1. Usage of EpiFinder clinical decision support in the assessment of epilepsy
- Author
-
Amy Z. Crepeau, Lidia Csernak, Joseph I Sirven, Neel Mehta, Robert Yao, Matthew T. Hoerth, Erin M. Okazaki, Katherine H. Noe, Joseph F. Drazkowski, and Edgar Salinas
- Subjects
Adult ,Male ,Pediatrics ,medicine.medical_specialty ,Adult population ,Sensitivity and Specificity ,Clinical decision support system ,Diagnosis, Differential ,03 medical and health sciences ,Behavioral Neuroscience ,Epilepsy ,0302 clinical medicine ,medicine ,Screening method ,Humans ,Prospective Studies ,030212 general & internal medicine ,Medical diagnosis ,Monitoring, Physiologic ,business.industry ,Electroencephalography ,Usability ,Middle Aged ,Decision Support Systems, Clinical ,medicine.disease ,Confidence interval ,Neurology ,Epilepsy syndromes ,Female ,Neurology (clinical) ,business ,Algorithms ,030217 neurology & neurosurgery - Abstract
Background The diagnosis of epilepsy is at times elusive for both neurologists and nonneurologists, resulting in delays in diagnosis and therapy. The development of screening methods has been identified as a priority in response to this diagnostic and therapeutic gap. EpiFinder is a novel clinical decision support tool designed to enhance the process of information gathering and integration of patient/proxy respondent data. It is designed specifically to take key terms from a patient's history and incorporate them into a heuristic algorithm that dynamically produces differential diagnoses of epilepsy syndromes. Objective The objective of this study was to test the usability and diagnostic accuracy of the clinical decision support application EpiFinder in an adult population. Methods Fifty-seven patients were prospectively identified upon admission to the Epilepsy Monitoring Unit (EMU) for episode classification from January through June of 2017. Based on semiologic input, the application generates a list of epilepsy syndromes. The EpiFinder-generated diagnosis for each subject was compared to the final diagnosis obtained via continuous video electroencephalogram (cVEEG) monitoring. Results Fifty-three patients had habitual events recorded during their EMU stay. A diagnosis of epilepsy was confirmed (with cVEEG monitoring) in 26 patients while 27 patients were found to have a diagnosis other than epilepsy. The algorithm appropriately predicted differentiation between the presence of an epilepsy syndrome and an alternative diagnosis with 86.8% (46/53 participants) accuracy. EpiFinder correctly identified the presence of epilepsy with a sensitivity of 86.4% (95% confidence interval [CI]: 65.0–97.1) and specificity of 85.1% (95% CI: 70.2–96.4). Conclusion The initial testing of the EpiFinder algorithm suggests possible utility in differentiating between an epilepsy syndrome and an alternative diagnosis in adult patients.
- Published
- 2018
- Full Text
- View/download PDF