Deep active learning for interictal ictal injury continuum EEG patterns

Ge, Wendong; Jin, Jing; An, Sungtae; Herlopian, Aline; Ng, Marcus; Struck, Aaron F.; Appavu, Brian; Johnson, Emily L.; Osman, Gamaleldin; Haider, Hiba A.; Karakis, Ioannis; Kim, Jennifer A; Halford, Jonathan J.; Dhakar, Monica B.; Sarkis, Rani A.; Swisher, Christa B.; Schmitt, Sarah; Lee, Jong Woo; Tabaeizadeh, Mohammad; Rodríguez, Andrés; Gaspard, Nicolas; Gilmore, Emily; Herman, Susan T.; Kaplan, Peter W.; Pathmanathan, Jay; Hong, Shenda; Rosenthal, Eric S.; Zafar, Sahar F.; Sun, Jimeng; Westover, M. Brandon

doi:10.1016/j.jneumeth.2020.108966

Cited by 12 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We applied change point detection (CPD) with conservative settings on the total power to divide cEEG data into homogeneous segments, that is, segments in which the EEG patterns remain constant. We then used an unsupervised affinity propagation plus bag‐of‐words–based model to cluster CPD‐segmented cEEG data from each patient into 30 to 50 clusters 15,16 Rapid manual cEEG annotation.…”

Section: Methodsmentioning

confidence: 99%

“…Rather, clustering was an intermediate step used as part of the process of gathering the labeled samples that were used to train the model in the final step, described next. Automated final annotation. Finally, using the labels created in the prior step, we trained a convolutional neural network, and used this to label all EEG segments in the 2,000 EEG recordings consistently, at a resolution of one annotation per 2 seconds 16 Calculation of EA burden.…”

Section: Methodsmentioning

confidence: 99%

“…The cEEG data were then divided into 2‐second nonoverlapping segments. We then extracted several features in the spectral and time domains (eg, line length, kurtosis, entropy), as previously described 16 . To obtain information from the surrounding EEG, we also extracted these features in windows of 6, 10, and 14 seconds centered on each 2‐second segment.…”

Section: Methodsmentioning

confidence: 99%

“…We then extracted several features in the spectral and time domains (eg, line length, kurtosis, entropy), as previously described. 16 To obtain information from the surrounding EEG, we also extracted these features in windows of 6, 10, and 14 seconds centered on each 2-second segment. The scalp spatial representation included 4 regions (left lateral, right lateral, left parasagittal, and right parasagittal).…”

Section: Automated Annotation and Quantification Of Ea Burdenmentioning

confidence: 99%

See 3 more Smart Citations

Automated Annotation of Epileptiform Burden and Its Association with Outcomes

Zafar

Rosenthal

Jin

et al. 2021

Annals of Neurology

Self Cite

View full text Add to dashboard Cite

This study was undertaken to determine the dose-response relation between epileptiform activity burden and outcomes in acutely ill patients. Methods: A single center retrospective analysis was made of 1,967 neurologic, medical, and surgical patients who underwent >16 hours of continuous electroencephalography (EEG) between 2011 and 2017. We developed an artificial intelligence algorithm to annotate 11.02 terabytes of EEG and quantify epileptiform activity burden within 72 hours of recording. We evaluated burden (1) in the first 24 hours of recording, (2) in the 12-hours epoch with highest burden (peak burden), and (3) cumulatively through the first 72 hours of monitoring. Machine learning was applied to estimate the effect of epileptiform burden on outcome. Outcome measure was discharge modified Rankin Scale, dichotomized as good (0-4) versus poor (5-6). Results: Peak epileptiform burden was independently associated with poor outcomes (p < 0.0001). Other independent associations included age, Acute Physiology and Chronic Health Evaluation II score, seizure on presentation, and diagnosis of hypoxic-ischemic encephalopathy. Model calibration error was calculated across 3 strata based on the time interval between last EEG measurement (up to 72 hours of monitoring) and discharge: (1) <5 days between last measurement and discharge, 0.0941 (95% confidence interval [CI] = 0.0706-0.1191); 5 to 10 days between last measurement and discharge, 0.0946 (95% CI = 0.0631-0.1290); >10 days between last measurement and discharge, 0.0998 (95% CI = 0.0698-0.1335). After adjusting for covariates, increase in peak epileptiform activity burden from 0 to 100% increased the probability of poor outcome by 35%. Interpretation: Automated measurement of peak epileptiform activity burden affords a convenient, consistent, and quantifiable target for future multicenter randomized trials investigating whether suppressing epileptiform activity improves outcomes.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Automated Annotation and Quantification Of Ea Burdenmentioning

confidence: 99%

See 2 more Smart Citations

Automated Annotation of Epileptiform Burden and Its Association with Outcomes

Zafar

Rosenthal

Jin

et al. 2021

Annals of Neurology

Self Cite

View full text Add to dashboard Cite

show abstract

“…To do this, we need to first identify segments of the EEG signal containing seizure-like EA behavior. Doing this using human annotators would be extremely time consuming, so we use a convolutional neural network (CNN) trained on human annotators' classifications of 10 second windows into non-EA and EA in a semi-supervised fashion (Ge et al, 2021b;Zafar et al, 2021;Jing et al, 2016). We use the predictions to compute EA time series (Z ω t ).…”

Section: Methodsmentioning

confidence: 99%

Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It

Parikh¹,

Hoffman²,

Sun³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Many fundamental problems affecting the care of critically ill patients lead to similar analytical challenges: physicians cannot easily estimate the effects of at-risk medical conditions or treatments (which is problematic for treatment decisions) because the causal effects of medical conditions and drugs are entangled. They also cannot easily perform studies: there are not enough critically ill patients for high-dimensional observational causal inference analysis, and randomized controlled trials often cannot ethically be conducted. However, mechanistic knowledge is available, including how drugs are absorbed into the body, and the combination of this knowledge with the limited data could potentially suffice -if we knew how to combine them. In this work, we present a framework for interpretable estimation of causal effects for critically ill patients under exactly these complex conditions: interactions between drugs and observations over time, patient data sets that are not large, and mechanistic knowledge that can substitute for lack of data. Our framework incorporates pharmacokinetics and pharmacodynamics with interpretable matching methods to adjust for confounders such as patients' drug response, medical history, and demographic variables. We apply this framework to an extremely important problem affecting critically ill patients, namely the effect of seizures and other potentially harmful electrical events in the brain (called epileptiform activity -EA) on outcomes. EA is a key indicator of whether the patient will suffer long term severe

show abstract

How many patients do you need? Investigating trial designs for anti‐seizure treatment in acute brain injury patients

Parikh,

Sun,

Amerineni

et al. 2024

Ann Clin Transl Neurol

Self Cite

View full text Add to dashboard Cite

Background/objectivesEpileptiform activity (EA), including seizures and periodic patterns, worsens outcomes in patients with acute brain injuries (e.g., aneurysmal subarachnoid hemorrhage [aSAH]). Randomized control trials (RCTs) assessing anti‐seizure interventions are needed. Due to scant drug efficacy data and ethical reservations with placebo utilization, and complex physiology of acute brain injury, RCTs are lacking or hindered by design constraints. We used a pharmacological model‐guided simulator to design and determine the feasibility of RCTs evaluating EA treatment.MethodsIn a single‐center cohort of adults (age >18) with aSAH and EA, we employed a mechanistic pharmacokinetic‐pharmacodynamic framework to model treatment response using observational data. We subsequently simulated RCTs for levetiracetam and propofol, each with three treatment arms mirroring clinical practice and an additional placebo arm. Using our framework, we simulated EA trajectories across treatment arms. We predicted discharge modified Rankin Scale as a function of baseline covariates, EA burden, and drug doses using a double machine learning model learned from observational data. Differences in outcomes across arms were used to estimate the required sample size.ResultsSample sizes ranged from 500 for levetiracetam 7 mg/kg versus placebo, to >4000 for levetiracetam 15 versus 7 mg/kg to achieve 80% power (5% type I error). For propofol 1 mg/kg/h versus placebo, 1200 participants were needed. Simulations comparing propofol at varying doses did not reach 80% power even at samples >1200.ConclusionsOur simulations using drug efficacy show sample sizes are infeasible, even for potentially unethical placebo‐control trials. We highlight the strength of simulations with observational data to inform the null hypotheses and propose use of this simulation‐based RCT paradigm to assess the feasibility of future trials of anti‐seizure treatment in acute brain injury.

show abstract

Deep active learning for interictal ictal injury continuum EEG patterns

Cited by 12 publications

References 15 publications

Automated Annotation of Epileptiform Burden and Its Association with Outcomes

Automated Annotation of Epileptiform Burden and Its Association with Outcomes

Why Interpretable Causal Inference is Important for High-Stakes Decision Making for Critically Ill Patients and How To Do It

How many patients do you need? Investigating trial designs for anti‐seizure treatment in acute brain injury patients

Contact Info

Product

Resources

About