Facemask Signs Sickness Via Density Neural Complex
Main Article Content
Abstract
Facial and bodily (clinical gestalt) in Deep learning (DL) models improve the assessment of patients’ health status, as shown in genetic syndromes and acute coronary syndrome. It is unknown if the inclusion of clinical gestalt improves classification of acutely ill patients. As in previous research in DL analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt. In this study, we developed a computer-aided diagnosis system for automatic Rug sick detection using Facial Cue of illness images. Acutely sick people were rated by naive observers as having paler lips and skin, a more swollen face, droopier corners of the mouth, more hanging eyelids, redder eyes, and less glossy and patchy skin, as well as appearing more tired. Our findings suggest that facial cues associated with the skin, mouth and eyes can aid in the detection of acutely sick and potentially contagious people. We employed deep transfer learning to handle the scarcity of available data and designed a Neural Network (CNN) model along with the four transfer learning methods: VGG16, VGG19, InceptionV3, Xception and ResNet50. Where, in the existing methods ResNet101 is used that which did not got the proper accuracy and that tend to be improved. Hence the present method with other transfer learning methods is proposed. The proposed approach was evaluated on publicly available Facial Cue of illness dataset.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
How to Cite
References
G, Nilsen RM, Flaatten H, SolligårdE, Frich JC, Bondevik GT,et al. Early diagnosis of epsis in emergency departments, time to treatment, and association with mortality: an observational study.
Rothberg MB, Shieh MS, Pekow PS, Steingrub JS, Lindenauer PK. Hospitalizations, costs, and out comes of severesepsis in the United States 2003 to 2007.
R, Pavenstädt H, Kümpers P. Sepsis recognition in the emergency department–impact on quality of care and outcome? BMC Emerge Med. (2017)
D, Seymour CW, Shankar-HariM, Annane D, BauerM, et al. The third international consensus definitions for sepsis and septics hock (Sepsis-3).
Komorowski M, Celi LA, Badawi O, Gordon AC, Faisal AA. The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care. Nat Med. (2018).
Zwager CL, Schoon made LJ, Guo T, RoggeveenLF, et al. Machine learning for the prediction of sepsis: a systematic reviewand meta-analysis of diagnostic test accuracy.
Jay M, Hoffman JL, Calvert J, Barton C, Shimabukuro D, et al.Multi centre validation of a sepsis prediction algorithm using only vital sign data in the emergency department, general ward and ICU. BMS Open.
F, Svantesson M, Bassford C, Dale J, Blake C, McCreedy A,et al. Decision-making around admission to intensive care in the UK pre-COVID-19: a multicentre ethnographic study. Anaesthesia.(2020).
C, Morris N, Body R. Can emergency physician gestalt “Rule In” or “Rule Out” acute coronary syndrome: validation in a multicentre prospective diagnostic cohort study. Acad Emerg Med. (2020).
A, Breedveld R, terAvest E. HEART score and clinical gestalt have similar diagnostic accuracy for diagnosing ACS in an unselected population of patients with chest pain presenting in the ED.
C, Ebell MH. Clinical gestalt to diagnose Facial Cues, sinusitis, and pharyngitis: a meta-analysis. Br J Gen Pract. (2019) 69:e444–53.
F, Delarche N, Faure I, Pradeau C, Thicoipe M, et al.Predictive criteria for acute heart failure in emergency department patientswith acute dyspnoea: the PREDICA study. Eur J Emerg Med. (2019).