Weitere Kapitel dieses Buchs durch Wischen aufrufen
We have recently studied the rapidly increasing stroke in the elderly. Stroke focuses on extracting meaningful variables for early diagnosis because early diagnosis has a strong influence on the survival probability. Therefore, we proceeded as follows. We measured vital signs and motion data from 80 stroke patients and 50 normal elderly. This study is part of a study to compare the data patterns of the elderly people by measuring daily life data, motion data, body pressure, EEG (electroencephalogram), ECG (Electrocardiogram), EMG (electromyography), GSR (galvanic skin reflex) data of stroke patients. We experimented with scenarios (walking, moving objects, sitting, etc.) to get natural daily data from stroke patients.
We found that the data of the stroke patients and the normal elderly group were clearly differentiated by the R-R interval parameter of the ECG data and the brain wave data of the frontal and temporal lobe among the EEG data (p < 0.05). These features are analyzed to develop algorithms that can detect strokes early, compared with the conventional NIHSS questionnaire to determine stroke patients or the way physicians diagnose. In addition, the bio-signal data is extracted from the experiment, and a judgment model is established by taking the data of the participant’s 10-year health examination together. This data includes various screening data such as height, smoking, exercise, triglyceride, LDL-cholesterol, and HDL-cholesterol.
In addition to analyzing these vital signs and analysis data, we are analyzing the cohort data of 2.5 million health checkup patients in the stroke patients group to improve the accuracy of the diagnostic algorithm by extracting the factors influencing the stroke.
The purpose of our research is to detect stroke in advance using big data and bio-signal analysis technology, and contribute to human health promotion. The data we are measuring is the data that elderly people often live in daily life. In this experiment, data were measured with professional measurement equipment, but items measurable in wearable device were selected for future service commercialization. Because, in the future, the patient must be informed about his or her health condition before going to the hospital. Therefore, if we introduce the early detection algorithm of stroke, we think that many people will be able to detect the stroke early and save many lives without going to the hospital.
Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten
Sie möchten Zugang zu diesem Inhalt erhalten? Dann informieren Sie sich jetzt über unsere Produkte:
Park SJ, Hong S, Kim D, Seo Y et al (2018) Development of a real-time stroke detection system for elderly drivers using quad-chamber air cushion and IoT devices. SAE Technical Paper 2018-01-0046. https://doi.org/10.4271/2018-01-0046
Park SJ, Subramaniyam M, Hong S, Kim D, Yu J (2017) Conceptual design of the elderly healthcare services in-vehicle using IoT. SAE Technical paper (No. 2017-01-1647)
Park SJ, Subramaniyam M, Kim SE, Hong SH, Lee JH, Jo CM (2017) Older driver’s physiological response under risky driving conditions–overtaking, unprotected left turn. In: Duffy V (ed) Advances in applied digital human modeling and simulation, AISC, vol 481. Springer, Heidelberg, pp 107–114. https://doi.org/10.1007/978-3-319-41627-4_11
Park SJ, Min SN, Lee H, Subramaniyam M (2015) A driving simulator study: elderly and younger driver’s physiological, visual and driving behavior on intersection. In: IEA 2015, Melbourne, Australia
- Analysis of Bio-signal Data of Stroke Patients and Normal Elderly People for Real-Time Monitoring
Se Jin Park
Neuer Inhalt/© ITandMEDIA, Best Practices für die Mitarbeiter-Partizipation in der Produktentwicklung/© astrosystem | stock.adobe.com