Psychogenic nonepileptic seizures in patients with surgically treated temporal lobe epilepsy: Presurgical and de novo postsurgical occurrence

Supervised machine learning compared to large language models for identifying functional seizures from medical records

OBJECTIVE

The Functional Seizures Likelihood Score (FSLS) is a supervised machine learning-based diagnostic score that was developed to differentiate functional seizures (FS) from epileptic seizures (ES). In contrast to this targeted approach, large language models (LLMs) can identify patterns in data for which they were not specifically trained. To evaluate the relative benefits of each approach, we compared the diagnostic performance of the FSLS to two LLMs: ChatGPT and GPT-4.

METHODS

In total, 114 anonymized cases were constructed based on patients with documented FS, ES, mixed ES and FS, or physiologic seizure-like events (PSLEs). Text-based data were presented in three sequential prompts to the LLMs, showing the history of present illness (HPI), electroencephalography (EEG) results, and neuroimaging results. We compared the accuracy (number of correct predictions/number of cases) and area under the receiver-operating characteristic (ROC) curves (AUCs) of the LLMs to the FSLS using mixed-effects logistic regression.

RESULTS

The accuracy of FSLS was 74% (95% confidence interval [CI] 65%-82%) and the AUC was 85% (95% CI 77%-92%). GPT-4 was superior to both the FSLS and ChatGPT (p <.001), with an accuracy of 85% (95% CI 77%-91%) and AUC of 87% (95% CI 79%-95%). Cohen's kappa between the FSLS and GPT-4 was 40% (fair). The LLMs provided different predictions on different days when the same note was provided for 33% of patients, and the LLM's self-rated certainty was moderately correlated with this observed variability (Spearman's rho2: 30% [fair, ChatGPT] and 63% [substantial, GPT-4]).

SIGNIFICANCE

Both GPT-4 and the FSLS identified a substantial subset of patients with FS based on clinical history. The fair agreement in predictions highlights that the LLMs identified patients differently from the structured score. The inconsistency of the LLMs' predictions across days and incomplete insight into their own consistency was concerning. This comparison highlights both benefits and cautions about how machine learning and artificial intelligence could identify patients with FS in clinical practice.

New-onset psychogenic nonepileptic seizures after intracranial neurosurgery: A meta-analysis

BACKGROUND

The epidemiology of psychogenic non-epileptic seizures (PNES) is still unclear. Although approximately 14 million people need neurosurgical care annually, there is a dearth of thorough analysis on PNES occurrence following surgery. This study seeks to estimate the proportion of newly diagnosed PNES.

METHODS

We conducted a literature search of the PubMed, Ovid, CINAHL, and Cochrane Library databases up to December 2023. We identified studies using an observational design on the occurrence of PNES in patients who underwent intracranial surgery, and confirmed diagnosis using video-EEG. Estimates are reported as proportions using random effects models. We reported both 95 % CIs and prediction intervals (PI). We assessed the risk of bias and identified the pooled odds ratio (OR) for mutually exclusive groups. The heterogeneity was investigated using the I² statistic and significance determined using Cochran's Q-test. Post-hoc Egger's regression test, and several sensitivity analyses were performed. This study was registered in PROSPERO (CRD42023488611).

RESULTS

Of the 1766 unique studies identified, 86 were selected for full-text review. Eight studies (n = 3,699) were eligible for inclusion. Studies, spanning from 1995 to 2017, primarily focused on epilepsy surgeries. The pooled proportion was 3 % (95 % CI 2 %-5 %; 95 % PI 0 %-11 %). Temporal resections indicated twofold increase of PNES comparing to either resections (OR 2.05, 95 %CI 0.81-5.19). The risk of bias assessment indicated satisfactory quality for included studies, and heterogeneity in estimates was mainly explained by publication year of studies and their rounded sample size.

CONCLUSIONS

Given the estimations, there is expected impact of intracranial procedures on functional seizures epidemiology. Further efforts need to understand the contribution of brain resections to PNES incidence.

Psychogenic non-epileptic seizures (PNES) in the context of concurrent epilepsy – making the right diagnosis

Epilepsy is a risk factor for the development of psychogenic non-epileptic seizures (PNES) and comorbid epilepsy is recognized as a comorbidity in about 10–30% of patients with PNES. The combination of epileptic and nonepileptic seizures poses a particular diagnostic challenge. In patients with epilepsy, additional PNES may be suspected on the basis of their typical semiology. The possibility of additional PNES should also be considered if seizures fail to respond to antiepileptic drug treatment, in patients with frequent emergency admissions with seizures and in those who develop new types of seizures. The description of semiological details by patients and witnesses can suggest additional PNES. Home video recordings can support an initial diagnosis, however, especially in patients with mixed seizure disorders it is advisable to seek further diagnostic confirmation by capturing all habitual seizure types with video-EEG. The clinical features of PNES associated with epilepsy are similar to those in isolated PNES disorders and include longer duration, fluctuating course, asynchronous movements, pelvic thrusting, side-to-side head or body movement, persistently closed eyes and mouth, ictal crying, recall of ictal experiences and absence of postictal confusion. PNES can also present as syncope-like episodes with unresponsiveness and reduced muscle tone. There is no unique epileptological or brain pathology profile putting patients with epilepsy at risk of additional PNES. However, patients with epilepsy and PNES typically have lower educational achievements and higher levels of psychiatric comorbidities than patients with epilepsy alone. Psychological trauma, including sexual abuse, appears to be a less relevant aetiological factor in patients with mixed seizure disorders than those with isolated PNES, and the gender imbalance (i.e. the greater prevalence in women) is less marked in patients with PNES and additional epilepsy than those with PNES alone. PNES sometimes develop after epilepsy surgery. A diagnosis of ‘known epilepsy’ should never be accepted without (at least brief) critical review. This narrative review summarises clinical, electrophysiological and historical features that can help identify patients with epilepsy and additional PNES.

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.

A European questionnaire survey on epilepsy monitoring units' current practice for postoperative psychogenic nonepileptic seizures' detection

BACKGROUND

In cases undergoing epilepsy surgery, postoperative psychogenic nonepileptic seizures (PNES) may be underdiagnosed complicating the assessment of postsurgical seizures' outcome and the clinical management. We conducted a survey to investigate the current practices in the European epilepsy monitoring units (EMUs) and the data that EMUs could provide to retrospectively detect cases with postoperative PNES and to assess the feasibility of a subsequent postoperative PNES research project for cases with postoperative PNES.

METHODS

We developed and distributed a questionnaire survey to 57 EMUs. Questions addressed the number of patients undergoing epilepsy surgery, the performance of systematic preoperative and postoperative psychiatric evaluation, the recording of sexual or other abuse, the follow-up period of patients undergoing epilepsy surgery, the performance of video-electroencephalogram (EEG) and postoperative psychiatric assessment in suspected postoperative cases with PNES, the existence of electronic databases to allow extraction of cases with postoperative PNES, the data that these bases could provide, and EMUs' interest to participate in a retrospective postoperative PNES project.

RESULTS

Twenty EMUs completed the questionnaire sheet. The number of patients operated every year/per center is 26.7 ( ± 19.1), and systematic preoperative and postoperative psychiatric evaluation is performed in 75% and 50% of the EMUs accordingly. Sexual or other abuse is systematically recorded in one-third of the centers, and the mean follow-up period after epilepsy surgery is 10.5 ± 7.5 years. In suspected postoperative PNES, video-EEG is performed in 85% and psychiatric assessment in 95% of the centers. An electronic database to allow extraction of patients with PNES after epilepsy surgery is used in 75% of the EMUs, and all EMUs that sent the sheet completed expressed their interest to participate in a retrospective postoperative PNES project.

CONCLUSION

Postoperative PNES is an underestimated and not well-studied entity. This is a European survey to assess the type of data that the EMUs surgical cohorts could provide to retrospectively detect postoperative PNES. In cases with suspected PNES, most EMUs perform video-EEG and psychiatric assessment, and most EMUs use an electronic database to allow extraction of patients developing PNES.

Welfare consequences for people diagnosed with nonepileptic seizures: A matched nationwide study in Denmark

OBJECTIVE

We aimed to evaluate the excess direct and indirect costs associated with nonepileptic seizures.

METHODS

From the Danish National Patient Registry (2011-2016), we identified 1057 people of any age with a diagnosis of psychogenic nonepileptic seizures (PNESs) and matched them with 2113 control individuals. Additionally, 239 partners of patients with PNES aged ≥18 years were identified and compared with 471 control partners. Direct costs included frequencies and costs of hospitalizations and outpatient use weighted by diagnosis-related group, and specific outpatient costs based on data from the Danish Ministry of Health. The use and costs of drugs were based on data from the Danish Medicines Agency. The frequencies of visits and hospitalizations and costs of general practice were derived from National Health Security data. Indirect costs included labor supply-based income data, and all social transfer payments were obtained from Coherent Social Statistics.

RESULTS

A higher percentage of people with PNES and their partners compared with respective control subjects received welfare benefits (sick pay, disability pension, home care). Those with PNES had a lower employment rate than did controls for equivalent periods up to three years before the diagnosis was made. The additional direct and indirect annual costs for those aged ≥18 years, including transfers to patients with PNES, compared with controls, were €33,697 for people with PNES and €15,121 for their partners.

SIGNIFICANCE

Psychogenic nonepileptic seizures have substantial socioeconomic consequences for individual patients, their partners, and society.

Are psychogenic nonepileptic seizures risk factors for a worse outcome in patients with refractory mesial temporal epilepsy submitted to surgery? Results of a retrospective cohort study

OBJECTIVE

The objective of this study was to verify if the presence of psychogenic nonepileptic seizures (PNES) could be a risk factor precluding corticoamygdalohippocampectomy (CAH) in patients with refractory temporal lobe epilepsy (TLE) and mesial temporal sclerosis (MTS) (TLE-MTS).

METHODS

This retrospective cohort study analyzed medical data of patients with refractory TLE-MTS accompanied in a Brazilian epilepsy surgery center. Presurgical psychiatric evaluations were performed using the Diagnostic and Statistical Manual of Mental Disorders (DSM-5) criteria. Engel's I classification two years after surgery was considered as a favorable outcome.

RESULTS

Of the 81 patients initially included (65 females; 56.5%), 49 (60.5%) had TLE-MTS without PNES, 24 (29.7%) with TLE-MTS and PNES, and eight (9.8%) with PNES only, who were excluded from further statistical comparisons. Nine patients with PNES (37.5%) underwent CAH versus 35 (71.4%) without PNES (p = 0.005). Five patients (55.5%) with PNES versus 26 (74.3%) without PNES presented Engel I (p = 0.54). The relative risk (RR) was of 1.90 for patients without PNES to undergo CAH and of 1.33 to be at Engel I.

CONCLUSIONS

In this study, PNES were associated with less CAH. There were no differences, however, regarding favorable postsurgical outcomes. These results highlight that the sole presence of PNES should not preclude CAH in patients with TLE-MTS, despite the necessity of careful presurgical psychiatric evaluation.