Artificial intelligence as applied to the diagnosis and management of epilepsy

From Clinfowiki
Jump to: navigation, search

Artificial intelligence as applied to the diagnosis and management of epilepsy has included the following activities

  • using clinical information such as seizures as prognostic aids (38
  • classification of seizure type and epilepsy syndrome using clinical information (24,25,26,32,33,35,36)
  • choice of anticonvulsants (17,28,29)
  • identification of normal wave forms and epileptogenic discharges, classification of seizure type, distinguishing epileptic from non-epileptic seizures (6,8,9,10,16,19,22,23,27,30,31, 34,37)
  • understanding the pathophysiology of epilepsy and epileptogenesis (2,4,14,21)
  • video analysis to identify seizures (1,15)
  • integration of seizure detection with additional diagnostic tools (such as injection of radionuclides) (11,13,18)
  • EEG signals as a bridge between thought and robotic commands. (3,12)
  • developing implantable device programs for identification of seizures (à la Michael Creighton the terminal Man) (7)
  • short time prediction of impending seizures using EEG tracings (5)


To a certain extent, the above list is in

  • chronological order
  • increasing frequency of published papers that bring together "artificial intelligence" and "epilepsy"
  • increasing use of artificial intelligence as an ancillary tool, decreasing use as a substitute for traditional physician activities.


In general, artificial intelligence from the 80’s and 90’s promised to take in information and analyze it as a clinician would, making a diagnosis of epilepsy and epileptic syndrome, and deciding on treatment. Over time, these programs were more likely to be used in the context of training rather than daily clinician use. Recently, artificial intelligence seems to be concentrating more on EEGs themselves, as being an intrinsically very mathematical and geometric exercise. Artificial intelligence will allow for rapid and automated detection and classification of EEG abnormalities. There is growing optimism that we can predict the occurrence of clinical seizures ion advance from analysis of ongoing EEG, and perhaps intervene with implanted devices.

There is, however, little progress in using artificial intelligence to substitute for classic physician activities, such as using historical and examination data to arrive at diagnoses. As with other exercises in artificial intelligence, these programs developed may be more helpful in the training of new physicians than in aiding trained physicians in their daily work.

References

  1. Carvalho LM, Nassar SM, Azevedo FM, Carvalho HJ, Monteiro LL, Rech CM. A neuro-fuzzy system to support in the diagnostic of epileptic events and non-epileptic events using different fuzzy arithmetical operations. Arq Neuropsiquiatr. 2008 Jun;66(2A):179-83.
  2. Prinz AA. Understanding epilepsy through network modeling. Proc Natl Acad Sci U S A. 2008 Apr 22;105(16):5953-4. Epub 2008 Apr 14.
  3. Ferreira A, Celeste WC, Cheein FA, Bastos-Filho TF, Sarcinelli-Filho M,Carelli R. Human-machine interfaces based on EMG and EEG applied to robotic systems.J Neuroeng Rehabil. 2008 Mar 26;5:10.
  4. Ubeyli ED. Recurrent neural networks with composite features for detection of electrocardiographic changes in partial epileptic patients. Comput Biol Med. 2008 Mar;38(3):401-10. Epub 2008 Feb 14.
  5. Ataee P, Yazdani A, Setarehdan S, Noubari HA. Manifold learning applied on EEG signal of the epileptic patients for detection of normal and pre-seizure States.Conf Proc IEEE Eng Med Biol Soc. 2007;2007:5489-92.
  6. Casson AJ, Yates DC, Patel S, Rodriguez-Villegas E. Algorithm for AEEG data selection leading to wireless and long term epilepsy monitoring. Conf Proc IEEE Eng Med Biol Soc. 2007;2007:2456-9.
  7. Aziz JN, Karakiewicz R, Genov R, Bardakjian BL, Derchansky M, Carlen PL. Towards real-time in-implant epileptic seizure prediction.Conf Proc IEEE Eng Med Biol Soc. 2006;1:5476-9.
  8. Tafreshi R, Dumont G, Gross D, Ries CR, Puil E, MacLeod BA. Seizure detection by a novel wavelet packet method.Conf Proc IEEE Eng Med Biol Soc. 2006;1:6141-4.
  9. Glassman EL, Guttag JV. Reducing the number of channels for an ambulatory patient-specific EEG-based epileptic seizure detector by applying recursive feature elimination.Conf Proc IEEE Eng Med Biol Soc. 2006;1:2175-8.
  10. Schuyler R, White A, Staley K, Cios KJ. Epileptic seizure detection. IEEE Eng Med Biol Mag. 2007 Mar-Apr;26(2):74-82.
  11. Feichtinger M, Eder H, Holl A, Körner E, Zmugg G, Aigner R, Fazekas F, Ott E. Automatic and remote controlled ictal SPECT injection for seizure focus localization by use of a commercial contrast agent application pump. Epilepsia. 2007 Jul;48(7):1409-13. Epub 2007 Mar 26.
  12. Maciunas RJ. Computer-assisted neurosurgery.Clin Neurosurg. 2006;53:267-71. Review.
  13. Alayón S, Robertson R, Warfield SK, Ruiz-Alzola J. A fuzzy system for helping medical diagnosis of malformations of cortical development. J Biomed Inform. 2007 Jun;40(3):221-35. Epub 2006 Nov 18.
  14. Lee U, Kim S, Jung KY. Classification of epilepsy types through global network analysis of scalp electroencephalograms. Phys Rev E Stat Nonlin Soft Matter Phys. 2006 Apr;73(4 Pt 1):041920. Epub 2006Apr 17.
  15. Karayiannis NB, Tao G, Frost JD Jr, Wise MS, Hrachovy RA, Mizrahi EM. Automated detection of videotaped neonatal seizures based on motion segmentation methods.Clin Neurophysiol. 2006 Jul;117(7):1585-94. Epub 2006 May 8.
  16. Grewal S, Gotman J. An automatic warning system for epileptic seizures recorded on intracerebral EEGs. Clin Neurophysiol. 2005 Oct;116(10):2460-72.
  17. Chappell B, Crawford P. An audit of lamotrigine, levetiracetam and topiramate usage for epilepsy in a district general hospital. Seizure. 2005 Sep;14(6):422-8.
  18. Aubert-Broche B, Jannin P, Biraben A, Bernard AM, Haegelen C, Le Jeune FP, Gibaud B. Evaluation of methods to detect interhemispheric asymmetry on cerebral perfusion SPECT: application to epilepsy.J Nucl Med. 2005 Apr;46(4):707-13.
  19. Kobayashi K, Yoshinaga H, Ohtsuka Y, Gotman J. Dipole modeling of epileptic spikes can be accurate or misleading. Epilepsia. 2005 Mar;46(3):397-408.
  20. van Ast JF, Talmon JL, Renier WO, Hasman A. An approach to knowledge base construction based on expert opinions. Methods Inf Med. 2004;43(4):427-32.
  21. Nigam VP, Graupe D. A neural-network-based detection of epilepsy. Neurol Res. 2004 Jan;26(1):55-60.
  22. Pang CC, Upton AR, Shine G, Kamath MV. A comparison of algorithms for detection of spikes in the electroencephalogram. IEEE Trans Biomed Eng. 2003 Apr;50(4):521-6.
  23. Castellaro C, Favaro G, Castellaro A, Casagrande A, Castellaro S, Puthenparampil DV, Salimbeni CF. An artificial intelligence approach to classify and analyse EEG traces. Neurophysiol Clin. 2002 Jun;32(3):193-214.
  24. Vassilakis KM, Vorgia L, Micheloyannis S. Decision support system for classification of epilepsies in childhood. J Child Neurol. 2002 May;17(5):357-63.
  25. Thomas SV, Kurup JR, Kuruvilla A, Nair BN, Thomas KL, Sarma PS. An expert system for the diagnosis of epilepsy: results of a clinical trial. Natl Med J India. 2001 Sep-Oct;14(5):274-6.
  26. Brasil LM, de Azevedo FM, Barreto JM. A hybrid expert system for the diagnosis of epileptic crisis. Artif Intell Med. 2001 Jan-Mar;21(1-3):227-33.
  27. Black MA, Jones RD, Carroll GJ, Dingle AA, Donaldson IM, Parkin PJ. Real-time detection of epileptiform activity in the EEG: a blinded clinical trial. Clin Electroencephalogr. 2000 Jul;31(3):122-30.
  28. Smeets R, Talmon J, Meinardi H, Hasman A. Validating a decision support system for anti-epileptic drug treatment. Part II: adjusting anti-epileptic drug treatment.Int J Med Inform. 1999 Nov;55(3):199-209.
  29. Smeets R, Talmon J, Meinardi H, Hasman A. Validating a decision support system for anti-epileptic drug treatment. Part I: initiating anti-epileptic drug treatment. Int J Med Inform. 1999 Nov;55(3):189-98.
  30. Ebersole JS. EEG source modeling. The last word. J Clin Neurophysiol. 1999 May;16(3):297-302. Review.
  31. Webber WR, Lesser RP, Richardson RT, Wilson K. An approach to seizure detection using an artificial neural network (ANN). Electroencephalogr Clin Neurophysiol. 1996 Apr;98(4):250-72.
  32. Korpinen L, Pietilä T, Peltola J, Nissilä M, Keränen T, Touvinen T, Falck B, Petránek ES, Frey H. Evaluation of Epilepsy Expert--a decision support system. Comput Methods Programs Biomed. 1994 Nov;45(3):223-31.
  33. Doller HJ, Hostetler W, Krishnamurthy K, Peterson LL. Epileptologist's assistant: a cost effective expert system. Proc Annu Symp Comput Appl Med Care. 1993:384-8.
  34. Mishra RB. A decision table and rule based interpretation system for epileptic discharges. Int J Clin Monit Comput. 1992 Oct;9(3):165-78.
  35. Ruchelman M, Krishnamurthy K, Hostetler W, Peterson LL, Jungmann J, Doller HJ. A cost effective expert system to assist physicians: epileptologists' assistant. Proc Annu Symp Comput Appl Med Care. 1992:816-7.
  36. Alpherts WC, Aldenkamp AP. Computerized neuropsychological assessment of cognitive functioning in children with epilepsy. Epilepsia. 1990;31 Suppl 4:S35-40.
  37. Davey BL, Fright WR, Carroll GJ, Jones RD. Expert system approach to detection of epileptiform activity in the EEG. Med Biol Eng Comput. 1989 Jul;27(4):365-70.
  38. Margolis LH, Shaywitz BA. The outcome of prolonged coma in childhood. Pediatrics. 1980 Mar;65(3):477-83.

--Vgibbons 12:38, 16 November 2008 (CST)