Search

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. [ABSTRACT FROM AUTHOR]

Background: Various noninvasive intermittent rhythm monitoring strategies have been used to assess arrhythmia recurrences in trials evaluating pharmacological and invasive therapeutic interventions for atrial fibrillation (AF). We determined whether a frequency and duration of noninvasive rhythm monitoring could be identified that accurately detects arrhythmia recurrences and approximates the AF burden derived from continuous monitoring using an implantable cardiac monitor (ICM).Methods: The rhythm history of 346 patients enrolled in the CIRCA-DOSE trial (Cryoballoon Versus Contact-Force Irrigated Radiofrequency Catheter Ablation) was reconstructed. Using computer simulations, we evaluated event-free survival, sensitivity, negative predictive value, and AF burden of a range of noninvasive monitoring strategies, including those used in contemporary AF ablation trials.Results: A total of 126 290 monitoring days were included in the analysis. At 12 months, 164 patients experienced atrial arrhythmia recurrence as documented by the ICM (1-year event-free survival, 52.6%). Most noninvasive monitoring strategies used in AF ablation trials had poor sensitivity for detecting arrhythmia recurrence. Sensitivity increased with the intensity of monitoring, with serial (3) short-duration monitors (24-/48-hour ECG monitors) missing a substantial proportion of recurrences (sensitivity, 15.8% [95% CI, 8.9%-20.7%] and 24.5% [95% CI, 16.2%-30.6%], respectively). Serial (3) longer-term monitors (14-day ECG monitors) more closely approximated the gold standard ICM (sensitivity, 64.6% [95% CI, 53.6%-74.3%]). AF burden derived from short-duration monitors significantly overestimated the true AF burden in patients with recurrences. Increasing monitoring duration resulted in improved correlation and concordance between noninvasive estimates of the invasive AF burden (R2 = 0.85 and interclass correlation coefficient = 0.91 for serial [3] 14-day ECG monitors versus ICM).Conclusions: The observed rate of postablation atrial tachyarrhythmia recurrence is highly dependent on the arrhythmia monitoring strategy employed. Between-trial discrepancies in outcomes may reflect different monitoring protocols. On the basis of measures of agreement, serial long-term (7-14 day) intermittent monitors accumulating at least 28 days of annual monitoring provide estimates of AF burden comparable with ICM. However, ICMs outperform intermittent monitoring for arrhythmia detection, and should be considered the gold standard for clinical trials. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT01913522. [ABSTRACT FROM AUTHOR]

Background: Artificial intelligence (AI) has influenced all aspects of human life and neurology is no exception to this growing trend. The aim of this paper is to guide medical practitioners on the relevant aspects of artificial intelligence, i.e., machine learning, and deep learning, to review the development of technological advancement equipped with AI, and to elucidate how machine learning can revolutionize the management of neurological diseases. This review focuses on unsupervised aspects of machine learning, and how these aspects could be applied to precision neurology to improve patient outcomes. We have mentioned various forms of available AI, prior research, outcomes, benefits and limitations of AI, effective accessibility and future of AI, keeping the current burden of neurological disorders in mind. Discussion: The smart device system to monitor tremors and to recognize its phenotypes for better outcomes of deep brain stimulation, applications evaluating fine motor functions, AI integrated electroencephalogram learning to diagnose epilepsy and psychological non-epileptic seizure, predict outcome of seizure surgeries, recognize patterns of autonomic instability to prevent sudden unexpected death in epilepsy (SUDEP), identify the pattern of complex algorithm in neuroimaging classifying cognitive impairment, differentiating and classifying concussion phenotypes, smartwatches monitoring atrial fibrillation to prevent strokes, and prediction of prognosis in dementia are unique examples of experimental utilizations of AI in the field of neurology. Though there are obvious limitations of AI, the general consensus among several nationwide studies is that this new technology has the ability to improve the prognosis of neurological disorders and as a result should become a staple in the medical community. Conclusion: AI not only helps to analyze medical data in disease prevention, diagnosis, patient monitoring, and development of new protocols, but can also assist clinicians in dealing with voluminous data in a more accurate and efficient manner. [ABSTRACT FROM AUTHOR]