AutoMated BUrn Diagnostic System for Healthcare (AMBUSH)

NCT05167461 | Completed DMC

• 1 other identifier: 12689
• Study Type: observational
• Target: 30
• Locations: 1 country
• Sites: 1

Brief Summary

The primary objective of this study is to develop a high accuracy and automated system that can provide early assessment of burn injuries with at least 90% accuracy in absence of burn experts, using AI and FDA cleared harmonic ultrasound TDI data based on the analysis of mechanical and hemodynamic properties of the subcutaneous burned tissue. Data collected in this study will lead to the development of better diagnostic tools that could inform clinical burn practices by enabling doctors to determine burn depth and the need for surgery with greater speed and accuracy, resulting in better clinical outcomes.

Conditions

Burns Multiple; Burns; Thermal Burn; Burn Infection

Keywords

burns; thermal burn

Outcome Measures

Primary Outcomes (1)

• Compare human assessment of burn depth to AI assessment

  Compare human assessment of burn depth to the technology output (Artificial Intelligence and TDI) as determined by need for surgery (time points include day 0 +/- 3 days). Biopsy collected from patients that go to OR (one-time collection) to verify the burn depth via histological analysis.

  2 year

Secondary Outcomes (1)

• Confirm burn conversion

  2 years

Other Outcomes (1)

• Evaluate burn software accuracy

  2 yrs

Interventions

Collection of imaging by ultrasonography OTHER

The investigators will collect burn image data to be processed through the software combined with the deep machine learning to find automated diagnostic burn assessment with accuracy of \>95% compared to human assessment

Also known as: deep machine learning

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Subjects aged 18 years and above, male and female, with a thermal burn injury will be considered for participation in this study. Enrollment of 30 subjects is planned

You may not qualify if:

• Unable to provide informed consent
• Age \<18 years
• Burn ≥ 75% of body surface
• Burns caused by chemicals, electricity or radiation.
• Patients presenting with only 3rd-degree/full-thickness wounds which require immediate autografting.
• Burn injury has had prior surgical treatment.
• Prisoners
• Pregnant individuals
• Unable to follow study schedule or understand study instructions

Sponsors & Collaborators

• Indiana University: lead
• Eskenazi Health: collaborator

Study Sites (1)

Eskenazi Health

Indianapolis, Indiana, 46202, United States

Location

Biospecimen

Retention: SAMPLES WITH DNA

discarded burn tissue will be taken

MeSH Terms

Conditions

Burns

Interventions

Reinforcement Machine Learning

Condition Hierarchy (Ancestors)

Wounds and Injuries

Intervention Hierarchy (Ancestors)

Machine Learning; Artificial Intelligence; Algorithms; Mathematical Concepts

Study Officials

• Gayle Gordillo, MD

  Indiana University

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: CASE CROSSOVER
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Professor of Plastic Surgery

Study Record Dates

• First Submitted: November 5, 2021
• First Posted: December 22, 2021
• Study Start: May 24, 2022
• Primary Completion: May 25, 2023
• Study Completion: May 25, 2023
• Last Updated: October 23, 2023

Record last verified: 2023-10

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF
• Time Frame: 1 yr after all data collected until 3 yrs after study results
• Access Criteria: via email from statistician

Locations

US (1)