Cargando…

Deep Learning for Identification of Acute Illness and Facial Cues of Illness

Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves 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 ML-based classificati...

Descripción completa

Detalles Bibliográficos
Autores principales: Forte, Castela, Voinea, Andrei, Chichirau, Malina, Yeshmagambetova, Galiya, Albrecht, Lea M., Erfurt, Chiara, Freundt, Liliane A., Carmo, Luisa Oliveira e, Henning, Robert H., van der Horst, Iwan C. C., Sundelin, Tina, Wiering, Marco A., Axelsson, John, Epema, Anne H.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8350122/
https://www.ncbi.nlm.nih.gov/pubmed/34381793
http://dx.doi.org/10.3389/fmed.2021.661309
_version_ 1783735686390611968
author Forte, Castela
Voinea, Andrei
Chichirau, Malina
Yeshmagambetova, Galiya
Albrecht, Lea M.
Erfurt, Chiara
Freundt, Liliane A.
Carmo, Luisa Oliveira e
Henning, Robert H.
van der Horst, Iwan C. C.
Sundelin, Tina
Wiering, Marco A.
Axelsson, John
Epema, Anne H.
author_facet Forte, Castela
Voinea, Andrei
Chichirau, Malina
Yeshmagambetova, Galiya
Albrecht, Lea M.
Erfurt, Chiara
Freundt, Liliane A.
Carmo, Luisa Oliveira e
Henning, Robert H.
van der Horst, Iwan C. C.
Sundelin, Tina
Wiering, Marco A.
Axelsson, John
Epema, Anne H.
author_sort Forte, Castela
collection PubMed
description Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves 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 ML-based classification of acutely ill patients. As in previous research in ML analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt. Objective: To assess whether a deep learning algorithm trained on a dataset of simulated and augmented facial photographs reflecting acutely ill patients can distinguish between healthy and LPS-infused, acutely ill individuals. Methods: Photographs from twenty-six volunteers whose facial features were manipulated to resemble a state of acute illness were used to extract features of illness and generate a synthetic dataset of acutely ill photographs, using a neural transfer convolutional neural network (NT-CNN) for data augmentation. Then, four distinct CNNs were trained on different parts of the facial photographs and concatenated into one final, stacked CNN which classified individuals as healthy or acutely ill. Finally, the stacked CNN was validated in an external dataset of volunteers injected with lipopolysaccharide (LPS). Results: In the external validation set, the four individual feature models distinguished acutely ill patients with sensitivities ranging from 10.5% (95% CI, 1.3–33.1% for the skin model) to 89.4% (66.9–98.7%, for the nose model). Specificity ranged from 42.1% (20.3–66.5%) for the nose model and 94.7% (73.9–99.9%) for skin. The stacked model combining all four facial features achieved an area under the receiver characteristic operating curve (AUROC) of 0.67 (0.62–0.71) and distinguished acutely ill patients with a sensitivity of 100% (82.35–100.00%) and specificity of 42.11% (20.25–66.50%). Conclusion: A deep learning algorithm trained on a synthetic, augmented dataset of facial photographs distinguished between healthy and simulated acutely ill individuals, demonstrating that synthetically generated data can be used to develop algorithms for health conditions in which large datasets are difficult to obtain. These results support the potential of facial feature analysis algorithms to support the diagnosis of acute illness.
format Online
Article
Text
id pubmed-8350122
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-83501222021-08-10 Deep Learning for Identification of Acute Illness and Facial Cues of Illness Forte, Castela Voinea, Andrei Chichirau, Malina Yeshmagambetova, Galiya Albrecht, Lea M. Erfurt, Chiara Freundt, Liliane A. Carmo, Luisa Oliveira e Henning, Robert H. van der Horst, Iwan C. C. Sundelin, Tina Wiering, Marco A. Axelsson, John Epema, Anne H. Front Med (Lausanne) Medicine Background: The inclusion of facial and bodily cues (clinical gestalt) in machine learning (ML) models improves 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 ML-based classification of acutely ill patients. As in previous research in ML analysis of medical images, simulated or augmented data may be used to assess the usability of clinical gestalt. Objective: To assess whether a deep learning algorithm trained on a dataset of simulated and augmented facial photographs reflecting acutely ill patients can distinguish between healthy and LPS-infused, acutely ill individuals. Methods: Photographs from twenty-six volunteers whose facial features were manipulated to resemble a state of acute illness were used to extract features of illness and generate a synthetic dataset of acutely ill photographs, using a neural transfer convolutional neural network (NT-CNN) for data augmentation. Then, four distinct CNNs were trained on different parts of the facial photographs and concatenated into one final, stacked CNN which classified individuals as healthy or acutely ill. Finally, the stacked CNN was validated in an external dataset of volunteers injected with lipopolysaccharide (LPS). Results: In the external validation set, the four individual feature models distinguished acutely ill patients with sensitivities ranging from 10.5% (95% CI, 1.3–33.1% for the skin model) to 89.4% (66.9–98.7%, for the nose model). Specificity ranged from 42.1% (20.3–66.5%) for the nose model and 94.7% (73.9–99.9%) for skin. The stacked model combining all four facial features achieved an area under the receiver characteristic operating curve (AUROC) of 0.67 (0.62–0.71) and distinguished acutely ill patients with a sensitivity of 100% (82.35–100.00%) and specificity of 42.11% (20.25–66.50%). Conclusion: A deep learning algorithm trained on a synthetic, augmented dataset of facial photographs distinguished between healthy and simulated acutely ill individuals, demonstrating that synthetically generated data can be used to develop algorithms for health conditions in which large datasets are difficult to obtain. These results support the potential of facial feature analysis algorithms to support the diagnosis of acute illness. Frontiers Media S.A. 2021-07-26 /pmc/articles/PMC8350122/ /pubmed/34381793 http://dx.doi.org/10.3389/fmed.2021.661309 Text en Copyright © 2021 Forte, Voinea, Chichirau, Yeshmagambetova, Albrecht, Erfurt, Freundt, Carmo, Henning, Horst, Sundelin, Wiering, Axelsson and Epema. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Medicine
Forte, Castela
Voinea, Andrei
Chichirau, Malina
Yeshmagambetova, Galiya
Albrecht, Lea M.
Erfurt, Chiara
Freundt, Liliane A.
Carmo, Luisa Oliveira e
Henning, Robert H.
van der Horst, Iwan C. C.
Sundelin, Tina
Wiering, Marco A.
Axelsson, John
Epema, Anne H.
Deep Learning for Identification of Acute Illness and Facial Cues of Illness
title Deep Learning for Identification of Acute Illness and Facial Cues of Illness
title_full Deep Learning for Identification of Acute Illness and Facial Cues of Illness
title_fullStr Deep Learning for Identification of Acute Illness and Facial Cues of Illness
title_full_unstemmed Deep Learning for Identification of Acute Illness and Facial Cues of Illness
title_short Deep Learning for Identification of Acute Illness and Facial Cues of Illness
title_sort deep learning for identification of acute illness and facial cues of illness
topic Medicine
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8350122/
https://www.ncbi.nlm.nih.gov/pubmed/34381793
http://dx.doi.org/10.3389/fmed.2021.661309
work_keys_str_mv AT fortecastela deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT voineaandrei deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT chichiraumalina deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT yeshmagambetovagaliya deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT albrechtleam deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT erfurtchiara deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT freundtlilianea deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT carmoluisaoliveirae deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT henningroberth deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT vanderhorstiwancc deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT sundelintina deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT wieringmarcoa deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT axelssonjohn deeplearningforidentificationofacuteillnessandfacialcuesofillness
AT epemaanneh deeplearningforidentificationofacuteillnessandfacialcuesofillness