SBIR-STTR Award

P22-145 ITM Ph II Expansion (CCHAT Protocol)
Award last edited on: 10/15/2018

Sponsored Program
SBIR
Awarding Agency
DOD : DARPA
Total Award Amount
$3,135,716
Award Phase
2
Solicitation Topic Code
DHA17B-002
Principal Investigator
Alyssa Tanaka

Company Information

Soar Technology Inc (AKA: SoarTech)

3600 Green Court Suite 600
Ann Arbor, MI 48105
   (734) 627-8072
   info@soartech.com
   www.soartech.com
Location: Multiple
Congr. District: 12
County: Washtenaw

Phase I

Contract Number: W81XWH-18-C-0028
Start Date: 11/15/2017    Completed: 6/14/2018
Phase I year
2018
Phase I Amount
$149,876
Research has identified that handoffs are particularly important communication processes, during which communication error can lead to patient safety situations. Organizations have created standard practices and training materials to encourage teamwork communication for handoffs, however these do not necessarily capture the needs of military medicine of combat casualty care. Combat casualty handoffs can be even more complex, allowing for more opportunity for error. They require specific protocols and techniques that address the unique needs of the patients, providers, and environments and will allow for effective communication and information transfer.Thus, the proposed effort aims to design and develop a new concept for handoff protocols, for use through the continuum of care for combat casualty care. The CCHAT Handoff Protocol will outline the protocol for the purpose of implementation into an automated speech recognition system. The effort will develop descriptions of the correct methodology for performing a combat casualty handoff and a description of the concept of operations for future handoff training systems. These descriptions will be used to create the speech ontology for the speech recognition training system. This effort will result in the protocol documentation needed for the DHA17B-001 performer to develop requirements for a speech recognition prototype.

Phase II

Contract Number: W912CG23C0036
Start Date: 6/7/2023    Completed: 7/8/2026
Phase II year
2023
Phase II Amount
$2,985,840
Current artificial intelligence (AI) algorithms are built to align with ground truth or consensus of trusted human decision-makers. This is not effective for difficult decision domains, such as patient triage, where even experts disagree on the best course of action. A key reason human experts disagree is that their individual attributes influence their decision-making. To develop human-off-the-loop triage systems that are trusted by humans, understanding and alignment with these attributes is critical. This will enable effective communication of system decisions, based on these attributes may further support trust in the system. During this effort, the team will use proven interview-based approaches and machine learning tools to identify attributes that predict communication and decision-making styles used during high-stakes situations such as patient triage, and will develop tools that give insights into alignment scores and communicate AI-based decisions to human users. This effort will produce five unique products: 1) KDMAs / KCAs grounded in data gathered from SME interviews and identified using machine learning models; 2) triage scenarios that elicit decisions and corresponding attributes; 3) a model for cue utilization that will inform scenarios; 4) visualizations to give insight into human-AI attribute alignment; 5) tools to help communicate AI-based decisions to humans.