Basic principles and concept design of a real-time clinical decision support system for managing medical emergencies on missions to Mars

Abstract

Space agencies and private companies prepare the beginning of the human space exploration for the 2030s with missions to put the first human on the Mars surface. The absence of gravity and radiation, along with distance, isolation and hostile environment are expected to increase medical events with unidentified manifestations along the crewmembers. The current healthcare strategy based on telemedicine and the possibility to stabilise and transport the injured crewmember to a terrestrial definitive medical facility is not applicable in exploration class missions. Therefore, full autonomous capability to solve medical situations will guide design of future healthcare systems onboard.This study presents the basic principles and concept design of a software suite to bring on-board decision support to help dealing with medical conditions of the crewmembers, with special attention to emergency care situations and critical monitoring. MEDEA is an autonomous clinical decision support system that provides real-time advice to tertiary interventions on-board in space exploration missions. Its basic principles are 1) to give real-time support for medical decision making, 2) give patient-specific advice for executive problemsolving, 3) take into account available information from life support and monitoring of crewmembers, 4) be full autonomous from remote facilities, 5) continuously adapt predictions to physiological disturbance and changing conditions, 6) optimise medical decision making in terms of mission fundamental priorities, 7) take into account medical supplies and equipment on-board, 8) apply health standards for levels of care V, 9) apply ethical standards for spaceflights, and 10) apply ethical standards for artificial intelligence.To fulfil these principles, MEDEA is conceptually designed as a software suite consists of four interconnected modules. The main of them is responsible to give direct advice to the crew by means of a deep learning multitask neural network to predict the characters of the medical event (e.g. life-threatening, delayability, ethical dilemma, duration of therapy, and compatible diagnoses), a classifier of the tertiary medical intervention and an optimiser of medical action plans. This module is continuously evaluate and re-trained with changing physiological data from the crew by an adaptive deep learning module, ensuring fairness, interpretability and traceability of decision making during the full operational time of MEDEA. Finally, MEDEA would be semantically interoperable with health information systems on-board by a FHIR module.The deployment of MEDEA on-board of future missions to Mars will facilitate the deployment of a comprehensive preventive medical strategy. Moreover, the advance in technology may represent a stepstone of the future quantitative medicine on Earth and on the expansion of humans throughout the solar system.