Epilepsy surgery for children and adolescents: evidence-based but underused

Cross, J. Helen; Reilly, Colin; Delicado, Eva Gutierrez; Smith, Mary Lou; Malmgren, Kristina

doi:10.1016/s2352-4642(22)00098-0

Cited by 28 publications

(24 citation statements)

References 101 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Presurgical evaluation is largely standardized in that all patients undergo a full clinical history, structural MRI, and scalp- or video-EEG, but the extent of further investigations will be patient dependent. 44 To mitigate the occurrence of bias, we used a minimal dataset, which included only clinical variables typically obtained for all epilepsy surgery patients. As such, we did not train our model using positron emission tomography (PET), single-photon emission computed tomography (SPECT), magnetoencephalography (MEG), or functional MRI (fMRI) measures.…”

Section: Discussionmentioning

confidence: 99%

Predicting seizure outcome after epilepsy surgery: do we need more complex models, larger samples, or better data?

Eriksson

Ripart

Piper

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: The accurate prediction of seizure freedom after epilepsy surgery remains challenging. We investigated if 1) training more complex models, 2) recruiting larger sample sizes, or 3) using data-driven selection of clinical predictors would improve our ability to predict post-operative seizure outcome. We also conducted the first external validation of a machine learning model trained to predict post-operative seizure outcome. Methods: We performed a retrospective cohort study of 797 children who had undergone resective or disconnective epilepsy surgery at a single tertiary center. We extracted patient information from medical records and trained three models - a logistic regression, a multilayer perceptron, and an XGBoost model - to predict one-year post-operative seizure outcome on our dataset. We evaluated the performance of a recently published XGBoost model on the same patients. We further investigated the impact of sample size on model performance, using learning curve analysis to estimate performance at samples up to N=2,000. Finally, we examined the impact of predictor selection on model performance. Results: Our logistic regression achieved an accuracy of 72% (95% CI=68-75%, AUC=0.72), while our multilayer perceptron and XGBoost both achieved accuracies of 71% (95% CI-MLP=67-74%, AUC-MLP=0.70; 95% CI-XGBoost own=68-75%, AUC-XGBoost own=0.70). There was no significant difference in performance between our three models (all P>0.4) and they all performed better than the external XGBoost, which achieved an accuracy of 63% (95% CI=59-67%, AUC=0.62; P-LR=0.005, P-MLP=0.01, P-XGBoost own=0.01) on our data. All models showed improved performance with increasing sample size, with limited improvements above N=400. The best model performance was achieved with data-driven feature selection. Significance: We show that neither the deployment of complex machine learning models nor the assembly of thousands of patients alone is likely to generate significant improvements in our ability to predict post-operative seizure freedom. We instead propose that improved feature selection alongside collaboration, data standardization, and model sharing is required to advance the field.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting seizure outcome after epilepsy surgery: do we need more complex models, larger samples, or better data?

Eriksson

Ripart

Piper

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Just as for adults, epilepsy surgery can be effective for children, 41 and seizure‐free outcomes have gradually improved over several decades 42 . The set of variables influencing surgical outcomes in children differs from adults, primarily because children's neuro‐ and psychodevelopmental trajectories are still evolving.…”

Section: Enhancing Outcomes In the Pediatric Contextmentioning

confidence: 99%

Life following epilepsy surgery: Building a holistic framework for enhancing postsurgical recovery and rehabilitation

et al. 2023

View full text Add to dashboard Cite

“…1 Despite a randomized clinical trial in pediatric epilepsy proving efficacy; epilepsy surgery in pediatric drug-resistant epilepsy is underutilized. 2 -4 One of the barriers to epilepsy surgery utilization includes patient as well as physician knowledge gap/s. Data on ASM reduction as a surrogate for epilepsy surgery success is not widely published. Background …”

Section: Commentarymentioning

confidence: 99%

What Are the Chances That Epilepsy Surgery Will Allow My Child to Come Off Meds? Assessing Pediatric Epilepsy Surgery Outcomes: Data on ASM Freedom

Joshi

2022

Epilepsy Curr

View full text Add to dashboard Cite

show abstract

Epilepsy surgery for children and adolescents: evidence-based but underused

Cited by 28 publications

References 101 publications

Predicting seizure outcome after epilepsy surgery: do we need more complex models, larger samples, or better data?

Predicting seizure outcome after epilepsy surgery: do we need more complex models, larger samples, or better data?

Life following epilepsy surgery: Building a holistic framework for enhancing postsurgical recovery and rehabilitation

What Are the Chances That Epilepsy Surgery Will Allow My Child to Come Off Meds? Assessing Pediatric Epilepsy Surgery Outcomes: Data on ASM Freedom

Contact Info

Product

Resources

About