Ioannis Karakis

Ioannis Karakis

Auto-generated profile, based on publicly available information

Ioannis Karakis

Department of Neurology Emory University School of Medicine Atlanta Georgia USA

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2020 in JAMA Neurology
Verified
Journal Article
Closed access
PDF file
JJJin Jing
Jin Jing
HSHaoqi Sun
Haoqi Sun
JKJennifer A. Kim
Jennifer A. Kim
AHAline Herlopian
Aline Herlopian
IKIoannis Karakis
Ioannis Karakis
MWMichael Brandon Westover
Michael Brandon Westover
Importance Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are a biomarker of epilepsy, seizure risk, and clinical decline. However, there is a scarcity of experts qualified to interpret EEG results. Prior attempts to automate IED detection have been limited by small samples and have not demonstrated expert-level performance. There is a need for a validated automated method to detect IEDs with expert-level reliability. Objective To develop and validate a computer algorithm with the ability to identify IEDs as reliably as experts and classify an EEG recording as containing IEDs vs no IEDs. Design, Setting, and Participants A total of 9571 scalp EEG records with and without IEDs were used to train a deep neural network (SpikeNet) to perform IED detection. Independent training and testing data sets were generated from 13 262 IED candidates, independently annotated by 8 fellowship-trained clinical neurophysiologists, and 8520 EEG records containing no IEDs based on clinical EEG reports. Using the estimated spike probability, a classifier designating the whole EEG recording as positive or negative was also built. Main Outcomes and Measures SpikeNet accuracy, sensitivity, and specificity compared with fellowship-trained neurophysiology experts for identifying IEDs and classifying EEGs as positive or negative or negative for IEDs. Statistical performance was assessed via calibration error and area under the receiver operating characteristic curve (AUC). All performance statistics were estimated using 10-fold cross-validation. Results SpikeNet surpassed both expert interpretation and an industry standard commercial IED detector, based on calibration error (SpikeNet, 0.041; 95% CI, 0.033-0.049; vs industry standard, 0.066; 95% CI, 0.060-0.078; vs experts, mean, 0.183; range, 0.081-0.364) and binary classification performance based on AUC (SpikeNet, 0.980; 95% CI, 0.977-0.984; vs industry standard, 0.882; 95% CI, 0.872-0.893). Whole EEG classification had a mean calibration error of 0.126 (range, 0.109-0.1444) vs experts (mean, 0.197; range, 0.099-0.372) and AUC of 0.847 (95% CI, 0.830-0.865). Conclusions and Relevance In this study, SpikeNet automatically detected IEDs and classified whole EEGs as IED-positive or IED-negative. This may be the first time an algorithm has been shown to exceed expert performance for IED detection in a representative sample of EEGs and may thus be a valuable tool for expedited review of EEGs.

1 January 2020 in JAMA Neurology
Verified
Journal Article
Open access
PDF file
JJJin Jing
Jin Jing
AHAline Herlopian
Aline Herlopian
IKIoannis Karakis
Ioannis Karakis
MNMarcus Ng
Marcus Ng
JHJonathan J. Halford
Jonathan J. Halford
MWMichael Brandon Westover
Michael Brandon Westover
Detecting interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) is a fundamental part of evaluating patients with suspected epilepsy.1-3 Identifying IEDs helps explain recurrence following a first seizure,1,2 classify epilepsy type,4 localize ictal onset,5,6 and manage anticonvulsants.4,7-9 Identification is challenging because IEDs’ morphologies vary and can resemble waves in normal background activity (eg, vertex waves in sleep) or artifacts (eg, extracerebral potentials from muscle, eyes, or heart).10 Mistakes in recognizing IEDs are common and consequential among neurologists without subspecialty training.11-15 False-negative findings delay treatment, whereas false-positive findings lead to inappropriate treatment and delay diagnosis of other disorders.11

15 March 2016 in Journal of Alzheimer’s Disease
Verified
Journal Article
Closed access
PDF file
IKIoannis Karakis
Ioannis Karakis
MPMatthew Pase
Matthew Pase
ABAlexa Beiser
Alexa Beiser
SBSarah L Booth
Sarah L Booth
PJPaul F Jacques
Paul F Jacques
SSSudha Seshadri
Sudha Seshadri
Background: Identifying nutrition- and lifestyle-based risk factors for cognitive impairment and dementia may aid future primary prevention efforts. Objective: We aimed to examine the association of serum vitamin D levels with incident all-cause deme

8 April 2014 in Epilepsy Research and Treatment
Verified
Journal Article
Open access
PDF file
IKIoannis Karakis
Ioannis Karakis
ACAndrew J. Cole
Andrew J. Cole
GMGeorgia D. Montouris
Georgia D. Montouris
MLMarta San Luciano
Marta San Luciano
KMKimford J. Meador
Kimford J. Meador
CPCharitomeni Piperidou
Charitomeni Piperidou
Aim. Caregiver burden (CB) in epilepsy constitutes an understudied area. Here we attempt to identify the magnitude of this burden, the factors associated with it, and its impact to caregiver quality of life (QOL). Methods. 48 persons with epilepsy (PWE) underwent video-EEG monitoring and their caregivers completed questionnaires providing demographic, disease-related, psychiatric, cognitive, sleep, QOL, and burden information. Results. On regression analysis, higher number of antiepileptic drugs, poorer patient neuropsychological performance, lower patient QOL score, and lower caregiver education level were associated with higher CB. Time allocated to patient care approximated but did not attain statistical significance. A moderate inverse correlation between CB and caregiver QOL physical component summary score and a stronger inverse correlation between CB and caregiver QOL mental component summary score were seen. Conclusion. In a selected cohort of PWE undergoing video-EEG monitoring, we identified modest degree of CB, comparable to that reported in the literature for other chronic neurological conditions. It is associated with specific patient and caregiver characteristics and has a negative effect on caregiver QOL.

27 July 2023 in Epileptic Disorders
Verified
Journal Article
Open access
UAUshtar Amin
Ushtar Amin
FNFábio A. Nascimento
Fábio A. Nascimento
IKIoannis Karakis
Ioannis Karakis
DSDonald Schomer
Donald Schomer
SBSelim R. Benbadis
Selim R. Benbadis
Overinterpretation of EEG is an important contributor to the misdiagnosis of epilepsy. For the EEG to have a high diagnostic value and high specificity, it is critical to recognize waveforms that can be mistaken for abnormal patterns. This article describes artifacts, normal rhythms, and normal patterns that are prone to being misinterpreted as abnormal. Artifacts are potentials generated outside the brain. They are divided into physiologic and extraphysiologic. Physiologic artifacts arise from the body and include EMG, eyes, various movements, EKG, pulse, and sweat. Some physiologic artifacts can be useful for interpretation such as EMG and eye movements. Extraphysiologic artifacts arise from outside the body, and in turn can be divided into the environments (electrodes, equipment, and cellphones) and devices within the body (pacemakers and neurostimulators). Normal rhythms can be divided into awake patterns (alpha rhythm and its variants, mu rhythm, lambda waves, posterior slow waves of youth, HV‐induced slowing, photic driving, and photomyogenic response) and sleep patterns (POSTS, vertex waves, spindles, K complexes, sleep‐related hypersynchrony, and frontal arousal rhythm). Breach can affect both awake and sleep rhythms. Normal variants or variants of uncertain clinical significance include variants that may have been considered abnormal in the early days of EEG but are now considered normal. These include wicket spikes and wicket rhythms (the most common normal pattern overread as epileptiform), small sharp spikes (aka benign epileptiform transients of sleep), rhythmic midtemporal theta of drowsiness (aka psychomotor variant), Cigánek rhythm (aka midline theta), 6 Hz phantom spike–wave, 14 and 6 Hz positive spikes, subclinical rhythmic epileptiform discharges of adults (SREDA), slow‐fused transients, occipital spikes of blindness, and temporal slowing of the elderly. Correctly identifying artifacts and normal patterns can help avoid overinterpretation and misdiagnosis. This is an educational review paper addressing a learning objective of the International League Against Epilepsy (ILAE) curriculum.

1 January 2014 in Seizure: European Journal of Epilepsy
Verified
Journal Article
Closed access
IKIoannis Karakis
Ioannis Karakis
GMGeorgia D. Montouris
Georgia D. Montouris
CPCharitomeni Piperidou
Charitomeni Piperidou
MLMarta San Luciano
Marta San Luciano
KMKimford J. Meador
Kimford J. Meador
ACAndrew J. Cole
Andrew J. Cole