ICG for Gallbladder Disorders

Overseen By Christopher McCulloh, MD

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Activ Surgical

Must not be taking: Investigational agents

Disqualifiers: Pregnancy, Liver disease, Renal dysfunction, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: 4

120 Participants Needed

Trial Summary

What is the purpose of this trial?

The goal of this study is to evaluate the utility and efficacy of an artificial intelligence (AI) model at identifying structures and phases of surgery compared to traditional white light assessment by trained surgeons. Surgeons will perform the procedure in their standard practice, while the AI model analyzes data from the laparoscopic camera. Surgeons will be asked to audibly state when they identify structures and enter different phases of the surgical procedure. The AI will not alter the surgeon's view or be visible to the surgeon, and the surgeon will perform the procedure in the exact same fashion as they typically do.

Will I have to stop taking my current medications?

The trial protocol does not specify whether you need to stop taking your current medications. However, if you are on any investigational agents, you would not be eligible to participate.

What data supports the effectiveness of the AI Model treatment for gallbladder disorders?

Research shows that artificial intelligence (AI) can help in diagnosing and managing various gastroenterology conditions by analyzing medical images and data. AI has been used to guide the management of bile duct injuries and improve the care of patients with acute biliary pancreatitis, suggesting its potential effectiveness in gallbladder disorders. ^{1 2 3 4 5}

How does ICG for Gallbladder Disorders differ from other treatments?

ICG (Indocyanine Green) is unique because it is used in combination with artificial intelligence (AI) to enhance the safety of laparoscopic cholecystectomy (gallbladder removal surgery) by identifying safe and dangerous zones during the procedure, potentially reducing the risk of bile duct injuries. ^{5 6 7 8 9}

Research Team

Peter Kim, MD, PhD

Principal Investigator

Activ Surgical

Eligibility Criteria

Adults over 18 needing elective gallbladder removal due to conditions like gallstones can join. They must understand the local language, be able to follow study procedures, and have normal organ function tests. Excluded are those with allergies to ICG dye, liver disease, coagulopathy, pregnant or breastfeeding women, and anyone unable to consent.

Inclusion Criteria

My liver function tests are within normal ranges.

I don't have trouble breathing at rest and my oxygen level is above 94%.

Your platelet count is at least 75,000 per microliter, and if it's lower, you may receive a transfusion.

Exclusion Criteria

Pregnant women

Prisoners

People who may need extra protection or care.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Pre-dissection

Surgeons perform the procedure in their standard practice while AI analyzes data from the laparoscopic camera to identify structures and phases before dissection.

Immediately before surgery

1 visit (in-person)

Intra-dissection

AI/ML model analyzes surgical video in real time to identify anatomic structures and phases during dissection.

During surgery

1 visit (in-person)

Post-dissection

AI/ML model continues to analyze surgical video to ensure all critical structures are identified after dissection.

Immediately after surgery

1 visit (in-person)

Follow-up

Participants are monitored for safety and effectiveness after the procedure.

4 weeks

1 visit (in-person)

Treatment Details

Interventions

• AI Model

Trial Overview The trial is testing an AI model's ability to identify surgical structures and phases during laparoscopic cholecystectomy against traditional methods by trained surgeons. Surgeons will operate as usual while the AI analyzes video data without altering their view.

Participant Groups

Group I: Indocyanine green (ICG) Experimental Treatment 1 Intervention

Patients in this arm will receive an intravenous injection of indocyanine green (ICG) 45 minutes prior to the start of surgery. This will be used to visualize the biliary anatomy using ActivSight, a device that is FDA 510(k)-cleared for this indication. The surgeon will perform the procedure in their standard fashion using ActivSight. ActivInsight artificial intelligence will be used to analyze the surgical video in real time to identify anatomic structures and phases of surgery.

Group II: Non-Indocyanine Green (Non-ICG) Active Control 1 Intervention

The surgeon will perform the procedure in their standard fashion without the use of ICG. ActivInsight artificial intelligence will be used to analyze the surgical video in real time to identify anatomic structures and phases of surgery.

Who Is Running the Clinical Trial?

Activ Surgical

Lead Sponsor

Trials

4

Recruited

260+

Findings from Research

A Danish initiative has successfully developed computer-assisted decision support tools that significantly reduce the rates of perforated appendices and negative laparotomies in acute abdomen cases.

In jaundice diagnosis, three statistical methods have been tested to effectively identify causes, demonstrating the potential to integrate ultrasonographic data into clinical assessments, paving the way for improved diagnostic accuracy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Computer-assisted diagnosis in gastroenterology. Malchow-Møller, A., Bjerregaard, B., Hilden, J.[2019]

A study of 748 patients with iatrogenic bile duct injury (IBDI) found that machine learning models can accurately predict the success of initial repairs, achieving an accuracy of 82.8%.

Factors such as non-type E injuries, treatment at specialized centers, and surgical repair significantly improve prognosis, highlighting the importance of timely and appropriate management in IBDI cases.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Machine Learning-Based Analysis in the Management of Iatrogenic Bile Duct Injury During Cholecystectomy: a Nationwide Multicenter Study. Lopez-Lopez, V., Maupoey, J., López-Andujar, R., et al.[2022]

The newly developed care bundle for managing acute biliary pancreatitis includes 7 key elements, emphasizing the avoidance of antibiotic prophylaxis and recommending a full-solid diet for patients with mild to moderate cases.

The bundle also highlights the importance of timely interventions, such as performing endoscopic retrograde cholangiopancreatography within 48 to 72 hours for patients with cholangitis and recommending early laparoscopic cholecystectomy for mild cases, enhancing patient care through evidence-based practices supported by AI analysis.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The 2023 MANCTRA Acute Biliary Pancreatitis Care Bundle: A Joint Effort Between Human Knowledge and Artificial Intelligence (ChatGPT) to Optimize the Care of Patients With Acute Biliary Pancreatitis in Western Countries. Podda, M., Di Martino, M., Ielpo, B., et al.[2023]

Artificial intelligence (AI) has the potential to revolutionize gastroenterology by rapidly and accurately analyzing clinical data, which could surpass human specialists in certain diagnostic tasks.

Current research is focused on using AI for tasks such as interpreting colonoscopy results, enhancing the detection of polyps, and predicting patient responses to treatments, indicating a promising future for AI in improving patient care.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial Intelligence for Understanding Imaging, Text, and Data in Gastroenterology. Stidham, RW.[2022]

Artificial intelligence, particularly artificial neural networks, is revolutionizing gastroenterology by enhancing the analysis of endoscopy and imaging data, allowing for better detection of subtle patterns in medical images.

AI not only aids in identifying and classifying pathological findings but also has the potential to predict clinical outcomes based on these subtle image features, improving patient care.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

[Artificial intelligence in gastroenterology]. Kather, JN., Krause, J., Luedde, T.[2021]

The GoNoGoNet AI algorithm was able to identify unsafe dissection zones during laparoscopic cholecystectomy, showing that a significant proportion of dissection interactions in cases of bile duct injury occurred outside the predicted safe zones.

Injury-causing interactions were found in both the No-Go and Go zones, indicating that while the AI can help identify dangerous areas, further optimization is needed for its effective integration into surgical practice to prevent bile duct injuries.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Use of artificial intelligence for decision-support to avoid high-risk behaviors during laparoscopic cholecystectomy. Khalid, MU., Laplante, S., Masino, C., et al.[2023]

An artificial intelligence framework was developed to classify the vascularity of the gallbladder wall during laparoscopic cholecystectomy, achieving high accuracy rates of 92.6% to 93.2% and F1 scores of 93.5% to 93.9% based on analysis of 234 gallbladder images.

The AI model's performance closely matched that of expert evaluators, indicating its potential as a reliable tool for enhancing surgical decision-making regarding gallbladder vascular patterns.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Multiple instance convolutional neural network for gallbladder assessment from laparoscopic images. Loukas, C., Gazis, A., Schizas, D.[2022]

A new laparoscopic surgical system using Artificial Intelligence (AI) has been developed to accurately identify key anatomical landmarks during laparoscopic cholecystectomy, aiming to prevent intraoperative bile duct injuries.

The AI system has shown high accuracy in clinical tests, and while it has the potential to support surgeons and reduce complications, challenges remain in adapting it to various surgical conditions, such as inflammation of the gallbladder.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Development of Endoscopic Surgery Navigated by Artificial Intelligence. Inomata, M., Fujinaga, A., Nakanuma, H., et al.[2021]

AI models developed for laparoscopic cholecystectomy can effectively identify safe (Go) and dangerous (No-Go) zones of dissection, achieving high accuracy and specificity, which may help reduce surgical errors.

The models were trained on a large dataset of 290 videos from 37 countries, demonstrating their potential for real-time guidance during surgery to enhance safety and minimize adverse events.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial Intelligence for Intraoperative Guidance: Using Semantic Segmentation to Identify Surgical Anatomy During Laparoscopic Cholecystectomy. Madani, A., Namazi, B., Altieri, MS., et al.[2023]

References

1. England pubmed.ncbi.nlm.nih.gov

Computer-assisted diagnosis in gastroenterology. [2019]

2. United States pubmed.ncbi.nlm.nih.gov

Machine Learning-Based Analysis in the Management of Iatrogenic Bile Duct Injury During Cholecystectomy: a Nationwide Multicenter Study. [2022]

3. United States pubmed.ncbi.nlm.nih.gov

The 2023 MANCTRA Acute Biliary Pancreatitis Care Bundle: A Joint Effort Between Human Knowledge and Artificial Intelligence (ChatGPT) to Optimize the Care of Patients With Acute Biliary Pancreatitis in Western Countries. [2023]

4. United States pubmed.ncbi.nlm.nih.gov

Artificial Intelligence for Understanding Imaging, Text, and Data in Gastroenterology. [2022]

5. Germany pubmed.ncbi.nlm.nih.gov

[Artificial intelligence in gastroenterology]. [2021]

6. Germany pubmed.ncbi.nlm.nih.gov

Use of artificial intelligence for decision-support to avoid high-risk behaviors during laparoscopic cholecystectomy. [2023]

7. England pubmed.ncbi.nlm.nih.gov

Multiple instance convolutional neural network for gallbladder assessment from laparoscopic images. [2022]

8. United States pubmed.ncbi.nlm.nih.gov

Development of Endoscopic Surgery Navigated by Artificial Intelligence. [2021]

9. United States pubmed.ncbi.nlm.nih.gov

Artificial Intelligence for Intraoperative Guidance: Using Semantic Segmentation to Identify Surgical Anatomy During Laparoscopic Cholecystectomy. [2023]