Your browser doesn't support javascript.
loading
Constructing personalized characterizations of structural brain aberrations in patients with dementia using explainable artificial intelligence.
Leonardsen, Esten H; Persson, Karin; Grødem, Edvard; Dinsdale, Nicola; Schellhorn, Till; Roe, James M; Vidal-Piñeiro, Didac; Sørensen, Øystein; Kaufmann, Tobias; Westman, Eric; Marquand, Andre; Selbæk, Geir; Andreassen, Ole A; Wolfers, Thomas; Westlye, Lars T; Wang, Yunpeng.
Afiliación
  • Leonardsen EH; Department of Psychology, University of Oslo, Oslo, Norway. estenhl@uio.no.
  • Persson K; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway. estenhl@uio.no.
  • Grødem E; The Norwegian National Centre for Ageing and Health, Vestfold Hospital Trust, Tønsberg, Norway.
  • Dinsdale N; Department of Geriatric Medicine, Oslo University Hospital, Oslo, Norway.
  • Schellhorn T; Department of Psychology, University of Oslo, Oslo, Norway.
  • Roe JM; Computational Radiology & Artificial Intelligence (CRAI) Unit, Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway.
  • Vidal-Piñeiro D; Oxford Machine Learning in NeuroImaging (OMNI) Lab, University of Oxford, Oxford, UK.
  • Sørensen Ø; Institute of Clinical Medicine, University of Oslo, Oslo, Norway.
  • Kaufmann T; Division of Radiology and Nuclear Medicine, Oslo University Hospital, Oslo, Norway.
  • Westman E; Department of Psychology, University of Oslo, Oslo, Norway.
  • Marquand A; Department of Psychology, University of Oslo, Oslo, Norway.
  • Selbæk G; Department of Psychology, University of Oslo, Oslo, Norway.
  • Andreassen OA; Norwegian Centre for Mental Disorders Research (NORMENT), Oslo University Hospital & Institute of Clinical Medicine, University of Oslo, Oslo, Norway.
  • Wolfers T; Department of Psychiatry and Psychotherapy, Tübingen Center for Mental Health, University of Tübingen, Tübingen, Germany.
  • Westlye LT; German Center for Mental Health (DZPG), Munich, Germany.
  • Wang Y; Division of Clinical Geriatrics, Department of Neurobiology, Care Sciences, and Society, Karolinska Institutet, Stockholm, Sweden.
NPJ Digit Med ; 7(1): 110, 2024 May 02.
Article en En | MEDLINE | ID: mdl-38698139
ABSTRACT
Deep learning approaches for clinical predictions based on magnetic resonance imaging data have shown great promise as a translational technology for diagnosis and prognosis in neurological disorders, but its clinical impact has been limited. This is partially attributed to the opaqueness of deep learning models, causing insufficient understanding of what underlies their decisions. To overcome this, we trained convolutional neural networks on structural brain scans to differentiate dementia patients from healthy controls, and applied layerwise relevance propagation to procure individual-level explanations of the model predictions. Through extensive validations we demonstrate that deviations recognized by the model corroborate existing knowledge of structural brain aberrations in dementia. By employing the explainable dementia classifier in a longitudinal dataset of patients with mild cognitive impairment, we show that the spatially rich explanations complement the model prediction when forecasting transition to dementia and help characterize the biological manifestation of disease in the individual brain. Overall, our work exemplifies the clinical potential of explainable artificial intelligence in precision medicine.

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: NPJ Digit Med Año: 2024 Tipo del documento: Article País de afiliación: Noruega

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Idioma: En Revista: NPJ Digit Med Año: 2024 Tipo del documento: Article País de afiliación: Noruega