Application of an infrared thermography-based model to detect pressure injuries: a prospective cohort study

Abstract

Background It is challenging to detect pressure injuries at an early stage of their development. Objectives To assess the ability of an infrared thermography (IRT)‐based model, constructed using a convolution neural network, to reliably detect pressure injuries. Methods A prospective cohort study compared validity in patients with pressure injury (n = 58) and without pressure injury (n = 205) using different methods. Each patient was followed up for 10 days. Results The optimal cut‐off values of the IRT‐based model were 0·53 for identifying tissue damage 1 day before visual detection of pressure injury and 0·88 for pressure injury detection on the day visual detection is possible. Kaplan–Meier curves and Cox proportional hazard regression model analysis showed that the risk of pressure injury increased 13‐fold 1 day before visual detection with a cut‐off value higher than 0·53 [hazard ratio (HR) 13·04, 95% confidence interval (CI) 6·32–26·91; P < 0·001]. The ability of the IRT‐based model to detect pressure injuries [area under the receiver operating characteristic curve (AUC)lag 0 days, 0·98, 95% CI 0·95–1·00] was better than that of other methods. Conclusions The IRT‐based model is a useful and reliable method for clinical dermatologists and nurses to detect pressure injuries. It can objectively and accurately detect pressure injuries 1 day before visual detection and is therefore able to guide prevention earlier than would otherwise be possible. What is already known about this topic? Detection of pressure injuries at an early stage is challenging. Infrared thermography can be used for the physiological and anatomical evaluation of subcutaneous tissue abnormalities. A convolutional neural network is increasingly used in medical imaging analysis. What does this study add? The optimal cut‐off values of the IRT‐based model were 0·53 for identifying tissue damage 1 day before visual detection of pressure injury and 0·88 for pressure injury detection on the day visual detection is possible. Infrared thermography‐based models can be used by clinical dermatologists and nurses to detect pressure injuries at an early stage objectively and accurately.

Association between hypertension and pressure ulcer: A systematic review and meta‐analysis

“…To detect the source of heterogeneity that affects the pooled effect size of association between hypertension and PU, subgroup analyses were performed on patient source, research design and primary disease (Table 2 ). In the subgroup analysis of patient source, the meta‐analysis results indicated no significant association between hypertension and PU in Asia group (OR = 1.12, 95% CI = 0.83–1.50, I 2 = 63%, p = 0.46) 11 , 12 , 17 , 20 , 22 , 24 , 25 , 27 , 28 , 29 , 30 , 31 , 32 and Non‐Asia group (OR = 1.20, 95% CI = 0.75–1.94, I 2 = 88%, p = 0.45). 10 , 18 , 19 , 21 , 23 , 26 In the subgroup analysis of study design, the results also showed no significant association between hypertension and PU in cohort study (OR = 1.16, 95% CI = 0.84–1.61, I 2 = 63%, p = 0.36) 10 , 11 , 17 , 21 , 22 , 27 , 28 , 31 , 32 and case–control study (OR = 1.14, 95% CI = 0.79–1.64, I 2 = 82%, p = 0.49).…”

“…In the subgroup analysis of patient source, the meta‐analysis results indicated no significant association between hypertension and PU in Asia group (OR = 1.12, 95% CI = 0.83–1.50, I 2 = 63%, p = 0.46) 11 , 12 , 17 , 20 , 22 , 24 , 25 , 27 , 28 , 29 , 30 , 31 , 32 and Non‐Asia group (OR = 1.20, 95% CI = 0.75–1.94, I 2 = 88%, p = 0.45). 10 , 18 , 19 , 21 , 23 , 26 In the subgroup analysis of study design, the results also showed no significant association between hypertension and PU in cohort study (OR = 1.16, 95% CI = 0.84–1.61, I 2 = 63%, p = 0.36) 10 , 11 , 17 , 21 , 22 , 27 , 28 , 31 , 32 and case–control study (OR = 1.14, 95% CI = 0.79–1.64, I 2 = 82%, p = 0.49). 12 , 18 , 19 , 20 , 23 , 24 , 25 , 26 , 29 , 30 Due to the primary disease difference, subgroup analysis was performed based on primary disease, and the results showed that there was a significant association between hypertension and PU in COVID‐19 patients(OR = 1.73, 95% CI = 1.35–2.22, I 2 = 0%, p < 0.0001), 10 , 21 , 26 whereas no association was found in str...…”

Advances in acne clinical research: a new class of topical treatment for moderate-to-severe facial acne

“…Trifarotene was developed as a fourth-generation topical retinoid, 20 years after the third-generation retinoid adapalene, 3 and clascoterone was approved by the US Food and Drug Administration as a topical androgen receptor inhibitor for acne in patients 12 years and older, in 2020. 4 On the other hand, high-quality, evidence-based results for acne treatments can be provided by randomized, double-blind, controlled trials with adequate sample size and reporting of efficacy, safety and tolerability core outcomes, as with the study of Picardo et al A considerable part of acne clinical research is limited by the lack of randomization, which may result in bias, or the lack of a control arm, which is necessary to demonstrate efficacy considering the fluctuating nature of acne. In turn, the design of new antiacne agents is only possible by building on previous laboratory research into key players in the pathophysiology of acne.…”

“…The prospective cohort study reported by Jiang and coauthors in this issue of the BJD utilizes a handheld noncontact infrared thermal imaging device that may meet this need. 4 A recent systematic review evaluated the evidence to support the use of bedside technologies in the early detection of PIs. Of the five modalities identified (ultrasound, thermography, subepidermal moisture measurement, reflectance spectrometry and laser Doppler), subepidermal moisture had the most consistent findings.…”

Can technology change the status quo for pressure injury prevention?

“…A simple, inexpensive and easy‐to‐use device to detect PIs early, before an open and deep wound is inevitable, would be extremely beneficial. The prospective cohort study reported by Jiang and coauthors in this issue of the BJD utilizes a handheld noncontact infrared thermal imaging device that may meet this need 4 …”