Requirement Analysis for Data-Driven Electroencephalography Seizure Monitoring Software to Enhance Quality and Decision Making in Digital Care Pathways for Epilepsy: A Feasibility Study from the Perspectives of Health Care Professionals
Bibliographic record
Abstract
BACKGROUND: Abnormal brain activity is the source of epileptic seizures, which can present a variety of symptoms and influence patients' quality of life. Therefore, it is critical to track epileptic seizures, diagnose them, and provide potential therapies to manage people with epilepsy. Electroencephalography (EEG) is helpful in the diagnosis and classification of the seizure type, epilepsy, or epilepsy syndrome. Ictal EEG is rarely recorded, whereas interictal EEG is more often recorded, and the results can be abnormal or normal even in the case of epilepsy. The current digital care pathway for epilepsy (DCPE) lacks the integration of data-driven seizure detection, which could potentially enhance epilepsy treatment and management. OBJECTIVE: This study aimed to determine the requirements for integrating data-driven medical software into the DCPE to meet the project's goals and demonstrate practical feasibility regarding resource availability, time constraints, and technological capabilities. This adjustment emphasized ensuring that the proposed system is realistic and achievable. Perspectives on the feasibility of data-driven medical software that meets the project's goals and demonstrates practical feasibility regarding resource availability, time constraints, and technological capabilities are presented. METHODS: A 4-round Delphi study using focus group discussions was conducted with 7 diverse panels of experts from Oulu University Hospital to address the research questions and evaluate the feasibility of data-driven medical software for monitoring individuals with epilepsy. This collaborative approach fostered a thorough understanding of the topic and considered the perspectives of various stakeholders. In addition, a qualitative study was carried out using semistructured interviews. RESULTS: Drawing from the findings of the thematic analytics, a detailed set of guidelines was created to facilitate the seamless integration of the proposed data-driven medical software for EEG seizure monitoring into the DCPE. These guidelines encompass system requirements, data collection and analysis, and user training, offering a comprehensive road map for the effective implementation of the software. CONCLUSIONS: The study outcome presents a comprehensive strategy for improving the quality of care, providing personalized solutions, managing health care resources, and using artificial intelligence and sensor technology in clinical settings. The potential of artificial intelligence and sensor technology to revolutionize health care is exciting. The study identified practical strategies, such as real-time EEG seizure monitoring, predictive modeling for seizure occurrence, and data-driven analytics integration to enhance decision-making. These strategies were aimed at reducing diagnostic delays and providing personalized care. We are actively working on integrating these features into clinical workflows. However, further case studies and pilot implementations are planned for future studies. The results of this study will guide system developers in the meticulous design and development of systems that meet user needs in the DCPE.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.066 | 0.098 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".