Do temporal changes in facial expressions help identify patients at risk of deterioration in hospital wards? A post-hoc analysis of the VIEWS study
2020
Objectives: To determine whether time series analysis and Shannon information entropy of facial
expressions predict acute clinical deterioration in patients on general hospital wards.
Design: Post-hoc analysis of a prospective observational feasibility study (VIEWS study)
Setting: General ward patients in a Community Hospital
Patients: Thirty-four patients at risk of clinical deterioration
Interventions: A 3 minute video (153000 frames) for each of the patients enrolled into the VIEWS
study database was analysed by a trained psychologist for facial expressions measured as Action
Units (AU) using the Facial Action Coding System (FACS).
Measurements and Main Results: 3688 AU were analysed over the 34 three-minute study periods.
The AU time variables considered were onset, apex, offset and total time duration. A generalized
linear regression model and time series analyses were performed. Shannon Information entropy
(Hn) and Diversity (Dn) were calculated from the frequency and repertoire of facial expressions.
Patients subsequently admitted to critical care displayed a reduced frequency rate (95% CI moving
average of the mean: 9.5-10.9 vs. 26.1-28.9 in those not admitted), a higher Shannon information
entropy (0.30±0.06 vs. 0.26±0.05, p=0.019) and a prolonged AU reaction time (23.5 vs. 9.4 seconds)
compared to patients not admitted to ICU. The number of AU identified per window within the
time-series analysis predicted admission to critical care with an area under the curve (AUC) of 0.88.
The AUC for NEWS alone, Hn alone, NEWS plus Hn, and NEWS plus Hn plus Dn were 0.53, 0.75, 0.76
and 0.81, respectively.
Conclusion: Time-series analysis and Shannon information theory applied to facial AU identified a
decreased frequency and a higher information entropy of facial expression in patients at risk of
deterioration in hospital wards.
Keywords:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
0
References
0
Citations
NaN
KQI