AI-Driven Personalized Perioperative Management in Colorectal Cancer: A Randomized Controlled Clinical Trial - The AIDPRO-CRC Trial
Trial Snapshot
- Phase
- Not Applicable
- Status
- Recruiting
- Sponsor
- Zealand University Hospital
- Enrollment
- 1,200
- Locations
- 9
- Primary Endpoint
- Cost Effectiveness
Study Overview
Brief Summary
The AIDPRO-CRC trial aims to improve outcomes for patients undergoing surgery for colorectal cancer by using artificial intelligence (AI) to assist surgeons in risk assessment. The trial will evaluate whether AI can help surgeons better predict the risk of complications and death, leading to improved care, fewer complications, and better use of healthcare resources.
In this nationwide, randomized clinical trial, participants will be divided into two groups. One group will have their risk assessed by a surgeon using standard clinical methods, while the other group will have their risk assessed by a surgeon using AI assistance. Based on the risk level, patients will receive varying levels of perioperative care. The AI-assisted risk assessment aims to tailor the treatment more precisely to each patient's individual needs, precisely allocating care to those who need it to more efficiently allocate heath system resources while having no deterioration in patient outcomes.
The primary hypothesis is that AI-assisted risk assessment will lead to more efficient and economic patient care without a deterioration in patient outcomes. The trial also aims to explore clinician satisfaction with the platform and its perceived effect. This is paired with a substudy exploring the variability of suggested treatment plans by clinicians with and without access to the MDT presentation platform.
The trial will include patients at seven hospitals across Denmark, involving patients diagnosed with colorectal cancer who are scheduled for curative surgery. All patients will receive standard treatment according to national guidelines, with the only difference being the modality of risk assessment. For the evaluation of the clinicians satisfactory with the device and the substudy of variability of suggested treatment plans, the trial will enroll clinicians using the device.
This study is a researcher-initiated, nationwide, randomized clinical trial involving patients diagnosed with colorectal cancer across eight hospitals in Denmark. Participants will be randomly assigned to one of two groups: AI-assisted risk assessment or standard surgeon-led assessment. The intervention focuses on optimizing perioperative care based on individual risk levels determined by either AI or the surgeon's clinical judgment.
The study builds on a successful pilot project (AID-SURG) that showed promising results in reducing complications, hospital stays, and readmissions.
Detailed Description
Introduction:
The AIDPRO-CRC trial is an investigator-initiated nationwide multicenter randomized controlled trial. The trial aims to investigate the clinical effects of an AI-augmented solution "AIDPRO manual CRC" for optimization of perioperative treatment by personalized risk stratification of patients undergoing CRC surgery. The protocol adheres to the SPIRIT Statement recommendations.
The AIDPRO-CRC trial is a pre-market, pivotal stage, confirmatory clinical investigation designed to evaluate the safety and effectiveness of the AIDPRO manual CRC algorithm. As a pivotal clinical investigation, this study is critical for generating the robust evidence required to support regulatory submissions for CE marking. The investigation involves an interventional approach, meaning that participants will undergo specific procedures or treatments as part of the study. This design has been specifically chosen to rigorously assess the performance of the AIDPRO manual CRC device in a real-world clinical setting, providing the necessary data to demonstrate its safety and effectiveness. The results from this trial will be used to seek CE marking, enabling the AIDPRO manual CRC to be brought to market in the future.
Objective of the Study:
Colorectal cancer (CRC) is the second leading cause of cancer-related mortality worldwide. Despite advances in standardized treatment protocols, significant challenges remain in reducing complications, readmissions, and mortality. Addressing these challenges necessitates a transition toward individualized, data-driven treatment strategies.
Study Design
- Study Type
- Interventional
- Allocation
- Randomized
- Intervention Model
- Parallel
- Primary Purpose
- Supportive Care
- Masking
- Single (Participant)
Eligibility Criteria
- Ages
- 18 Years to — (Adult, Older Adult)
- Sex
- All
- Accepts Healthy Volunteers
- No
Inclusion Criteria
- •To be eligible for study participation, the following criteria must be met:
- •Histologically confirmed diagnosis or strong clinical suspicion of first-time colon or rectal cancer, clinical stage I-IV.
- •Signed written informed consent obtained prior to any study-specific procedures.
- •Age ≥18 years at the time of consent.
- •Scheduled for potentially curative surgery as determined by a multidisciplinary team (MDT) conference.
- •Availability of all required input variables for the AI model not directly assessed by the surgeon (e.g., ASA score, WHO performance status).
Exclusion Criteria
- •A patient will be excluded from the study if:
- •Surgery with curative intent is no longer planned despite previous eligibility.
- •Healthcare Professionals Surgeons and other healthcare professionals involved in the use of the AI-based platform will be invited to participate in two sub-studies: a user satisfaction survey and a simulation-based study. Eligible personnel will be automatically invited upon registration as platform users.
- •Inclusion criteria - healthcare professionals
- •To be eligible to participate in the survey and simulation study, individuals must:
- •Be licensed medical doctors.
- •Be either board-certified specialists in surgical oncology or currently in training to become one.
- •Exclusion criteria - healthcare professionals There are no exclusion criteria for participation in the survey or simulation study.
Arms & Interventions
AI-augmented risk-stratification
- Description: An advanced AI model functions as a decision-support tool to estimate each patient's perioperative risk.
- Purpose: The AI model uses various patient-specific data inputs to predict risk and assign a tailored care pathway, based on a large historical dataset.
- Expected Outcome: The use of AI is expected to improve the precision of risk stratification, thereby optimizing resource utilization.
Intervention: AI augmented risk-stratification (Device)
Expert-based Risk-stratification
- Description: Experienced colorectal surgeons assess patient risk based on clinical judgment and national guidelines.
- Purpose: Traditional clinical assessment is used to assign patients to the appropriate care pathway.
- Expected Outcome: This arm serves as the clinical standard-of-care comparator against which the effectiveness of AI-guided decision-making is evaluated.
Intervention: Expert-based Risk-stratification (Other)
Outcomes
Primary Outcomes
Cost Effectiveness
Time Frame: Baseline
This primary endpoint is the saved marginal cost of perioperative intervention bundles achieved by integrating AI-augmented decision support. This will be assessed by comparing the overall marginal cost per patient between the AI-assisted arm (Intervention-arm) and the standard clinician-based stratification arm (control-arm). This cost-calculation factors in the following: * Distribution of patients across risk strata (A, B, C, D) * Cost per intervention bundle * Total perioperative expenditure per patient pr. bundle
Perceived Effect of Clinical Support Tool & User Feedback
Time Frame: After 8 weeks of use again at 24-52 weeks of use and at after inclusion of last patient
This primary endpoint domain evaluates the user-perceived satisfaction with and clinical relevance of the AI-driven MDTPlatform medical device which contains the risk prediction algorithm. * Perceived relevance of the MDTPlatform provided information (i.e., the risk stratification and other displayed data) in support of making clinical decisions regarding perioperative treatment for a patient? * Perceived relevance of the displayed information provided by the MDTPlatform to clinical decision-making? * Comparison of the ability of MDTPlatform to provide a better overview of the current patient's treatment course in the context of multidisciplinary decision-making compared to usual practice? Each measured using a 7 point Likert scale where responses of 5, 6 or 7 are considered relevant All perceived clinician satisfaction with the use of the MDTPlatform will be assessed by questionnaire sent to users
Variability of Suggested Treatment With and Without MDTPlatform
Time Frame: Baseline
This primary endpoint relates to the simulation substudy which will be carried out by letting users a subset of a set of patients. Over 1-2 sessions clinicians will evaluate a subset of a predetermined set of realistic patient cases. The total set will include 75 patients with and without MDTPlatform, yielding a total of 150 (2x75) cases. Clinicians will be asked to evaluate a minimum of 20 cases. Clinicians will score risk class based on the given data and will suggest a treatment plan, which will be recorded. The data given will be the same for cases with and without MDTPlatform, except for the risk stratification which will only be included in the cases presented via the MDTPlatform. The cases that are not presented via the MDTPlatform will be presented in the standard manner of the site where the clinician works. These data will show whether treatment recommendations vary less when MDTPlatform is used for risk prediction and case presentation versus standard care.
Secondary Outcomes
- The rate of complicated postoperative course 90 days after surgery(90 days post-operative)
- Postoperative Complications(90 days Post-Operative)
- Length of Hospital stay (LOS) > 4 days(90 days post-operative)
- Readmission Rates(90 days postoperatively)
- Days Alive and Out of Hospital 30 days and 90 days(90 Days Postoperatively)
- Composite outcomes:(90 days post-operative)
- Time from MDT to Surgery(Preoperative)
Investigators
Ismail Gögenur
Professor, MD, DMSc, Consultant
Zealand University Hospital