Validation of a Natural Language Processing Algorithm for the Extraction of the Sleep Parameters from the
Mahbubur Rahman1,2,3, Sara Nowakowski1,2,4, Ritwick Agrawal2,3
1Houston Veterans Affairs Health Services Research and Development Service, Center for Innovations in Quality, Effectiveness and Safety, Michael E. DeBakey Veteran Affairs Medical Center, Houston, TX 77030, USA.
Healthcare (Basel, Switzerland)
|October 27, 2022
Summary
Natural Language Processing (NLP) accurately extracts sleep parameters from electronic medical records. This technology aids in understanding sleep and chronic disease associations, improving patient care.
Area of Science:
- Medical Informatics
- Sleep Medicine
- Artificial Intelligence
Background:
- Growing evidence links sleep disturbances to chronic diseases.
- Electronic Medical Records (EMR) contain valuable polysomnography (PSG) data.
- Extracting sleep parameters from EMR free-text notes is challenging.
Purpose of the Study:
- Develop and evaluate a Natural Language Processing (NLP) algorithm.
- Automate the extraction of key sleep parameters from PSG reports.
- Assess NLP accuracy against manual review for sleep metrics.
Main Methods:
- Utilized Veterans Health Administration EMR data (2000-2019).
- Identified 46,093 PSG studies via CPT code 95,810.
- Trained and tested an NLP algorithm on 200 randomly selected PSG notes, comparing against masked human raters.
Main Results:
- NLP achieved >0.90 precision, recall, and F-1 scores in both training and testing phases.
- High accuracy was demonstrated for Total Sleep Time (TST), Sleep Efficiency (SE), Sleep Onset Latency (SOL), Wake After Sleep Onset (WASO), and Apnea-Hypopnea Index (AHI).
Conclusions:
- NLP is a validated and accurate method for extracting sleep parameters from EMR PSG reports.
- NLP facilitates large-scale analysis of sleep data in healthcare systems.
- This approach can enhance patient care by improving sleep disorder evaluation.
Related Concept Videos
01:24Sleep-Wake Cycles
1.5K
Sleep is an essential physiological process vital to maintaining overall well-being. The reticular activating system (RAS), a network of neurons in the brainstem, regulates wakefulness and sleep. While it may seem passive, sleep consists of distinct cycles, each with its unique characteristics and functions. Two key sleep phases are non-rapid eye movement (NREM) and rapid eye movement (REM).
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
NREM Sleep
NREM sleep comprises four progressive stages that seamlessly merge:
1.5K
01:11Understanding Sleep
461
Sleep, an essential biological state, involves significant reductions in physical activity, sensory awareness, and interaction with the environment. This complex physiological process is primarily regulated by specific brain regions, notably the hypothalamus and pons, which govern the sleep-wake cycle or circadian rhythm.
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
The circadian rhythm, a nearly 24-hour cycle, is deeply influenced by environmental light cues. Light exposure directly affects the hypothalamus, which in turn regulates...
461
01:07Narcolepsy
179
Narcolepsy is a chronic sleep disorder characterized by pervasive, uncontrolled sleepiness and other sleep disturbances. One of its hallmark symptoms is an abrupt transition to REM sleep upon falling asleep, which causes symptoms typically associated with this phase to occur unexpectedly during wakefulness. These include the following symptoms, which typically last from a minute or two to half an hour.
179