Orejel Bustos Amaranta Soledad, Tramontano Marco, Morone Giovanni, Ciancarelli Irene, Panza Giuseppe, Minnetti Andrea, Picelli Alessandro, Smania Nicola, Iosa Marco, Vannozzi Giuseppe
Fondazione Santa Lucia IRCCS, Rome, Italy.
Department of Life, Health and Environmental Sciences, University of L'Aquila, L'Aquila, Italy.
Expert Rev Med Devices. 2023 Jul-Dec;20(10):821-828. doi: 10.1080/17434440.2023.2245320. Epub 2023 Aug 23.
Monitoring systems at home are critical in the event of a fall, and can range from standalone fall detection devices to activity recognition devices that aim to identify behaviors in which the user may be at risk of falling, or to detect falls in real-time and alert emergency personnel.
This review analyzes the current literature concerning the different devices available for home fall detection.
Included studies highlight how fall detection at home is an important challenge both from a clinical-assistance point of view and from a technical-bioengineering point of view. There are wearable, non-wearable and hybrid systems that aim to detect falls that occur in the patient's home. In the near future, a greater probability of predicting falls is expected thanks to an improvement in technologies together with the prediction ability of machine learning algorithms. Fall prevention must involve the clinician with a person-centered approach, low cost and minimally invasive technologies able to evaluate the movement of patients and machine learning algorithms able to make an accurate prediction of the fall event.
在发生跌倒时，家庭监测系统至关重要，其范围从独立的跌倒检测设备到旨在识别用户可能有跌倒风险的行为、或实时检测跌倒并提醒急救人员的活动识别设备。
本综述分析了有关可用于家庭跌倒检测的不同设备的当前文献。
纳入的研究强调，从临床辅助角度和技术生物工程角度来看，家庭跌倒检测都是一项重要挑战。有旨在检测患者家中发生的跌倒的可穿戴、非可穿戴和混合系统。在不久的将来，由于技术的改进以及机器学习算法的预测能力，预计预测跌倒的可能性会更大。预防跌倒必须让临床医生采用以人为本的方法，采用低成本、微创技术来评估患者的运动，以及采用能够准确预测跌倒事件的机器学习算法。
