Forskning
Udskriv Udskriv
Switch language
Region Hovedstaden - en del af Københavns Universitetshospital
Udgivet

Automatic sleep stage classification with deep residual networks in a mixed-cohort setting

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. Robust, ECG-based detection of Sleep-disordered breathing in large population-based cohorts

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Functional brown adipose tissue and sympathetic activity after cold exposure in humans with type 1 narcolepsy

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Cerebrospinal fluid biomarkers of neurodegeneration are decreased or normal in narcolepsy

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Breathing Disturbances Without Hypoxia Are Associated With Objective Sleepiness in Sleep Apnea

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  5. Onset of Impaired Sleep and Cardiovascular Disease Risk Factors: A Longitudinal Study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. A genome-wide meta-analysis yields 46 new loci associating with biomarkers of iron homeostasis

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Long-term employment, education, and healthcare costs of childhood and adolescent onset of epilepsy

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

Vis graf over relationer

STUDY OBJECTIVES: Sleep stage scoring is performed manually by sleep experts and is prone to subjective interpretation of scoring rules with low intra- and interscorer reliability. Many automatic systems rely on few small-scale databases for developing models, and generalizability to new datasets is thus unknown. We investigated a novel deep neural network to assess the generalizability of several large-scale cohorts.

METHODS: A deep neural network model was developed using 15,684 polysomnography studies from five different cohorts. We applied four different scenarios: (1) impact of varying timescales in the model; (2) performance of a single cohort on other cohorts of smaller, greater, or equal size relative to the performance of other cohorts on a single cohort; (3) varying the fraction of mixed-cohort training data compared with using single-origin data; and (4) comparing models trained on combinations of data from 2, 3, and 4 cohorts.

RESULTS: Overall classification accuracy improved with increasing fractions of training data (0.25%: 0.782 ± 0.097, 95% CI [0.777-0.787]; 100%: 0.869 ± 0.064, 95% CI [0.864-0.872]), and with increasing number of data sources (2: 0.788 ± 0.102, 95% CI [0.787-0.790]; 3: 0.808 ± 0.092, 95% CI [0.807-0.810]; 4: 0.821 ± 0.085, 95% CI [0.819-0.823]). Different cohorts show varying levels of generalization to other cohorts.

CONCLUSIONS: Automatic sleep stage scoring systems based on deep learning algorithms should consider as much data as possible from as many sources available to ensure proper generalization. Public datasets for benchmarking should be made available for future research.

OriginalsprogEngelsk
TidsskriftSleep
Vol/bind44
Udgave nummer1
Sider (fra-til)zsaa161
ISSN0161-8105
DOI
StatusUdgivet - 21 jan. 2021

ID: 61827290