RT Journal Article
SR Electronic
T1 Temporal prediction of in-hospital falls using tensor factorisation
JF BMJ Innovations
JO BMJ Innov
FD All India Institute of Medical Sciences
SP bmjinnov-2017-000221
DO 10.1136/bmjinnov-2017-000221
A1 Haolin Wang
A1 Qingpeng Zhang
A1 Hing-Yu So
A1 Angela Kwok
A1 Zoie Shui-Yee Wong
YR 2018
UL http://innovations.bmj.com/content/early/2018/03/09/bmjinnov-2017-000221.abstract
AB In-hospital fall incidence is a critical indicator of healthcare outcome. Predictive models for fall incidents could facilitate optimal resource planning and allocation for healthcare providers. In this paper, we proposed a tensor factorisation-based framework to capture the latent features for fall incidents prediction over time. Experiments with real-world data from local hospitals in Hong Kong demonstrated that the proposed method could predict the fall incidents reasonably well (with an area under the curve score around 0.9). As compared with the baseline time series models, the proposed tensor based models were able to successfully identify high-risk locations without records of fall incidents during the past few months.