1
|
Quilter EEV, Downes S, Deighan MT, Stuart L, Charles R, Tittensor P, Junges L, Kissack P, Qureshi Y, Kamaraj AK, Brigden A. A Digital Intervention for Capturing the Real-Time Health Data Needed for Epilepsy Seizure Forecasting: Protocol for a Formative Co-Design and Usability Study (The ATMOSPHERE Study). JMIR Res Protoc 2024; 13:e60129. [PMID: 39298757 DOI: 10.2196/60129] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/13/2024] [Revised: 07/01/2024] [Accepted: 07/16/2024] [Indexed: 09/22/2024] Open
Abstract
BACKGROUND Epilepsy is a chronic neurological disorder affecting individuals globally, marked by recurrent and apparently unpredictable seizures that pose significant challenges, including increased mortality, injuries, and diminished quality of life. Despite advancements in treatments, a significant proportion of people with epilepsy continue to experience uncontrolled seizures. The apparent unpredictability of these events has been identified as a major concern for people with epilepsy, highlighting the need for innovative seizure forecasting technologies. OBJECTIVE The ATMOSPHERE study aimed to develop and evaluate a digital intervention, using wearable technology and data science, that provides real-time, individualized seizure forecasting for individuals living with epilepsy. This paper reports the protocol for one of the workstreams focusing on the design and testing of a prototype to capture real-time input data needed for predictive modeling. The first aim was to collaboratively design the prototype (work completed). The second aim is to conduct an "in-the-wild" study to assess usability and refine the prototype (planned research). METHODS This study uses a person-based approach to design and test the usability of a prototype for real-time seizure precipitant data capture. Phase 1 (work completed) involved co-design with individuals living with epilepsy and health care professionals. Sessions explored users' requirements for the prototype, followed by iterative design of low-fidelity, static prototypes. Phase 2 (planned research) will be an "in-the-wild" usability study involving the deployment of a mid-fidelity, functional prototype for 4 weeks, with the collection of mixed methods usability data to assess the prototype's real-world application, feasibility, acceptability, and engagement. This phase involves primary participants (adults diagnosed with epilepsy) and, optionally, their nominated significant other. The usability study will run in 3 rounds of deployment and data collection, aiming to recruit 5 participants per round, with prototype refinement between rounds. RESULTS The phase-1 co-design study engaged 22 individuals, resulting in the development of a mid-fidelity, functional prototype based on identified requirements, including the tracking of evidence-based and personalized seizure precipitants. The upcoming phase-2 usability study is expected to provide insights into the prototype's real-world usability, identify areas for improvement, and refine the technology for future development. The estimated completion date of phase 2 is the last quarter of 2024. CONCLUSIONS The ATMOSPHERE study aims to make a significant step forward in epilepsy management, focusing on the development of a user-centered, noninvasive wearable device for seizure forecasting. Through a collaborative design process and comprehensive usability testing, this research aims to address the critical need for predictive seizure forecasting technologies, offering a promising approach to improving the lives of individuals with epilepsy. By leveraging predictive analytics and personalized machine learning models, this technology seeks to offer a novel approach to managing epilepsy, potentially improving clinical outcomes, including quality of life, through increased predictability and seizure management. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/60129.
Collapse
Affiliation(s)
- Emily E V Quilter
- School of Engineering Mathematics and Technology, University of Bristol, Bristol, United Kingdom
| | - Samuel Downes
- School of Engineering Mathematics and Technology, University of Bristol, Bristol, United Kingdom
| | - Mairi Therese Deighan
- School of Engineering Mathematics and Technology, University of Bristol, Bristol, United Kingdom
| | - Liz Stuart
- School of Computing, Ulster University, Belfast, Ireland
| | | | - Phil Tittensor
- The Royal Wolverhampton NHS Trust, Wolverhampton, United Kingdom
| | - Leandro Junges
- Centre for Systems Modelling & Quantitative Biomedicine (SMQB), The University of Birmingham, Birmingham, United Kingdom
| | - Peter Kissack
- Centre for Systems Modelling & Quantitative Biomedicine (SMQB), The University of Birmingham, Birmingham, United Kingdom
- School of Mathematics, The University of Birmingham, Birmingham, United Kingdom
| | - Yasser Qureshi
- Centre for Systems Modelling & Quantitative Biomedicine (SMQB), The University of Birmingham, Birmingham, United Kingdom
- School of Engineering, The University of Warwick, Coventry, United Kingdom
| | - Aravind Kumar Kamaraj
- Centre for Systems Modelling & Quantitative Biomedicine (SMQB), The University of Birmingham, Birmingham, United Kingdom
| | - Amberly Brigden
- School of Engineering Mathematics and Technology, University of Bristol, Bristol, United Kingdom
| |
Collapse
|
2
|
Carmo AS, Abreu M, Baptista MF, de Oliveira Carvalho M, Peralta AR, Fred A, Bentes C, da Silva HP. Automated algorithms for seizure forecast: a systematic review and meta-analysis. J Neurol 2024:10.1007/s00415-024-12655-z. [PMID: 39240346 DOI: 10.1007/s00415-024-12655-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/20/2024] [Revised: 08/16/2024] [Accepted: 08/18/2024] [Indexed: 09/07/2024]
Abstract
This study aims to review the proposed methodologies and reported performances of automated algorithms for seizure forecast. A systematic review was conducted on studies reported up to May 10, 2024. Four databases and registers were searched, and studies were included when they proposed an original algorithm for automatic human epileptic seizure forecast that was patient specific, based on intraindividual cyclic distribution of events and/or surrogate measures of the preictal state and provided an evaluation of the performance. Two meta-analyses were performed, one evaluating area under the ROC curve (AUC) and another Brier Skill Score (BSS). Eighteen studies met the eligibility criteria, totaling 43 included algorithms. A total of 419 patients participated in the studies, and 19442 seizures were reported across studies. Of the analyzed algorithms, 23 were eligible for the meta-analysis with AUC and 12 with BSS. The overall mean AUC was 0.71, which was similar between the studies that relied solely on surrogate measures of the preictal state, on cyclic distributions of events, and on a combination of these. BSS was also similar for the three types of input data, with an overall mean BSS of 0.13. This study provides a characterization of the state of the art in seizure forecast algorithms along with their performances, setting a benchmark for future developments. It identified a considerable lack of standardization across study design and evaluation, leading to the proposal of guidelines for the design of seizure forecast solutions.
Collapse
Affiliation(s)
- Ana Sofia Carmo
- Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal.
- Instituto de Telecomunicações, Lisboa, Portugal.
| | - Mariana Abreu
- Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal
- Instituto de Telecomunicações, Lisboa, Portugal
| | - Maria Fortuna Baptista
- Neurophysiology Monitoring Unit EEG/Sleep Laboratory, Hospital de Santa Maria, Unidade Local de Saúde Santa Maria, Lisboa, Portugal
- Centro de Estudos Egas Moniz. Faculdade de Medicina da Universidade de Lisboa, Lisboa, Portugal
| | - Miguel de Oliveira Carvalho
- Neurophysiology Monitoring Unit EEG/Sleep Laboratory, Hospital de Santa Maria, Unidade Local de Saúde Santa Maria, Lisboa, Portugal
- Centro de Estudos Egas Moniz. Faculdade de Medicina da Universidade de Lisboa, Lisboa, Portugal
| | - Ana Rita Peralta
- Neurophysiology Monitoring Unit EEG/Sleep Laboratory, Hospital de Santa Maria, Unidade Local de Saúde Santa Maria, Lisboa, Portugal
- Centro de Estudos Egas Moniz. Faculdade de Medicina da Universidade de Lisboa, Lisboa, Portugal
| | - Ana Fred
- Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal
- Instituto de Telecomunicações, Lisboa, Portugal
| | - Carla Bentes
- Neurophysiology Monitoring Unit EEG/Sleep Laboratory, Hospital de Santa Maria, Unidade Local de Saúde Santa Maria, Lisboa, Portugal
- Centro de Estudos Egas Moniz. Faculdade de Medicina da Universidade de Lisboa, Lisboa, Portugal
| | - Hugo Plácido da Silva
- Department of Bioengineering, Instituto Superior Técnico, Universidade de Lisboa, Lisboa, Portugal
- Instituto de Telecomunicações, Lisboa, Portugal
- LUMLIS The Lisbon ELLIS Unit | European Laboratory for Learning and Intelligent Systems, Lisboa, Portugal
| |
Collapse
|
3
|
Nasseri M, Grzeskowiak C, Brinkmann BH, Dümpelmann M. Editorial: Seizure forecasting tools, biomarkers and devices. Front Neurosci 2024; 18:1470640. [PMID: 39263238 PMCID: PMC11387221 DOI: 10.3389/fnins.2024.1470640] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/25/2024] [Accepted: 08/08/2024] [Indexed: 09/13/2024] Open
Affiliation(s)
- Mona Nasseri
- School of Engineering, University of North Florida, Jacksonville, FL, United States
- Neurology Department, Mayo Clinic, Rochester, MN, United States
| | - Caitlin Grzeskowiak
- Research and Innovation Department, Epilepsy Foundation, Landover, MD, United States
| | | | - Matthias Dümpelmann
- Epilepsy Center, Department of Neurosurgery, Medical Center, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| |
Collapse
|
4
|
Goldenholz DM, Eccleston C, Moss R, Westover MB. Prospective validation of a seizure diary forecasting falls short. Epilepsia 2024; 65:1730-1736. [PMID: 38606580 PMCID: PMC11166505 DOI: 10.1111/epi.17984] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/17/2023] [Revised: 03/13/2024] [Accepted: 04/02/2024] [Indexed: 04/13/2024]
Abstract
OBJECTIVE Recently, a deep learning artificial intelligence (AI) model forecasted seizure risk using retrospective seizure diaries with higher accuracy than random forecasts. The present study sought to prospectively evaluate the same algorithm. METHODS We recruited a prospective cohort of 46 people with epilepsy; 25 completed sufficient data entry for analysis (median = 5 months). We used the same AI method as in our prior study. Group-level and individual-level Brier Skill Scores (BSSs) compared random forecasts and simple moving average forecasts to the AI. RESULTS The AI had an area under the receiver operating characteristic curve of .82. At the group level, the AI outperformed random forecasting (BSS = .53). At the individual level, AI outperformed random in 28% of cases. At the group and individual level, the moving average outperformed the AI. If pre-enrollment (nonverified) diaries (with presumed underreporting) were included, the AI significantly outperformed both comparators. Surveys showed most did not mind poor-quality LOW-RISK or HIGH-RISK forecasts, yet 91% wanted access to these forecasts. SIGNIFICANCE The previously developed AI forecasting tool did not outperform a very simple moving average forecasting in this prospective cohort, suggesting that the AI model should be replaced.
Collapse
Affiliation(s)
- Daniel M. Goldenholz
- Department of Neurology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA
- Department of Neurology, Harvard Medical School, Boston, Massachusetts, USA
| | - Celena Eccleston
- Department of Neurology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA
- Department of Neurology, Harvard Medical School, Boston, Massachusetts, USA
| | | | - M. Brandon Westover
- Department of Neurology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, USA
- Department of Neurology, Harvard Medical School, Boston, Massachusetts, USA
- Department of Neurology, Massachusetts General Hospital, Boston, Massachusetts, USA
- McCance Center for Brain Health, Boston, Massachusetts, USA
| |
Collapse
|
5
|
Pontes ED, Pinto M, Lopes F, Teixeira C. Concept-drifts adaptation for machine learning EEG epilepsy seizure prediction. Sci Rep 2024; 14:8204. [PMID: 38589379 PMCID: PMC11001609 DOI: 10.1038/s41598-024-57744-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/01/2024] [Accepted: 03/21/2024] [Indexed: 04/10/2024] Open
Abstract
Seizure prediction remains a challenge, with approximately 30% of patients unresponsive to conventional treatments. Addressing this issue is crucial for improving patients' quality of life, as timely intervention can mitigate the impact of seizures. In this research field, it is critical to identify the preictal interval, the transition from regular brain activity to a seizure. While previous studies have explored various Electroencephalogram (EEG) based methodologies for prediction, few have been clinically applicable. Recent studies have underlined the dynamic nature of EEG data, characterised by data changes with time, known as concept drifts, highlighting the need for automated methods to detect and adapt to these changes. In this study, we investigate the effectiveness of automatic concept drift adaptation methods in seizure prediction. Three patient-specific seizure prediction approaches with a 10-minute prediction horizon are compared: a seizure prediction algorithm incorporating a window adjustment method by optimising performance with Support Vector Machines (Backwards-Landmark Window), a seizure prediction algorithm incorporating a data-batch (seizures) selection method using a logistic regression (Seizure-batch Regression), and a seizure prediction algorithm with a dynamic integration of classifiers (Dynamic Weighted Ensemble). These methods incorporate a retraining process after each seizure and use a combination of univariate linear features and SVM classifiers. The Firing Power was used as a post-processing technique to generate alarms before seizures. These methodologies were compared with a control approach based on the typical machine learning pipeline, considering a group of 37 patients with Temporal Lobe Epilepsy from the EPILEPSIAE database. The best-performing approach (Backwards-Landmark Window) achieved results of 0.75 ± 0.33 for sensitivity and 1.03 ± 1.00 for false positive rate per hour. This new strategy performed above chance for 89% of patients with the surrogate predictor, whereas the control approach only validated 46%.
Collapse
Affiliation(s)
- Edson David Pontes
- Department of Informatics Engineering, CISUC, University of Coimbra, Coimbra, Portugal.
| | - Mauro Pinto
- Department of Informatics Engineering, CISUC, University of Coimbra, Coimbra, Portugal
| | - Fábio Lopes
- Department of Informatics Engineering, CISUC, University of Coimbra, Coimbra, Portugal
- Epilepsy Center, Department Neurosurgery, Medical Center - University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - César Teixeira
- Department of Informatics Engineering, CISUC, University of Coimbra, Coimbra, Portugal
| |
Collapse
|
6
|
Carè M, Chiappalone M, Cota VR. Personalized strategies of neurostimulation: from static biomarkers to dynamic closed-loop assessment of neural function. Front Neurosci 2024; 18:1363128. [PMID: 38516316 PMCID: PMC10954825 DOI: 10.3389/fnins.2024.1363128] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Accepted: 02/22/2024] [Indexed: 03/23/2024] Open
Abstract
Despite considerable advancement of first choice treatment (pharmacological, physical therapy, etc.) over many decades, neurological disorders still represent a major portion of the worldwide disease burden. Particularly concerning, the trend is that this scenario will worsen given an ever expanding and aging population. The many different methods of brain stimulation (electrical, magnetic, etc.) are, on the other hand, one of the most promising alternatives to mitigate the suffering of patients and families when conventional treatment fall short of delivering efficacious treatment. With applications in virtually all neurological conditions, neurostimulation has seen considerable success in providing relief of symptoms. On the other hand, a large variability of therapeutic outcomes has also been observed, particularly in the usage of non-invasive brain stimulation (NIBS) modalities. Borrowing inspiration and concepts from its pharmacological counterpart and empowered by unprecedented neurotechnological advancement, the neurostimulation field has seen in recent years a widespread of methods aimed at the personalization of its parameters, based on biomarkers of the individuals being treated. The rationale is that, by taking into account important factors influencing the outcome, personalized stimulation can yield a much-improved therapy. Here, we review the literature to delineate the state-of-the-art of personalized stimulation, while also considering the important aspects of the type of informing parameter (anatomy, function, hybrid), invasiveness, and level of development (pre-clinical experimentation versus clinical trials). Moreover, by reviewing relevant literature on closed loop neuroengineering solutions in general and on activity dependent stimulation method in particular, we put forward the idea that improved personalization may be achieved when the method is able to track in real time brain dynamics and adjust its stimulation parameters accordingly. We conclude that such approaches have great potential of promoting the recovery of lost functions and enhance the quality of life for patients.
Collapse
Affiliation(s)
- Marta Carè
- IRCCS Ospedale Policlinico San Martino, Genova, Italy
| | - Michela Chiappalone
- Department of Informatics, Bioengineering, Robotics System Engineering (DIBRIS), University of Genova, Genova, Italy
- Rehab Technologies Lab, Istituto Italiano di Tecnologia, Genova, Italy
| | | |
Collapse
|
7
|
Costa G, Teixeira C, Pinto MF. Comparison between epileptic seizure prediction and forecasting based on machine learning. Sci Rep 2024; 14:5653. [PMID: 38454117 PMCID: PMC10920642 DOI: 10.1038/s41598-024-56019-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Accepted: 02/29/2024] [Indexed: 03/09/2024] Open
Abstract
Epilepsy affects around 1% of the population worldwide. Anti-epileptic drugs are an excellent option for controlling seizure occurrence but do not work for around one-third of patients. Warning devices employing seizure prediction or forecasting algorithms could bring patients new-found comfort and quality of life. These algorithms would attempt to detect a seizure's preictal period, a transitional moment between regular brain activity and the seizure, and relay this information to the user. Over the years, many seizure prediction studies using Electroencephalogram-based methodologies have been developed, triggering an alarm when detecting the preictal period. Recent studies have suggested a shift in view from prediction to forecasting. Seizure forecasting takes a probabilistic approach to the problem in question instead of the crisp approach of seizure prediction. In this field of study, the triggered alarm to symbolize the detection of a preictal period is substituted by a constant risk assessment analysis. The present work aims to explore methodologies capable of seizure forecasting and establish a comparison with seizure prediction results. Using 40 patients from the EPILEPSIAE database, we developed several patient-specific prediction and forecasting algorithms with different classifiers (a Logistic Regression, a 15 Support Vector Machines ensemble, and a 15 Shallow Neural Networks ensemble). Results show an increase of the seizure sensitivity in forecasting relative to prediction of up to 146% and in the number of patients that displayed an improvement over chance of up to 300%. These results suggest that a seizure forecasting methodology may be more suitable for seizure warning devices than a seizure prediction one.
Collapse
Affiliation(s)
- Gonçalo Costa
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, 3030-290, Coimbra, Portugal.
| | - César Teixeira
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, 3030-290, Coimbra, Portugal
| | - Mauro F Pinto
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, 3030-290, Coimbra, Portugal
| |
Collapse
|
8
|
Goldenholz DM, Eccleston C, Moss R, Westover MB. Prospective validation of a seizure diary forecasting falls short. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2024:2024.01.11.24301175. [PMID: 38260666 PMCID: PMC10802655 DOI: 10.1101/2024.01.11.24301175] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/24/2024]
Abstract
OBJECTIVE Recently, a deep learning AI model forecasted seizure risk using retrospective seizure diaries with higher accuracy than random forecasts. The present study sought to prospectively evaluate the same algorithm. METHODS We recruited a prospective cohort of 46 people with epilepsy; 25 completed sufficient data entry for analysis (median 5 months). We used the same AI method as in our prior study. Group-level and individual-level Brier Skill Scores (BSS) compared random forecasts and simple moving average forecasts to the AI. RESULTS The AI had an AUC of 0.82. At the group level, the AI outperformed random forecasting (BSS=0.53). At the individual level, AI outperformed random in 28% of cases. At the group and individual level, the moving average outperformed the AI. If pre-enrollment (non-verified) diaries (with presumed under-reporting) were included, the AI significantly outperformed both comparators. Surveys showed most did not mind poor quality LOW-RISK or HIGH-RISK forecasts, yet 91% wanted access to these forecasts. SIGNIFICANCE The previously developed AI forecasting tool did not outperform a very simple moving average forecasting this prospective cohort, suggesting that the AI model should be replaced.
Collapse
Affiliation(s)
- Daniel M Goldenholz
- Dept. of Neurology, Beth Israel Deaconess Medical Center, Boston 02215 MA
- Dept. of Neurology, Harvard Medical School, Boston 02215 MA
| | - Celena Eccleston
- Dept. of Neurology, Beth Israel Deaconess Medical Center, Boston 02215 MA
- Dept. of Neurology, Harvard Medical School, Boston 02215 MA
| | | | - M Brandon Westover
- Dept. of Neurology, Beth Israel Deaconess Medical Center, Boston 02215 MA
- Dept. of Neurology, Harvard Medical School, Boston 02215 MA
- Dept. of Neurology, Massachusetts General Hospital, Boston 02114 MA
- McCance Center for Brain Health, Boston, 02114 MA
| |
Collapse
|
9
|
Beniczky S, Ryvlin P. Mobile health and digital technology in epilepsy: The dawn of a new era. Epilepsia 2023; 64 Suppl 4:S1-S3. [PMID: 37921045 DOI: 10.1111/epi.17813] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/27/2023] [Accepted: 10/31/2023] [Indexed: 11/04/2023]
Affiliation(s)
- Sándor Beniczky
- Department of Neurophysiology, Danish Epilepsy Center, Dianalund, Denmark
- Department of Clinical Medicine, Aarhus University and Department of Clinical Neurophysiology, Aarhus University Hospital, Aarhus, Denmark
- Department of Neurology, University of Szeged, Szeged, Hungary
| | - Philippe Ryvlin
- Department of Clinical Neurosciences, Lausanne University Hospital, Lausanne, Switzerland
| |
Collapse
|
10
|
Andrzejak RG, Zaveri HP, Schulze‐Bonhage A, Leguia MG, Stacey WC, Richardson MP, Kuhlmann L, Lehnertz K. Seizure forecasting: Where do we stand? Epilepsia 2023; 64 Suppl 3:S62-S71. [PMID: 36780237 PMCID: PMC10423299 DOI: 10.1111/epi.17546] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2023] [Accepted: 02/06/2023] [Indexed: 02/14/2023]
Abstract
A lot of mileage has been made recently on the long and winding road toward seizure forecasting. Here we briefly review some selected milestones passed along the way, which were discussed at the International Conference for Technology and Analysis of Seizures-ICTALS 2022-convened at the University of Bern, Switzerland. Major impetus was gained recently from wearable and implantable devices that record not only electroencephalography, but also data on motor behavior, acoustic signals, and various signals of the autonomic nervous system. This multimodal monitoring can be performed for ultralong timescales covering months or years. Accordingly, features and metrics extracted from these data now assess seizure dynamics with a greater degree of completeness. Most prominently, this has allowed the confirmation of the long-suspected cyclical nature of interictal epileptiform activity, seizure risk, and seizures. The timescales cover daily, multi-day, and yearly cycles. Progress has also been fueled by approaches originating from the interdisciplinary field of network science. Considering epilepsy as a large-scale network disorder yielded novel perspectives on the pre-ictal dynamics of the evolving epileptic brain. In addition to discrete predictions that a seizure will take place in a specified prediction horizon, the community broadened the scope to probabilistic forecasts of a seizure risk evolving continuously in time. This shift of gears triggered the incorporation of additional metrics to quantify the performance of forecasting algorithms, which should be compared to the chance performance of constrained stochastic null models. An imminent task of utmost importance is to find optimal ways to communicate the output of seizure-forecasting algorithms to patients, caretakers, and clinicians, so that they can have socioeconomic impact and improve patients' well-being.
Collapse
Grants
- NIH NS109062 NIH HHS
- MR/N026063/1 Medical Research Council
- R01 NS109062 NINDS NIH HHS
- R01 NS094399 NINDS NIH HHS
- NIH NS094399 NIH HHS
- Medical Research Council Centre for Neurodevelopmental Disorders
- National Health and Medical Research Council
- National Institutes of Health
- University of Bern, the Inselspital, University Hospital Bern, the Alliance for Epilepsy Research, the Swiss National Science Foundation, UCB, FHC, the Wyss Center for bio‐ and neuro‐engineering, the American Epilepsy Society (AES), the CURE epilepsy Foundation, Ripple neuro, Sintetica, DIXI medical, UNEEG medical and NeuroPace.
Collapse
Affiliation(s)
- Ralph G. Andrzejak
- Department of Information and Communication TechnologiesUniversitat Pompeu FabraBarcelonaSpain
| | | | - Andreas Schulze‐Bonhage
- Epilepsy Center, NeurocenterUniversity Medical Center, University of FreiburgFreiburgGermany
| | - Marc G. Leguia
- Department of Information and Communication TechnologiesUniversitat Pompeu FabraBarcelonaSpain
| | - William C. Stacey
- Department of Neurology, Department of Biomedical EngineeringBioInterfaces Institute, University of MichiganAnn ArborMichiganUSA
- Division of NeurologyVA Ann Arbor Medical CenterAnn ArborMichiganUSA
| | - Mark P. Richardson
- School of NeuroscienceInstitute of Psychiatry Psychology and Neuroscience, King's College LondonLondonUK
| | - Levin Kuhlmann
- Department of Data Science and AI, Faculty of Information TechnologyMonash UniversityClaytonVictoriaAustralia
| | - Klaus Lehnertz
- Department of EpileptologyUniversity of Bonn Medical CentreBonnGermany
- Helmholtz Institute for Radiation and Nuclear PhysicsUniversity of BonnBonnGermany
- Interdisciplinary Center for Complex SystemsUniversity of BonnBonnGermany
| |
Collapse
|
11
|
Knight A, Gschwind T, Galer P, Worrell GA, Litt B, Soltesz I, Beniczky S. Artificial intelligence in epilepsy phenotyping. Epilepsia 2023:10.1111/epi.17833. [PMID: 37983589 PMCID: PMC11102939 DOI: 10.1111/epi.17833] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2023] [Accepted: 11/17/2023] [Indexed: 11/22/2023]
Abstract
Artificial intelligence (AI) allows data analysis and integration at an unprecedented granularity and scale. Here we review the technological advances, challenges, and future perspectives of using AI for electro-clinical phenotyping of animal models and patients with epilepsy. In translational research, AI models accurately identify behavioral states in animal models of epilepsy, allowing identification of correlations between neural activity and interictal and ictal behavior. Clinical applications of AI-based automated and semi-automated analysis of audio and video recordings of people with epilepsy, allow significant data reduction and reliable detection and classification of major motor seizures. AI models can accurately identify electrographic biomarkers of epilepsy, such as spikes, high-frequency oscillations, and seizure patterns. Integrating AI analysis of electroencephalographic, clinical, and behavioral data will contribute to optimizing therapy for patients with epilepsy.
Collapse
Affiliation(s)
| | - Tilo Gschwind
- Department of Neurosurgery, Stanford University, Stanford, USA
| | - Peter Galer
- Center for Neuroengineering and Therapeutics; Department of Bioengineering; Department of Neurology, Perelman School of Medicine, University of Pennsylvania, USA
| | | | - Brian Litt
- Center for Neuroengineering and Therapeutics; Department of Bioengineering; Department of Neurology, Perelman School of Medicine, University of Pennsylvania, USA
| | - Ivan Soltesz
- Department of Neurosurgery, Stanford University, Stanford, USA
| | - Sándor Beniczky
- Danish Epilepsy Centre Filadelfia, Dianalund, Aarhus University Hospital and Aarhus University, Aarhus, Denmark
| |
Collapse
|
12
|
Cui J, Balzekas I, Nurse E, Viana P, Gregg N, Karoly P, Stirling RE, Worrell G, Richardson MP, Freestone DR, Brinkmann BH. Perceived seizure risk in epilepsy: Chronic electronic surveys with and without concurrent electroencephalography. Epilepsia 2023; 64:2421-2433. [PMID: 37303239 PMCID: PMC10526687 DOI: 10.1111/epi.17678] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/22/2023] [Revised: 06/07/2023] [Accepted: 06/07/2023] [Indexed: 06/13/2023]
Abstract
OBJECTIVE Previous studies suggested that patients with epilepsy might be able to forecast their own seizures. This study aimed to assess the relationships between premonitory symptoms, perceived seizure risk, and future and recent self-reported and electroencephalographically (EEG)-confirmed seizures in ambulatory patients with epilepsy in their natural home environments. METHODS Long-term e-surveys were collected from patients with and without concurrent EEG recordings. Information obtained from the e-surveys included medication adherence, sleep quality, mood, stress, perceived seizure risk, and seizure occurrences preceding the survey. EEG seizures were identified. Univariate and multivariate generalized linear mixed-effect regression models were used to estimate odds ratios (ORs) for the assessment of the relationships. Results were compared with the seizure forecasting classifiers and device forecasting literature using a mathematical formula converting OR to equivalent area under the curve (AUC). RESULTS Fifty-four subjects returned 10 269 e-survey entries, with four subjects acquiring concurrent EEG recordings. Univariate analysis revealed that increased stress (OR = 2.01, 95% confidence interval [CI] = 1.12-3.61, AUC = .61, p = .02) was associated with increased relative odds of future self-reported seizures. Multivariate analysis showed that previous self-reported seizures (OR = 5.37, 95% CI = 3.53-8.16, AUC = .76, p < .001) were most strongly associated with future self-reported seizures, and high perceived seizure risk (OR = 3.34, 95% CI = 1.87-5.95, AUC = .69, p < .001) remained significant when prior self-reported seizures were added to the model. No correlation with medication adherence was found. No significant association was found between e-survey responses and subsequent EEG seizures. SIGNIFICANCE Our results suggest that patients may tend to self-forecast seizures that occur in sequential groupings and that low mood and increased stress may be the result of previous seizures rather than independent premonitory symptoms. Patients in the small cohort with concurrent EEG showed no ability to self-predict EEG seizures. The conversion from OR to AUC values facilitates direct comparison of performance between survey and device studies involving survey premonition and forecasting.
Collapse
Affiliation(s)
- Jie Cui
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
- Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, Minnesota, USA
- Mayo College of Medicine and Science, Mayo Clinic, Rochester, Minnesota, USA
| | - Irena Balzekas
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Ewan Nurse
- Seer Medical, Melbourne, Australia
- Department of Medicine, St. Vincent’s Hospital Melbourne, University of Melbourne, Melbourne, Australia
| | - Pedro Viana
- School of Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, UK
- Faculty of Medicine, University of Lisbon, Portugal
| | - Nicholas Gregg
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Philippa Karoly
- Department of Medicine, St. Vincent’s Hospital Melbourne, University of Melbourne, Melbourne, Australia
| | - Rachel E Stirling
- Seer Medical, Melbourne, Australia
- Department of Medicine, St. Vincent’s Hospital Melbourne, University of Melbourne, Melbourne, Australia
| | - Gregory Worrell
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Mark P Richardson
- School of Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, UK
| | | | - Benjamin H Brinkmann
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
- Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, Minnesota, USA
| |
Collapse
|
13
|
Viana PF, Duun-Henriksen J, Winston JS, Kjaer TW, Skaarup C, Richardson MP. Atlas of ambulatory subcutaneous electroencephalography. Epileptic Disord 2023; 25:584-585. [PMID: 37149497 DOI: 10.1002/epd2.20066] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2023] [Revised: 04/25/2023] [Accepted: 04/29/2023] [Indexed: 05/08/2023]
Affiliation(s)
- Pedro F Viana
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
- Centre for Epilepsy, King's College Hospital NHS Foundation Trust, London, UK
- Faculty of Medicine, University of Lisbon, Lisbon, Portugal
| | | | - Joel S Winston
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
- Centre for Epilepsy, King's College Hospital NHS Foundation Trust, London, UK
| | | | | | - Mark P Richardson
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK
- Centre for Epilepsy, King's College Hospital NHS Foundation Trust, London, UK
| |
Collapse
|
14
|
Xiong W, Stirling RE, Payne DE, Nurse ES, Kameneva T, Cook MJ, Viana PF, Richardson MP, Brinkmann BH, Freestone DR, Karoly PJ. Forecasting seizure likelihood from cycles of self-reported events and heart rate: a prospective pilot study. EBioMedicine 2023; 93:104656. [PMID: 37331164 PMCID: PMC10300292 DOI: 10.1016/j.ebiom.2023.104656] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/18/2022] [Revised: 05/30/2023] [Accepted: 05/31/2023] [Indexed: 06/20/2023] Open
Abstract
BACKGROUND Seizure risk forecasting could reduce injuries and even deaths in people with epilepsy. There is great interest in using non-invasive wearable devices to generate forecasts of seizure risk. Forecasts based on cycles of epileptic activity, seizure times or heart rate have provided promising forecasting results. This study validates a forecasting method using multimodal cycles recorded from wearable devices. METHOD Seizure and heart rate cycles were extracted from 13 participants. The mean period of heart rate data from a smartwatch was 562 days, with a mean of 125 self-reported seizures from a smartphone app. The relationship between seizure onset time and phases of seizure and heart rate cycles was investigated. An additive regression model was used to project heart rate cycles. The results of forecasts using seizure cycles, heart rate cycles, and a combination of both were compared. Forecasting performance was evaluated in 6 of 13 participants in a prospective setting, using long-term data collected after algorithms were developed. FINDINGS The results showed that the best forecasts achieved a mean area under the receiver-operating characteristic curve (AUC) of 0.73 for 9/13 participants showing performance above chance during retrospective validation. Subject-specific forecasts evaluated with prospective data showed a mean AUC of 0.77 with 4/6 participants showing performance above chance. INTERPRETATION The results of this study demonstrate that cycles detected from multimodal data can be combined within a single, scalable seizure risk forecasting algorithm to provide robust performance. The presented forecasting method enabled seizure risk to be estimated for an arbitrary future period and could be generalised across a range of data types. In contrast to earlier work, the current study evaluated forecasts prospectively, in subjects blinded to their seizure risk outputs, representing a critical step towards clinical applications. FUNDING This study was funded by an Australian Government National Health & Medical Research Council and BioMedTech Horizons grant. The study also received support from the Epilepsy Foundation of America's 'My Seizure Gauge' grant.
Collapse
Affiliation(s)
- Wenjuan Xiong
- School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, Australia
| | - Rachel E Stirling
- Department of Biomedical Engineering, The University of Melbourne, Melbourne, Australia; Seer Medical, Melbourne, Australia
| | | | - Ewan S Nurse
- Seer Medical, Melbourne, Australia; Department of Medicine, St Vincent's Hospital Melbourne, The University of Melbourne, Melbourne, Australia
| | - Tatiana Kameneva
- School of Science, Computing and Engineering Technologies, Swinburne University of Technology, Melbourne, Australia; Department of Biomedical Engineering, The University of Melbourne, Melbourne, Australia
| | - Mark J Cook
- Seer Medical, Melbourne, Australia; Department of Medicine, St Vincent's Hospital Melbourne, The University of Melbourne, Melbourne, Australia; Graeme Clark Institute, The University of Melbourne, Melbourne, Australia
| | - Pedro F Viana
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; Centre for Epilepsy, King's College Hospital NHS Foundation Trust, London, UK; Centro de Estudos Egas Moniz, Faculty of Medicine, University of Lisbon, Lisbon, Portugal
| | - Mark P Richardson
- Institute of Psychiatry, Psychology and Neuroscience, King's College London, London, UK; Centre for Epilepsy, King's College Hospital NHS Foundation Trust, London, UK; NIHR Biomedical Research Centre at South London and Maudsley NHS Foundation Trust, London, UK
| | - Benjamin H Brinkmann
- Bioelectronics Neurophysiology and Engineering Lab, Mayo Clinic, Rochester, MN, USA
| | | | - Philippa J Karoly
- Department of Biomedical Engineering, The University of Melbourne, Melbourne, Australia; Department of Medicine, St Vincent's Hospital Melbourne, The University of Melbourne, Melbourne, Australia; Graeme Clark Institute, The University of Melbourne, Melbourne, Australia.
| |
Collapse
|
15
|
Lopes F, Leal A, Pinto MF, Dourado A, Schulze-Bonhage A, Dümpelmann M, Teixeira C. Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models. Sci Rep 2023; 13:5918. [PMID: 37041158 PMCID: PMC10090199 DOI: 10.1038/s41598-023-30864-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/07/2022] [Accepted: 03/02/2023] [Indexed: 04/13/2023] Open
Abstract
The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.
Collapse
Affiliation(s)
- Fábio Lopes
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal.
- Epilepsy Center, Department Neurosurgery, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany.
| | - Adriana Leal
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal
| | - Mauro F Pinto
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal
| | - António Dourado
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal
| | - Andreas Schulze-Bonhage
- Epilepsy Center, Department Neurosurgery, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - Matthias Dümpelmann
- Epilepsy Center, Department Neurosurgery, Medical Center-University of Freiburg, Faculty of Medicine, University of Freiburg, Freiburg, Germany
| | - César Teixeira
- Center for Informatics and Systems of the University of Coimbra, Department of Informatics Engineering, University of Coimbra, Coimbra, Portugal
| |
Collapse
|
16
|
Cui J, Balzekas I, Nurse E, Viana P, Gregg N, Karoly P, Worrell G, Richardson MP, Freestone DR, Brinkmann BH. Perceived seizure risk in epilepsy â€" Chronic electronic surveys with and without concurrent EEG. MEDRXIV : THE PREPRINT SERVER FOR HEALTH SCIENCES 2023:2023.03.23.23287561. [PMID: 37034596 PMCID: PMC10081426 DOI: 10.1101/2023.03.23.23287561] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 04/29/2023]
Abstract
Objective Previous studies suggested that patients with epilepsy might be able to fore-cast their own seizures. We sought to assess the relationships of premonitory symptoms and perceived seizure risk with future and recent self-reported and EEG-confirmed seizures in the subjects living with epilepsy in their natural home environments. Methods We collected long-term e-surveys from ambulatory patients with and without concurrent EEG recordings. Information obtained from the e-surveys included medication compliance, sleep quality, mood, stress, perceived seizure risk and seizure occurrences preceding the survey. EEG seizures were identified. Univariate and multivariate generalized linear mixed-effect regression models were used to estimate odds ratios (ORs) for the assessment of the relationships. Results were compared with device seizure forecasting literature using a mathematical formula converting OR to equivalent area under the curve (AUC). Results Sixty-nine subjects returned 12,590 e-survey entries, with four subjects acquiring concurrent EEG recordings. Univariate analysis revealed increased stress (OR = 2.52, 95% CI = [1.52, 4.14], p < 0.001) and decreased mood (0.32, [0.13, 0.82], 0.02) were associated with increased relative odds of future self-reported seizures. On multivariate analysis, previous self-reported seizures (4.24, [2.69, 6.68], < 0.001) were most strongly associated with future self-reported seizures, and high perceived seizure risk (3.30, [1.97, 5.52], < 0.001) remained significant when prior self-reported seizures were added to the model. No significant association was found between e-survey responses and subsequent EEG seizures. Significance It appears that patients may tend to self-forecast seizures that occur in sequential groupings. Our results suggest that low mood and increased stress may be the result of previous seizures rather than independent premonitory symptoms. Patients in the small cohort with concurrent EEG showed no ability to self-predict EEG seizures. The conversion from OR to AUC values facilitates direct comparison of performance between survey and device studies involving survey premonition and forecasting. Key points Long-term e-surveys data and concurrent EEG signals were collected across three study sites to assess the ability of the patients to self-forecast their seizures.Patients may tend to self-forecast self-reported seizures that occur in sequential groupings.Factors, such as mood and stress, may not be independent premonitory symptoms but may be the consequence of recent seizures.No ability to self-forecast EEG confirmed seizures was observed in a small cohort with concurrent EEG validation.A mathematic relation between OR and AUC provides a means to compare forecasting performance between survey and device studies.
Collapse
Affiliation(s)
- Jie Cui
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
- Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, Minnesota, USA
- Mayo College of Medicine and Science, Mayo Clinic, Rochester, Minnesota, USA
| | - Irena Balzekas
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Ewan Nurse
- Seer Medical, Melbourne, Australia
- Department of Medicine, St. Vincent’s Hospital Melbourne, University of Melbourne, Melbourne, Australia
| | - Pedro Viana
- School of Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, UK
- Faculty of Medicine, University of Lisbon, Portugal
| | - Nicholas Gregg
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Philippa Karoly
- Department of Medicine, St. Vincent’s Hospital Melbourne, University of Melbourne, Melbourne, Australia
| | - Gregory Worrell
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
| | - Mark P Richardson
- School of Neuroscience, Institute of Psychiatry, Psychology and Neuroscience, King’s College London, UK
| | | | - Benjamin H. Brinkmann
- Department of Neurology, Mayo Clinic, Rochester, Minnesota, USA
- Department of Physiology and Biomedical Engineering, Mayo Clinic, Rochester, Minnesota, USA
| |
Collapse
|