Dharma Abdi, Sihombing Poltak, Efendi Syahril, Mawengkang Herman, Turnip Arjon
Department of Computer Science, Faculty of Computer Science and Information Technology, Universitas Sumatera Utara, Medan, Indonesia.
Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Sumatera Utara, Medan, Indonesia.
J Biomed Phys Eng. 2025 Aug 1;15(4):393-406. doi: 10.31661/jbpe.v0i0.2411-1856. eCollection 2025 Aug.
The increasing prevalence of cardiovascular diseases underscores the need for efficient and user-friendly tools to monitor heart health. Traditional Holter monitors, while effective, are often bulky and inconvenient, limiting their use in real-world scenarios. This study introduces the Smart Portable Holter, a wireless device designed for real-time cardiac monitoring, enabling early detection of heart irregularities with enhanced accuracy and user convenience. The device captures continuous electrocardiogram signals and transmits them to a secure cloud platform for processing. Machine learning models, including Random Forest and Extreme Gradient Boosting (XGBoost), analyze the data to detect cardiac events. The system's performance was evaluated using real-world datasets, emphasizing accuracy and reliability in identifying cardiac arrhythmias. The Smart Portable Holter delivers an impressive 98% accuracy in detecting cardiac events. Its compact and wireless design enhances user comfort, allowing for seamless wear throughout the day. Coupled with advanced analytics, it offers detailed, time-stamped records that empower both users and healthcare professionals. These features facilitated early diagnosis and supported personalized treatment planning for patients with varying cardiac conditions. The Smart Portable Holter represents a significant advancement in cardiac care, combining portability, real-time analytics, and high diagnostic accuracy. By empowering patients and healthcare providers with actionable insights, it fosters proactive heart health management and contributes to improved clinical outcomes.
心血管疾病患病率的不断上升凸显了对高效且用户友好的心脏健康监测工具的需求。传统的动态心电图监测仪虽然有效，但通常体积庞大且使用不便，限制了其在实际场景中的应用。本研究介绍了智能便携式动态心电图监测仪，这是一种用于实时心脏监测的无线设备，能够以更高的准确性和用户便利性早期检测出心脏异常。该设备可捕获连续的心电图信号，并将其传输到安全的云平台进行处理。包括随机森林和极端梯度提升（XGBoost）在内的机器学习模型对数据进行分析，以检测心脏事件。使用真实世界数据集对该系统的性能进行了评估，重点在于识别心律失常时的准确性和可靠性。智能便携式动态心电图监测仪在检测心脏事件方面的准确率高达98%，令人印象深刻。其紧凑的无线设计提高了用户的舒适度，可实现全天无缝佩戴。再加上先进的分析功能，它提供详细的、带时间戳的记录，这对用户和医疗保健专业人员都有帮助。这些功能有助于早期诊断，并为患有不同心脏疾病的患者支持个性化治疗方案的制定。智能便携式动态心电图监测仪代表了心脏护理领域的一项重大进步，它将便携性、实时分析和高诊断准确性结合在一起。通过为患者和医疗保健提供者提供可采取行动的见解，它促进了积极主动的心脏健康管理，并有助于改善临床结果。
