Current Projects
Data Aggregation
AGGREGATING AND TIME SYNCHRONIZING DATA FROM DIVERSE SOURCES:
We are developing pathways and tools to aggregate data from diverse data sources. These sources can be commercial products or other repositories.
Terminology and Harmonization
CREATING MISSING TERMS AND HARMONIZING TERM:
We are proposing standard definitions for those terms where they are missing. We are expanding Common Data Elements where needed. We are developing tools to annotate and harmonize data from diverse sources.
Cloud Storage and Governance
CREATING A STANDARDZED MULTIMODAL DATABASE FOR NEUROCRITICAL CARE:
We are developing a standardized file naming format. We are developing secure, HIPAA-compliant cloud storage with customizable governance.
Analytics
CREATING PLUG-IN APPS FOR ANALYTIC METHODS:
We are developing a general purpose API to the standardized data repository. We are working with collaborators wishing to test their methods on the harmonized data.
Visualization
CREATING VISUALIZATIONS THAT COMMUNICATE PATIENT STATUS:
Visualization tools are being created that communicate patient status.
The Brain Medical Record
CREATING A MORE MEANINGFUL MEDICAL RECORD FOR THE BRAIN:
The ultimate goal is to create from the harmonized data a medical record for the brain that enables precision management.
Terminology
Background
This project is focused on the consensus development of standards needed for data management in neurocritical care. Neurocritical care is a new discipline in medicine and rapidly growing with new knowledge about the injured brain and new ways to measure it. Patients in neurocritical care are high-volume data generators and this field is ripe for the use of big data technology. Unfortunately, there is a lack of standardized terminologies as well as metadata to describe how it was collected. Our goal is to create a comprehensive vocabulary specific to neurocritical care by leveraging existing standards and filling in the gaps.
The problems encountered in neurocritical care terminology are as follows:
1. Orphan Terms: Terms that have no standard definition (e.g. partial pressure of brain tissue oxygen)
2. Multiple Definitions: Terms that have different definitions in multiple standards (e.g. Intracranial Pressure)
3. Ambiguous Terms: Terms that are ambiguous (e.g. Mean ICP)
4. Structure: A general lack of the sematic structure of the terms (ontology)
5. Metadata: A lack of metadata or annotations important in further defining a term (e.g. EVD stopcock open/closed)
Approach
Our approach is as follows:
1. Scope: Our scope is limited to physiological measurements obtained from patients such as intracranial pressure, brain oxygen, pupil reactivity, blood pressure, etc.
2. Priority: The priority is to focus on the more neuro-centric measurements.
3. Resources: We are reviewing existing standards and documents to determine gaps in nomenclature and areas of ambiguity. We are working with existing projects such as Common Data Elements, OHDSI, and others.
4. Tools: We have developed a wiki, discussion forum, and Github to document our progress (see below)
5. Consensus Group: We are creating subject matter consensus groups to develop and refine the terminology and ontologies. We are working with several professional organizations such as the Neurocritical Care Society.
6. Publications: Our work is available on our website and is periodically published and presented at scientific meetings.
Tools
The tools we have created and their intended use are as follows:
1. Terminology Wiki: This wiki is devoted exclusively to terminology issues. The purpose is to organize existing information and to document our progress.
2. Discussion Forum: The Vocabulary category in the discussion forum is devoted to discussions on terminology. Topics focus on specific measurements and related issues.
3. GitHub: We are developing a repository of documents related to our topics and/or generated by our group.
Participate
You many freely view the results of our work. Join the group to participate in the discussions and help with project.
Data Sources and Aggregation
Background
A challenge in neurocritical care is the aggregation of data from multiple diverse sources so that it can be used efficiently in patient management as well as in algorithms that extract additional value. The data of interest is often in silos and may not be in the most usable form. Additionally, the interoperability of data from source to user has been challenging. Four sources of data are being addressed:
1. Medical device data
2. Electronic medical record data
3. Imaging
4. Nursing interventions
1. Data Aggregation of Medical Devices
Our focus is on the capture of high-resolution physiological data in neurocritical care as this is one of the most significant gaps in creating a connected neuro ICU. There is no widely used medical device communications standard which has led to these gaps. Some devices send waveform and trend data over the hospital network and several commercial products can collect this data (Capsule Technologies, Excel Medical, Sickbay). Some do it for the purpose of sending the data to the medical record but it may end up in a resolution that might not be useful for precision management. Others have developed systems that collect the high resolution data directly from devices (Moberg Research, ICM+).
Approach
Progress
Our approach is not to attempt to develop a medical communication standard due to the time and effort involved. Other groups are working on such a standard. Rather our approach is to interface to devices or to devices that already aggregate signals and convert the data into a common format.
Our Group has developed recommendations for medical device manufacturers that guide them in the development of a robust communications protocol. We have presented our work at meetings and published it in journals. Current work is partnering with clinical trials and developing software that can robustly See Work Products.
2. Data from the Electronic Medical Record
EMR data is important to provide context to the physiological data and vice versa. Unfortunately, EMR data has been elusive to obtain, however, that is changing with the advent of FHIR (Fast Healthcare Interoperability Resources) and other technologies.
Approach
Progress
Our approach is to partner with other organizations addressing automated communications with the medical record systems. We are using manually retrieved EMR data to demonstrate the contextual value of EMR data (such as medications) to the physiological data.
We have developed upload methods to get the data to our cloud storage as well as methods to harmonize the data from two centers both using Epic. We have developed displays to show the time synchronization of medications with the physiological data.
3. Imaging
Image data is important in the management of patients in neurocritical care and it can be obtained via a PACS viewer using the DICOM standard. Our focus will be to investigate image descriptors that can be used in the analysis of the data. We have not worked on this project yet.
4. Nursing Interventions
Nursing interventions are generally recorded in the EMR but this record may not be complete In addition, the synchronization of time from when the event occurred to when it is noted in the record could be quite variable. We will investigate methods to address these issue