Overview
Integration of iRevive with the Lightweight Trauma Module
NASA Use Case. (Image courtesy of 10Blade, Inc.) Click here for Larger image.
Principal Investigator:
John P. Crossin
Organization:
10Blade, Inc.
Astronauts on long-duration missions will not be able to return to Earth for routine or emergency medical care. Therefore, crew members will need to rely on each other and the devices available to them for medical care.
John Crossin’s project seeks to provide a system that will function autonomously, yet communicate with Earth, to provide astronaut health assessment and care. The new system will integrate two existing technologies. The first is iRevive — a flexible, mobile electronic medical record. The second is the lightweight trauma module, a combined ventilator/critical care monitor and therapeutic system that has integrated automatic control systems. The integrated system will effectively guide the actions of the crew medical officer to help direct and manage therapeutic healthcare.
NASA Taskbook Entry
Technical Summary
Astronauts on long-duration missions will not be able to return to Earth for routine or emergency medical care. We are developing an integrated system that can function autonomously yet communicate with Earth to provide astronaut health assessment, maintenance and medical care.
The system is based on the integration of two existing medical platforms. iRevive, which is a semantically flexible, mobile electronic medical record, serves as the primary interface between the patient and crew medical officer. The Lightweight Trauma Module (LTM), which is a combination ventilator/critical care monitor and therapeutic system with integrated automatic control systems, provides manifold physiological monitoring and support functions. The integrated system will collect, monitor and fuse patient care information with physiological patient data to further study and optimize remote medical diagnosis, ventilator support, intravenous (IV) fluid therapy and treatment options.
The heart of the system is a relational database with a user friendly graphical user interface (GUI). The former is backed by a rich data dictionary, while the latter simplifies data collection and data entry through a variety of pull-down options. The overriding goal is an intuitive, easy-to-use system that requires little medical training to understand and use.
Objectives
- Formalize communication protocol between iRevive and the LTM.
- Design GUI for LTM integration into clinical workflow.
- Alter iRevive GUI to accommodate LTM data fields.
- Re-factor iRevive database.
- Testing and integration.
- Clinical trial, system modifications and data exchange.
- Prepare and submit written report
Key Findings
During the first year of this program, significant progress has been made in several areas. Communication between the two systems is now controlled by a firmware-driven field-programmable gate array (FPGA) in the LTM. A protocol verification simulator has been written, debugged and used for testing with iRevive. All levels of communication, such as sensor definition, data definitions, transmission packets, alarms and time synchronization, have been addressed and integrated into the simulator.
Extensive work has been done to define the data for nearly 30 vital signs delivered by approximately 20 sensor types. The data structure of the transport (UDP) packet is defined and implemented. Specific packets have been defined, including types for synch packet, parametric vital sign packet, device alarm packet, wave data packet and general LTM information. The structure for verification of the contents of each of these packets has been implemented, as well as protocols for missed and lost packets. Internal controls have been defined and resolved. Situations such as coordination of time between devices and resolution of redundant data, such as pulse rate from different devices, have been addressed. As a result, communications data is presented in a concise, cohesive and consistent manner. The resultant system is extensible and robust.
Data definitions within iRevive are in place, as are the underpinnings for a new, browser-based GUI. The GUI is what allows the crew medical officer to enter all relevant data necessary to ensure an optimal outcome. The GUI directs the user to successive screens specific to an injury or condition. An example of this is a "body picker" pop-up. By simply touching a representation of the part of the body where the condition exists, a series of screens appear to guide the entry of required data in a standardized manner. Successive screens are then accessed until a complete description of the condition is entered.
All data collected is placed in a database that is flexible, reportable, queryable and much faster than previous versions. Every action is time stamped, creating a uniform record of actions, interventions, medications, observations. Vital sign data is collected and preserved for current medical and future research purposes. Audio and visual alarms from the LTM are in place in iRevive to warn of impending problems or the need for immediate action. These alarms range from simple reminders to reassess the patient or hang a new bag of IV fluid, to more complex alarms concerning an abnormal set of vital signs or ventilator malfunction.
Proposed Research Plan for Coming Year
During the second year of this program the full iRevive-LTM system will come together. Refinements include general streamlining of the iRevive-LTM communication protocol, adding waveform data to the database, refinement of the data model and database, and improvements to the GUI. Waveforms will increase the user experience beyond the current, periodic data input model. Processes for waveform generation and use are underway. Once these are defined and verified by the simulator, these results will be included into the firmware FPGA code that implements the communications protocol. This tested and verified version will then be integrated into the hardware that will be submitted for regulatory certification.
Database and GUI improvements are geared toward faster, more organized data entry. Focus groups composed of physicians and intensive care unit nurses are being used to vet the structure, format and color scheme of GUI as it is developed. The communication protocol, database and GUI refinements should be completed within the next 6-7 months, at which time the iRevive-LTM system will be ready for clinical testing in a patient care setting. An Institutional Review Board application has been completed and is in review to allow evaluation of the system on a minimum of 40 patients at Denver Health Medical Center. Results from the clinical trial will be used to further improve application.
Earth Applications
Civilian pre-hospital providers (i.e., paramedics and emergency medical technicians) collect and act upon a wide variety of complex visual clues, while at the same time monitoring and adjusting to continually changing sets of vital signs. Pre-hospital vital sign information in the form of waveform data is rarely integrated into the patient care record, so how the vital signs change in response to specific treatment measures is largely undocumented and poorly understood. As a consequence, the care that is provided to a patient in the field is anticipatory and reactive. It is not time-sensitive, and the accompanying patient medical record is poorly contextual. Healthcare providers do not give medications or adjust the ventilator and intravenous fluids as often or as accurately as a smart, vigilant system might, and as a result, patients likely do not respond or recover as quickly as they could.
We are developing a fully integrated system for mobile critical care patient support and documentation. The iRevive-Lightweight Trauma Module (LTM) system is composed of physiological sensors, monitors and therapeutic hardware devices, linked by a suite of software applications. The components integral to the LTM include: a ventilator; 3/5/12-lead electrocardiography; pulse oximeter; noninvasive blood pressure; end-tidal carbon dioxide (EtCO2); patient temperature; invasive arterial and intracranial pressure monitoring capabilities; ethernet communications; closed-loop control of oxygenation (and soon ventilation and IV fluid control); an integrated electronic medical record (iRevive) for data storage and export; alarm modules and smart help.
The LTM supports up to three external IV pumps and is designed to support other (yet to be developed) noninvasive monitors, all connected via powered- USB ports. It supports several additional modules, including an oxygen concentrator, patient warming and an anesthesia control module. Software will oversee a growing number of autonomous care applications within the integrated system, which will reduce the need for constant attention by a healthcare provider or crew medical officer.
While spaceflight design requirements are of paramount importance to the current project, we are cognizant of U.S. military and civilian needs for improved monitoring technology used during transport. The small, lightweight, rugged, low-power design specifications for spaceflight are similarly important here on Earth. A transport monitor that goes into space should have facility for remote calibration and maintenance, as should a transport monitor that is deployed on the battlefield. Incorporation of redundant systems, automated alarms and increasingly closed-loop control algorithms will be equally important.
The value of consolidating patient monitoring, support and documentation into a single system, capable of automatically collecting and transmitting real-time patient care data, cannot be overemphasized. Integrating these data streams has many advantages, not only in providing real-time information display both locally and centrally for triage decision support, but in trauma system development. More importantly, the physiologic and electronic patient care data that will be captured by the iRevive-LTM system will be fully integrated and time synchronized. New state-of-the-art machine learning, feature extraction and advanced statistical methods are showing great promise in analyzing these types of complex data sets, uncovering many important, previously hidden physiological relationships and treatment effects. As these relationships are further defined and understood, our models of health and disease will become more complex and accurate. They will provide more reliable, real-time insight into the current and predicted future status of patients. In time, machine-based comprehension of semantic clinical information together with real-time physiological data will lead to the development of fully autonomous patient care systems.
This project's funding ended in 2011
