Identifying the presence and severity of dementia by applying interpretable machine learning techniques on structured clinical records.

Journal: BMC medical informatics and decision making
Published Date:

Abstract

BACKGROUND: Dementia develops as cognitive abilities deteriorate, and early detection is critical for effective preventive interventions. However, mainstream diagnostic tests and screening tools, such as CAMCOG and MMSE, often fail to detect dementia accurately. Various graph-based or feature-dependent prediction and progression models have been proposed. Whenever these models exploit information in the patients' Electronic Medical Records, they represent promising options to identify the presence and severity of dementia more precisely.

Authors

  • Akhilesh Vyas
    L3S Research Center, Leibniz University Hannover, Hannover, Germany.
  • Fotis Aisopos
    Software and Knowledge Engineering Laboratory, Institute of Informatics and Telecommunications, NCSR "Demokritos", Athens, Greece. fotis.aisopos@iit.demokritos.gr.
  • Maria-Esther Vidal
  • Peter Garrard
    Molecular and Clinical Science Research Institute, St. George's, University of London, London, UK.
  • Georgios Paliouras
    Institute of Informatics and Telecommunications, NCSR Demokritos, Patr. Gregoriou E and 27 Neapoleos St, Athens, 15341, Greece.