Thermographic visualization of facial vasoconstriction is associated with 30-day all-cause mortality in medical patients; prospective observational two-site cohort study

Jensen, Nadia H; Lo, Rachel; Hung, Kevin Kei Ching; Lorentzen, Morten Hjarnø; Laugesen, Sune; Posth, Stefan; Hansen, Søren; Jensen, Kenneth B.; Kellett, John; Graham, Colin A.; Brabrand, Mikkel

doi:10.52964/amja.0849

Cited by 4 publications

(16 citation statements)

References 11 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Research has been conducted to investigate the most optimal reference point for measuring the peripheral temperature. The research concluded that the tip of the nose was the most accurate reference point when compared with the third finger and the ear lobes (Holm et al, 2018;Jensen et al, 2021a).…”

Section: The Initial Analysismentioning

confidence: 99%

Using Facial Landmark Detection on Thermal Images as a Novel Prognostic Tool for Emergency Departments

Baskaran

Møller

Wiil

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

IntroductionEmergency departments (ED) at hospitals sometimes experience unexpected deterioration in patients that were assessed to be in a stable condition upon arrival. Odense University Hospital (OUH) has conducted a retrospective study to investigate the possibilities of prognostic tools that can detect these unexpected deterioration cases at an earlier stage. The study suggests that the temperature difference (gradient) between the core and the peripheral body parts can be used to detect these cases. The temperature between the patient's inner canthus (core temperature) and the tip of the nose (peripheral temperature) can be measured with a thermal camera. Based on the temperature measurement from a thermal image, a gradient value can be calculated, which can be used as an early indicator of potential deterioration.ProblemThe lack of a tool to automatically calculate the gradient has prevented the ED at OUH in conducting a comprehensive prospective study on early indicators of patients at risk of deterioration. The current manual way of doing facial landmark detection on thermal images is too time consuming and not feasible as part of the daily workflow at the ED, where nurses have to triage patients within a few minutes.ObjectiveThe objective of this study was to automate the process of calculating the gradient by developing a handheld prognostic tool that can be used by nurses for automatically performing facial landmark detection on thermal images of patients as they arrive at the ED.MethodsA systematic literature review has been conducted to investigate previous studies that have been done for applying computer vision methods on thermal images. Several meetings, interviews and field studies have been conducted with the ED at OUH in order to understand their workflow, formulate and prioritize requirements and co-design the prognostic tool.ResultsThe study resulted in a novel Android app that can capture a thermal image of a patient's face with a thermal camera attached to a smartphone. Within a few seconds, the app then automatically calculates the gradient to be used in the triage process. The developed tool is the first of its kind using facial landmark detection on thermal images for calculating a gradient that can serve as a novel prognostic indicator for ED patients.

show abstract

Section: The Initial Analysismentioning

confidence: 99%

Using Facial Landmark Detection on Thermal Images as a Novel Prognostic Tool for Emergency Departments

Baskaran

Møller

Wiil

et al. 2022

Front. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…2 In a prospective study of 726 patients they demonstrated that the temperature gradient between nose and eye could help identify variations in skin perfusion and was predictive Evolve, Adapt, Innovate and Deliver: Acute Medicine post COVID pandemic of all cause 30 day mortality. 3 This requires further study but may become a further useful tool in the assessment of physiology of acute unwell medical patients. Dutch colleagues prospectively studied 1328 patients presenting acutely with infective illnesses.…”

Section: Editorialmentioning

confidence: 99%

Editorial – Evolve, Adapt, Innovate and Deliver: Acute Medicine post COVID pandemic

Lovell¹

2021

Acute Med

View full text Add to dashboard Cite

Predictions for acute care in the upcoming months are difficult. There will be challenges: there always are and that to a degree is what makes working in acute care so fulfilling. However, even the most adaptive and innovative acute care systems will toil when these challenges become overwhelming. Back in 2015, the then SAM President Mark Holland described a “perfect storm” of events that could lead to a challenging winter period. It was as predicted; but this storm continues to evolve and has not yet reached its perfected chaotic peak. A picture of the COVID pandemic without the brilliant and innovative work of Acute Medicine teams is even darker. As a specialty we should and must remain proud of the impact we are having in delivering safe and sustainable care despite immense pressures. There is an escalating sense of desperation to reach a post-pandemic phase. Increasingly the sense of community unity and spirit at the beginning of the pandemic is being replaced by fear and disgruntlement. A toxic mix of emotions permeates and increasingly hostile divisions as to how manage the next stage of the pandemic grow. Opposing viewpoints are entrenched and neither wants to countenance a brief reflection on any deviation from their position. Meanwhile many people simply observe with bafflement and a sense of betrayal desperate for their lives to return to “normal”. Delivering acute medical care on this background is a challenge that none of us have faced. The skills and resilience of our teams will face its sternest test yet. As a specialty we will continue to do what we have always done since its inception: evolve, adapt, innovate and deliver. This issue of the journal reflects the fantastic work in Acute Medicine that continues to be delivered internationally despite the current challenges. Chris Subbe and the SAM Quality Improvement team have written a review considering frameworks for measuring quality in Acute Medicine.1 Quantifying the impact that Acute Medicine has on the patient journey with defined measurable metrics is key to embedding high quality acute care. The recognition and evaluation of abnormal physiology remains core to the practice of Acute Medicine. International Acute Medicine colleagues from Denmark and Hong Kong present some innovative work on the potential use of thermography in predicting prognosis in acute care.2 In a prospective study of 726 patients they demonstrated that the temperature gradient between nose and eye could help identify variations in skin perfusion and was predictive of all cause 30 day mortality.3 This requires further study but may become a further useful tool in the assessment of physiology of acute unwell medical patients. Dutch colleagues prospectively studied 1328 patients presenting acutely with infective illnesses. Their results reaffirmed the superiority of NEWS to SIRS and qSOFA in predicting mortality and outcomes in this cohort.4 The evolving nature and clinical characteristics of COVID19 are described by Cat Atkin and her colleagues from Birmingham.5 This important paper provides robust data on which to benchmark the severity of future variants of the virus and can support complex service provision planning adapted to the pandemic. Once again, SAM and the editorial board of Acute Medicine thank all colleagues for their amazing and diligent work during the pandemic, which we know will continue long after it. We hope that all friends and colleagues are able to have some well deserved rest and relaxation during a summer break.

show abstract

“…The proportion of studies with a low-risk rating for concerns around the applicability of their findings in the patient selection, index test and reference standard domains were 73, 57 and 77%, respectively. Ten studies scored low risk ratings across all domains (11,12,18,20,24,25,27,30,36,39). One scored high-risk ratings across all domains (16).…”

Section: Quality Appraisalmentioning

confidence: 99%

“…The majority of authors identified their studies as exploratory or assessing feasibility (n = 16) (11, 12, 14-16, 19, 21, 22, 26, 27, 31, 32, 34, 35, 37, 39). Few were described as validation or diagnostic accuracy studies (n = 8) (13,17,18,20,24,33,36,38).…”

Thermographic visualization of facial vasoconstriction is associated with 30-day all-cause mortality in medical patients; prospective observational two-site cohort study

Cited by 4 publications

References 11 publications

Using Facial Landmark Detection on Thermal Images as a Novel Prognostic Tool for Emergency Departments

Using Facial Landmark Detection on Thermal Images as a Novel Prognostic Tool for Emergency Departments

Editorial – Evolve, Adapt, Innovate and Deliver: Acute Medicine post COVID pandemic

Table_1.DOCX

Contact Info

Product

Resources

About