Differentiating PNES from epileptic seizures using conversational analysis

Predicting the cause of seizures using features extracted from interactions with a virtual agent

OBJECTIVE

A clinical decision tool for Transient Loss of Consciousness (TLOC) could reduce currently high misdiagnosis rates and waiting times for specialist assessments. Most clinical decision tools based on patient-reported symptom inventories only distinguish between two of the three most common causes of TLOC (epilepsy, functional /dissociative seizures, and syncope) or struggle with the particularly challenging differentiation between epilepsy and FDS. Based on previous research describing differences in spoken accounts of epileptic seizures and FDS seizures, this study explored the feasibility of predicting the cause of TLOC by combining the automated analysis of patient-reported symptoms and spoken TLOC descriptions.

METHOD

Participants completed an online web application that consisted of a 34-item medical history and symptom questionnaire (iPEP) and spoken interaction with a virtual agent (VA) that asked eight questions about the most recent experience of TLOC. Support Vector Machines (SVM) were trained using different combinations of features and nested leave-one-out cross validation. The iPEP provided a baseline performance. Inspired by previous qualitative research three spoken language based feature sets were designed to assess: (1) formulation effort, (2) the proportion of words from different semantic categories, and (3) verb, adverb, and adjective usage.

RESULTS

76 participants completed the application (Epilepsy = 24, FDS = 36, syncope = 16). Only 61 participants also completed the VA interaction (Epilepsy = 20, FDS = 29, syncope = 12). The iPEP model accurately predicted 65.8 % of all diagnoses, but the inclusion of the language features increased the accuracy to 85.5 % by improving the differential diagnosis between epilepsy and FDS.

CONCLUSION

These findings suggest that an automated analysis of TLOC descriptions collected using an online web application and VA could improve the accuracy of current clinical decisions tools for TLOC and facilitate clinical stratification processes (such as ensuring appropriate referral to cardiological versus neurological investigation and management pathways).

Metaphoric language in the differential diagnosis of epilepsy and psychogenic non-epileptic seizures: Time to move forward

Conversation analysis (CA) to identify metaphoric language (ML) has been proposed as a tool for the differential diagnosis of epileptic (ES) and psychogenic nonepileptic seizures (PNES). However, the clinical relevance of metaphoric conceptualizations is not clearly defined. The current study aims to investigate the ML utilized by individuals with ES and PNES in a pulled multi-country sample. Two blinded researchers examined the transcripts and videos of 54 interviews of individuals (n = 29, Italy; n = 11, USA; n = 14, Russia) with ES and PNES, identifying the patient-seizure relationship representative of the patient's internal experience. The diagnoses were based on video-EEG. Metaphors were classified as "Space/place", "External force", "Voluntary action", and "Other". A total of 175 metaphors were identified. No differences between individuals with ES and PNES were found in metaphoric occurrence (χ2 (1, N = 54) = 0.07; p = 0.74). No differences were identified when comparing the types of metaphors utilized by participants with ES and those with PNES. Patients with PNES and ES did not demonstrate differences in terms of occurrence and categories in ML. Therefore, researchers and clinicians should carefully consider the use of metaphor conceptualizations for diagnostic purposes.

Differentiating between epileptic and functional/dissociative seizures using semantic content analysis of transcripts of routine clinic consultations

The common causes of Transient Loss of Consciousness (TLOC) are syncope, epilepsy, and functional/dissociative seizures (FDS). Simple, questionnaire-based decision-making tools for non-specialists who may have to deal with TLOC (such as clinicians working in primary or emergency care) reliably differentiate between patients who have experienced syncope and those who have had one or more seizures but are more limited in their ability to differentiate between epileptic seizures and FDS. Previous conversation analysis research has demonstrated that qualitative expert analysis of how people talk to clinicians about their seizures can help distinguish between these two TLOC causes. This paper investigates whether automated language analysis - using semantic categories measured by the Linguistic Inquiry and Word Count (LIWC) toolkit - can contribute to the distinction between epilepsy and FDS. Using patient-only talk manually transcribed from recordings of 58 routine doctor-patient clinic interactions, we compared the word frequencies for 21 semantic categories and explored the predictive performance of these categories using 5 different machine learning algorithms. Machine learning algorithms trained using the chosen semantic categories and leave-one-out cross-validation were able to predict the diagnosis with an accuracy of up to 81%. The results of this proof of principle study suggest that the analysis of semantic variables in seizure descriptions could improve clinical decision tools for patients presenting with TLOC.

Frequency and economic burden of psychogenic non-epileptic seizures in patients applying for disability benefits due to epilepsy

BACKGROUND

Psychogenic non-epileptic seizures (PNES) resemble epileptic seizures and are often misdiagnosed as epilepsy.

OBJECTIVE

To investigate the frequency of PNES and to calculate the economic burden of the patients who admitted to video-electroencephalographicmonitoring (VEM) to obtain a diagnosis of epilepsy in order to apply for disability retirement.

METHODS

The present retrospective study included 134 patients who required disability reports between 2013 and 2019 and had their definite diagnoses after VEM. Following VEM, the patients were divided into three groups: epilepsy, PNES, and epilepsy + PNES.

RESULTS

In total, 22.4% (n = 30) of the patients were diagnosed with PNES, 21.6% (n = 29) with PNES and epilepsy, and 56% (n = 75), with epilepsy. The frequency of PNES among all patients was of 44% (n = 59). In patients with PNES alone, the annual cost of using anti-seizure medication was of 160.67 ± 94.04 dollars; for psychostimulant drugs, it was of 148.3 ± 72.48 dollars a year; and the mean direct cost for diagnostic procedures was of 582.9 ± 330.0 (range: 103.52-1601.3) dollars.

CONCLUSIONS

Although it is challenging to determine the qualitative and quantitative total cost in these patient groups, early diagnosis and sociopsychological support will reduce the additional financial burden on the health system and increase the quality of life of the patients.

"It's hard!": Adolescents' experience attending school with psychogenic nonepileptic seizures

Adolescents with psychogenic nonepileptic seizures (PNES) face many challenges in the school setting. Researchers have identified school stressors as potential predisposing, precipitating, and perpetuating factors for PNES. However, few researchers have explored the perspectives of adolescents with PNES regarding their experiences of attending school, where they spend much of their time. Therefore, this qualitative study employed content analysis to explore the experience of attending school as an adolescent with PNES. Ten adolescents (100% female, 80% White) were interviewed. With an overwhelming response of "It's hard!" from respondents, five themes regarding the school experience emerged: stress, bullying, accusations of "faking" seizure events, feeling left out because of the condition, and school-management of PNES. Underlying these themes were expressions of the need for increased understanding from and collaboration among peers, as well as the need for increased understanding from families, healthcare providers, and school personnel including school nurses. Study findings should inform future adolescent PNES research, practice decisions made by healthcare providers in the health and education sectors, education of healthcare and school professionals, and policy development and implementation.

Differential diagnosis between epileptic and psychogenic nonepileptic seizures through conversational analysis: A blinded prospective study in the Russian language

The current study examined the validity of conversational analysis (CA) in Russian patients with seizures, using a scoring table for the Simplified Linguistic Evaluation (SLE). The study sample was composed of 12 adult participants suffering either from epilepsy (ES) or psychogenic nonepileptic seizures (PNES) recruited in the Moscow Research and Clinical Center for Neuropsychiatry. Definitive diagnosis was established only after a habitual event was captured onvEEG. All participants with PNES or ES and at least one mental disorder underwent a 20-minute-long interview recorded on video. The interview then was evaluated by the external blinded physician already experienced in CA. Finally, that physician filled the SLE, consisting of 5 items analyzing the main characteristics of patient narrations. A score of ≥12 suggested a diagnosis of ES, while a score of <12 suggested a diagnosis of PNES. The blinded evaluator correctly identified 11 out of 12 cases. The concordance between the vEEG diagnosis and the CA diagnostic hypothesis was 91.67%. The sensitivity of the scoring table was 100%, while the specificity was 80%. The positive and the negative predictive values were, respectively, 87.5% and 100%. Our results suggested that the differences in seizure descriptions between patients with PNES and patients with ES are similar across Indo-European language family and are independent of psychiatric comorbidity.

[Psychogenic non-epileptic seizures]

The review provides epidemiological data and discuss the associated burden of non-epileptic seizures (PNES). Data on the prevalence, socio-demographic and clinical risk factors for the development of PNES are presented. The hypotheses of the PNES origin, including the contribution of psychological trauma, are considered. We also describe contemporary methods for differential diagnosis of epileptic seizures and PNES, including biomarkers and the use of diagnostic questionnaires. Special attention is given to the issues of the psychiatric comorbidity of PNES.

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

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.

Reliability of additional reported seizure manifestations to identify dissociative seizures

PURPOSE

Descriptions of seizure manifestations (SM), or semiology, can help localize the symptomatogenic zone and subsequently included brain regions involved in epileptic seizures, as well as identify patients with dissociative seizures (DS). Patients and witnesses are not trained observers, so these descriptions may vary from expert review of seizure video recordings of seizures. To better understand how reported factors can help identify patients with DS or epileptic seizures (ES), we evaluated the associations between more than 30 SMs and diagnosis using standardized interviews.

METHODS

Based on patient- and observer-reported data from 490 patients with diagnoses documented by video-electoencephalography, we compared the rate of each SM in five mutually exclusive groups: epileptic seizures (ES), DS, physiologic seizure-like events (PSLE), mixed DS and ES, and inconclusive testing.

RESULTS

In addition to SMs that we described in a prior manuscript, the following were associated with DS: light triggers, emotional stress trigger, pre-ictal and post-ictal headache, post-ictal muscle soreness, and ictal sensory symptoms. The following were associated with ES: triggered by missing medication, aura of déjà vu, and leftward eye deviation. There were numerous manifestations separately associated with mixed ES and DS.

CONCLUSIONS

Reported SM can help identify patients with DS, but no manifestation is pathognomonic for either ES or DS. Patients with mixed ES and DS reported factors divergent from both ES-alone and DS-alone.

Objective score from initial interview identifies patients with probable dissociative seizures

OBJECTIVE

To develop a Dissociative Seizures Likelihood Score (DSLS), which is a comprehensive, evidence-based tool using information available during the first outpatient visit to identify patients with "probable" dissociative seizures (DS) to allow early triage to more extensive diagnostic assessment.

METHODS

Based on data from 1616 patients with video-electroencephalography (vEEG) confirmed diagnoses, we compared the clinical history from a single neurology interview of patients in five mutually exclusive groups: epileptic seizures (ES), DS, physiologic nonepileptic seizure-like events (PSLE), mixed DS plus ES, and inconclusive monitoring. We used data-driven methods to determine the diagnostic utility of 76 features from retrospective chart review and applied this model to prospective interviews.

RESULTS

The DSLS using recursive feature elimination (RFE) correctly identified 77% (95% confidence interval (CI), 74-80%) of prospective patients with either ES or DS, with a sensitivity of 74% and specificity of 84%. This accuracy was not significantly inferior than neurologists' impression (84%, 95% CI: 80-88%) and the kappa between neurologists' and the DSLS was 21% (95% CI: 1-41%). Only 3% of patients with DS were missed by both the fellows and our score (95% CI 0-11%).

SIGNIFICANCE

The evidence-based DSLS establishes one method to reliably identify some patients with probable DS using clinical history. The DSLS supports and does not replace clinical decision making. While not all patients with DS can be identified by clinical history alone, these methods combined with clinical judgement could be used to identify patients who warrant further diagnostic assessment at a comprehensive epilepsy center.

Differentiating PNES from epileptic seizures using conversational analysis on French patients: A prospective blinded study

Psychogenic nonepileptic seizures (PNES) resemble epileptic seizures (ES) but are not caused by the occurrence of excessive cortical neuronal discharge. Previous studies in German-, English-, and Italian-speaking patients showed that patients used a different communicative style to talk about their seizures. They demonstrated that the diagnosis between PNES and ES could be predicted using qualitative assessment and a diagnostic scoring aid (DSA). The objective of our study was to evaluate the contribution of linguistic analysis in the differential diagnosis between ES and PNES in a French patient population. During an extended video-electroencephalogram (video-EEG) monitoring, 13 patients presented PNES and 19 patients with ES. Two neurologists blindly and independently analyzed the interview of each patient. Rater 1 predicted the correct diagnosis in 27 of 32 patients (84%) and Rater 2 in 28 of 32 patients (88%). Interrater reliability of qualitative analysis was satisfactory (k = 0.68, interrater agreement = 84.4%). Using a simplified DSA, Rater 1 and Rater 2 would have correctly diagnosed 88% (28/32 patients) and 91 % (29/32) of the cases, respectively. Our blinded prospective study confirms the diagnostic value of conversational analysis, performed by neurologists, to differentiate PNES from ES in French-speaking patients.

Development and use of the art therapy seizure assessment sculpture on an inpatient epilepsy monitoring unit

•

Patients diagnosed with PNES created sculptures notably different than patients diagnosed with epilepsy.

•

Art therapy may help both PNES and Epilepsy patients with emotional expression.

•

Along with a conventional diagnostic interview, SAS could help could provide important information at a much quicker rate.