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

Role of Artificial Intelligence in Improving Syncope Management

Syncope is common in the general population and is a common presenting symptom in acute care settings. Substantial costs are attributed to care of patients with syncope. Current challenges include differentiating syncope from its mimickers, identifying serious underlying conditions that caused the syncope, and wide variations in current management. While validated risk tools exist especially for short-term prognosis, there is inconsistent application, and the current approach does not meet the patient needs/expectations. Artificial intelligence (AI) techniques such as machine learning methods including natural language processing can potentially address the current challenges in syncope management. Preliminary evidence from published studies indicates that it is possible to accurately differentiate syncope from its mimickers and predict short-term prognosis/ hospitalization. More recently AI analysis of ECG has shown promise in detection of serious structural and functional cardiac abnormalities which has the potential to improve syncope care. Future AI studies have the potential to address current issues in syncope management. AI can automatically prognosticate risk in real time by accessing traditional and non-traditional data. However, steps to mitigate known problems such generalizability, patient privacy, data protection, and liability will be needed. In the past AI has had limited impact due to underdeveloped analytical methods, lack of computing power, poor access to powerful computing systems, and availability of reliable high-quality data. All impediments except data have been solved. AI will live up to its promise to transform syncope care if the health care system can satisfy AI requirement of large scale, robust, accurate, and reliable data.

A complex case with generalized epilepsy, probable focal seizures, and functional seizures

In this patient, now 42 years old, genetic generalized epilepsy (juvenile myoclonic epilepsy) manifested itself at the age of 13. At the age of 39, she experienced a status episode with prolonged ICU treatment. She was left with a left-sided hippocampal sclerosis and probably focal seizures. In addition, since the age of 24, the patient also experiences functional seizures on the background of a borderline personality disorder. While generalized epileptic seizures could be controlled with antiseizure medication (ASM), the patient was multiple times admitted to Emergency Departments for her functional seizures with subsequent intensive care treatments, including intubation. As a complication, the patient developed critical illness polyneuropathy and myopathy, resulting in wheelchair dependence. Additionally, she acquired a complex regional pain syndrome after extravasation of ASM. The report demonstrates the uncommon development of hippocampal sclerosis after a generalized tonic-clonic status epilepticus and the poor treatability of functional seizures as compared to generalized and focal seizures.

Improving epilepsy diagnosis across the lifespan: approaches and innovations

Epilepsy diagnosis is often delayed or inaccurate, exposing people to ongoing seizures and their substantial consequences until effective treatment is initiated. Important factors contributing to this problem include delayed recognition of seizure symptoms by patients and eyewitnesses; cultural, geographical, and financial barriers to seeking health care; and missed or delayed diagnosis by health-care providers. Epilepsy diagnosis involves several steps. The first step is recognition of epileptic seizures; next is classification of epilepsy type and whether an epilepsy syndrome is present; finally, the underlying epilepsy-associated comorbidities and potential causes must be identified, which differ across the lifespan. Clinical history, elicited from patients and eyewitnesses, is a fundamental component of the diagnostic pathway. Recent technological advances, including smartphone videography and genetic testing, are increasingly used in routine practice. Innovations in technology, such as artificial intelligence, could provide new possibilities for directly and indirectly detecting epilepsy and might make valuable contributions to diagnostic algorithms in the future.

Testing the diagnostic accuracy of common questions for seizure diagnosis: Challenges and future directions

OBJECTIVE

The aim of this study was to evaluate the diagnostic accuracy of common interview questions used to distinguish a diagnosis of epilepsy from seizure mimics including non-epileptic seizures (NES), migraine, and syncope.

METHODS

200 outpatients were recruited with an established diagnosis of focal epilepsy (n = 50), NES (n = 50), migraine (n = 50), and syncope (n = 50). Patients completed an eight-item, yes-or-no online questionnaire about symptoms related to their events. Sensitivity and specificity were calculated. Using a weighted scoring for the questions alone with baseline characteristics, the overall questionnaire was tested for diagnostic accuracy.

RESULTS

Of individual questions, the most sensitive one asked if events are sudden in onset (98 % sensitive for epilepsy (95 % CI: 89 %, 100 %)). The least sensitive question asked if events are stereotyped (46 % sensitive for epilepsy (95 % CI: 32 %, 60 %)). Overall, three of the eight questions showed an association with epilepsy as opposed to mimics. These included questions about "sudden onset" (OR 10.76, 95 % CI: (1.66, 449.21) p = 0.0047), "duration < 5 min" (OR 3.34, 95 % CI: (1.62, 6.89), p = 0.0008), and "duration not > 30 min" (OR 4.44, 95 % CI: (1.94, 11.05), p = <0.0001). When individual seizure mimics were compared to epilepsy, differences in responses were most notable between the epilepsy and migraine patients. Syncope and NES were most similar in responses to epilepsy. The overall weighted questionnaire incorporating patient age and sex produced an area under the ROC curve of 0.80 (95 % CI: 0.74, 0.87)).

CONCLUSION

In this study, we examined the ability of common interview questions used by physicians to distinguish between epilepsy and prevalent epilepsy mimics, specifically NES, migraines, and syncope. Using a weighted scoring system for questions, and including age and sex, produced a sensitive and specific predictive model for the diagnosis of epilepsy. In contrast to many prior studies which evaluated either a large number of questions or used methods with difficult practical application, our study is unique in that we tested a small number of easy-to-understand "yes" or "no" questions that can be implemented in most clinical settings by non-specialists.

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).

Machine Learning and Artificial Intelligence Applications to Epilepsy: a Review for the Practicing Epileptologist

PURPOSE OF REVIEW

Machine Learning (ML) and Artificial Intelligence (AI) are data-driven techniques to translate raw data into applicable and interpretable insights that can assist in clinical decision making. Some of these tools have extremely promising initial results, earning both great excitement and creating hype. This non-technical article reviews recent developments in ML/AI in epilepsy to assist the current practicing epileptologist in understanding both the benefits and limitations of integrating ML/AI tools into their clinical practice.

RECENT FINDINGS

ML/AI tools have been developed to assist clinicians in almost every clinical decision including (1) predicting future epilepsy in people at risk, (2) detecting and monitoring for seizures, (3) differentiating epilepsy from mimics, (4) using data to improve neuroanatomic localization and lateralization, and (5) tracking and predicting response to medical and surgical treatments. We also discuss practical, ethical, and equity considerations in the development and application of ML/AI tools including chatbots based on Large Language Models (e.g., ChatGPT). ML/AI tools will change how clinical medicine is practiced, but, with rare exceptions, the transferability to other centers, effectiveness, and safety of these approaches have not yet been established rigorously. In the future, ML/AI will not replace epileptologists, but epileptologists with ML/AI will replace epileptologists without ML/AI.

Using Verbally-Reported and Video-Observed Semiology to Identify Functional Seizures

Diagnosis of functional seizures, also known as psychogenic nonepileptic seizures, starts with a clinical interview and description of the seizures. A targeted approach to this evaluation can provide valuable information to gauge the likelihood of functional seizures as compared with other similar conditions including but not limited to epileptic seizures. This review focuses on the use of patient and witness descriptions and seizure videos to identify patients with probable functional seizures. Particular emphasis is given to recognizing the limitations of the available data and the influence of health-care provider expertise on diagnostic accuracy.

Can Artificial Intelligence Enhance Syncope Management?: A JACC: Advances Multidisciplinary Collaborative Statement

Syncope, a form of transient loss of consciousness, remains a complex medical condition for which adverse cardiovascular outcomes, including death, are of major concern but rarely occur. Current risk stratification algorithms have not completely delineated which patients benefit from hospitalization and specific interventions. Patients are often admitted unnecessarily and at high cost. Artificial intelligence (AI) and machine learning may help define the transient loss of consciousness event, diagnose the cause, assess short- and long-term risks, predict recurrence, and determine need for hospitalization and therapeutic intervention; however, several challenges remain, including medicolegal and ethical concerns. This collaborative statement, from a multidisciplinary group of clinicians, investigators, and scientists, focuses on the potential role of AI in syncope management with a goal to inspire creation of AI-derived clinical decision support tools that may improve patient outcomes, streamline diagnostics, and reduce health-care costs.

Epilepsy diagnosis using a clinical decision tool and artificially intelligent electroencephalography

OBJECTIVE

To construct a tool for non-experts to calculate the probability of epilepsy based on easily obtained clinical information combined with an artificial intelligence readout of the electroencephalogram (AI-EEG).

MATERIALS AND METHODS

We performed a chart review of 205 consecutive patients aged 18 years or older who underwent routine EEG. We created a point system to calculate the pre-EEG probability of epilepsy in a pilot study cohort. We also computed a post-test probability based on AI-EEG results.

RESULTS

One hundred and four (50.7%) patients were female, the mean age was 46 years, and 110 (53.7%) were diagnosed with epilepsy. Findings favoring epilepsy included developmental delay (12.6% vs 1.1%), prior neurological injury (51.4% vs 30.9%), childhood febrile seizures (4.6% vs 0.0%), postictal confusion (43.6% vs 20.0%), and witnessed convulsions (63.6% vs 21.1%); findings favoring alternative diagnoses were lightheadedness (3.6% vs 15.8%) or onset after prolonged sitting or standing (0.9% vs 7.4%). The final point system included 6 predictors: Presyncope (-3 points), cardiac history (-1), convulsion or forced head turn (+3), neurological disease history (+2), multiple prior spells (+1), postictal confusion (+2). Total scores of ≤1 point predicted <5% probability of epilepsy, while cumulative scores ≥7 predicted >95%. The model showed excellent discrimination (AUROC: 0.86). A positive AI-EEG substantially increases the probability of epilepsy. The impact is greatest when the pre-EEG probability is near 30%.

SIGNIFICANCE

A decision tool using a small number of historical clinical features accurately predicts the probability of epilepsy. In indeterminate cases, AI-assisted EEG helps resolve uncertainty. This tool holds promise for use by healthcare workers without specialty epilepsy training if validated in an independent cohort.

Trauma and syncope: looking beyond the injury

Background

42% of the population experience syncope by the age of 70, accounting for up to 6% of hospital admissions that frequently present as falls. The etiologies of some falls are benign, and others, such as cardiac syncope, are associated with a greater mortality and must be identified.

Methods

This review article aims to bridge the literature gap by providing a comprehensive practice review and critical summary of the current syncope guidance relating to the trauma patient.

Results

The National Institute for Health and Care Excellence, the American College of Cardiology, and European Society of Cardiology published syncope risk stratification guidance. The inclusion of certain high-risk features represented in all three guidelines suggests their significance to identify cardiac syncope including heart failure, abnormal vital signs, syncope during exercise with little to no prodrome, family history of sudden cardiac death, and ECG abnormalities. Of 11 syncope risk stratification scoring systems based on these guidelines, only 2 are externally validated in the emergency department, neither of which are validated for major trauma use. Adherence to thorough history-taking, examination, orthostatic blood pressure recording, and an ECG can diagnose the cause of syncope in up to 50% of patients. ECG findings are 95% to 98% sensitive in the detection of serious adverse outcomes after cardiac syncope and should form part of a standardized syncope trauma assessment. Routine blood testing in trauma is often performed despite evidence that it is neither useful nor cost effective, where the screening of cardiac enzymes and D-dimer rarely influences management.

Discussion

In the absence of a gold-standard clinical test to identify the cause of a syncopal episode, standardized syncope guidelines as described in this review could be incorporated into trauma protocols to analyze high-risk etiologies, improve diagnostic accuracy, reduce unnecessary investigations, and develop an effective and safer management strategy.

Clinical MRI morphological analysis of functional seizures compared to seizure-naïve and psychiatric controls

PURPOSE

Functional seizures (FS), also known as psychogenic nonepileptic seizures (PNES), are physical manifestations of acute or chronic psychological distress. Functional and structural neuroimaging have identified objective signs of this disorder. We evaluated whether magnetic resonance imaging (MRI) morphometry differed between patients with FS and clinically relevant comparison populations.

METHODS

Quality-screened clinical-grade MRIs were acquired from 666 patients from 2006 to 2020. Morphometric features were quantified with FreeSurfer v6. Mixed-effects linear regression compared the volume, thickness, and surface area within 201 regions-of-interest for 90 patients with FS, compared to seizure-naïve patients with depression (n = 243), anxiety (n = 68), and obsessive-compulsive disorder (OCD, n = 41), respectively, and to other seizure-naïve controls with similar quality MRIs, accounting for the influence of multiple confounds including depression and anxiety based on chart review. These comparison populations were obtained through review of clinical records plus research studies obtained on similar scanners.

RESULTS

After Bonferroni-Holm correction, patients with FS compared with seizure-naïve controls exhibited thinner bilateral superior temporal cortex (left 0.053 mm, p = 0.014; right 0.071 mm, p = 0.00006), thicker left lateral occipital cortex (0.052 mm, p = 0.0035), and greater left cerebellar white-matter volume (1085 mm³, p = 0.0065). These findings were not accounted for by lower MRI quality in patients with FS.

CONCLUSIONS

These results reinforce prior indications of structural neuroimaging correlates of FS and, in particular, distinguish brain morphology in FS from that in depression, anxiety, and OCD. Future work may entail comparisons with other psychiatric disorders including bipolar and schizophrenia, as well as exploration of brain structural heterogeneity within FS.

The hermeneutics of symptoms

The clinical encounter begins with presentation of an illness experience; but throughout that encounter, something else is constructed from it – a symptom. The symptom is a particular interpretation of that experience, useful for certain purposes in particular contexts. The hermeneutics of medicine – the study of the interpretation of human experience in medical terms – has largely taken the process of symptom-construction to be transparent, focussing instead on how constellations of symptoms are interpreted as representative of particular conditions. This paper examines the hermeneutical activity of symptom-construction more closely. I propose a fourfold account of the clinical function of symptoms: as theoretical entities; as tools for communication; as guides to palliative intervention; and as candidates for medical explanation or intervention. I also highlight roles they might play in illness experience. I use this framework to discuss four potential failures of symptom-interpretation: failure of symptom-type and symptom-token recognition; loss of the complete picture of illness experience through overwhelming emphasis on its symptomatic interpretation; and intersubjective feedback effects of symptom description altering the ill person’s own perceptions of their phenomenal experience. I conclude with some suggestions of potential remedies for failures in the process of symptom-construction.

Functional neurological disorder: new subtypes and shared mechanisms

Functional neurological disorder is common in neurological practice. A new approach to the positive diagnosis of this disorder focuses on recognisable patterns of genuinely experienced symptoms and signs that show variability within the same task and between different tasks over time. Psychological stressors are common risk factors for functional neurological disorder, but are often absent. Four entities-functional seizures, functional movement disorders, persistent perceptual postural dizziness, and functional cognitive disorder-show similarities in aetiology and pathophysiology and are variants of a disorder at the interface between neurology and psychiatry. All four entities have distinctive features and can be diagnosed with the support of clinical neurophysiological studies and other biomarkers. The pathophysiology of functional neurological disorder includes overactivity of the limbic system, the development of an internal symptom model as part of a predictive coding framework, and dysfunction of brain networks that gives movement the sense of voluntariness. Evidence supports tailored multidisciplinary treatment that can involve physical and psychological therapy approaches.

Machine learning applications to differentiate comorbid functional seizures and epilepsy from pure functional seizures

PURPOSE

We have utilized different methods in machine learning (ML) to develop the best algorithm to differentiate comorbid functional seizures (FS) and epilepsy from those who have pure FS.

METHODS

This was a retrospective study of an electronic database of patients with seizures. All patients with a diagnosis of FS (with or without comorbid epilepsy) were studied at the outpatient epilepsy clinic at Shiraz University of Medical Sciences, Shiraz, Iran, from 2008 until 2021. We arbitrarily selected 14 features that are important in making the diagnosis of patients with seizures and also are easily obtainable during history taking. Pytorch and Scikit-learn packages were used to construct various models including random forest classifier, decision tree classifier, support vector classifier, k-nearest neighbor, and TabNet classifier.

RESULTS

Three hundred and two patients had FS (82.5%), while 64 patients had FS and comorbid epilepsy (17.5%). The "TabNet classifier" could provide the best sensitivity (90%) and specificity (74%) measures (accuracy of 76%) to help differentiate patients with FS from those with FS and comorbid epilepsy.

CONCLUSION

These satisfactory differentiating measures suggest that the current algorithm could be used in clinical practice to help with the difficult task of distinguishing patients with FS from those with FS and comorbid epilepsy. Based on the results of the current study, we have developed an Application (SeiDx). This App is freely accessible at the following address: https://drive.google.com/file/d/1rAgBXKNPW9bmUCDioaGHHzLBQgzZ-HZ2/view. This App should be validated in a prospective assessment.

Recent Updates and Technological Developments in Evaluating Cardiac Syncope in the Emergency Department

Syncope is a commonly encountered problem in the emergency department (ED), accounting for approximately 3% of presenting complaints. Clinical assessment of syncope can be challenging due to the diverse range of conditions that can precipitate the symptom. Annual mortality for patients presenting with syncope ranges from 0-12%, and if the syncope is secondary to a cardiac cause, then this figure rises to 18-33%. In ED, it is paramount to accurately identify those presenting with syncope, especially patients with an underlying cardiac aetiology, initiate appropriate management, and refer them for further investigations. In 2018, the European Society of Cardiology (ESC) updated its guidelines with regard to diagnosing and managing patients with syncope. We highlight recent developments and considerations in various components of the workup, such as history, physical examination, investigations, risk stratification, and novel biomarkers, since the establishment of the 2018 ESC guidelines. We further discuss the emerging role of artificial intelligence in diagnosing cardiac syncope and postulate how wearable technology may transform evaluating cardiac syncope in ED.

Diagnosing Neurally Mediated Syncope Using Classification Techniques

Syncope is a medical condition resulting in the spontaneous transient loss of consciousness and postural tone with spontaneous recovery. The diagnosis of syncope is a challenging task, as similar types of symptoms are observed in seizures, vertigo, stroke, coma, etc. The advent of Healthcare 4.0, which facilitates the usage of artificial intelligence and big data, has been widely used for diagnosing various diseases based on past historical data. In this paper, classification-based machine learning is used to diagnose syncope based on data collected through a head-up tilt test carried out in a purely clinical setting. This work is concerned with the use of classification techniques for diagnosing neurally mediated syncope triggered by a number of neurocardiogenic or cardiac-related factors. Experimental results show the effectiveness of using classification-based machine learning techniques for an early diagnosis and proactive treatment of neurally mediated syncope.

A Sneak-Peek into the Physician's Brain: A Retrospective Machine Learning-Driven Investigation of Decision-Making in TAVR versus SAVR for Young High-Risk Patients with Severe Symptomatic Aortic Stenosis

Transcatheter aortic valve replacement (TAVR) has rapidly become a viable alternative to the conventional isolated surgical aortic valve replacement (iSAVR) for treating severe symptomatic aortic stenosis. However, data on younger patients is scarce and a gap exists between data-based recommendations and the clinical use of TAVR. In our study, we utilized a machine learning (ML) driven approach to model the complex decision-making process of Heart Teams when treating young patients with severe symptomatic aortic stenosis with either TAVR or iSAVR and to identify the relevant considerations. Out of the considered factors, the variables most prominently featured in our ML model were congestive heart failure, established risk assessment scores, previous cardiac surgeries, a reduced left ventricular ejection fraction and peripheral vascular disease. Our study demonstrates a viable application of ML-based approaches for studying and understanding complex clinical decision-making processes.

Support Vector Machine-Based Classification of Vasovagal Syncope Using Head-Up Tilt Test

Syncope is the medical condition of loss of consciousness triggered by the momentary cessation of blood flow to the brain. Machine learning techniques have been established to be very effective way to address such problems, where a class label is predicted for given input data. This work presents a Support Vector Machine (SVM) based classification of neuro-mediated syncope evaluated using train-test-split and K-fold cross-validation methods using the patient's physiological data collected through the Head-up Tilt Test in pure clinical settings. The performance of the model has been analyzed over standard statistical performance indices. The experimental results prove the effectiveness of using SVM-based classification for the proactive diagnosis of syncope.

A web-based algorithm to rapidly classify seizures for the purpose of drug selection

OBJECTIVE

To develop and validate a pragmatic algorithm that classifies seizure types, to facilitate therapeutic decision-making.

METHODS

Using a modified Delphi method, five experts developed a pragmatic classification of nine types of epileptic seizures or combinations of seizures that influence choice of medication, and constructed a simple algorithm, freely available on the internet. The algorithm consists of seven questions applicable to patients with seizure onset at the age of 10 years or older. Questions to screen for nonepileptic attacks were added. Junior physicians, nurses, and physician assistants applied the algorithm to consecutive patients in a multicenter prospective validation study (ClinicalTrials.gov identifier: NCT03796520). The reference standard was the seizure classification by expert epileptologists, based on all available data, including electroencephalogram (EEG), video-EEG monitoring, and neuroimaging. In addition, physicians working in underserved areas assessed the feasibility of using the web-based algorithm in their clinical setting.

RESULTS

A total of 262 patients were assessed, of whom 157 had focal, 51 had generalized, and 10 had unknown onset epileptic seizures, and 44 had nonepileptic paroxysmal events. Agreement between the algorithm and the expert classification was 83.2% (95% confidence interval = 78.6%-87.8%), with an agreement coefficient (AC1) of .82 (95% confidence interval = .77-.87), indicating almost perfect agreement. Thirty-two health care professionals from 14 countries evaluated the feasibility of the web-based algorithm in their clinical setting, and found it applicable and useful for their practice (median = 6.5 on 7-point Likert scale).

SIGNIFICANCE

The web-based algorithm provides an accurate classification of seizure types, which can be used for selecting antiseizure medications in adolescents and adults.

Machine Learning and Syncope Management in the ED: The Future Is Coming

In recent years, machine learning (ML) has been promisingly applied in many fields of clinical medicine, both for diagnosis and prognosis prediction. Aims of this narrative review were to summarize the basic concepts of ML applied to clinical medicine and explore its main applications in the emergency department (ED) setting, with a particular focus on syncope management. Through an extensive literature search in PubMed and Embase, we found increasing evidence suggesting that the use of ML algorithms can improve ED triage, diagnosis, and risk stratification of many diseases. However, the lacks of external validation and reliable diagnostic standards currently limit their implementation in clinical practice. Syncope represents a challenging problem for the emergency physician both because its diagnosis is not supported by specific tests and the available prognostic tools proved to be inefficient. ML algorithms have the potential to overcome these limitations and, in the future, they could support the clinician in managing syncope patients more efficiently. However, at present only few studies have addressed this issue, albeit with encouraging results.

Epilepsy, dissociative seizures, and mixed: Associations with time to video-EEG

PURPOSE

Video-electroencephalographic monitoring (VEM) is a core component to the diagnosis and evaluation of epilepsy and dissociative seizures (DS)-also known as functional or psychogenic seizures-but VEM evaluation often occurs later than recommended. To understand why delays occur, we compared how patient-reported clinical factors were associated with time from first seizure to VEM (TVEM) in patients with epilepsy, DS or mixed.

METHODS

We acquired data from 1245 consecutive patients with epilepsy, VEM-documented DS or mixed epilepsy and DS. We used multivariate log-normal regression with recursive feature elimination (RFE) to evaluate which of 76 clinical factors interacting with patients' diagnoses were associated with TVEM.

RESULTS

The mean and median TVEM were 14.6 years and 10 years, respectively (IQR 3-23 years). In the multivariate RFE model, the factors associated with longer TVEM in all patients included unemployment and not student status, more antiseizure medications (current and past), concussion, and ictal behavior suggestive of temporal lobe epilepsy. Average TVEM was shorter for DS than epilepsy, particularly for patients with depression, anxiety, migraines, and eye closure. Average TVEM was longer specifically for patients with DS taking more medications, more seizure types, non-metastatic cancer, and with other psychiatric comorbidities.

CONCLUSIONS

In all patients with seizures, trials of numerous antiseizure medications, unemployment and non-student status was associated with longer TVEM. These associations highlight a disconnect between International League Against Epilepsy practice parameters and observed referral patterns in epilepsy. In patients with dissociative seizures, some but not all factors classically associated with DS reduced TVEM.

Validation of a predictive calculator to distinguish between patients presenting with dissociative versus epileptic seizures

Dissociative seizures (also known as psychogenic nonepileptic seizures) are a common functional neurological disorder that can be difficult to distinguish from epileptic seizures. Patients with dissociative seizures provide diagnostic challenges, leading to delays in care, inappropriate care, and significant healthcare utilization and associated costs. The dissociative seizure likelihood score (DSLS) was developed by Kerr and colleagues at UCLA to distinguish between patients with epileptic seizures and dissociative seizures based on clinical and medication history as well as features of seizure semiology. We validated this calculator at the University of Colorado, which is a Level 4 National Association of Epilepsy Center. The DSLS accurately predicted the diagnosis in 81% of patients, despite local variability in the factors associated with epileptic versus dissociative seizures between the two populations. The DSLS can be a useful tool to assist with history taking and may have important utility for clinical decision making with these difficult to distinguish patient populations.

Factors associated with delay to video-EEG in dissociative seizures

PURPOSE

While certain clinical factors suggest a diagnosis of dissociative seizures (DS), otherwise known as functional or psychogenic nonepileptic seizures (PNES), ictal video-electroencephalography monitoring (VEM) is the gold standard for diagnosis. Diagnostic delays were associated with worse quality of life and more seizures, even after treatment. To understand why diagnoses were delayed, we evaluated which factors were associated with delay to VEM.

METHODS

Using data from 341 consecutive patients with VEM-documented dissociative seizures, we used multivariate log-normal regression with recursive feature elimination (RFE) and multiple imputation of some missing data to evaluate which of 76 clinical factors were associated with time from first dissociative seizure to VEM.

RESULTS

The mean delay to VEM was 8.4 years (median 3 years, IQR 1-10 years). In the RFE multivariate model, the factors associated with longer delay to VEM included more past antiseizure medications (0.19 log-years/medication, standard error (SE) 0.05), more medications for other medical conditions (0.06 log-years/medication, SE 0.03), history of physical abuse (0.75 log-years, SE 0.27), and more seizure types (0.36 log-years/type, SE 0.11). Factors associated with shorter delay included active employment or student status (-1.05 log-years, SE 0.21) and higher seizure frequency (0.14 log-years/log[seizure/month], SE 0.06).

CONCLUSIONS

Patients with greater medical and seizure complexity had longer delays. Delays in multiple domains of healthcare can be common for victims of physical abuse. Unemployed and non-student patients may have had more barriers to access VEM. These results support earlier referral of complex cases to a comprehensive epilepsy center.

DDESVSFS: A simple, rapid and comprehensive screening tool for the Differential Diagnosis of Epileptic Seizures VS Functional Seizures

OBJECTIVE

Functional seizures (FS) are often misclassified as epileptic seizures (ES). This study aimed to create an easy to use but comprehensive screening tool to guide further evaluation of patients presenting with this diagnostic dilemma.

MATERIALS AND METHODS

Demographic, clinical and diagnostic data were collected on patients admitted for video-EEG monitoring for clarification of their diagnosis. Upon discharge, patients were classified as having ES vs FS. Using the collected characteristics and video-EEG diagnosis, we created a multivariable logistic regression model to identify predictors of ES. Then, we trained an integer-coefficient model with the most frequently selected predictors, creating a pointing system coined DDESVSFS, with scores ranging from -17 to +8 points.

RESULTS

43 patients with FS and 165 patients with ES were recruited. In the final integer-coefficient model, 8 predictors were identified as significant in differentiating ES from FS: normal electroencephalogram (-3 points), predisposing factors for FS (-3 points), increased number of comorbidities (-3 points), semiology suggestive of FS (-4 points), increased seizure frequency (-4 points), longer disease duration (+3 points), antiepileptic polypharmacy (+2 points) and compliance with antiepileptic drugs (+3 points). Cumulative scores of ≤ -9 points carried <5% predictive value for ES, while cumulative scores of ≥ -1 points carried >95% predictive value. The model performed well (AUC: 0.923, sensitivity: 0.945, specificity: 0.698).

CONCLUSIONS

We propose DDESVSFS as a simple, rapid and comprehensive prediction score for the Differential Diagnosis of Epileptic Seizures VS Functional Seizures. Large prospective studies are needed to evaluate its utility in clinical practice.

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.