DIGITAL PHENOTYPING AND NEUROLOGICAL DISORDERS: EMPHASIS ON EPILEPSY

M. Di Giannantonio^*

Department of Neuroscience, Imaging and Clinical Sciences, “G. d’Annunzio” University, Chieti, Italy.

*Correspondence to:
Massimo Di Giannantonio,
Department of Neuroscience, Imaging and Clinical Sciences,
“G. d’Annunzio” University,
Chieti, Italy.
e-mail: digiannantonio@unich.it

Received: 31 March, 2026 Accepted: 29 June, 2026

ISSN 2279-5855 print / 3103-7364 [online] Copyright 2026 © by Biolife Publisher This publication and/or article is for individual use only and may not be further reproduced without written permission from the copyright holder. Unauthorized reproduction may result in financial and other penalties. Disclosure: All authors report no conflicts of interest relevant to this article.

ABSTRACT

Neurological disorders encompass a wide range of conditions affecting the central and peripheral nervous systems, leading to motor, cognitive, autonomic, and emotional impairments. Diseases such as Parkinson’s disease, multiple sclerosis, Alzheimer’s disease, epilepsy, and stroke can significantly impact physiological and behavioral functions. Digital biomarkers derived from smartphones, wearable devices, global positioning systems (GPS), accelerometers, and other sensors provide objective and continuous measurements of clinical status, disease progression, and treatment response. Through digital phenotyping, real-world behavioral and physiological data can be collected and analyzed to improve disease monitoring and patient management. These technologies enable the early detection of subtle changes in motor, cognitive, and functional performance that may not be captured during routine clinical assessments. Continuous remote monitoring supports personalized care, precision medicine, standardized measurements, reduced hospital visits, and improved quality of life. In epilepsy, digital phenotyping facilitates the monitoring of seizures, sleep patterns, treatment adherence, daily activities, and seizure triggers through wearable technologies and artificial intelligence (AI). Despite its potential, challenges related to device accuracy, privacy protection, and clinical validation remain important considerations. At the biological level, epilepsy is associated with complex genetic, molecular, and cellular alterations, including ion channel dysfunction, neurotransmitter imbalances, neuroinflammation, astrocyte abnormalities, and neuronal hyperexcitability. The integration of digital biomarkers with genetic, molecular, cellular, and electrophysiological phenotyping offers a comprehensive multilevel approach to neurological disorders, supporting precision medicine and the development of targeted therapeutic strategies.

KEYWORDS: Digital phenotyping, neurological disorder, epilepsy, digital biomarker, digital data

INTRODUCTION

Neurological disorders affect the central nervous system (CNS) and peripheral nerves and therefore, both physical and mental functioning (1).  Depending on the specific neurological condition, which include Parkinson’s disease, multiple sclerosis, Alzheimer’s disease, epilepsy, and stroke, they can affect various functions, such as movement, coordination, anxiety, depression, changes in the perception of heat and cold, blood pressure, heart rate, breathing, sweating, bowel function, and many others (2). In neurology, potential digital biomarkers enable objective and continuous measures that can reflect clinical status, disease progression, level of independence, treatment response, and quality of life (3).

Digital phenotyping is the process of continuously collecting and analyzing data generated by smartphones, global positioning systems (GPS), wearable devices, and other digital sensors to characterize an individual’s behavior, physiology, sleep-wake patterns, and daily functioning (4).  Digital phenotyping is one of the most promising innovations in modern neurology (5). Through smartphones, sensors, and wearable devices, it is possible to obtain continuous and objective digital biomarkers that help monitor the progression of neurological diseases, evaluate the effectiveness of treatments, and promote an increasingly personalized approach to patient care (6). In neurology, this methodology allows patients to be monitored in their real-world environment, providing information that complements traditional clinical assessments (6).

DIGITAL PHENOTYPING

Digital devices enable the detection of even minimal and early changes, transforming behavioral data into digital biomarkers (7). Digital devices (passive sensors), such as smartphone sensors, accelerometers, GPS, gyroscopes, and others, collect information without requiring patient intervention (8).

Data collected via smartphones allows for a continuous assessment of motor status, often more representative than periodic visits (9). In dementias such as Alzheimer’s disease, biomarkers can detect early cognitive decline, disruptions in daily routines, reduced mobility, changes in social interactions, and spatial disorientation (10). Analysis of movement patterns and smartphone use can help identify early cognitive decline (11). In multiple sclerosis, digital phenotyping helps monitor fatigue, cognitive function, balance, and walking ability (7) (Table I).

Table I.  Table describing the options for collecting and processing digital data.

In stroke patients, digital phenotyping can monitor many parameters, such as response to rehabilitation, social participation, motor recovery, sleep duration and regularity, mobility in daily life, and language improvement (12). Continuous and remote monitoring can bring benefits such as early identification of clinical changes, personalized therapies, reduced frequency of hospital visits, support for precision medicine, accuracy and standardization of measurements, and protection of privacy and personal data (13).

In epilepsy, digital devices can be used for seizure monitoring, sleep assessment, patient safety monitoring, early warning signs identification, and analysis of daily activity (11).

Epilepsy

In epilepsy, digital phenotyping can be used to detect changes in sleep patterns, which can influence seizure risk, monitor seizures using motion sensors, analyze physical activity and daily routines to identify potential triggers, assess treatment adherence through apps that track medication intake, and predict periods of increased risk using artificial intelligence (AI) algorithms that integrate various physiological parameters (14).  Digital devices can offer advantages such as more continuous monitoring compared to periodic visits and better personalized care (15). However, the use of this method still has several limitations related to device accuracy, personal data protection, and the need for clinical validation (16).

The biological mechanisms at play in epilepsy include ion channel mutation, excitatory/inhibitory imbalance with GABA reduction, neuroinflammation, and astrocyte dysfunction. Epilepsies can result from alterations in numerous genes and molecular pathways, such as mutations in genes encoding neuronal ion channels, such as sodium, potassium, calcium, and chloride, which alter neuronal excitability (17). Alterations in synaptic transmission, such as a reduction in GABA-mediated inhibition and an increase in glutamatergic excitatory transmission, can also occur (18).  Epilepsies often involve dysregulation of intracellular pathways, such as the mTOR signalling pathway, associated with cortical malformations (19). Furthermore, epileptic neuroinflammation can cause an increase in proinflammatory cytokines (IL-1β, TNF) and activation of microglia and astrocytes (20).  Epilepsy also results in neuronal hyperexcitability with a reduction in the firing threshold, an increase in the frequency of action potentials, pathological synchronization of neuronal groups that promote seizure generation, and alterations in neuronal morphology with dendritic changes (21). In this context, astrocytes are important because they play a crucial role in controlling the extracellular environment by altering extracellular potassium buffering, reducing glutamate uptake, and releasing inflammatory mediators (21). All these biological effects can increase the excitability of neuronal networks.

Cellular phenotyping also includes the study of networks with an imbalance between excitatory and inhibitory neurons, circuit reorganization after brain injury, and axonal sprouting phenomena, such as “mossy fiber sprouting” in temporal lobe epilepsy.

To characterize all these phenotypes, various techniques are used, such as genomic and exomic sequencing, single-cell transcriptomics (single-cell RNA-seq), metabolomic proteomics, patient-derived induced pluripotent stem cells (iPSCs), electrophysiological recordings (patch-clamp), calcium imaging, and animal models and brain organoids (22,23).

CONCLUSIONS

The integration of genetic, molecular, cellular, and electrophysiological data now enables multilevel phenotyping of neurological diseases, including epilepsy, which is essential for precision medicine and the development of targeted therapies.

Conflict of interest

The author declares that they have no conflict of interest.

REFERENCES

1. Socała K, Doboszewska U, Szopa A, et al. The role of microbiota-gut-brain axis in neuropsychiatric and neurological disorders. Pharmacological Research. 2021;172(105840):105840. doi:https://doi.org/10.1016/j.phrs.2021.105840
2. Fan LY, Yang J, Liu RY, Kong Y, Guo GY, Xu YM. Integrating single-nucleus sequence profiling to reveal the transcriptional dynamics of Alzheimer’s disease, Parkinson’s disease, and multiple sclerosis. Journal of translational medicine. 2023;21(1). doi:https://doi.org/10.1186/s12967-023-04516-6
3. Youn BY, Ko Y, Moon S, Lee J, Ko SG, Kim JY. Digital Biomarkers for Neuromuscular Disorders: A Systematic Scoping Review. Diagnostics. 2021;11(7):1275. doi:https://doi.org/10.3390/diagnostics11071275
4. Tonon AC, Nexha A, Mendonça M, Gomes FA, Hidalgo MP, Frey BN. Sleep and circadian disruption in bipolar disorders: From psychopathology to digital phenotyping in clinical practice. Psychiatry and Clinical Neurosciences. 2024;78(11):654-666. doi:https://doi.org/10.1111/pcn.13729
5. Bethlehem RAI, Seidlitz J, White SR, et al. Brain Charts for the Human Lifespan. Nature. 2022;604(604):1-11. doi:https://doi.org/10.1038/s41586-022-04554-y
6. Harris C, Tang Y, Birnbaum E, Cherian C, Mendhe D, Chen MH. Digital Neuropsychology beyond Computerized Cognitive Assessment: Applications of Novel Digital Technologies. Archives of Clinical Neuropsychology. 2024;39(3):290-304. doi:https://doi.org/10.1093/arclin/acae016
7. Dillenseger A, Weidemann ML, Trentzsch K, et al. Digital Biomarkers in Multiple Sclerosis. Brain Sciences. 2021;11(11):1519. doi:https://doi.org/10.3390/brainsci11111519
8. Snyder CW, Dorsey ER, Atreja A. The Best Digital Biomarkers Papers of 2017. Digital Biomarkers. 2018;2(2):64-73. doi:https://doi.org/10.1159/000489224
9. Karen A, Hirt J, Woelfle T, Janiaud P, Hemkens LG. Definitions of digital biomarkers: a systematic mapping of the biomedical literature. BMJ health & care informatics. 2024;31(1):e100914-e100914. doi:https://doi.org/10.1136/bmjhci-2023-100914
10. Qi W, Zhu X, Wang B, et al. Alzheimer’s disease digital biomarkers multidimensional landscape and AI model scoping review. npj Digital Medicine. 2025;8(1). doi:https://doi.org/10.1038/s41746-025-01640-z
11. Hay SI, Ong KL, Santomauro DF, et al. Burden of 375 diseases and injuries, risk-attributable burden of 88 risk factors, and healthy life expectancy in 204 countries and territories, including 660 subnational locations, 1990–2023: a systematic analysis for the Global Burden of Disease Study 2023. The Lancet. 2025;406(10513):1873-1922. doi:https://doi.org/10.1016/s0140-6736(25)01637-x
12. Lee H, Deignan JL, Dorrani N, et al. Clinical Exome Sequencing for Genetic Identification of Rare Mendelian Disorders. JAMA. 2014;312(18):1880. doi:https://doi.org/10.1001/jama.2014.14604
13. Alosco ML, Morrison M, Au R, et al. Boston University Alzheimer’s Disease Research Center Clinical Core: Infrastructure to facilitate research on post‐traumatic Alzheimer’s disease and related dementias. Alzheimer s & Dementia. 2025;21(9):e70654-e70654. doi:https://doi.org/10.1002/alz.70654
14. Knight A, Gschwind T, Galer P, et al. Artificial Intelligence in Epilepsy Phenotyping. Epilepsia. 2023;66(Suppl 3):39-52. doi:https://doi.org/10.1111/epi.17833
15. Adhyapak N, Cardenas GE, Abboud MA, Krishnan V. Rest‐activity rhythm phenotypes in adults with epilepsy and intellectual disability. Epilepsia Open. 2025;10(4):1086-1098. doi:https://doi.org/10.1002/epi4.70063
16. Lhatoo SD, Bernasconi N, Blumcke I, et al. Big data in epilepsy: Clinical and research considerations. Report from the Epilepsy Big Data Task Force of the International League Against Epilepsy. Epilepsia. 2020;61(9):1869-1883. doi:https://doi.org/10.1111/epi.16633
17. Bechny M, Kishi A, Fiorillo L, et al. Novel digital markers of sleep dynamics: causal inference approach revealing age and gender phenotypes in obstructive sleep apnea. Scientific Reports. 2025;15(1). doi:https://doi.org/10.1038/s41598-025-97172-3
18. Yang Y, Zhang F, Gao X, Feng L, Xu K. Progressive alterations in electrophysiological and epileptic network properties during the development of temporal lobe epilepsy in rats. Epilepsy & Behavior. 2023;141:109120. doi:https://doi.org/10.1016/j.yebeh.2023.109120
19. Ravizza T, Scheper M, Rossella Di Sapia, Gorter J, Aronica E, Vezzani A. mTOR and neuroinflammation in epilepsy: implications for disease progression and treatment. Nature reviews Neuroscience (Print). 2024;25(5):334-350. doi:https://doi.org/10.1038/s41583-024-00805-1
20. Soltani Khaboushan A, Yazdanpanah N, Rezaei N. Neuroinflammation and Proinflammatory Cytokines in Epileptogenesis. Molecular Neurobiology. 2022;59(3):1724-1743. doi:https://doi.org/10.1007/s12035-022-02725-6
21. Vezzani A, Ravizza T, Bedner P, Aronica E, Steinhäuser C, Boison D. Astrocytes in the initiation and progression of epilepsy. Nature Reviews Neurology. 2022;18(12):707-722. doi:https://doi.org/10.1038/s41582-022-00727-5
22. Smedley D, Smith KR, Martin A, et al. 100,000 Genomes Pilot on Rare-Disease Diagnosis in Health Care — Preliminary Report. New England Journal of Medicine. 2021;385(20):1868-1880. doi:https://doi.org/10.1056/nejmoa2035790
23. Koga Y, Daisuke Tsuchimoto, Hayashi Y, et al. Neural stem cell–specific ITPA deficiency causes neural depolarization and epilepsy. JCI Insight. 2020;5(22). doi:https://doi.org/10.1172/jci.insight.140229