View as PDF version
The recent FDA clearance of a device that uses eye tracking to predict concussion (Brooks 2021) rekindled our curiosity about use of eye tracking as a patient safety tool. The EYE-SYNC technology includes neurocognitive batteries, symptom inventories, and standardized patient inventories to identify the type and severity of dysfunction after concussion. But the heart of the system is that it utilizes a series of 60-second eye tracking assessments under virtual reality. A clinical study showed that EYE-SYNC demonstrated sensitivity above 82% and specificity above 93%, for predicting concussion.
But our interest is in use of eye tracking methodologies to identify fatigue in healthcare workers. Our many columns listed below have highlighted the role fatigue in healthcare workers plays in medical errors and patient safety. We, ourselves, are not very good at recognizing when we are already in the early throes of fatigue. Hence, we need more objective methods of predicting and identifying fatigue. Weve always suspected we will ultimately adopt technology as a means to identify fatigue earlier. In our July 29, 2014 Patient Safety Tip of the Week The 12-Hour Nursing Shift: Debate Continues we predicted that someday we will have the equivalent of the brief sobriety or breathalyzer test that can rapidly identify healthcare workers who are impaired by fatigue. We might envision that at regular intervals beyond 8 hours (maybe even sooner) or during periods of prolonged concentration the healthcare worker will get buzzed on his/her smartphone and have to complete some simple test of reaction times or attention span. If the worker scores outside the established threshold the hospital will need to have resources in place to take over duties of that worker (completely or at least temporarily until fatigue is alleviated by, for example, a nap).
Well, eye tracking has the capability to be that breathalyzer test equivalent and could potentially be performed in a nonobtrusive manner. There are a variety of ocular phenomena that can be used to detect early fatigue. In addition to eyelid drooping, alteration of saccadic eye movements, number of fixations, fixation durations, changes in the blink rate, and changes in pupillary responses may be early signs of fatigue.
Much of the work on the relationship between eye movements and fatigue has been done on people using computers. In healthcare, a logical specialty to analyze is the radiologist. Radiologists often spend long periods at computer screens reading various types of imaging. Our January 19, 2021 Patient Safety Tip of the Week Technology to Identify Fatigue? discussed many of those studies involving radiologists.
Of course, other occupations where fatigue is a significant factor leading to errors and accidents include airline pilot, bus driver, train engineer, etc. There is probably more research ongoing to come up with ways to identify fatigue in those occupations than in healthcare. Naeeri and colleagues (Naeeri 2021) recently performed a multimodal analysis of eye movements and fatigue in a simulated glass cockpit environment. The researchers first reviewed the literature on methods of assessing pilot fatigue, including psychometric testing, various physiologic testing, and eye tracking.
They noted that eye tracking can be done in a nonintrusive manner and can provide measures such as eye fixation position (or location), duration, pupil dilation, visual scanpath (i.e., the time order of the eye fixations that occurred on display), saccade, blink, and eyelid closure, in which eyelid closure slowed as fatigue increased and saccadic velocity decreased as fatigue increased after long simulated flights.
They correlated eye tracking with results of psychometric vigilance tests (PVT) and reaction times. The complicated regression models they used to assess the eye tracking results are beyond the scope of our column. You can see them in the Naeeri article itself, along with details of the psychomotor vigilance test used and the equipment used to do the eye tracking, plus the various tasks and procedures monitored in the pilots.
As in previous research, the increase in fatigue was verified through the PVT measures of reaction time, number of lapses, and number of false starts. The results allowed them to devise a unified PVT measure of combining three measures to quantify a fatigued state as a single point. As fatigue increased, eye fixation duration increased, visual entropies (i.e., transition and stationary) increased, eye fixation number decreased, and pupil size decreased. These phenomena enabled the researchers to discover viable fatigue prediction models based on expertise and using eye movement measures. Moreover, they found that there were differences between experienced and novice pilots. Unlike novices, the expert pilots had a greater number of eye fixations and shorter eye fixation duration. That suggests that more eye fixations might indicate more active information processing, whereas longer eye fixation might indicate the pilot needing more time to focus and process the information of interest. In addition, pupil size became progressively smaller for both expert and novices as fatigue increased but the experts pupil size remained relatively larger compared to the novice pilots as the task number increased. All this suggests that the experienced pilots were able to keep the arousal state better than the novices. It would certainly be of interest to see whether similar disparities exist in more experienced healthcare workers compared to more novice ones.
But only performing the test at a specified time (the breathalyzer model) would obviously miss many cases where a healthcare worker is already fatigued and at risk for committing errors. And it would require the healthcare worker take the time to administer the test, whether it is a psychomotor or physiologic test. Hence, the need for an unobtrusive tool. Sure, we could strap EEG electrodes to the heads of all healthcare workers and see the earliest signs of fatigue and lack of vigilance. But that obviously is impractical. We need an unobtrusive method similar to that used by Naeeri and colleagues in the simulated cockpit study.
Obviously, it would take considerable engineering expertise to develop similar eye tracking assessment methods in various healthcare settings, but these could theoretically be used to help identify fatigue and loss of vigilance in real time. We can
The subsequent question is what do you do with the results? If a healthcare worker shows findings compatible with fatigue at the end of a first shift, you would preclude overtime (or at least consider a rest period prior to any overtime work). If a test performed, say 6 hours into a shift, shows findings compatible with fatigue, you might consider an intervention such as a quick nap (see our November 2012 What's New in the Patient Safety World column The Mid-Day Nap and our September 6, 2016 Patient Safety Tip of the Week Napping Debate Rekindled). For a radiologist, it might mean stepping away from the computer screen for a specified period of time. Or for a pharmacist preparing and dispensing medications, it might call for a brief rest break. But the dilemma becomes more complicated if you were to identify signs of fatigue in a surgeon in the midst of an operation.
We hope youll goo back to our January 19, 2021 Patient Safety Tip of the Week Technology to Identify Fatigue? for discussion of multiple studies using eye tracking technology in a variety of settings. This technology is a tool with great potential in healthcare and patient safety.
Some of our other columns on the role of fatigue in Patient Safety:
November 9, 2010 12-Hour Nursing Shifts and Patient Safety
April 26, 2011 Sleeping Air Traffic Controllers: What About Healthcare?
February 2011 Update on 12-hour Nursing Shifts
September 2011 Shiftwork and Patient Safety
November 2011 Restricted Housestaff Work Hours and Patient Handoffs
January 3, 2012 Unintended Consequences of Restricted Housestaff Hours
June 2012 June 2012 Surgeon Fatigue
November 2012 The Mid-Day Nap
November 13, 2012 The 12-Hour Nursing Shift: More Downsides
July 29, 2014 The 12-Hour Nursing Shift: Debate Continues
October 2014 Another Rap on the 12-Hour Nursing Shift
December 2, 2014 ANA Position Statement on Nurse Fatigue
August 2015 Surgical Resident Duty Reform and Postoperative Outcomes
September 2015 Surgery Previous Night Does Not Impact Attending Surgeon Next Day
September 29, 2015 More on the 12-Hour Nursing Shift
September 6, 2016 Napping Debate Rekindled
April 18, 2017 Alarm Response and Nurse Shift Duration
July 11, 2017 The 12-Hour Shift Takes More Hits
February 13, 2018 Interruptions in the ED
April 2018 Radiologists Get Fatigued, Too
August 2018 Burnout and Medical Errors
September 4, 2018 The 12-Hour Nursing Shift: Another Nail in the Coffin
August 2020 New Twist on Resident Work Hours and Patient Safety
August 25, 2020 The Off-Hours Effect in Radiology
September 2020 Daylight Savings Time Impacts Patient Safety?
January 19, 2021 Technology to Identify Fatigue?
Brooks M. FDA Clears First Mobile Rapid Test for Concussion. Medscape Medical News 2021; October 05, 2021
Naeeri S. Kang Z. Mandal S. Kim K. Multimodal Analysis of Eye Movements and Fatigue in a Simulated Glass Cockpit Environment. Aerospace 2021; 8: 283
Print PDF version