Feasibility of using an automated analysis of formulation effort in patients' spoken seizure descriptions in the differential diagnosis of epileptic and nonepileptic seizures. (October 2021)

• Record Type: Journal Article
• Authors: Pevy, Nathan; Christensen, Heidi; Walker, Traci; Reuber, Markus
• Is Part Of: Seizure. Volume 91(2021)
• Page Start: 141
• Page End: 145
• Publication Date: 2021-10
• Subjects: Epilepsy -- Nonepileptic seizures -- Classification -- Natural language processing -- Speech analysis -- Diagnosis; Epilepsy -- Periodicals; Epilepsy -- Periodicals; Seizures -- Periodicals; Épilepsie -- Périodiques; Electronic journals; Electronic journals; 616.853
• DOI: 10.1016/j.seizure.2021.06.009
• Languages: English
• ISSNs: 1059-1311

Abstract

Highlights: People with epilepsy demonstrate more formulation effort while describing their seizure than people with nonepileptic seizures. People with epilepsy use more hesitations and repetitions. Measures of formulation effort can accurately predict the cause of seizures using the Random Forest algorithm. Including features that measure patterns in the use of pauses improves model performance. Abstract: Objective: There are three common causes of Transient Loss of Consciousness (TLOC), syncope, epileptic and psychogenic nonepileptic seizures (PNES). Many individuals who have experienced TLOC initially receive an incorrect diagnosis and inappropriate treatment. Whereas syncope can be distinguished relatively easily with a small number of "yes"/"no" questions, the differentiation of the other two causes of TLOC is more challenging. Previous qualitative research based on the methodology of Conversation Analysis has demonstrated that the descriptions of epileptic seizures contain more formulation effort than accounts of PNES. This research investigates whether features likely to reflect the level of formulation effort can be automatically elicited from audio recordings and transcripts of speech and used to differentiate between epileptic and nonepileptic seizures. Method: Verbatim transcripts of conversations between patients and neurologists were manually produced from video and audio recordings of 45 interactions (21 epilepsy and 24 PNES). The subsection of each transcript containing the person's account of their first seizure was manually extracted for the analysis. Seven automatically detectable features were designed as markers of formulation effort. These features were used to train a Random Forest machine learning classifier. Result: There were significantly more hesitations and repetitions in descriptions of epileptic than nonepileptic seizures. Using a nested leave-one-out cross validation approach, 71% of seizures were correctly classified by the Random Forest classifier. Discussion: This pilot study provides proof of principle that linguistic features that have been automatically extracted from audio recordings and transcripts could be used to distinguish between epileptic seizures and PNES and thereby contribute to the differential diagnosis of TLOC. Future research should explore whether additional observations can be incorporated into a diagnostic stratification tool and compare the performance of these features when they are combined with additional information provided by patients and witnesses about seizure manifestations and medical history.