Naslov
Automatic classifier based on heart rate variability to identify fallers among hypertensive subjects

Autori
Melillo, Paolo ; Jović, Alan ; De Luca, Nicola ; Pecchia, Leandro

Izvornik
Healthcare technology letters (2053-3713) 2 (2015), 2; 1-6

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Fall detection ; Data mining ; Support vector machines ; Signal processing ; Electrocardiography ; Algorithms ; Artificial intelligence ; Assistive technology ; Decision support systems

Sažetak
Accidental falls are a major problem of later life. Different technologies to predict falls have been investigated, but with limited success, mainly because of low specificity due to high false positive rate. This paper presents an automatic classifier based on heart rate variability (HRV) analysis with the goal to identify fallers automatically. HRV was used in this study as it is considered a good estimator of autonomic nervous system (ANS) states, which are responsible, among other things, for human balance control. Nominal 24h ECG recordings from 168 cardiac patients (age 72 ± 8 years, 60 female), of which 47 fallers, were investigated. Linear and nonlinear HRV properties were analyzed in 30-minute excerpts. Different data mining approaches were adopted and their performances were compared with a subject-based Receiver Operating Characteristic (ROC) analysis. The best performance was achieved by a hybrid algorithm, RUSBoost, integrated with feature selection method based on principal component analysis, which achieved satisfactory specificity and accuracy (80% and 72% respectively), but low sensitivity (51%). These results suggested that ANS states causing falls could have been reliable detected, but not all the falls were due to ANS states.

Izvorni jezik
Engleski

Znanstvena područja
Računarstvo, Kliničke medicinske znanosti

POVEZANOST RADA