Here’s How Artificial Intelligence Can Help During Sleep Lab Labor Shortages


Artificial intelligence is already making an appearance in diagnostic sleep labs throughout the world. Here at Nox Medical, we have a team of internal sleep medicine experts who came together to share their thoughts about how AI can help streamline workflows and ease the potential burden of labor shortages. 

Sleep technologists make a living by monitoring people’s sleep, but that is far from the only thing they do. The busy life of a sleep tech involves hooking patients up to diagnostic equipment, carefully placing each electrode onto each patient’s skin, understanding physiological sleep measurements, and combing through diagnostic data. All that is involved in the life of a sleep tech can be tedious and time-consuming, and coupled with the labor shortages that some sleep labs are experiencing, the day-to-day work of a sleep tech can become hectic.

“This is not a straightforward job. There are a lot of moving parts that go into this,” says Helgi Helgason, MS, RPSGT, RST, who began his career as a sleep technologist at the National University Hospital Sleep Research Laboratory in Reykjavik, Iceland, and now works as a Nox Medical product specialist in the United States.

According to a survey of 8,074 sleep techs from The Board of Registered Polysomnographic Technologists, at least half of all those surveyed believe that there is a sleep technologist shortage in the United States. Anecdotally, the pandemic caused this shortage to grow worse. More labs seemed to cut down on the ratio of sleep techs to patient beds, which put greater strain on working technologists. Also, many sleep labs shuttered and some never opened again, says Nox Health’s Director of Program Strategy and Innovation Nigel Ball, PhD, who also spent many years running sleep labs.

Fortunately, there are many ways to cope with staffing shortages and hiring woes in the sleep lab: Artificial intelligence rises to the top as a way to increase efficiency.

Artificial intelligence in this context simply refers to algorithms that data scientists have developed to score sleep study data.

Those algorithms can cut the time it takes to score an in-lab sleep test in half compared to a human scorer, who may typically take up to an hour to manually score a test, says sleep technologist Jay Hemnani, RPSGT, who is the former sleep lab manager at Fusion Health in Georgia.

For instance, in some labs, artificial intelligence-driven sleep software Noxturnal has changed and challenged the way that they operate, optimizing workflows, and saving valuable time and resources.

Noxturnal, which incorporates both manual and automatic sleep-scoring capabilities, comes with all of Nox Medical’s diagnostic testing equipment, including the Nox A1s PSG system and the T3s PG system. All software updates are also included for users.

The Noxturnal artificial intelligence-driven algorithms are trained on datasets of manually scored sleep test results. You could almost say that the algorithms have “learned”’ how to score a sleep test.

Of course, artificial intelligence cannot speed up the process of hooking patients up to the various electrodes, but it can help sleep techs work faster when scoring tests.*

“AI can alleviate the sleep tech shortage that is out there,” says Sleep Educator Byron Jamerson, RPSGT, a product specialist at Nox Medical.

At Fusion Sleep in Georgia, Noxturnal made all the difference when the sleep lab struggled to hire a new sleep tech, says Hemnani, who is now Nox Medical’s product training specialist.

It took the sleep lab over a year to fill a sleep technologist opening. The sleep lab even hired an outside recruiter to work on filling the position with help from the company’s internal human resources department, but still, there was a struggle to fill the job.

“We had the job posted everywhere, and hiring took a while,” Hemnani says. “Also, I am part of a sleep tech Facebook group and constantly everyone is posting job openings and not getting a whole lot of responses from them because you see that in another two weeks, they post the jobs again.”

When no one came forward to fill the position at the Georgia sleep lab, artificial intelligence via Noxturnal made things easier, he says.

Artificial intelligence has definitely reduced the amount of time taken to score a sleep study,” says Hemnani. The output for the average sleep scoring tech could be doubled.

While output could be doubled with Noxturnal, accuracy remains high.

Recent research publications have demonstrated that Noxturnal’s respiratory analysis is accurate and reliable when compared to AHI scored manually by a human sleep technologist.

One study, published in the journal Sleep and Breathing, compared Noxturnal with nine human scorers from seven sleep labs across the world. The study found strong AHI scoring agreement between the automatic scoring of Noxturnal and manually scored recordings from experienced technologists.2

Of course, the results of autoscoring must be reviewed by healthcare professionals, but overall, AI is increasing efficiency while maintaining the high degree of accuracy that sleep medicine demands.

“It certainly can help with efficiency,” says Helgason.


  1. Magalang UJ, Johns JN, Wood KA, et al.
  2.  Home sleep apnea testing: comparison of manual and automated scoring across international sleep centers. Sleep Breath. 2019;23(1):25-31. doi:10.1007/s11325-018-1715-6

* The automatic analysis results should always be reviewed by a technologist or a physician prior to diagnosis.



Topic: Industry News