Keikhosrokiani Pantea, Annunen Johanna, Komulainen-Ebrahim Jonna, Kortelainen Jukka, Kallio Mika, Vieira Päivi, Isomursu Minna, Uusimaa Johanna
Empirical Software Engineering in Software Systems and Services, Faculty of Information Technology and Electrical Engineering, University of Oulu, Oulu, Finland.
Research Unit of Health Sciences and Technology, Faculty of Medicine, University of Oulu, Oulu, Finland.
JMIR Hum Factors. 2025 May 30;12:e59558. doi: 10.2196/59558.
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.
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.
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.
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.
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.
大脑异常活动是癫痫发作的根源，癫痫发作会呈现出各种症状并影响患者的生活质量。因此，追踪癫痫发作、进行诊断并提供潜在治疗方法以管理癫痫患者至关重要。脑电图（EEG）有助于癫痫发作类型、癫痫或癫痫综合征的诊断和分类。发作期脑电图很少被记录，而发作间期脑电图记录更为常见，即使在癫痫患者中，其结果也可能正常或异常。当前的癫痫数字护理路径（DCPE）缺乏数据驱动的癫痫发作检测整合，而这有可能加强癫痫的治疗和管理。
本研究旨在确定将数据驱动的医疗软件整合到DCPE中的要求，以实现项目目标，并在资源可用性、时间限制和技术能力方面证明实际可行性。这种调整强调确保所提议的系统切实可行且能够实现。本文介绍了关于符合项目目标并在资源可用性、时间限制和技术能力方面证明实际可行性的数据驱动医疗软件可行性的观点。
采用焦点小组讨论的方式，对奥卢大学医院的7个不同专家小组进行了4轮德尔菲研究，以解决研究问题并评估用于监测癫痫患者的数据驱动医疗软件的可行性。这种协作方法促进了对该主题的深入理解，并考虑了不同利益相关者的观点。此外，还使用半结构化访谈进行了定性研究。
根据主题分析的结果，制定了一套详细的指南，以促进将提议的用于脑电图癫痫发作监测的数据驱动医疗软件无缝整合到DCPE中。这些指南涵盖系统要求、数据收集与分析以及用户培训，为软件的有效实施提供了全面的路线图。
研究结果提出了一项全面战略，用于提高护理质量、提供个性化解决方案、管理医疗资源以及在临床环境中使用人工智能和传感器技术。人工智能和传感器技术变革医疗保健的潜力令人兴奋。该研究确定了一些实际策略，如实时脑电图癫痫发作监测、癫痫发作发生的预测建模以及数据驱动分析的整合以加强决策制定。这些策略旨在减少诊断延迟并提供个性化护理。我们正在积极致力于将这些功能整合到临床工作流程中。然而，计划在未来的研究中进行进一步的案例研究和试点实施。本研究结果将指导系统开发者精心设计和开发满足DCPE中用户需求的系统。
