1
|
Kerr WT, McFarlane KN. Machine Learning and Artificial Intelligence Applications to Epilepsy: a Review for the Practicing Epileptologist. Curr Neurol Neurosci Rep 2023; 23:869-879. [PMID: 38060133 DOI: 10.1007/s11910-023-01318-7] [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] [Accepted: 10/24/2023] [Indexed: 12/08/2023]
Abstract
PURPOSE OF REVIEW Machine Learning (ML) and Artificial Intelligence (AI) are data-driven techniques to translate raw data into applicable and interpretable insights that can assist in clinical decision making. Some of these tools have extremely promising initial results, earning both great excitement and creating hype. This non-technical article reviews recent developments in ML/AI in epilepsy to assist the current practicing epileptologist in understanding both the benefits and limitations of integrating ML/AI tools into their clinical practice. RECENT FINDINGS ML/AI tools have been developed to assist clinicians in almost every clinical decision including (1) predicting future epilepsy in people at risk, (2) detecting and monitoring for seizures, (3) differentiating epilepsy from mimics, (4) using data to improve neuroanatomic localization and lateralization, and (5) tracking and predicting response to medical and surgical treatments. We also discuss practical, ethical, and equity considerations in the development and application of ML/AI tools including chatbots based on Large Language Models (e.g., ChatGPT). ML/AI tools will change how clinical medicine is practiced, but, with rare exceptions, the transferability to other centers, effectiveness, and safety of these approaches have not yet been established rigorously. In the future, ML/AI will not replace epileptologists, but epileptologists with ML/AI will replace epileptologists without ML/AI.
Collapse
Affiliation(s)
- Wesley T Kerr
- Department of Neurology, University of Pittsburgh, 3471 Fifth Ave, Kaufmann 811.22, Pittsburgh, PA, 15213, USA.
- Department of Biomedical Informatics, University of Pittsburgh, 3471 Fifth Ave, Kaufmann 811.22, Pittsburgh, PA, 15213, USA.
- Department of Neurology, Michigan Medicine, University of Michigan, Ann Arbor, MI, USA.
| | - Katherine N McFarlane
- Department of Neurology, University of Pittsburgh, 3471 Fifth Ave, Kaufmann 811.22, Pittsburgh, PA, 15213, USA
| |
Collapse
|
2
|
Abdelsamad A, Kachhadia MP, Hassan T, Kumar L, Khan F, Kar I, Panta U, Zafar W, Sapna F, Varrassi G, Khatri M, Kumar S. Charting the Progress of Epilepsy Classification: Navigating a Shifting Landscape. Cureus 2023; 15:e46470. [PMID: 37927689 PMCID: PMC10624359 DOI: 10.7759/cureus.46470] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/21/2023] [Accepted: 10/04/2023] [Indexed: 11/07/2023] Open
Abstract
Epilepsy, a neurological disorder characterized by recurrent seizures, has witnessed a remarkable transformation in its classification paradigm, driven by advances in clinical understanding, neuroimaging, and molecular genetics. This narrative review navigates the dynamic landscape of epilepsy classification, offering insights into recent developments, challenges, and the promising horizon. Historically, epilepsy classification relied heavily on clinical observations, categorizing seizures based on their phenomenology and presumed etiology. However, the field has profoundly shifted from a symptom-based approach to a more refined, multidimensional system. One pivotal aspect of this evolution is the integration of neuroimaging techniques, particularly magnetic resonance imaging (MRI) and functional imaging modalities. These tools have unveiled the intricate neural networks implicated in epilepsy, facilitating the identification of distinct brain abnormalities and the categorization of epilepsy subtypes based on structural and functional findings. Furthermore, the role of genetics has become increasingly prominent in epilepsy classification. Genetic discoveries have not only unraveled the molecular underpinnings of various epileptic syndromes but have also provided valuable diagnostic and prognostic insights. This narrative review delves into the expanding realm of genetic testing and its impact on tailoring treatment strategies to individual patients. As the classification landscape evolves, there are accompanying challenges. The narrative review underscores the transformative potential of artificial intelligence and machine learning in epilepsy classification. These technologies hold promise in automating the analysis of complex neuroimaging and genetic data, offering enhanced accuracy and efficiency in epilepsy diagnosis and classification. In conclusion, navigating the shifting landscape of epilepsy classification is a journey marked by progress, complexity, and the prospect of improved patient care. We are charting a course toward more precise diagnoses and tailored treatments by embracing advanced neuroimaging, genetics, and innovative technologies. As the field continues to evolve, collaborative efforts and a holistic understanding of epilepsy's diverse manifestations will be instrumental in harnessing the full potential of this dynamic landscape.
Collapse
Affiliation(s)
- Alaa Abdelsamad
- Research and Development, Michigan State University, East Lansing, USA
| | | | - Talha Hassan
- Internal Medicine, KEMU (King Edward Medical University) Mayo Hospital, Lahore, PAK
| | - Lakshya Kumar
- General Medicine, PDU (Pandit Dindayal Upadhyay) Medical College, Rajkot, IND
| | - Faisal Khan
- Medicine, Dow University of Health Sciences (DUHS), Karachi, PAK
| | - Indrani Kar
- Medicine, Lady Hardinge Medical College, New Delhi, IND
| | - Uttam Panta
- Medicine, Chitwan Medical College, Bharatpur, NPL
| | - Wirda Zafar
- Medicine, University of Medicine and Health Sciences, Toronto, CAN
| | - Fnu Sapna
- Pathology, Albert Einstein College of Medicine, New York, USA
| | | | - Mahima Khatri
- Medicine and Surgery, Dow University of Health Sciences (DUHS), Karachi, PAK
| | - Satesh Kumar
- Medicine and Surgery, Shaheed Mohtarma Benazir Bhutto Medical College, Karachi, PAK
| |
Collapse
|
3
|
Chen JS, Lamoureux AA, Shlobin NA, Elkaim LM, Wang A, Ibrahim GM, Obaid S, Harroud A, Guadagno E, Dimentberg E, Bouthillier A, Bernhardt BC, Nguyen DK, Fallah A, Weil AG. Magnetic resonance-guided laser interstitial thermal therapy for drug-resistant epilepsy: A systematic review and individual participant data meta-analysis. Epilepsia 2023; 64:1957-1974. [PMID: 36824029 DOI: 10.1111/epi.17560] [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: 10/28/2022] [Revised: 01/30/2023] [Accepted: 02/22/2023] [Indexed: 02/25/2023]
Abstract
Magnetic resonance-guided laser interstitial thermal therapy (MRgLITT) has emerged as a popular minimally invasive alternative to open resective surgery for drug-resistant epilepsy (DRE). We sought to perform a systematic review and individual participant data meta-analysis to identify independent predictors of seizure outcome and complications following MRgLITT for DRE. Eleven databases were searched from January 1, 2010 to February 6, 2021 using the terms "MR-guided ablation therapy" and "epilepsy". Multivariable mixed-effects Cox and logistic regression identified predictors of time to seizure recurrence, seizure freedom, operative complications, and postoperative neurological deficits. From 8705 citations, 46 studies reporting on 450 MRgLITT DRE patients (mean age = 29.5 ± 18.1 years, 49.6% female) were included. Median postoperative seizure freedom and follow-up duration were 15.5 and 19.0 months, respectively. Overall, 240 (57.8%) of 415 patients (excluding palliative corpus callosotomy) were seizure-free at last follow-up. Generalized seizure semiology (hazard ratio [HR] = 1.78, p = .020) and nonlesional magnetic resonance imaging (MRI) findings (HR = 1.50, p = .032) independently predicted shorter time to seizure recurrence. Cerebral cavernous malformation (CCM; odds ratio [OR] = 7.97, p < .001) and mesial temporal sclerosis/atrophy (MTS/A; OR = 2.21, p = .011) were independently associated with greater odds of seizure freedom at last follow-up. Operative complications occurred in 28 (8.5%) of 330 patients and were independently associated with extratemporal ablations (OR = 5.40, p = .012) and nonlesional MRI studies (OR = 3.25, p = .017). Postoperative neurological deficits were observed in 53 (15.1%) of 352 patients and were independently predicted by hypothalamic hamartoma etiology (OR = 5.93, p = .006) and invasive electroencephalographic monitoring (OR = 4.83, p = .003). Overall, MRgLITT is particularly effective in treating patients with well-circumscribed lesional DRE, such as CCM and MTS/A, but less effective in nonlesional cases or lesional cases with a more diffuse epileptogenic network associated with generalized seizures. This study identifies independent predictors of seizure freedom and complications following MRgLITT that may help further guide patient selection.
Collapse
Affiliation(s)
- Jia-Shu Chen
- Warren Alpert Medical School, Brown University, Providence, Rhode Island, USA
| | - Audrey-Anne Lamoureux
- Division of Pediatric Neurosurgery, Department of Surgery, Sainte Justine Hospital, University of Montreal, Montreal, Quebec, Canada
| | - Nathan A Shlobin
- Department of Neurological Surgery, Feinberg School of Medicine, Northwestern University, Chicago, Illinois, USA
| | - Lior M Elkaim
- Division of Neurology and Neurosurgery, McGill University, Montreal, Quebec, Canada
| | - Andrew Wang
- Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, California, USA
| | - George M Ibrahim
- Division of Neurosurgery, Hospital for Sick Children, University of Toronto, Toronto, Ontario, Canada
| | - Sami Obaid
- Division of Pediatric Neurosurgery, Department of Surgery, Sainte Justine Hospital, University of Montreal, Montreal, Quebec, Canada
- Division of Neurosurgery, University of Montreal Hospital Center, Montreal, Quebec, Canada
| | - Adil Harroud
- Division of Neurology and Neurosurgery, McGill University, Montreal, Quebec, Canada
- Montreal Neurological Institute, McGill University, Montreal, Quebec, Canada
| | - Elena Guadagno
- Harvey E. Beardmore Division of Pediatric Surgery, McGill University Health Center, Montreal, Quebec, Canada
| | - Evan Dimentberg
- Division of Pediatric Neurosurgery, Department of Surgery, Sainte Justine Hospital, University of Montreal, Montreal, Quebec, Canada
- Faculty of Medicine, Université Laval, Quebec City, Quebec, Canada
| | - Alain Bouthillier
- Division of Neurosurgery, University of Montreal Hospital Center, Montreal, Quebec, Canada
| | - Boris C Bernhardt
- McConnell Brain Imaging Center, Montreal Neurological Institute and Hospital, McGill University, Quebec, Canada
| | - Dang K Nguyen
- Division of Neurology, University of Montreal Medical Center, Montreal, Quebec, Canada
| | - Aria Fallah
- Department of Neurosurgery, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, California, USA
- Department of Pediatrics, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, California, USA
| | - Alexander G Weil
- Division of Pediatric Neurosurgery, Department of Surgery, Sainte Justine Hospital, University of Montreal, Montreal, Quebec, Canada
- Division of Neurosurgery, University of Montreal Hospital Center, Montreal, Quebec, Canada
- Brain and Child Development Axis, Sainte Justine Research Center, Montreal, Quebec, Canada
| |
Collapse
|
4
|
Gaur S, Panda A, Fajardo JE, Hamilton J, Jiang Y, Gulani V. Magnetic Resonance Fingerprinting: A Review of Clinical Applications. Invest Radiol 2023; 58:561-577. [PMID: 37026802 PMCID: PMC10330487 DOI: 10.1097/rli.0000000000000975] [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] [Indexed: 04/08/2023]
Abstract
ABSTRACT Magnetic resonance fingerprinting (MRF) is an approach to quantitative magnetic resonance imaging that allows for efficient simultaneous measurements of multiple tissue properties, which are then used to create accurate and reproducible quantitative maps of these properties. As the technique has gained popularity, the extent of preclinical and clinical applications has vastly increased. The goal of this review is to provide an overview of currently investigated preclinical and clinical applications of MRF, as well as future directions. Topics covered include MRF in neuroimaging, neurovascular, prostate, liver, kidney, breast, abdominal quantitative imaging, cardiac, and musculoskeletal applications.
Collapse
Affiliation(s)
- Sonia Gaur
- Department of Radiology, Michigan Medicine, Ann Arbor, MI
| | - Ananya Panda
- All India Institute of Medical Sciences, Jodhpur, Rajasthan, India
| | | | - Jesse Hamilton
- Department of Radiology, Michigan Medicine, Ann Arbor, MI
| | - Yun Jiang
- Department of Radiology, Michigan Medicine, Ann Arbor, MI
| | - Vikas Gulani
- Department of Radiology, Michigan Medicine, Ann Arbor, MI
| |
Collapse
|
5
|
Madireddy S, Madireddy S. Therapeutic Strategies to Ameliorate Neuronal Damage in Epilepsy by Regulating Oxidative Stress, Mitochondrial Dysfunction, and Neuroinflammation. Brain Sci 2023; 13:brainsci13050784. [PMID: 37239256 DOI: 10.3390/brainsci13050784] [Citation(s) in RCA: 13] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Revised: 05/09/2023] [Accepted: 05/10/2023] [Indexed: 05/28/2023] Open
Abstract
Epilepsy is a central nervous system disorder involving spontaneous and recurring seizures that affects 50 million individuals globally. Because approximately one-third of patients with epilepsy do not respond to drug therapy, the development of new therapeutic strategies against epilepsy could be beneficial. Oxidative stress and mitochondrial dysfunction are frequently observed in epilepsy. Additionally, neuroinflammation is increasingly understood to contribute to the pathogenesis of epilepsy. Mitochondrial dysfunction is also recognized for its contributions to neuronal excitability and apoptosis, which can lead to neuronal loss in epilepsy. This review focuses on the roles of oxidative damage, mitochondrial dysfunction, NAPDH oxidase, the blood-brain barrier, excitotoxicity, and neuroinflammation in the development of epilepsy. We also review the therapies used to treat epilepsy and prevent seizures, including anti-seizure medications, anti-epileptic drugs, anti-inflammatory therapies, and antioxidant therapies. In addition, we review the use of neuromodulation and surgery in the treatment of epilepsy. Finally, we present the role of dietary and nutritional strategies in the management of epilepsy, including the ketogenic diet and the intake of vitamins, polyphenols, and flavonoids. By reviewing available interventions and research on the pathophysiology of epilepsy, this review points to areas of further development for therapies that can manage epilepsy.
Collapse
Affiliation(s)
- Sahithi Madireddy
- Department of Biology, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
| | | |
Collapse
|