Abstract: Circulatory shock is a potentially deadly condition characterized by inadequate cellular oxygen metabolism and rapidly emerging multi-organ failure. The survival rate for patients with circulatory shock is determined by timely recognition of shock onset and timely identification of underlying cause by combat medics. Use of machine learning (ML) can boost medics’ ability to analyze medical data while performing tactical combat casualty care (TCCC) in austere battlefield settings. This work is the first step toward the development of a decision support system using machine learning algorithms to detect and differentiate shock.

Describe the new knowledge and additional skills the participant will gain after attending your presentation.: Learning Objectives:
1. To outline the challenges in circulatory shock detection and differentiation in combat casualties.
2. To discuss potential of machine learning as a component of decision support system for healthcare providers.
3. To describe the approach we used in developing the Trauma Triage, Treatment, and Training Decision Support System.

Authors:

Yuliya Pinevich (Presenter)
Mayo clinic

Adam Amos-Binks, Applied Research Associates, Inc.
Christie S. Burris, Applied Research Associates, Inc.
Greg Rule, Applied Research Associates, Inc.
Ryan Lowe, Applied Research Associates, Inc.
Brian Pickering, Mayo clinic
Christopher Nemeth, Applied Research Associates, Inc.
Vitaly Herasevich, Mayo clinic