Association of comorbid-socioeconomic clusters with mortality in late onset epilepsy derived through unsupervised machine learning.

BACKGROUND AND OBJECTIVES: Late-onset epilepsy is a heterogenous entity associated with specific aetiologies and an elevated risk of premature mortality. Specific multimorbid-socioeconomic profiles and their unique prognostic trajectories have not been described. We sought to determine if specific clusters of late onset epilepsy exist, and whether they have unique hazards of premature mortality. METHODS: We performed a retrospective observational cohort study linking primary and hospital-based UK electronic health records with vital statistics data (covering years 1998-2019) to identify all cases of incident late onset epilepsy (from people aged ≥65) and 1:10 age, sex, and GP practice-matched controls. We applied hierarchical agglomerative clustering using common aetiologies identified at baseline to define multimorbid-socioeconomic profiles, compare hazards of early mortality, and tabulating causes of death stratified by cluster. RESULTS: From 1,032,129 people aged ≥65, we identified 1048 cases of late onset epilepsy who were matched to 10,259 controls. Median age at epilepsy diagnosis was 68 (interquartile range: 66-72) and 474 (45%) were female. The hazard of premature mortality related to late-onset epilepsy was higher than matched controls (hazard ratio [HR] 1.73; 95% confidence interval [95%CI] 1.51-1.99). Ten unique phenotypic clusters were identified, defined by 'healthy' males and females, ischaemic stroke, intracerebral haemorrhage (ICH), ICH and alcohol misuse, dementia and anxiety, anxiety, depression in males and females, and brain tumours. Cluster-specific hazards were often similar to that derived for late-onset epilepsy as a whole. Clusters that differed significantly from the base late-onset epilepsy hazard were 'dementia and anxiety' (HR 5.36; 95%CI 3.31-8.68), 'brain tumour' (HR 4.97; 95%CI 2.89-8.56), 'ICH and alcohol misuse' (HR 2.91; 95%CI 1.76-4.81), and 'ischaemic stroke' (HR 2.83; 95%CI 1.83-4.04). These cluster-specific risks were also elevated compared to those derived for tumours, dementia, ischaemic stroke, and ICH in the whole population. Seizure-related cause of death was uncommon and restricted to the ICH, ICH and alcohol misuse, and healthy female clusters. SIGNIFICANCE: Late-onset epilepsy is an amalgam of unique phenotypic clusters that can be quantitatively defined. Late-onset epilepsy and cluster-specific comorbid profiles have complex effects on premature mortality above and beyond the base rates attributed to epilepsy and cluster-defining comorbidities alone.

Adult onset epilepsy is defined by phenotypic clusters with unique comorbidities and risks of death.

OBJECTIVE: This study was undertaken to identify clusters of adult onset epilepsy with distinct comorbidities and risks of early and late death. METHODS: This was a retrospective open cohort study that included all adults meeting a case definition for epilepsy after the Acceptable Mortality Recording date in the Health Improvement Network database for the years 2000-2012 inclusive. Unsupervised agglomerative hierarchical clustering was performed to identify unique clusters of patients based on their predicted risk of early (<4 years of epilepsy diagnosis) and late (≥4 years from diagnosis) mortality and patient-level clinical characteristics. RESULTS: We identified 10 499 presumed incident cases of epilepsy from 11 194 182 patients. Four phenotypic clusters were identified in the early and late risk periods. Early clusters include older adults with cardiovascular disease and a high risk of death (median predicted risk = 20%, interquartile range [IQR] = 9%-31%), a group with moderate risk of death and cancer (median predicted risk = 6%, IQR = 2%-15%), a group with psychiatric disease/substance use and few somatic comorbidities (median predicted risk = 5%, IQR = 2%-9%), and one with a younger age at onset and few comorbidities (median predicted risk = 4%, IQR = 1%-11%). There was minimal movement of individuals between clusters for those surviving the early risk period. Age- and sex-standardized 3-year mortality ratios were more than sixfold higher than the general population for every cluster, even those primarily comprised of healthy younger adults. SIGNIFICANCE: Adult onset epilepsy is marked by unique clusters of comorbid conditions and elevated risks of death that form discrete populations for targeted therapeutic interventions. These clusters remain relatively stable between the early and late mortality risk periods. Of particular interest are the clusters marked by young and otherwise healthy adults whose standardized mortality ratio is sixfold higher than general population despite few conventional risk factors for premature death.

Predicting postoperative epilepsy surgery satisfaction in adults using the 19-item Epilepsy Surgery Satisfaction Questionnaire and machine learning.

OBJECTIVE: The 19-item Epilepsy Surgery Satisfaction Questionnaire (ESSQ-19) is a validated and reliable post hoc means of assessing patient satisfaction with epilepsy surgery. Prediction models building on these data can be used to counsel patients. METHODS: The ESSQ-19 was derived and validated on 229 patients recruited from Canada and Sweden. We isolated 201 (88%) patients with complete clinical data for this analysis. These patients were adults (≥18 years old) who underwent epilepsy surgery 1 year or more prior to answering the questionnaire. We extracted each patient's ESSQ-19 score (scale is 0-100; 100 represents complete satisfaction) and relevant clinical variables that were standardized prior to the analysis. We used machine learning (linear kernel support vector regression [SVR]) to predict satisfaction and assessed performance using the R2 calculated following threefold cross-validation. Model parameters were ranked to infer the importance of each clinical variable to overall satisfaction with epilepsy surgery. RESULTS: Median age was 41 years (interquartile range [IQR] = 32-53), and 116 (57%) were female. Median ESSQ-19 global score was 68 (IQR = 59-75), and median time from surgery was 5.4 years (IQR = 2.0-8.9). Linear kernel SVR performed well following threefold cross-validation, with an R2 of .44 (95% confidence interval = .36-.52). Increasing satisfaction was associated with postoperative self-perceived quality of life, seizure freedom, and reductions in antiseizure medications. Self-perceived epilepsy disability, age, and increasing frequency of seizures that impair awareness were associated with reduced satisfaction. SIGNIFICANCE: Machine learning applied postoperatively to the ESSQ-19 can be used to predict surgical satisfaction. This algorithm, once externally validated, can be used in clinical settings by fixing immutable clinical characteristics and adjusting hypothesized postoperative variables, to counsel patients at an individual level on how satisfied they will be with differing surgical outcomes.

Primary care electronic medical records can be used to predict risk and identify potentially modifiable factors for early and late death in adult onset epilepsy.

OBJECTIVE: To use clinically informed machine learning to derive prediction models for early and late premature death in epilepsy. METHODS: This was a population-based primary care observational cohort study. All patients meeting a case definition for incident epilepsy in the Health Improvement Network database for inclusive years 2000-2012 were included. A modified Delphi process identified 30 potential risk factors. Outcome was early (within 4 years of epilepsy diagnosis) and late (4 years or more from diagnosis) mortality. We used regularized logistic regression, support vector machines, Gaussian naive Bayes, and random forest classifiers to predict outcomes. We assessed model calibration, discrimination, and generalizability using the Brier score, mean area under the receiver operating characteristic curve (AUC) derived from stratified fivefold cross-validation, plotted calibration curves, and extracted measures of association where possible. RESULTS: We identified 10 499 presumed incident cases from 11 194 182 patients. All models performed comparably well following stratified fivefold cross-validation, with AUCs ranging from 0.73 to 0.81 and from 0.71 to 0.79 for early and late death, respectively. In addition to comorbid disease, social habits (alcoholism odds ratio [OR] for early death = 1.54, 95% confidence interval [CI] = 1.12-2.11 and OR for late death = 2.62, 95% CI = 1.66-4.16) and treatment patterns (OR for early death when no antiseizure medication [ASM] was prescribed at baseline = 1.33, 95% CI = 1.07-1.64 and OR for late death after receipt of enzyme-inducing ASM at baseline = 1.32, 95% CI = 1.04-1.66) were significantly associated with increased risk of premature death. Baseline ASM polytherapy (OR = 0.55, 95% CI = 0.36-0.85) was associated with reduced risk of early death. SIGNIFICANCE: Clinically informed models using routine electronic medical records can be used to predict early and late mortality in epilepsy, with moderate to high accuracy and evidence of generalizability. Medical, social, and treatment-related risk factors, such as delayed ASM prescription and baseline prescription of enzyme-inducing ASMs, were important predictors.