PG256191203S
ADVANCED WARFIGHTER PHYSIOLOGY: APPLICATION OF BIOMETRICS AND BODY WORN SENSORS TO REDUCE INJURY RISK AND OPTIMIZE PERFOR To provide detailed, repeated physiological function and physical performance assessments on a single-subject every month for 12 months. The assessments will take place during 8-day experimental windows that will include free-living/training (6 days) and controlled laboratory testing (control vs. heat stress trials, days 7 and 8) to determine the implications of environmental/seasonal variability on the physiological responses to exercise and heat stress. Arizona State University
Definitive Contract FA865019C6124 7/8/25 $137.8k 8/11/25 PG256191204S
ADVANCED WARFIGHTER PHYSIOLOGY: APPLICATION OF BIOMETRICS AND BODY WORN SENSORS TO REDUCE INJURY RISK AND OPTIMIZE PERFOR We aim to develop a human digital twin model specific to measured physiological responses during repeated periods of heat stress responsiveness. We will evaluate the physiological responses to environmental and seasonal situations. The approach will include a comprehensive series of single-subject, case study-oriented designs specific to heat stress. Our lab will provide a detailed physiological function and physical performance assessment before, during, and following the extended data collection cycles (anticipated at approximately one calendar year). Our lab will provide physiological measures continuously and intermittently acquired throughout an eight-day experimental window each month. Specifically, free-living/training (six days) and controlled laboratory testing (control vs. heat stress trials, days seven and eight) will be used to determine the implications of environmental/seasonal variability on the physiological responses to exercise and heat stress. Our lab will provide specific assessments during these windows, including a fasting blood sample obtained at the end of the six-day pre-testing period (comprehensive metabolic and blood lipid panel). On days seven and eight of each month's testing, subjects will complete a control (200C, 40% RH) or heat stress (380C, 40% RH) treadmill exercise trials (90 min, 1.6 m/s, 5% grade). Continuous measures of heart rate, core, skin (3 sites), and galvanic skin response (GSR) will be recorded during each trial. Sweat rate and composition (forehead) and pre/post blood parameters (Hb, hct, lactate) will also be collected. Steady-state expired air samples will be collected in the initial ten minutes and between 55-60 and 85-90 minutes to calculate whole-body muscle fuel use. All data collected will be shared with research team lead Dr. Brent Ruby and the Biophysics and Biomodelling research team at the US Army Institute of Environmental Medicine. California Baptist University
Definitive Contract FA865019C6124 4/8/25 $123.7k 5/28/25 PG256191205S
ADVANCED WARFIGHTER PHYSIOLOGY: APPLICATION OF BIOMETRICS AND BODY WORN SENSORS TO REDUCE INJURY RISK AND OPTIMIZE PERFOR Digital twin approach is based on merging two existing modeling methods: first-principles and data-driven. Merging two modeling techniques allows a more complete model as the two approaches complements each other combining their strengths and eliminating weaknesses. The first-principles modeling relies on either ordinary or partial differential equations derived from known physics or human physiology laws and principles. While being a powerful tool in investigating system's response to different inputs, the first-principles systems do not use the most current data and cannot reflect the immediate conditions of human physiology. Also, the first-principles model may not consider all factors affecting human's response to stress as some of them are not known or two complex to derive. On the other hand, the Artificial Intelligence/Machine Learning (AI/ML) -based data-driven models can use the most recently collected data to produce parameters predictions and can be adapted to the most immediate data. However, these data-driven algorithms tend to overfit the data and most of them lack explainability. Data overfitting leads to models which perform very well withing the range of training data, however, breaks down once the new data are outside of the historical data. The lack of explainability undermines trust in these models and leads to reluctance in accepting them for human-safety related applications. The digital twin approach addresses the weaknesses of these two modeling approaches and also offers an opportunity to provide an anticipatory physiologic guidance to the military personnel by first applying the anticipated guidance to the twin model prior advising it to the personnel. This project will develop digital twin models based on Physics-Informed Deep Neural Networks (PIDNNs). The Physics-Informed Deep Neural Networks (PIDNNs) will consist of the first-principle SCENARIO model developed at USARIEM and data-driven part represented by a deep neural network developed based on data collected from wearable sensor suits. The SCENARIO model developed at USARIEM, was designed to estimate and predict core temperature, heart rate, and sweat rate, without requiring prior knowledge and direct measurement of these physiological variables. The underlying model for SCENARIO simulates the time course of core temperature variations, while taking into account different factors that affect human thermoregulation. The temperature distribution within the human body is represented by a lump-parameter model consisting of six concentric cylindrical compartments. Heat flow is then modeled by a set of macroscopic energy conservation equations based on heat convection between the central blood compartment and the adjacent core, muscle, fat, and vascular skin compartments; radial heat conduction between every pair of adjacent compartments; and air convection, radiation, and sweat evaporation between the superficial avascular skin layer and the environment and transition through the clothing The energy conservation equations are represented by a set of six ordinary differential equations that can be expressed as a system. Battelle Energy Alliance, LLC
Definitive Contract FA865019C6124 4/14/25 $600.0k 5/28/25