Why the study?
To compare machine learning methods for predicting inpatient seizure risk and evaluate the feasibility of a 1-h screening EEG to identify low-risk patients.
Do machine learning models accurately predict inpatient seizure risk using a 1-h screening EEG in hospitalized patients?
Observational (n=7,716)
Yes
Do machine learning models accurately predict inpatient seizure risk using a 1-h screening EEG in hospitalized patients?
Absolute Event Rate: 0.83% vs 0.85%
p-value: p=<0.001
The 2HELPS2B model accurately identifies hospitalized patients at low risk for seizures using only a 1-hour screening EEG, performing comparably to more complex machine learning models.
OBJECTIVE: To compare machine learning methods for predicting inpatient seizures risk and determine the feasibility of 1-h screening EEG to identify low-risk patients (<5% seizures risk in 48 h). METHODS: The Critical Care EEG Monitoring Research Consortium (CCEMRC) multicenter database contains 7716 continuous EEGs (cEEG). Neural networks (NN), elastic net logistic regression (EN), and sparse linear integer model (RiskSLIM) were trained to predict seizures. RiskSLIM was used previously to generate 2HELPS2B model of seizure predictions. Data were divided into training (60% for model fitting) and evaluation (40% for model evaluation) cohorts. Performance was measured using area under the receiver operating curve (AUC), mean risk calibration (CAL), and negative predictive value (NPV). A secondary analysis was performed using Monte Carlo simulation (MCS) to normalize all EEG recordings to 48 h and use only the first hour of EEG as a "screening EEG" to generate predictions. RESULTS: RiskSLIM recreated the 2HELPS2B model. All models had comparable AUC: evaluation cohort (NN: 0.85, EN: 0.84, 2HELPS2B: 0.83) and MCS (NN: 0.82, EN; 0.82, 2HELPS2B: 0.81) and NPV (absence of seizures in the group that the models predicted to be low risk): evaluation cohort (NN: 97%, EN: 97%, 2HELPS2B: 97%) and MCS (NN: 97%, EN: 99%, 2HELPS2B: 97%). 2HELPS2B model was able to identify the largest proportion of low-risk patients. INTERPRETATION: For seizure risk stratification of hospitalized patients, the RiskSLIM generated 2HELPS2B model compares favorably to the complex NN and EN generated models. 2HELPS2B is able to accurately and quickly identify low-risk patients with only a 1-h screening EEG.
No takes yet. Share an insight, caveat, or question.
Struck et al. (2019) conducted an observational in Hospitalized patients undergoing continuous EEG monitoring (n=7,716). 2HELPS2B model vs. Neural network and elastic net logistic regression models was evaluated on Area under the receiver operating curve (AUC) for seizure prediction in the evaluation cohort (95% CI 0.81-0.85, p=<0.001).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: