Neural network analysis of sleep stages enables efficient diagnosis of narcolepsy

Abstract

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.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 75

1. 1.

   Krieger, A. C. Social and Economic Dimensions of Sleep Disorders, An Issue of Sleep Medicine Clinics (Elsevier, Philadelphia, PA, 2007).

   Not in our library

2. 2.

   American Academy of Sleep Medicine. International Classification of Sleep Disorders, 3rd edn (American Academy of Sleep Medicine, Darien, IL, 2014).

   Not in our library

3. 3.

   Peyron C, et al. A mutation in a case of early onset narcolepsy and a generalized absence of hypocretin peptides in human narcoleptic brains. Nat. Med. 2000;6:991-997.

   Not in our library10.1038/79690

4. 4.

   Kornum BR, et al. Narcolepsy. Nat. Rev. Dis. Prim. 2017;3:16100.

   Not in our library10.1038/nrdp.2016.100

5. 5.

   Han F, et al. HLA DQB1*06:02 negative narcolepsy with hypocretin/orexin deficiency. Sleep. 2014;37:1601-1608.

   Not in our library10.5665/sleep.4066

6. 6.

   Malhotra Raman K., Avidan Alon Y. Sleep Stages and Scoring Technique. Atlas of Sleep Medicine. 2014;77-99.

   Not in our library

7. 7.

   Berry, R. B. et al. The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, version 2.4 (American Academy of Sleep Medicine, Darien, IL, 2017).

   Not in our library

8. 8.

   Subramanian S, Hesselbacher S, Mattewal A, Surani S. Gender and age influence the effects of slow-wave sleep on respiration in patients with obstructive sleep apnea. Sleep Breath. 2013;17:51-56.

   Not in our library10.1007/s11325-011-0644-4

9. 9.

   Littner MR, et al. Practice parameters for clinical use of the multiple sleep latency test and the maintenance of wakefulness test. Sleep. 2005;28:113-121.

   Not in our library10.1093/sleep/28.1.113

10. 10.

    Andlauer O, et al. Nocturnal rapid eye movement sleep latency for identifying patients with narcolepsy/hypocretin deficiency. JAMA Neurol. 2013;70:891-902.

    Not in our library10.1001/jamaneurol.2013.1589

11. 11.

    Mignot E, et al. The role of cerebrospinal fluid hypocretin measurement in the diagnosis of narcolepsy and other hypersomnias. Arch. Neurol. 2002;59:1553-1562.

    Not in our library10.1001/archneur.59.10.1553

12. 12.

    Andlauer O, et al. Predictors of hypocretin (orexin) deficiency in narcolepsy without cataplexy. Sleep. 2012;35:1247-1255.

    Not in our library10.5665/sleep.2080

13. 13.

    Luca G, et al. Clinical, polysomnographic and genome-wide association analyses of narcolepsy with cataplexy: a European Narcolepsy Network study. J. Sleep Res. 2013;22:482-495.

    Not in our library10.1111/jsr.12044

14. 14.

    Dauvilliers Y, et al. Effect of age on MSLT results in patients with narcolepsy-cataplexy. Neurology. 2004;62:46-50.

    Not in our library10.1212/01.wnl.0000101725.34089.1e

15. 15.

    Moscovitch A, Partinen M, Guilleminault C. The positive diagnosis of narcolepsy and narcolepsy’s borderland. Neurology. 1993;43:55-60.

    Not in our library10.1212/wnl.43.1_part_1.55

16. 16.

    Rosenberg RS, Van Hout S. The American Academy of Sleep Medicine inter-scorer reliability program: sleep stage scoring. J. Clin. Sleep Med. 2013;9:81-87.

    Not in our library10.5664/jcsm.2350

17. 17.

    Zhang X, et al. Process and outcome for international reliability in sleep scoring. Sleep Breath. 2015;19:191-195.

    Not in our library10.1007/s11325-014-0990-0

18. 18.

    Danker-Hopfe H, et al. Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard. J. Sleep Res. 2009;18:74-84.

    Not in our library10.1111/j.1365-2869.2008.00700.x

19. 19.

    MacLean AW, Lue F, Moldofksy H. The reliability of visual scoring of alpha EEG activity during sleep. Sleep. 1995;18:565-569.

    Not in our library

20. 20.

    Kim Y, Kurachi M, Horita M, Matsuura K, Kamikawa Y. Agreement of visual scoring of sleep stages among many laboratories in Japan: effect of a supplementary definition of slow wave on scoring of slow wave sleep. J. Psychiatry Clin. Neurosci. 1993;47:91-97.

    Not in our library10.1111/j.1440-1819.1993.tb02035.x

21. 21.

    Hinton G, et al. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process. Mag. 2012;83:82-97.

    Not in our library10.1109/msp.2012.2205597

22. 22.

    He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In 2015 IEEEInternational Conference on Computer Vision (ICCV) 1026–1034 (IEEE, Santiago, Chile, 2015).

    Not in our library

23. 23.

    He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 770–778 (IEEE, Las Vegas, NV, 2016).

    Not in our library

24. 24.

    Gulshan V, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402-2410.

    Not in our library10.1001/jama.2016.17216

25. 25.

    Ting DSW, et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA. 2017;318:2211-2223.

    Not in our library10.1001/jama.2017.18152

26. 26.

    Bejnordi BE, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318:2199-2210.

    Not in our library10.1001/jama.2017.14585

27. 27.

    Esteva A, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115-118.

    Not in our library10.1038/nature21056

28. 28.
    Computer-Aided Diagnosis with Deep Learning Architecture: Applications to Breast Lesions in US Images and Pulmonary Nodules in CT Scans · 2016

    No notice
29. 29.

    Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology. 2017;284:574-582.

    Not in our library10.1148/radiol.2017162326

30. 30.
    Deep learning · 2015

    No notice
31. 31.

    Kuna ST, et al. Agreement in computer-assisted manual scoring of polysomnograms across sleep centers. Sleep. 2013;36:583-589.

    Not in our library10.5665/sleep.2550

32. 32.

    Moore HI, et al. Design and validation of a periodic leg movement detector. PLoS One. 2014;9:e114565.

    Not in our library10.1371/journal.pone.0114565

33. 33.

    Young T, et al. Burden of sleep apnea: rationale, design, and major findings of the Wisconsin Sleep Cohort study. WMJ. 2009;108:246-249.

    Not in our library

34. 34.

    Hong SC, et al. A study of the diagnostic utility of HLA typing, CSF hypocretin-1 measurements, and MSLT testing for the diagnosis of narcolepsy in 163 Korean patients with unexplained excessive daytime sleepiness. Sleep. 2006;29:1429-1438.

    Not in our library10.1093/sleep/29.11.1429

35. 35.

    Frauscher B, et al. Delayed diagnosis, range of severity, and multiple sleep comorbidities: a clinical and polysomnographic analysis of 100 patients of the Innsbruck Narcolepsy Cohort. J. Clin. Sleep Med. 2013;9:805-812.

    Not in our library10.5664/jcsm.2926

36. 36.

    Mander BA, Winer JR, Walker MP. Sleep and human aging. Neuron. 2017;94:19-36.

    Not in our library10.1016/j.neuron.2017.02.004

37. 37.

    Christensen JAE, et al. Sleep-stage transitions during polysomnographic recordings as diagnostic features of type 1 narcolepsy. Sleep Med. 2015;16:1558-1566.

    Not in our library10.1016/j.sleep.2015.06.007

38. 38.

    Olsen AV, et al. Diagnostic value of sleep stage dissociation as visualized on a 2-dimensional sleep state space in human narcolepsy. J. Neurosci. Methods. 2017;282:9-19.

    Not in our library10.1016/j.jneumeth.2017.02.004

39. 39.

    Jensen JB, et al. Sleep-wake transition in narcolepsy and healthy controls using a support vector machine. J. Clin. Neurophysiol. 2014;31:397-401.

    Not in our library10.1097/wnp.0000000000000074

40. 40.

    Vassalli A, et al. Electroencephalogram paroxysmal theta characterizes cataplexy in mice and children. Brain. 2013;136:1592-1608.

    Not in our library10.1093/brain/awt069

41. 41.

    Pizza F, et al. Nocturnal sleep dynamics identify narcolepsy type 1. Sleep. 2015;38:1277-1284.

    Not in our library10.5665/sleep.4908

42. 42.

    Guyon I, Weston J, Barnhill S. Gene selection for cancer classification using support vector machines. Mach. Learn. 2002;46:389-422.

    Not in our library10.1023/a:1012487302797

43. 43.

    International Xyrem Study Group. A double-blind, placebo-controlled study demonstrates sodium oxybate is effective for the treatment of excessive daytime sleepiness in narcolepsy. J. Clin. Sleep Med. 2005;1:391-397.

    Not in our library

44. 44.

    Anderer P, et al. An E-health solution for automatic sleep classification according to Rechtschaffen and Kales: validation study of the Somnolyzer 24 x 7 utilizing the Siesta database. Neuropsychobiology. 2005;51:115-133.

    Not in our library10.1159/000085205

45. 45.

    Olesen, A. N., Christensen, J. A. E., Sorensen, H. B. D. & Jennum, P. J. A noise-assisted data analysis method for automatic EOG-based sleep stage classification using ensemble learning. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 3769–3772 (IEEE, Orlando, FL, 2016).

    Not in our library10.1109/embc.2016.7591548

46. 46.

    Boostani R, Karimzadeh F, Nami M. A comparative review on sleep stage classification methods in patients and healthy individuals. Comput. Methods Prog. Biomed. 2017;140:77-91.

    Not in our library10.1016/j.cmpb.2016.12.004

47. 47.

    Lajnef T, et al. Learning machines and sleeping brains: automatic sleep stage classification using decision-tree multi-class support vector machines. J. Neurosci. Methods. 2015;250:94-105.

    Not in our library10.1016/j.jneumeth.2015.01.022

48. 48.

    da Silveira TLT, Kozakevicius AJ, Rodrigues CR. Single-channel EEG sleep stage classification based on a streamlined set of statistical features in wavelet domain. Med. Biol. Eng. Comput. 2017;55:343-352.

    Not in our library10.1007/s11517-016-1519-4

49. 49.

    Ronzhina M, et al. Sleep scoring using artificial neural networks. Sleep Med. Rev. 2012;16:251-263.

    Not in our library10.1016/j.smrv.2011.06.003

50. 50.

    Reiter J, Katz E, Scammell TE, Maski K. Usefulness of a nocturnal SOREMP for diagnosing narcolepsy with cataplexy in a pediatric population. Sleep. 2015;38:859-865.

    Not in our library10.5665/sleep.4728

51. 51.

    Banko, M. & Brill, E. Scaling to very very large corpora for natural language disambiguation. In ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics 26–33 (Association for Computational Linguistics, Stroudsburg, PA, 2001).

    Not in our library

52. 52.

    Shotton J, et al. Real-time human pose recognition in parts from single depth images. Stud. Comput. Intell. 2013;411:119-135.

    Not in our library

53. 53.

    Christensen JAE, et al. Novel method for evaluation of eye movements in patients with narcolepsy. Sleep Med. 2017;33:171-180.

    Not in our library10.1016/j.sleep.2016.10.016

54. 54.

    Goldbart A, et al. Narcolepsy and predictors of positive MSLTs in the Wisconsin Sleep Cohort. Sleep. 2014;37:1043-1051.

    Not in our library10.5665/sleep.3758

55. 55.

    Silber MH, et al. The visual scoring of sleep in adults. J. Clin. Sleep Med. 2007;3:121-131.

    Not in our library

56. 56.

    Hjorth B. EEG analysis based on time domain properties. Electroencephalogr. Clin. Neurophysiol. 1970;29:306-310.

    Not in our library10.1016/0013-4694(70)90143-4

57. 57.

    Mahalanobis PC. On the generalised distance in statistics. Proc. Natl. Inst. Sci. India. 1936;2:49-55.

    Not in our library

58. 58.

    Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput. 1997;9:1735-1780.

    Not in our library10.1162/neco.1997.9.8.1735

59. 59.

    Goodfellow I, Bengio Y, Courville A. Deep Learning. 2016.

    Not in our library

60. 60.

    Bishop, C. M. Pattern Recognition and Machine Learning (Springer, New York, 2006).

    Not in our library

61. 61.

    Hornik K, Stinchcombe M, White H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989;2:359-366.

    Not in our library10.1016/0893-6080(89)90020-8

62. 62.

    Lenc, K. & Vedaldi, A. Understanding image representations by measuring their equivariance and equivalence. In 2015IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 991–999 (IEEE, Boston, MA, 2015).

    Not in our library10.1007/s11263-018-1098-y

63. 63.

    Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. In 2015 International Conference on Learning Representation (ICLR) 1–14 (ICLR, San Diego, CA, 2015).

    Not in our library

64. 64.

    Polyak BT. Some methods of speeding up the convergence of iteration methods. USSR Comput. Math. Math. Phys. 1964;4:1-17.

    Not in our library10.1016/0041-5553(64)90137-5

65. 65.

    Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. Proc. 32nd Int. Conf. Mach. Learn. PLMR. 2015;37:448-456.

    Not in our library

66. 66.

    Krogh A, Hertz JA. A simple weight decay can improve generalization. Adv. Neural Inf. Process. Syst. 1992;4:950-957.

    Not in our library

67. 67.

    Caruana, R., Lawrence, S. & Giles, L. Overfitting in neural nets: backpropagation, conjugate gradient, and early stopping. In Proc. Advances in Neural Information Processing Systems 13 402–408 (MIT Press, Cambridge, MA, 2001).

    Not in our library

68. 68.

    Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014;15:1929-1958.

    Not in our library

69. 69.

    Roth T, et al. Disrupted nighttime sleep in narcolepsy. J. Clin. Sleep Med. 2013;9:955-965.

    Not in our library10.5664/jcsm.3004

70. 70.

    Hansen MH, Kornum BR, Jennum P. Sleep-wake stability in narcolepsy patients with normal, low and unmeasurable hypocretin levels. Sleep Med. 2017;34:1-6.

    Not in our library10.1016/j.sleep.2017.01.021

71. 71.

    Drakatos P, et al. First rapid eye movement sleep periods and sleep-onset rapid eye movement periods in sleep-stage sequencing of hypersomnias. Sleep Med. 2013;14:897-901.

    Not in our library10.1016/j.sleep.2013.03.021

72. 72.

    Liu Y, et al. Altered sleep stage transitions of REM sleep: a novel and stable biomarker of narcolepsy. J. Clin. Sleep Med. 2015;11:885-894.

    Not in our library10.5664/jcsm.4940

73. 73.

    Rasmussen CE, Williams CKI. Gaussian Processes for Machine Learning. 2006.

    Not in our library

74. 74.

    Hensman, J., Matthews, A. & Ghahramani, Z. Scalable variational Gaussian process classification. In 18th International Conference on Artificial Intelligence and Statistics (AISTATS) (PMLR, San Diego, CA, 2015).

    Not in our library

75. 75.

    Matthews AGDG, Nickson T, Boukouvalas A, Hensman J. GPflow: a Gaussian Process Library using TensorFlow. J. Mach. Learn. Res. 2017;18:1-6.

    Not in our library

Cited by papers we hold 2

• U-Sleep: resilient high-frequency sleep staging · 2021
  No notice
• An open-source, high-performance tool for automated sleep staging · 2021
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.