Open AccessMachine learning as a diagnostic decision aid for patients with transient loss of consciousness
Author(s) -
Alistair Wardrope,
Jenny Jamnadas-Khoda,
Mark Broadhurst,
Richard A. Grünewald,
Timothy J Heaton,
Stephen Howell,
Matthias J. Koepp,
Steve W. Parry,
Sanjay M. Sisodiya,
Matthew C. Walker,
Markus Reuber
Publication year - 2020
Publication title -
neurology. clinical practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.674
H-Index - 29
eISSN - 2163-0933
pISSN - 2163-0402
DOI - 10.1212/cpj.0000000000000726
Subject(s) - epilepsy , psychogenic disease , medical diagnosis , medicine , syncope (phonology) , emergency department , witness , pediatrics , artificial intelligence , psychiatry , computer science , radiology , programming language
Transient loss of consciousness (TLOC) is a common reason for presentation to primary/emergency care; over 90% are because of epilepsy, syncope, or psychogenic non-epileptic seizures (PNES). Misdiagnoses are common, and there are currently no validated decision rules to aid diagnosis and management. We seek to explore the utility of machine-learning techniques to develop a short diagnostic instrument by extracting features with optimal discriminatory values from responses to detailed questionnaires about TLOC manifestations and comorbidities (86 questions to patients, 31 to TLOC witnesses).