Machine learning as a diagnostic decision aid for patients with transient loss of consciousness

Alistair Wardrope; Jenny Jamnadas-Khoda; Mark Broadhurst; Richard A Grünewald; Timothy J Heaton; Stephen J Howell; Matthias Koepp; Steve W Parry; Sanjay Sisodiya; Matthew C Walker; Markus Reuber

doi:10.1212/CPJ.0000000000000726

Machine learning as a diagnostic decision aid for patients with transient loss of consciousness

Neurol Clin Pract. 2020 Apr;10(2):96-105. doi: 10.1212/CPJ.0000000000000726.

Affiliation

¹ Sheffield Teaching Hospitals NHS Foundation Trust (AW, RAG, SJH, MR), Royal Hallamshire Hospital; Division of Psychiatry and Applied Psychology (JJ-K), University of Nottingham, Institute of Mental Health, Innovation Park; Mental Health Liaison Team (MB), Derbyshire Healthcare NHS Foundation Trust Hartington Unit, Chesterfield; School of Mathematics and Statistics (TJH), University of Sheffield; Department of Clinical and Experimental Epilepsy (MK, SS, MCW), University College London Queen Square Institute of Neurology; NIHR Newcastle Biomedical Research Centre and Institute of Cellular Medicine (SWP), Newcastle University, Newcastle upon Tyne; and Academic Neurology Unit (MR), University of Sheffield, Royal Hallamshire Hospital, United Kingdom.

Abstract

Background: 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).

Methods: Multi-center retrospective self- and witness-report questionnaire study in secondary care settings. Feature selection was performed by an iterative algorithm based on random forest analysis. Data were randomly divided in a 2:1 ratio into training and validation sets (163:86 for all data; 208:92 for analysis excluding witness reports).

Results: Three hundred patients with proven diagnoses (100 each: epilepsy, syncope and PNES) were recruited from epilepsy and syncope services. Two hundred forty-nine completed patient and witness questionnaires: 86 epilepsy (64 female), 84 PNES (61 female), and 79 syncope (59 female). Responses to 36 questions optimally predicted diagnoses. A classifier trained on these features classified 74/86 (86.0% [95% confidence interval 76.9%-92.6%]) of patients correctly in validation (100 [86.7%-100%] syncope, 85.7 [67.3%-96.0%] epilepsy, 75.0 [56.6%-88.5%] PNES). Excluding witness reports, 34 features provided optimal prediction (classifier accuracy of 72/92 [78.3 (68.4%-86.2%)] in validation, 83.8 [68.0%-93.8%] syncope, 81.5 [61.9%-93.7%] epilepsy, 67.9 [47.7%-84.1%] PNES).

Conclusions: A tool based on patient symptoms/comorbidities and witness reports separates well between syncope and other common causes of TLOC. It can help to differentiate epilepsy and PNES. Validated decision rules may improve diagnostic processes and reduce misdiagnosis rates.

Classification of evidence: This study provides Class III evidence that for patients with TLOC, patient and witness questionnaires discriminate between syncope, epilepsy and PNES.