Diagnostic accuracy and cost‐effectiveness of dermoscopy in primary care: a cluster randomized clinical trial

Koelink, Cecile; Vermeulen, Karin M.; Kollen, Boudewijn J.; Bock, Geertruida H. de; Dekker, Janny H.; Jonkman, Marcel F.; Heide, Wouter K. van der

doi:10.1111/jdv.12306

Cited by 47 publications

(77 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The survey was addressed to dermatologists, as they are the main users of dermoscopy across all European countries. While the extension of dermoscopy training to general practitioners or specialized nurses is considered by some countries, this practice is still nascent in most parts of the European continent and could be considered for future research.…”

Section: Discussionmentioning

confidence: 99%

Factors driving the use of dermoscopy in Europe: a pan-European survey

Forsea

Tschandl

Marmol

et al. 2016

British Journal of Dermatology

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Factors driving the use of dermoscopy in Europe: a pan-European survey

Forsea

Tschandl

Marmol

et al. 2016

British Journal of Dermatology

View full text Add to dashboard Cite

show abstract

“…In practice, we believe the level of required diagnostic accuracy for the application should be higher than that of a regular GP, [16][17][18] and as close as possible to that of a dermatologist. Two recent studies compared the sensitivity of dermatologists and a machine learning algorithm to detect skin cancer, against histopathology.…”

Section: Discussionmentioning

confidence: 99%

Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms

Udrea

Mitra

Costea

et al. 2019

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background Machine learning algorithms achieve expert‐level accuracy in skin lesion classification based on clinical images. However, it is not yet shown whether these algorithms could have high accuracy when embedded in a smartphone app, where image quality is lower and there is high variability in image taking scenarios by users. In the past, these applications were criticized due to lack of accuracy. Objective In this study, we evaluate the accuracy of the newest version of a smartphone application (SA) for risk assessment of skin lesions. Methods This SA uses a machine learning algorithm to compute a risk rating. The algorithm is trained on 131 873 images taken by 31 449 users in multiple countries between January 2016 and August 2018 and rated for risk by dermatologists. To evaluate the sensitivity of the algorithm, we use 285 histopathologically validated skin cancer cases (including 138 malignant melanomas), from two previously published clinical studies (195 cases) and from the SA user database (90 cases). We calculate the specificity on a separate set from the SA user database containing 6000 clinically validated benign cases. Results The algorithm scored a 95.1% (95% CI, 91.9–97.3%) sensitivity in detecting (pre)malignant conditions (93% for malignant melanoma and 97% for keratinocyte carcinomas and precursors). This level of sensitivity was achieved with a 78.3% (95% CI, 77.2–79.3%) specificity. Conclusions This SA provides a high sensitivity to detect skin cancer; however, there is still room for improvement in terms of specificity. Future studies are needed to assess the impact of this SA on the health systems and its users.

show abstract

“…However, there is little evidence to confirm the optimal training modality and duration. Educational interventions in previous randomized controlled trials have ranged from a single hour to 10 h plus further textbook reading or e‐learning . However, there is no randomized controlled trial evidence comparing the effects of shorter and longer training periods.…”

Section: Discussionmentioning

confidence: 99%

“…Educational interventions in previous randomized controlled trials have ranged from a single hour 21 to 10 h plus further textbook reading or e-learning. 39 However, there is no randomized controlled trial evidence comparing the effects of shorter and longer training periods. Previous studies have found that perceived training requirements are amongst the most commonly cited barriers to implementation of dermoscopy.…”

Section: Comparisons With Existing Literaturementioning

confidence: 99%

Dermoscopy use in UK primary care: a survey of GPs with a special interest in dermatology

Jones

Jurascheck

Utukuri

et al. 2019

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background Melanoma accounts for 90% of skin cancer mortality and typically presents in primary care, where it can be challenging to distinguish from benign lesions. Dermoscopy is a tool for skin visualization that is routinely used for melanoma diagnosis in secondary care. However, the role of dermoscopy in primary care remains unclear. Objectives To determine views on, and use of, dermoscopy by dermatology‐interested general practitioners (GPs). Methods An online questionnaire was emailed to the UK Primary Care Dermatology Society members in February 2018, and responses collected over the following 4 weeks. Results A total of 205 responses were analysed. Most respondents were GPs (94%), aged over 50 (53%), had a postgraduate dermatological qualification (67%) and used dermoscopy regularly when reviewing pigmented skin lesions (97%). Dermoscopy use was commoner amongst GPs who had worked longer in primary care and had experience of secondary care dermatology. Most had undertaken training in dermoscopy (91%), although one‐fifth (20%) had not updated their training in over 5 years. Most of those who had received only 1 day of face‐to‐face training reported feeling confident using a dermatoscope. Few respondents (11%) reported access to teledermatology or teledermoscopy for urgent or routine referrals. Conclusions UK GPs with a special interest in dermatology are routinely using dermoscopy in the primary care setting. More research is needed to establish optimal approaches to training and updating GP dermoscopy skills. When dermoscopy has been shown to be safe, effective, acceptable and cost‐effective in this setting, more GPs may also be able to gain and maintain the skills to implement dermoscopy into routine primary care. Technological advances, including incorporation of artificial intelligence (AI) and algorithms to guide GPs, could also contribute to widening use of dermoscopy among GPs.

show abstract

Diagnostic accuracy and cost‐effectiveness of dermoscopy in primary care: a cluster randomized clinical trial

Cited by 47 publications

References 20 publications

Factors driving the use of dermoscopy in Europe: a pan-European survey

Factors driving the use of dermoscopy in Europe: a pan-European survey

Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms

Dermoscopy use in UK primary care: a survey of GPs with a special interest in dermatology

Contact Info

Product

Resources

About