A kiosk system is less expensive than a distributed system, but it
only allows data acquisition from one patient at a time, and then
only when the system is connected and turned on. Centralized
systems are costlier because they require set-up in multiple ICU
beds and a remote server for storage, but they are better for largescale
neurocritical care bioinformatics work than kiosk systems.
The Moberg CNS monitor (Moberg Research Inc., Ambler,
Pennsylvania) is one device capable of interfacing with numerous
other medical devices and providing real-time measurements of
several hundred physiological parameters that can promote critical
interventions by clinicians. Several National Institutes of Health
(NIH) research grants funded the research and development
of the monitor. It is run on a Linux-based platform built on
concepts learned from its predecessor, the Neurotrac, and it
stores information on a remote server. In doing so, the monitor
serves as an integration system, capable of collecting, integrating,
processing, and displaying real-time data from numerous external
monitoring devices in a “clinician-friendly” interface. The device
also integrates the use of cEEG, which is synchronized with the
physiological data and can be easily customized to assess various
parameters depending on the disease process being investigated.
As such, the advantages of having such an integration center
includes the ease of navigation and real-time access to numerous
physiological measurements, which allow neurointensivists
to easily detect changes in intracranial dynamics and devise
algorithms to prevent and/or treat secondary brain injury. It
is readily compatible with many devices commonly used in
the Neuro ICU setting, including the Camino, Licox, Hemedex
Bowman monitor, Pupillometer, Arctic Sun, Vigileo, PiCCO, and
microdialysis catheters. This data is then transmitted to a secure
remote server, which stores the collected data indefinitely.
A major disadvantage is the integration of artifactual data. A
stopcock is opened to drain cerebrospinal fluid. A transducer is
moved from a patient’s bedside, thereby rendering the recorded
value inaccurate. A monitor is turned off and on during patient
transport. In the status quo, the bulk of these erroneous readings
are “cleaned” by bedside nurses, who discard them due to
their obvious artifactual nature. However, when using a highresolution
data-acquisition system, data-cleaning algorithms are
needed to avoid interpreting artifactual data as real. Hence, many
fundamental obstacles must be overcome to ensure these data are
accurate, real, and integrated before advanced analysis can even
be considered. Other barriers related to data security and systems
architecture have limited implementation, especially across
multiple hospitals.
Other potential applications of AI systems include real-time
protocol-based adjustment of ventilator settings, antiepileptic
drugs, anesthetics/analgesics, neuromuscular blockade, glucose
management, and blood pressure, fluids and electrolytes
management. with little or no human input. More complex
predictive algorithms in the future may take thousands of variables
into account in order to predict complications and outcomes
with a fair degree of certainty, well ahead of time. The wealth of
data produced in the neurocritical care units makes them an ideal
environment to incorporate AI techniques that can efficiently
handle such data.
This emerging field requires a coordinated effort involving clinicians,
engineers, computer scientists, and experts in informatics
and complex-systems analysis, as well as industry, to develop
tools that can be used to improve data visualization and provide
real-time, user-friendly advanced data analysis that can be applied
clinically at the bedside of patients in the neurocritical care
unit. Using the power of bioinformatics and applying these algorithms
to large-scale patient populations, data-driven decisionsupport
tools will enable the neurointensivist to function more
efficiently, optimize patient-specific “tailored” treatment plans,
and care for more patients in a safer manner, in much the same
way that these same tools have been used to enhance the efficiency
of business applications.
36