Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy.

Analysis of sleep for the diagnosis of sleep disorders such as Type-1 Narcolepsy (T1N) currently requires visual inspection of polysomnography records by trained scoring technicians. Here, we used neural networks in approximately 3,000 normal and abnormal sleep recordings to automate sleep stage scoring, producing a hypnodensity graph-a probability distribution conveying more information than classical hypnograms. Accuracy of sleep stage scoring was validated in 70 subjects assessed by six scorers. The best model performed better than any individual scorer (87% versus consensus). It also reliably scores sleep down to 5 s instead of 30 s scoring epochs. A T1N marker based on unusual sleep stage overlaps achieved a specificity of 96% and a sensitivity of 91%, validated in independent datasets. Addition of HLA-DQB1*06:02 typing increased specificity to 99%. Our method can reduce time spent in sleep clinics and automates T1N diagnosis. It also opens the possibility of diagnosing T1N using home sleep studies.

Periodic limb movements in sleep: Prevalence and associated sleepiness in the Wisconsin Sleep Cohort.

OBJECTIVES: Periodic limb movements in sleep (PLMS) are thought to be prevalent in elderly populations, but their impact on quality of life remains unclear. We examined the prevalence of PLMS, impact of age on prevalence, and association between PLMS and sleepiness. METHODS: We identified limb movements in 2335 Wisconsin Sleep Cohort polysomnograms collected over 12 years. Prevalence of periodic limb movement index (PLMI) ≥15 was calculated at baseline (n = 1084). McNemar's test assessed changes in prevalence over time. Association of sleepiness and PLMS evaluated using linear mixed modeling and generalized estimating equations. Models adjusted for confounders. RESULTS: Prevalence of PLMI ≥15 at baseline was 25.3%. Longitudinal prevalence increased significantly with age (p = 2.97 × 10-14). Sleepiness did not differ significantly between PLMI groups unless stratified by restless legs syndrome (RLS) symptoms. The RLS+/PLM+ group was sleepier than the RLS+/PLM- group. Multiple Sleep Latency Test trended towards increased alertness in the RLS-/PLM+ group compared to RLS-/PLM-. CONCLUSIONS: A significant number of adults have PLMS and prevalence increased with age. No noteworthy association between PLMI category and sleepiness unless stratified by RLS symptoms. SIGNIFICANCE: Our results indicate that RLS and PLMS may have distinct clinical consequences and interactions that can help guide treatment approach.

Potential corner case cautions regarding publicly available implementations of the National Cancer Institute's nonwear/wear classification algorithm for accelerometer data.

The National Cancer Institute's (NCI) wear time classification algorithm uses a rule based on the occurrence of physical activity data counts-a cumulative measure of movement, influenced by both magnitude and duration of acceleration-to differentiate between when a physical activity monitoring (PAM) device (ActiGraph accelerometer) is being worn by a participant (wear) from when it is not (nonwear). It was applied to PAM data generated from the 2003-2004 National Health and Nutrition Examination Survey (NHANES 2003-2004). We discuss two corner case conditions that can produce unexpected, and perhaps unintended results when the algorithm is applied. We show, using simulated data of two special cases, how this algorithm classifies a 24-hour period with only 72 total counts as 100% wear in one case, and classifies a 24-hour period with 96,000 counts as 0.1% wear in another. The prevalence of like scenarios in the NHANES 2003-2004 PAM dataset is presented with corresponding summary statistics for varying degrees of the algorithm's nonwear classification threshold (T). The number of participants with valid days, defined as 10 or more hours classified as wear time in a 24-hour day, increased while the mean counts-per-minute (CPM) decreased as the threshold for excluding non-wear was reduced from the allowed 4,000 counts in an hour. The number of participants with four or more valid days increased 2.29% (n = 113) and mean CPM dropped 2.45% (9.5 CPM) when adjusting the nonwear classification threshold to 50 counts an hour. Applying the most liberal criteria, only excluding hours as nonwear which contained 1 count or less, resulted in a 397 more participants (7.83% increase) and 26.5 fewer CPM (6.98% decrease) in NHANES 2003-2004 participants with four or more valid days. The algorithm should be used with caution due to the potential influence of these corner cases.

Exploring medical diagnostic performance using interactive, multi-parameter sourced receiver operating characteristic scatter plots.

Determining diagnostic criteria for specific disorders is often a tedious task that involves determining optimal diagnostic thresholds for symptoms and biomarkers using receiver-operating characteristic (ROC) statistics. To help this endeavor, we developed softROC, a user-friendly graphic-based tool that lets users visually explore possible ROC tradeoffs. The software requires MATLAB installation and an Excel file containing threshold symptoms/biological measures, with corresponding gold standard diagnoses for a set of patients. The software scans the input file for diagnostic and symptom/biomarkers columns, and populates the graphical-user-interface (GUI). Users select symptoms/biomarkers of interest using Boolean algebra as potential inputs to create diagnostic criteria outputs. The software evaluates subtests across the user-established range of cut-points and compares them to a gold standard in order to generate ROC and quality ROC scatter plots. These plots can be examined interactively to find optimal cut-points of interest for a given application (e.g. sensitivity versus specificity needs). Split-set validation can also be used to set up criteria and validate these in independent samples. Bootstrapping is used to produce confidence intervals. Additional statistics and measures are provided, such as the area under the ROC curve (AUC). As a testing set, softROC is used to investigate nocturnal polysomnogram measures as diagnostic features for narcolepsy. All measures can be outputted to a text file for offline analysis. The softROC toolbox, with clinical training data and tutorial instruction manual, is provided as supplementary material and can be obtained online at http://www.stanford.edu/~hyatt4/software/softroc or from the open source repository at http://www.github.com/informaton/softroc.