Skip to main content
SpringerLink
Log in

„Big Data“ und künstliche Intelligenz zur Diagnoseunterstützung bei atypischer Demenz

Big data and artificial intelligence for diagnostic decision support in atypical dementia

  • Leitthema
  • Published:
Der Nervenarzt Aims and scope Submit manuscript

Zusammenfassung

Die Differenzialdiagnose bei atypischer Demenz ist schwierig. Bildgebend diagnostisch stellt die Positronenemissionstomographie (PET) immer noch den Goldstandard dar. Laut der aktuellen Studienlage ist jedoch die Magnetresonanztomographie (MRT) unter Verwendung neuer Big-Data- und „Machine-learning“-Methoden dem Fluordesoxyglucose(FDG)-PET nahezu ebenbürtig. Bei atypischen Fällen, speziell bei jüngeren Patienten und zur Verlaufskontrolle, ist somit das MRT der Computertomographie (CT) vorzuziehen. In der klinischen Routine anwendbare, effiziente MRT-Verfahren sind z. B. die automatisierte Volumetrie anatomischer 3‑D-Sequenzen sowie eine neue MRT-Perfusionsmethode ohne Kontrastmittelgabe, namens „arterial spin labelling“ (ASL). Nicht zuletzt aufgrund der rasch wachsenden Biomarker-Datenmenge besteht die Notwendigkeit computergestützter Big-Data-Analysen und künstlicher Intelligenz. Nur durch eine schnelle Analyse der vielfältigen und rasch zunehmenden Menge an klinischen, bildgebenden, epidemiologischen, molekulargenetischen, aber auch ökonomischen Daten kann neues Wissen zur Krankheitsentstehung, Prävention und Therapie generiert werden. Wesentliche Voraussetzungen für eine flächendeckende Etablierung vielversprechender Analysemethoden sind jedoch die allgemeine technische Verfügbarkeit, die qualitativ hochwertige Homogenisierung der zugrunde liegenden Daten und die Verfügbarkeit großer Vergleichsdatenmengen.

Abstract

The differential diagnosis of atypical dementia remains difficult. The use of positron emission tomography (PET) still represents the gold standard for imaging diagnostics. According to the current evidence, however, magnetic resonance imaging (MRI) is almost equal to fluorodeoxyglucose (FDG)-PET, but only when using new big data and machine learning methods. In cases of atypical dementia, especially in younger patients and for follow-up, MRI is preferable to computed tomography (CT). In the clinical routine, promising MRI procedures are e. g. the automated volumetry of anatomical 3D images, as well as a non-contrast-enhanced MRI perfusion method, called arterial spin labeling (ASL). Because of the rapidly growing amount of biomarker data, there is a need for computer-aided big data analyses and artificial intelligence. Based on fast analyses of the diverse and rapidly increasing amount of clinical, imaging, epidemiological, molecular genetic and economic data, new knowledge on the pathogenesis, prevention and treatment can be generated. Technical availability, homogenization of the underlying data and the availability of large reference data are the basis for the widespread establishment of promising analytical methods.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Abb. 1
Abb. 2
Abb. 3

Literatur

  1. Adler CH, Dugger BN, Hentz JG et al (2017) Peripheral synucleinopathy in early Parkinson’s disease: submandibular gland needle biopsy findings. Mov Disord 32:722–723. https://doi.org/10.1002/mds.27044

    Article  PubMed  Google Scholar 

  2. Becktepe J, Gövert F, Deuschl G (2017) Übergreifende Konzepte der Neurodegeneration. Aktuelle Neurol 44:19–26. https://doi.org/10.1055/s-0042-123500

    Article  Google Scholar 

  3. Berg D, Postuma RB, Adler CH et al (2015) MDS research criteria for prodromal Parkinson’s disease. Mov Disord 30:1600–1611. https://doi.org/10.1002/mds.26431 (MDS criteria for prodromal PD)

    Article  PubMed  Google Scholar 

  4. Breiman L, Friedman J, Stone JA, Olshen RA (1998) Classification and regression trees. Chapman & Hall [u. a.], Boca Raton (Repr.)

    Google Scholar 

  5. Butcher NJ, Merico D, Zarrei M et al (2017) Whole-genome sequencing suggests mechanisms for 22q11.2 deletion-associated Parkinson’s disease. PLoS ONE 12:e173944. https://doi.org/10.1371/journal.pone.0173944

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  6. Caminiti SP, Ballarini T, Sala A et al (2018) FDG-PET and CSF biomarker accuracy in prediction of conversion to different dementias in a large multicentre MCI cohort. Neuroimage Clin 18:167–177. https://doi.org/10.1016/j.nicl.2018.01.019

    Article  PubMed  PubMed Central  Google Scholar 

  7. Davids M, Zöllner FG, Ruttorf M et al (2014) Fully-automated quality assurance in multi-center studies using MRI phantom measurements. Magn Reson Imaging 32:771–780. https://doi.org/10.1016/j.mri.2014.01.017

    Article  PubMed  Google Scholar 

  8. Donadio V, Incensi A, Leta V et al (2014) Skin nerve-synuclein deposits: a biomarker for idiopathic Parkinson disease. Neurology 82:1362–1369. https://doi.org/10.1212/WNL.0000000000000316

    Article  PubMed  CAS  Google Scholar 

  9. Doppler K, Jentschke H‑M, Schulmeyer L et al (2017) Dermal phospho-alpha-synuclein deposits confirm REM sleep behaviour disorder as prodromal Parkinson’s disease. Acta Neuropathol 133:535–545. https://doi.org/10.1007/s00401-017-1684-z

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  10. Egger K, Yang S, Klöppel S (2018) Automated voxel- and region-based analysis of gray matter and cerebrospinal fluid space in primary dementia disorders. Unter Begutachtung

  11. Fagan AM, Roe CM, Xiong C et al (2007) Cerebrospinal fluid tau/β-amyloid42 ratio as a prediction of cognitive decline in Nondemented older adults. Arch Neurol 64:343. https://doi.org/10.1001/archneur.64.3.noc60123

    Article  PubMed  Google Scholar 

  12. Fällmar D, Haller S, Lilja J et al (2017) Arterial spin labeling-based Z‑maps have high specificity and positive predictive value for neurodegenerative dementia compared to FDG-PET. Eur Radiol. https://doi.org/10.1007/s00330-017-4784-1

    Article  PubMed  PubMed Central  Google Scholar 

  13. Fereshtehnejad S‑M, Montplaisir JY, Pelletier A et al (2017) Validation of the MDS research criteria for prodromal Parkinson’s disease: Longitudinal assessment in a REM sleep behavior disorder (RBD) cohort. Mov Disord 32:865–873. https://doi.org/10.1002/mds.26989 (Validation of the MDS Prodromal Parkinson Research Criteria)

    Article  PubMed  Google Scholar 

  14. Grade M, Hernandez Tamames JA, Pizzini FB et al (2015) A neuroradiologist’s guide to arterial spin labeling MRI in clinical practice. Neuroradiology 57:1181–1202. https://doi.org/10.1007/s00234-015-1571-z

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  15. Guerreiro R, Ross OA, Kun-Rodrigues C et al (2018) Investigating the genetic architecture of dementia with Lewy bodies: a two-stage genome-wide association study. Lancet Neurol 17:64–74. https://doi.org/10.1016/S1474-4422(17)30400-3

    Article  PubMed  Google Scholar 

  16. Harper L, Fumagalli GG, Barkhof F et al (2016) MRI visual rating scales in the diagnosis of dementia: evaluation in 184 post-mortem confirmed cases. Brain 139:1211–1225. https://doi.org/10.1093/brain/aww005

    Article  PubMed  PubMed Central  Google Scholar 

  17. Hellwig S, Amtage F, Kreft A et al (2012) 18F]FDG-PET is superior to [123I]IBZM-SPECT for the differential diagnosis of parkinsonism. Neurology 79:1314–1322. https://doi.org/10.1212/WNL.0b013e31826c1b0a

    Article  PubMed  CAS  Google Scholar 

  18. Höglinger GU, Respondek G, Stamelou M et al (2017) Clinical diagnosis of progressive supranuclear palsy: The movement disorder society criteria. Mov Disord 32:853–864. https://doi.org/10.1002/mds.26987 (MDS Clinical Diagnostic Criteria for PSP)

    Article  PubMed  PubMed Central  Google Scholar 

  19. International FTD-Genomics Consortium (IFGC), Yokoyama JS, Karch CM et al (2017) Shared genetic risk between corticobasal degeneration, progressive supranuclear palsy, and frontotemporal dementia. Acta Neuropathol 133:825–837. https://doi.org/10.1007/s00401-017-1693-y

    Article  CAS  Google Scholar 

  20. Jack CR, Therneau TM, Wiste HJ et al (2016) Transition rates between amyloid and neurodegeneration biomarker states and to dementia: a population-based, longitudinal cohort study. Lancet Neurol 15:56–64. https://doi.org/10.1016/S1474-4422(15)00323-3

    Article  PubMed  CAS  Google Scholar 

  21. Jack CR, Wiste HJ, Weigand SD et al (2017) Age-specific and sex-specific prevalence of cerebral β‑amyloidosis, tauopathy, and neurodegeneration in cognitively unimpaired individuals aged 50–95 years: a cross-sectional study. Lancet Neurol 16:435–444. https://doi.org/10.1016/S1474-4422(17)30077-7

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  22. Klöppel S, Peter J, Ludl A et al (2015) Applying Automated MR-Based Diagnostic Methods to the Memory Clinic: A Prospective Study. J Alzheimers Dis 47:939–954. https://doi.org/10.3233/JAD-150334

    Article  PubMed  PubMed Central  Google Scholar 

  23. Klöppel S, Hellwig S, Yang S (2018) Voxel-wise deviations from healthy aging for the detection of region-specific atrophy. Unter Begutachtung

  24. Koedam ELGE, Lehmann M, van der Flier WM et al (2011) Visual assessment of posterior atrophy development of a MRI rating scale. Eur Radiol 21:2618–2625. https://doi.org/10.1007/s00330-011-2205-4

    Article  PubMed  PubMed Central  Google Scholar 

  25. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444. https://doi.org/10.1038/nature14539

    Article  PubMed  CAS  Google Scholar 

  26. Martínez G, Vernooij RW, Fuentes Padilla P et al (2017) 18F PET with florbetapir for the early diagnosis of Alzheimer’s disease dementia and other dementias in people with mild cognitive impairment (MCI). Cochrane Database Syst Rev 11:CD12216. https://doi.org/10.1002/14651858.CD012216.pub2

    Article  PubMed  Google Scholar 

  27. Mattsson N (2009) CSF biomarkers and incipient alzheimer disease in patients with mild cognitive impairment. JAMA 302:385. https://doi.org/10.1001/jama.2009.1064

    Article  PubMed  CAS  Google Scholar 

  28. McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133. https://doi.org/10.1007/BF02478259

    Article  Google Scholar 

  29. Mollenhauer B, Cullen V, Kahn I et al (2008) Direct quantification of CSF α‑synuclein by ELISA and first cross-sectional study in patients with neurodegeneration. Exp Neurol 213:315–325. https://doi.org/10.1016/j.expneurol.2008.06.004

    Article  PubMed  CAS  Google Scholar 

  30. Möller C, van der Flier WM, Versteeg A et al (2014) Quantitative regional validation of the visual rating scale for posterior cortical atrophy. Eur Radiol 24:397–404. https://doi.org/10.1007/s00330-013-3025-5

    Article  PubMed  Google Scholar 

  31. Moussaud S, Jones DR, Moussaud-Lamodière EL et al (2014) Alpha-synuclein and tau: teammates in neurodegeneration? Mol Neurodegener 9:43. https://doi.org/10.1186/1750-1326-9-43

    Article  PubMed  PubMed Central  Google Scholar 

  32. Postuma RB, Berg D, Stern M et al (2015) MDS clinical diagnostic criteria for Parkinson’s disease. Mov Disord 30:1591–1601. https://doi.org/10.1002/mds.26424 (MDS-PD clinical diagnostic criteria)

    Article  PubMed  Google Scholar 

  33. Respondek G, Levin J, Höglinger G (2017) Neudefinition atypischer Parkinson-Syndrome. Aktuelle Neurol 44:82–88. https://doi.org/10.1055/s-0042-123730

    Article  Google Scholar 

  34. Sakurai K, Tokumaru AM, Shimoji K et al (2017) Beyond the midbrain atrophy: wide spectrum of structural MRI finding in cases of pathologically proven progressive supranuclear palsy. Neuroradiology 59:431–443. https://doi.org/10.1007/s00234-017-1812-4

    Article  PubMed  Google Scholar 

  35. Sandor C, Honti F, Haerty W et al (2017) Whole-exome sequencing of 228 patients with sporadic Parkinson’s disease. Sci Rep 7:41188. https://doi.org/10.1038/srep41188

    Article  PubMed  PubMed Central  CAS  Google Scholar 

  36. Schäffer E, Berg D (2017) Neudefinition der Parkinson-Erkrankung. Aktuelle Neurol 44:260–266. https://doi.org/10.1055/s-0043-103081

    Article  Google Scholar 

  37. Sheikh-Bahaei N, Sajjadi SA, Pierce AL (2017) Current role for biomarkers in clinical diagnosis of alzheimer disease and Frontotemporal dementia. Curr Treat Options Neurol 19:46. https://doi.org/10.1007/s11940-017-0484-z

    Article  PubMed  Google Scholar 

  38. Tin Kam Ho (1995) Random Decision Forests. IEEE Comput. Soc. Press. IEEE, Los Alamitos, Calif, S 278–282

    Google Scholar 

  39. Visser PJ, Verhey F, Knol DL et al (2009) Prevalence and prognostic value of CSF markers of Alzheimer’s disease pathology in patients with subjective cognitive impairment or mild cognitive impairment in the DESCRIPA study: a prospective cohort study. Lancet Neurol 8:619–627. https://doi.org/10.1016/S1474-4422(09)70139-5

    Article  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Klinik für Neuroradiologie, Universitätsklinikum Freiburg, Medizinische Fakultät, Albert-Ludwigs-Universität, Freiburg, Deutschland

    K. Egger

  2. Klinik für Neurologie, Universitätsklinikum Freiburg, Medizinische Fakultät, Albert-Ludwigs-Universität Freiburg, Freiburg, Deutschland

    M. Rijntjes

Authors
  1. K. Egger
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. M. Rijntjes
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to K. Egger.

Ethics declarations

Interessenkonflikt

K. Egger ist Gesellschafter der VeoBrain GmbH mit Sitz in Freiburg. M. Rijntjes gibt an, dass kein Interessenkonflikt besteht.

Alle beschriebenen Untersuchungen am Menschen wurden mit Zustimmung der zuständigen Ethik-Kommission, im Einklang mit nationalem Recht sowie gemäß der Deklaration von Helsinki von 1975 (in der aktuellen, überarbeiteten Fassung) durchgeführt. Von allen beteiligten Patienten liegt eine Einverständniserklärung vor.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Egger, K., Rijntjes, M. „Big Data“ und künstliche Intelligenz zur Diagnoseunterstützung bei atypischer Demenz. Nervenarzt 89, 875–884 (2018). https://doi.org/10.1007/s00115-018-0568-3

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00115-018-0568-3

Schlüsselwörter

Keywords

Search

Navigation