of degradation of image quality due to the device; (iii) Assessment of video delay due to marker annotation; and (iv) Assessment of real-time endoscopic video delay due to the device. (2)(ii)-(iv) have not been impacted by the change subject of this 510(k); testing that was conducted and reviewed in previous 510(k)s for this device is still applicable to the version of the device that is the subject of this 510(k). Standalone algorithm performance testing is summarized below: ### Polyp Detection Data Description & Standalone Performance testing Polyp Detection Standalone Bench Testing Dataset Standalone performance testing was performed to assess the ability of CADDIE to discriminate between normal mucosa and polyp tissue on video frames from a standard colonoscopy procedure. A set of recorded colonoscopy videos was analyzed by CADDIE and the results were compared to the historical control (known polyp status per frame). | | Test Set (No. of subjects=632) | | | --- | --- | --- | | | Mean (years) | SD (years) | | Age | 59.43 | 9.58 | | | Count | % | Page 7 of 14 {11} K260133 K260133 Page 8 of 14 Odin Vision | Sex | | | | --- | --- | --- | | Male | 339 | 53.64 | | Female | 276 | 43.67 | | Unknown | 17 | 2.69 | | Indication for Colonoscopy | | | | Surveillance | 178 | 28.16 | | Screening | 337 | 53.32 | | Other | 31 | 4.91 | | Unknown | 86 | 13.61 | | Race/Ethnicity | | | | African American | 110 | 17.41 | | American Indian | 1 | 0.180.16 | | Asian | 23 | 3.64 | | Caucasian | 225 | 35.60 | | Hispanic | 65 | 10.28 | | Persian | 20 | 3.16 | | North American | 36 | 5.70 | | African | 9 | 1.42 | | Latin American | 3 | 0.47 | | Black or Black British | 2 | 0.32 | | Mixed | 2 | 0.32 | | Caribbean | 1 | 0.16 | | Other | 23 | 0.47 | | Unknown | 132 | 20.89 | | Hospital's country | | | | United States of America | 222 | 35.13 | | Italy | 73 | 11.55 | | Spain | 69 | 10.92 | | Poland | 36 | 5.7 | | Germany | 54 | 8.54 | | Iran | 20 | 3.16 | | Japan | 54 | 8.54 | | Canada | 70 | 11.08 | | United Kingdom | 34 | 5.38 | The following table presents the standalone performance testing patients' demographic distribution, including the reason for colonoscopy: | Histopathology | Count | | --- | --- | | Adenoma | 646 | | Non-Adenoma | 493 | | Polyp Location | | | Cecum | 115 | | Ascending Colon | 183 | | Hepatic Flexure | 29 | | Transverse Colon | 203 | Page 8 of 14 {12} K260133 K260133 Page 9 of 14 Odin Vision | Splenic Flexure | 7 | | --- | --- | | Descending Colon | 113 | | Sigmoid Colon | 278 | | Rectum | 203 | | Unknown | 8 | | Polyp Morphology | | | --- | --- | | Polypoid | 813 | | Non-Polypoid | 293 | | Unknown | 33 | | Polyp Size | | | Diminutive | 817 | | Small | 238 | | Large | 84 | Annotation was performed on a per-frame basis, where a team of trained clinical annotators labelled polyp structures with a bounding box, followed by an additional layer of review by a separate team of experts (with over 2000 endoscopic procedures experience). Each polyp was histologically confirmed. These polyp annotations were used as ground truth reference standards. The table above shows the distribution of polyp characteristics. ### Standalone Performance Testing Results The table below shows a subgroup analysis. For video processors and endoscope family subgroup analyses, only models for which CADDIE compatibility is claimed are included. Overall performance results and all other subgroup analyses include all procedures in the evaluation dataset. These results are computed at a persistence of > 0.5 seconds and with an IoU > 20% (when applicable). The reported metrics correspond to the polyp detection endpoints and are summarized as follows: • Frame-level TPR: proportion of frames with polyps detected by the device • Object-level TPR: proportion of polyps detected by the device • Frame-level FPR: proportion of non-polyp frames where the device detects a polyp. | | TPR/Frame[95% CI] | Object-level TPR[95% CI] | Detected Polyps | Procedures | | --- | --- | --- | --- | --- | | Overall | 61.44% [59.80%, 63.07%] | 97.63% [96.75%, 98.51%] | 1112/1139 | 492 | | Histology | | | | | | Adenoma | 67.42% [65.43%, 69.40%] | 98.76% [97.91%, 99.61%] | 638/646 | 341 | | Non-Adenoma | 53.60% [51.03%, 56.18%] | 96.15% [94.45%, 97.85%] | 474/493 | 268 | | Lesion Size | | | | | | Diminutive (0-5mm) | 58.89% [56.92%, 60.85%] | 97.31% [96.20%, 98.42%] | 795/817 | 402 | Page 9 of 14 {13} K260133 K260133 Page 10 of 14 Odin Vision | Small(6-10mm) | 67.65% [64.35%,70.95%] | 98.32% [96.69%,99.95%] | 234/238 | 168 | | --- | --- | --- | --- | --- | | Large(>10mm) | 68.66% [63.47%,73.84%] | 98.81% [96.49%,100.00%] | 83/84 | 68 | | Accessory | | | | | | Endocuff | 77.96% [74.15%,81.77%] | 97.65% [95.37%,99.93%] | 166/170 | 69 | | Non-Endocuff | 58.54% [56.80%,60.28%] | 97.63% [96.67%,98.58%] | 946/969 | 423 | | | FPR/FRAME [95% CI] | Procedures | | --- | --- | --- | | Overall | 1.72% [1.49%, 1.95%] | 140 | | Accessory | | | | Endocuff | 1.80% [1.22%, 2.37%] | 12 | | Non-Endocuff | 1.72% [1.47%, 1.96%] | 128 | ### Summary Comprehensive standalone performance testing was conducted on a large dataset which was more than two times larger than the predicate device. The dataset comprised \( >30\% \) US patients and contained demographically diverse patients, representative of the US population. The standalone performance testing demonstrated the generalizability of the CADe device across race and ethnicity with \( >16\% \) African American patients and 10% Hispanic/Latino patients. The standalone performance testing demonstrated the efficacy of the device in detecting polyps of all sizes and morphologies across all locations in the colon in the intended population and comparison of the performance with and without using the additional compatible device, Arc Endocuff Vision. The results were compared to the predicate device's and were found to be similar or better. No claims other than equivalence are made. The evidence generated in the performance testing supports the substantial equivalence of the CADDIE device to the predicate. Page 10 of 14 {14} K260133 K260133 Page 11 of 14 Odin Vision ### Cecum AI Data Description & Standalone Performance Testing In addition to the standalone performance testing for the polyp-detection component of CADDIE, a standalone performance test for the convenience feature - Cecum AI was conducted to assess the ability of CADDIE to identify the cecum on photo-documented frames from a standard colonoscopy procedure. A set of recorded colonoscopy frames were analyzed by CADDIE and the results were compared to the historical control (known cecum status per frame). CADDIE's cecum AI is set up to only be used on photo-documentation static frames during a colonoscopy. To reflect this use case, this evaluation was performed on static images captured as photo-documentation during colonoscopies. #### Data Description The dataset used to develop the Cecum AI algorithm consisted of a diverse sample of patients and images. The summary breakdown of the development data used across the training, tuning, and testing phases are presented in the following table. | Split | Patients | Images | Positive images | AO images | ICV images | Negative images | | --- | --- | --- | --- | --- | --- | --- | | Training | 2,475 | 1,127,724 | 374,816 | 180,405 | 204,589 | 752,908 | | Tuning | 808 | 46,315 | 15,107 | 7,381 | 8,342 | 31,208 | | Testing | 109 | 1,656 | 211 | 129 | 83 | 1,445 | The dataset was generated by including all cecum images containing the appendiceal orifice (AO) and/or the ileocecal valve (ICV) as positive samples, and all other non-cecum photo-documented images as negative samples. The table below shows the distribution of cecal structure characteristics in the dataset used for the standalone performance evaluation. SD denotes standard deviation. | | Procedures | Frames | Frames/procedure (Mean [SD]) | Total (#frames) | | --- | --- | --- | --- | --- | | Positive | 400 | 921 | 2.3 [1.45] | 5,224 | | AO | 317 | 512 | 1.62 [0.95] | | | ICV | 290 | 451 | 1.56 [1.12] | | | Negative | 449 | 4,303 | 9.58 [8.63] | | #### Study Endpoints The study endpoints are the same as for the predicate device. The primary endpoints for Cecum AI are: - Frame-Level TPR: The proportion of all the frames annotated with cecum which CADDIE characterizes correctly. - Frame-Level FPR: The proportion of all frames without cecum landmarks which CADDIE incorrectly detects cecum. Page 11 of 14 {15} K260133 K260133 Page 12 of 14 Odin Vision The following table shows presents a subgroup analysis of the device performance, grouped by cecal structure, video processor, endoscope family, and accessories. For video processor and endoscope family subgroup analyses, only models for which CADDIE compatibility is claimed are included. Overall performance results and all other subgroup analyses include all procedures in the evaluation dataset. Frame-level performance metrics are summarized as the mean and 95% confidence intervals computed per procedures/patients. ## Results/Comparison to Predicate The performance testing indicates that the Cecum AI convenience feature performs as expected and is non-inferior to the performance of the predicate device. No claims other than equivalence are made. | | Accuracy/ FRAME (%) | TPR/ FRAME (%) | FPR/ FRAME (%) | Procedures | | --- | --- | --- | --- | --- | | Overall | 91.72 [90.58, 92.87] | 89.65 [87.28, 92.03] | 7.53 [6.20, 8.87] | 464 | | Structure | | | | | | AO | 94.38 [93.36, 95.39] | 85.28 [81.75, 88.82] | 3.88 [3.00, 4.76] | 317 | | ICV | 95.28 [94.48, 96.08] | 83.03 [79.10, 86.96] | 3.52 [2.70, 4.34] | 290 | | Accessory | | | | | | Endocuff | 92.24 [89.36, 95.12] | 92.22 [86.89, 97.55] | 5.03 [2.71, 7.34] | 45 | | Non-Endocuff | 91.67 [90.44, 92.90] | 89.33 [86.74, 91.92] | 7.81 [6.35, 9.27] | 419 | ## Summary The standalone performance testing demonstrated the efficacy of the device in detecting cecal landmarks in the colon in the intended population. The results were compared to the predicate devices and were found to be non-inferior when using the additional compatible device, Arc Endocuff Vision. No claims other than equivalence are made. The evidence generated in the performance testing supports the substantial equivalence of the Cecum AI convenience feature to the predicate. ## Summary of Clinical Performance Special control (1) Clinical performance testing must demonstrate that the device performs as intended under anticipated conditions of use, including detection of gastrointestinal lesions and evaluation of all adverse events. The baseline Clinical Performance Evaluation was conducted and reviewed in K240044 and is still applicable to the version of the device that is the subject of this 510(k). ## Labeling Special Control (6) Labeling must include: (i) Instructions for use, including a detailed description of the device and compatibility information; Page 12 of 14 {16} K260133 K260133 Page 13 of 14 Odin Vision - (ii) Warnings to avoid overreliance on the device, that the device is not intended to be used for diagnosis or characterization of lesions, and that the device does not replace clinical decision making; - (iii) A summary of the clinical performance testing conducted with the device, including detailed definitions of the study endpoints and statistical confidence intervals; and - (iv) A summary of the standalone performance testing and associated statistical analysis. Device labeling created as part of this 510(k) satisfies the special control requirements. Page 13 of 14 {17} K260133 K260133 Page 14 of 14 Odin^{}[] Vision ## **Substantial Equivalence Conclusion** The subject device is similar to the predicate device with the main difference being the addition of compatibility with a legally marketed accessory to endoscopes (Endocuff), which does not raise different questions of safety and effectiveness. The two CADDIE versions (subject and predicate) share the same intended use, indications for use and principles of operation. The main difference and subject of this 510(k) has been addressed through non-clinical performance testing, using methods, protocols, and acceptance criteria that supported the previously cleared version of CADDIE (K252586). Performance data demonstrate that the subject device is substantially equivalent to the predicate device. Page 14 of 14