Investigation of Adaptation Mechanisms During Five-Day Dry Immersion Utilizing Big-Data Analytics

2021

Self Cite

Technological and scientific advancements continue to enable safe prolonged human presence in space, while extending the boundaries of manned exploration from low-Earth orbit into deep space. As humankind prepares to embark on exploration-class missions, to the Moon and Mars, mission objectives, risks and challenges become more complex and vastly different from the majority of human manned space exploration experience known to-date. The potential health risks associated with deep space exploration are expected to amplify, the mitigation of which would necessitate complex and autonomous in-flight medical capacity, which has not been available to-date. The logistics of medical care delivery in-flight have been significantly limited by impracticality of existing biomedical monitoring modalities and retrospective data analytics methods and techniques. Conventionally, physiological health monitoring has been discontinuous and extremely limited, hindering the usability and practicality of the acquired data to support clinical decision-making in-flight. This paper presents an integrated big data framework that utilizes stream computing to support real-time autonomous clinicaldecision making in-flight. The proposed framework extends previous research known as the Artemis and Artemis Cloud platforms by integrating multi-source, multi-type data to provide in-depth adaption-based assessment and identify the activity of the various compensatory reactions of regulatory mechanisms, which have been known to impact human health in weightlessness. The instantiation of the proposed big data integrated framework is demonstrated within the context of a ground-based 5-day Dry Immersion study. More specifically, the paper demonstrates the potential to support adaption-based analytics-as-a-service within the context of space medicine. Further to that, adaption-based analytics are enhanced through the introduction of multimodal real-time analytics. The multimodal adaption-based analytics are based on traditional data sampling and a sliding-window approach for analysis of the heart rate variability (HRV) and its features. The introduction of a sliding-window approach offers numerous benefits, including increased sample size, greater stability of numerical estimates, de-trending of the HRV to ensure the observed patterns are attributed to an actual physiological response rather than noise or artefacts. As such, the proposed adaptionbased analytics-as-a-service demonstrate great potential to identify unstable physiological states and support proactive prognostics, diagnostics and health management during spaceflight. Additionally, the proposed approach contributes to meaningful use of the acquired physiological data in-flight.TABLE OF CONTENTS 1. INTRODUCTION .

Section: Introductionmentioning

confidence: 91%

Adaption-Based Analytics for Assessment of Human Deconditioning during Deep Space Exploration

Prysyazhnyuk

2021

Self Cite

“…In recent years the Russian cosmonauts have utilized the Cosmocard ECG Holter monitor style device on the ISS and within various analogue missions within the NEK isolation (Mars 500) facility [13] and their Dry Immersion tanks [15] to collect cosmonaut ECG data.…”

Section: Health Monitoring Within the Spacecraftmentioning

confidence: 99%

“…As noted previously, these devices record data within a data logger while being worn and require uploading of data afterwards. Research using the Cosmocard device for data collection has been completed within the Luna 2015 analogue mission [1], [13] and also dry immersion experiments in 2016 [1], [15]. Testing with the Hexoskin product companion to the Bio-Monitor has been completed with firefighter students [34].…”

Section: Data Collectionmentioning

confidence: 99%

“…Currently data acquisition from the Cosmocard and Bio-Monitor are via data download from the data loggers from each of the devices. In addition to the acquisition of data collected on the ISS, data acquisition from the Cosmocard device has been completed within the Luna 2015 analogue mission [1], [13] and also dry immersion experiments in 2016 [1], [15]. In these cases, data acquisition was performed post experiment.…”

Section: Data Acquisitionmentioning

confidence: 99%

See 1 more Smart Citation

A Platform for Real-Time Space Health Analytics as a Service Utilizing Space Data Relays

2021

Self Cite

The health, wellness and adaptation response of astronauts during spaceflight is a key component for the success of any manned mission. Physiological and psychological responses of astronauts during spaceflight have been monitored from the first manned missions sixty years ago. However, limited communication networks to and within the spacecraft have limited methods to monitor the health, wellness and adaptation response of astronauts in real-time. This has resulted in a paradigm of astronaut monitoring as discontinuous samplings of physiological data that are captured on board the spacecraft and transported to Earth on storage devices for retrospective down sampled analysis. In 2009, as part of prior research, McGregor proposed a big data analytics framework and platform, that enables the capture and processing of physiological data and other clinical data in real-time for new approaches to real-time health monitoring. The platform, was named the Artemis platform after the Greek goddess of childbearing as the first domain it was used was neonatal intensive care. Its efficacy and reliability as a new approach for real-time health monitoring has been demonstrated in the critical care domain and specifically within the domain of neonatal intensive care. McGregor previously proposed the application of Artemis as an approach for autonomous health monitoring within the spacecraft to support missions within and beyond low Earth orbit. This would enable sophisticated realtime health, wellness and adaptation assessment that did not require the transmission of data beyond the spacecraft. Artemis Cloud has been proposed as a cloud-based approach to provide remote health monitoring. Artemis Cloud enables Health Analytics as a Service and has been demonstrated utilizing the Ontario Research and Innovation Optical Network (ORION) in Ontario and Artemis Cloud instances located at the Compute Ontario advanced research computing node within the Centre for Advanced Computing, Queen's University, Ontario providing remote health monitoring of neonatal intensive care patients at two hospitals in Ontario, Canada.There is great potential for this Health Analytics as a Service model enabled through Artemis Cloud to support the assessment of health, wellness and adaptation response of astronauts in space, however, robust and reliable networks are required. The next stage of space exploration will see unmanned missions using robots that will require prognostics and health management. This will be followed by manned lunar orbiters, Moon bases and Mars missions that will all require the support of health, wellness and adaptation assessment of astronauts engaged in those missions. Deep space hybrid radio frequency and optical networks have great potential to address the current gap in space communication networks. This paper presents a framework and infrastructure to enable real-time equipment monitoring for prognostics and health management and astronaut health monitoring through cloud-based Health Analytics as a Service utilizing space da...

“…Athena is an extension of the McGregor's Big Data analytics Artemis platform, which was originally designed to support neonatal populations in critical care units. The capabilities of Artemis to demonstrate subtle behaviors of early onset condition detections and adaptive health states have been presented in [4,5]. Athena has been welldemonstrated to perform resilience assessment and development for the training assessments [7]- [11].…”

Section: Introductionmentioning

confidence: 99%

An Individualized Countermeasure Assessment Framework for Astronauts in Space

Yeung

2021

Self Cite

Preventive measures and countermeasure exercises play integral roles in maintaining the physiological health, wellbeing, and performance of astronauts in current day four to 11 month space missions to the ISS. While these activities help the body adapt to the adverse effects of spaceflight and minimize risks of physical deconditioning associated with weightlessness, these activities are inadequate for longer trips such as a 2-3 year mission to and from Mars. Furthermore, physical reconditioning and other issues such as visual impairment intracranial pressure (VIIP) syndrome remain for some astronauts returning from space missions. Combined with the effects of isolation and confinement in space, an astronaut's condition and performance can be compromised to a high degree with long-term impacts to their health and wellness upon returning to Earth if the appropriate interventions are not performed at appropriate times. Research has shown that representation of the relevant data to the active user during their activities has been proven effective in allowing them to perform the appropriate intervention to mitigate projected health risks. The physiological data and countermeasure equipment data currently located on the ISS has the potential to be correlated with the respective activities performed per astronaut for an individualized physiological monitoring approach for real-time health assessments. This paper presents a correlation method to enable individualized countermeasure assessments using big data collected during a simulated extreme environment workshop for firefighters as an analog. The online health analytics platform, created by McGregor, known as Artemis demonstrates this method using its capabilities in temporal abstraction for knowledge discovery, mechanisms for early detection of illnesses, and continuous real-time monitoring. TABLE OF CONTENTS 1. INTRODUCTION .