Quality and Perceived Usefulness of Patient-Submitted Store-and-Forward Teledermatology Images

Abstract

ImportancePatient-submitted images vary considerably in quality and usefulness. Studies that characterize patient-submitted images in a real-life setting are lacking.ObjectiveTo evaluate the quality and perceived usefulness of patient-submitted images as determined by dermatologists and characterize agreement of their responses.Design, Setting, and ParticipantsThis survey study included patient images submitted to the Department of Dermatology at Duke University (Durham, North Carolina) between August 1, 2018, and December 31, 2019. From a total pool of 1200 images, 10 dermatologists evaluated 200 or 400 images each, with every image being evaluated by 3 dermatologists. Data analysis occurred during the year leading up to the article being written.Main Outcomes and MeasuresThe primary outcomes were the responses to 2 questions and were analyzed using frequency counts and interrater agreement (Fleiss κ) to assess image quality and perceived usefulness. We performed a random-effects logistic regression model to investigate factors associated with evaluators’ decision-making comfort. We hypothesized that most images would be of low quality and perceived usefulness, and that interrater agreement would be poor.ResultsA total of 259 of 2915 patient-submitted images (8.9%) did not depict a skin condition at all. The final analysis comprised 3600 unique image evaluations. Dermatologist evaluators indicated that 1985 images (55.1%) were useful for medical decision-making and 2239 (62.2%) were of sufficient quality. Interrater agreement for a given image’s diagnostic categorization was fair to substantial (κ range, 0.36-0.64), while agreement on image quality (κ range, 0.35-0.47) and perceived usefulness (κ range, 0.29-0.38) were fair to moderate. Senior faculty had higher odds of feeling comfortable with medical decision-making than junior faculty (odds ratio [OR], 3.68; 95% CI, 2.9-4.66; P < .001) and residents (OR, 5.55; 95% CI, 4.38-7.04; P < .001). Images depicting wounds (OR, 1.75; 95% CI, 1.18-2.58; P = .01) compared with inflammatory skin conditions and that were in focus (OR, 5.56; 95% CI, 4.63-6.67; P < .001) had higher odds of being considered useful for decision-making.Conclusions and RelevanceIn this survey study including 10 dermatologists, a slight majority of patient-submitted images were judged to be of adequate quality and perceived usefulness. Fair agreement between dermatologists was found regarding image quality and perceived usefulness, suggesting that store-and-forward teledermatology initiatives should consider a physician’s individual experiences and comfort level. The study results suggest that images are most likely to be useful when they are in focus and reviewed by experienced attending physicians for wound surveillance, but dermatologists may be burdened by irrelevant or unsuitable images.

Development and Clinical Evaluation of an Artificial Intelligence Support Tool for Improving Telemedicine Photo Quality

“…3 Moreover, the influx of low quality images can lead to increased physician time and burnout. 5,15 In a retrospective assessment of 1700 images of skin disease from 650 patients who had Stanford Healthcare telemedicine visits from March 2020 to June 2021, we found that 37.6% of images did not meet the quality threshold for making a clinical assessment. This finding is in line with a 2022 study 5 in which dermatologists assessed 1200 telemedicine-submitted images and found that 37.8% were of insufficient quality.…”

“…In a retrospective assessment of 1700 images of skin disease from 650 patients who had Stanford Healthcare telemedicine visits from March 2020 to June 2021, we found that 37.6% of images did not meet the quality threshold for making a clinical assessment. This finding is in line with a 2022 study in which dermatologists assessed 1200 telemedicine-submitted images and found that 37.8% were of insufficient quality. In the present study, we found the most common reasons for insufficient quality were blurry images or poor lighting.…”

“…Most clinical photo-taking applications, including those used at Stanford Healthcare, primarily rely on the patient’s judgment for submitting adequate quality photos. However, even when given instructions, patients frequently take photos of insufficient quality for clinical use . This is partially due to a lack of experience with what features clinicians care most about .…”

“…However, even when given instructions, patients frequently take photos of insufficient quality for clinical use. [3][4][5] This is partially due to a lack of experience with what features clinicians care most about. 3 Common quality issues include blurriness, poor lighting conditions, cropping of the area of interest, and too little or too much zoom.…”

Letter to the editor regarding article “Falotico JM, Gu L, Lipner SR. Not just pimple popping: The utility of hybrid telemedicine models beyond acne management amidst the ongoing COVID‐19 pandemic. J Cosmet Dermatol. 2022;10.1111/jocd.15256”

“…4,5 Strategies adopted during COVID-19 pandemic such as email, phone or video calls and Whatsapp and Facebook supporting groups showed to be effective and safe for the management of several dermatologic conditions, with a high grade of satisfaction in patients. [6][7][8] We disagree with Falotico et al 2 who suggested in-person visits only for new patients, subjects with severe or unstable disease, or those needing diagnostic testing and procedures. Indeed, teledermatology cannot replace face-to-face consultations as the physician-patient relationship is at the basis of the daily clinical practice.…”