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).

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.

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.

Fully automated cognitive screening tool based on assessment of speech and language.

INTRODUCTION: Recent years have seen an almost sevenfold rise in referrals to specialist memory clinics. This has been associated with an increased proportion of patients referred with functional cognitive disorder (FCD), that is, non-progressive cognitive complaints. These patients are likely to benefit from a range of interventions (eg, psychotherapy) distinct from the requirements of patients with neurodegenerative cognitive disorders. We have developed a fully automated system, 'CognoSpeak', which enables risk stratification at the primary-secondary care interface and ongoing monitoring of patients with memory concerns. METHODS: We recruited 15 participants to each of four groups: Alzheimer's disease (AD), mild cognitive impairment (MCI), FCD and healthy controls. Participants responded to 12 questions posed by a computer-presented talking head. Automatic analysis of the audio and speech data involved speaker segmentation, automatic speech recognition and machine learning classification. RESULTS: CognoSpeak could distinguish between participants in the AD or MCI groups and those in the FCD or healthy control groups with a sensitivity of 86.7%. Patients with MCI were identified with a sensitivity of 80%. DISCUSSION: Our fully automated system achieved levels of accuracy comparable to currently available, manually administered assessments. Greater accuracy should be achievable through further system training with a greater number of users, the inclusion of verbal fluency tasks and repeat assessments. The current data supports CognoSpeak's promise as a screening and monitoring tool for patients with MCI. Pending confirmation of these findings, it may allow clinicians to offer patients at low risk of dementia earlier reassurance and relieve pressures on specialist memory services.

What 'form' does informal assessment take? A scoping review of the informal assessment literature for aphasia.

BACKGROUND: Aphasia assessment is traditionally divided into formal and informal approaches. Informal assessment is useful in developing a rich understanding of the person with aphasia's performance, e.g., describing performance in the context of real-world activities, and exploring the impact of environmental and/or partner supports upon communication. However, defining 'informal assessment' is problematic and can result in clinical issues including idiosyncratic practices regarding why, when and how to apply informal assessment. AIMS: To examine the extent to which the informal assessment literature can guide speech and language therapists (SLTs) in their clinical application of informal assessment for post-stroke aphasia. METHODS & PROCEDURES: A scoping review methodology was used. A systematic search of electronic databases (Scopus, Embase, PyscInfo, CINAHL, Ovid Medline and AMED) gave informal assessment references between 2000 and 2017 to which title/abstract and full-text screening against inclusion criteria were applied. Data were extracted from 28 resulting documents using an extraction template with fields based on the review's purpose. MAIN CONTRIBUTION: This review examines the informal assessment guidance regarding: rationale; areas of interest for informal assessment; available methods; procedural guidance; documentation; and analytical frameworks. The rationale for using informal assessment included several aspects such as gaining a 'representative' sample of the individual's language. Ten communication areas of interest were found with 13 different assessment methods. The procedural guidance for these methods varied considerably, with the exception of conversation and semi-structured interviewing. Overall, documentation guidance was limited but numerous analytical frameworks were found. CONCLUSIONS: Several informal assessment methods are available to SLTs. However, information is mixed regarding when they might be used or how they might be applied in terms of their administration, documentation and analysis.

Toward the Automation of Diagnostic Conversation Analysis in Patients with Memory Complaints.

BACKGROUND: The early diagnosis of dementia is of great clinical and social importance. A recent study using the qualitative methodology of conversation analysis (CA) demonstrated that language and communication problems are evident during interactions between patients and neurologists, and that interactional observations can be used to differentiate between cognitive difficulties due to neurodegenerative disorders (ND) or functional memory disorders (FMD). OBJECTIVE: This study explores whether the differential diagnostic analysis of doctor-patient interactions in a memory clinic can be automated. METHODS: Verbatim transcripts of conversations between neurologists and patients initially presenting with memory problems to a specialist clinic were produced manually (15 with FMD, and 15 with ND). A range of automatically detectable features focusing on acoustic, lexical, semantic, and visual information contained in the transcripts were defined aiming to replicate the diagnostic qualitative observations. The features were used to train a set of five machine learning classifiers to distinguish between ND and FMD. RESULTS: The mean rate of correct classification between ND and FMD was 93% ranging from 97% by the Perceptron classifier to 90% by the Random Forest classifier.Using only the ten best features, the mean correct classification score increased to 95%. CONCLUSION: This pilot study provides proof-of-principle that a machine learning approach to analyzing transcripts of interactions between neurologists and patients describing memory problems can distinguish people with neurodegenerative dementia from people with FMD.

Catastrophising and normalising in patient's accounts of their seizure experiences.

PURPOSE: To extend our previous research demonstrating that linguistic/interactional features in patients' talk can assist the challenging differential diagnosis of epilepsy and psychogenic nonepileptic seizures (PNES) by exploring the differential diagnostic potential of references to non co-present persons (third parties). METHOD: Initial encounters were recorded between 20 seizure patients (13 with PNES, seven with epilepsy) who were subsequently diagnosed by the recording of typical seizures with video-EEG. An analyst blinded to the medical diagnoses coded and analysed transcripts. RESULTS: There were no significant differences between the two diagnostic groups in terms of the total number of third party references or references made spontaneously by patients without prompting from the doctor. However, patients with PNES made significantly more prompted references to third parties (p=0.022). 'Castrophising' third party references were made in 12/13 (92.3%) of encounters with PNES patients and 1/7 (14.3%) of encounters with epilepsy patients (p=0.001, OR 72, 95% CI=3.8-1361.9). Normalising references were identified in 2/13 (15.4%) of encounters in the PNES and 6/7 (85.7%) of encounters in the epilepsy groups (p=0.004, OR 33, 95% CI=2.5-443.6). CONCLUSION: There are significant differences in how patients with epilepsy or patients with PNES refer to third parties. Patients with PNES are more likely to be prompted to tell doctors what others have told them about their seizures. Patients using third party references to catastrophise their seizure experiences are more likely to have PNES, whilst patients who use third party references to normalise their life with seizures are more likely to have epilepsy.