Teledermatology for diagnosing skin cancer in adults

Chuchu, Naomi; Dinnes, Jacqueline; Takwoingi, Yemisi; Matin, Rubeta; Bayliss, Sue; Davenport, Clare; Moreau, Jacqueline F.; Bassett, Oliver; Godfrey, Kathie; O'Sullivan, Colette; Walter, Fiona M; Motley, Richard; Deeks, Jonathan J; Williams, Hywel C

doi:10.1002/14651858.cd013193

Cited by 113 publications

(130 citation statements)

References 251 publications

Supporting

Mentioning

118

Contrasting

Unclassified

Order By: Relevance

“…Various reviews on teledermatological applications have been published over the last years, but to our knowledge, no up‐to‐date review on LI teledermatology across different conditions has been published. Hence, an overview is lacking on the effectiveness, costs and accuracy of LI applications compared to standard in‐person care.…”

Section: Introductionmentioning

confidence: 99%

Live interactive teledermatology compared to in‐person care – a systematic review

Andrees

Klein

Augustin

et al. 2020

Acad Dermatol Venereol

View full text Add to dashboard Cite

Teledermatology is a rapidly developing field of dermatological care, giving the opportunity to deliver more efficient healthcare to patients in remote areas. Live interactive (LI) teledermatology uses videoconferencing and, hence, allows for direct communication. A current overview on effectiveness, costs, feasibility and accuracy of LI applications compared to standard care is missing. The present systematic review provides this overview on LI teledermatology. Two databases were searched until April 2019, followed by title, abstract and full‐text screening. Additionally, reference lists of the detected eligible articles were screened for further eligible studies. Studies comparing LI applications with standard care were included. Data on study design, sample size, country, objectives, main findings and characteristics of LI applications were extracted. Results on time effectiveness, costs, accuracy and feasibility of LI applications were synthesized. Additionally, the quality of included studies was assessed. Twenty‐three publications were included in the final analysis: seventeen case–control studies and six randomized controlled trials. Included studies were published between 1997 and 2017. Study quality differed across studies. The studies were carried out in eight different countries. Eleven studies focused on patient consultation, three on patient organization and nine on combined applications of the aforementioned. Nine studies investigated applications facilitating patient–provider interaction. Fourteen studies evaluated applications combining patient–provider and provider–provider interaction, meaning the patient sits next to one provider while using LI applications to interact with another provider. This review reveals that LI applications can be a time effective substitute of or supplement to standard dermatological care. Results demonstrated that LI and standard care are comparable with regard to feasibility and accuracy. No clear tendencies can be reported with regard to costs. However, there is a lack of current comparative studies.

show abstract

Section: Introductionmentioning

confidence: 99%

Live interactive teledermatology compared to in‐person care – a systematic review

Andrees

Klein

Augustin

et al. 2020

Acad Dermatol Venereol

View full text Add to dashboard Cite

show abstract

“…In addition, time for evaluation was defined but not unlimited, as in other studies, reproducing a certain minimal stress level as in clinical activity. As recently demonstrated in a Cochrane review, the accuracy of teledermoscopic diagnosis, as well as the concordance between teledermoscopic ( store‐and‐forward) diagnosis and face‐to‐face diagnosis, depend on an adequate preselection of cases . The authors also stressed the importance of using a ‘more widely defined threshold’ before starting any telediagnostic procedure .…”

Section: Discussionmentioning

confidence: 93%

“…Panel 3 was dedicated to the ‘ABCD rule’ and panel 4 to the ‘7‐point checklist’ . In panel 3, they were required to assess the four criteria, asymmetry, borders, colours and dermoscopic structures, according to the ABCD rule scoring system . In panels 2 and 4, participants are asked to check YES/NO if a dermoscopic structure in the checklist was present/absent.…”

Section: Methodsmentioning

confidence: 99%

“…An example of the home page of a testing session is illustrated in Fig. 1a: a grid was composed by 30 dermoscopy images, each having four panels (1)(2)(3)(4) that open for the four consecutive tests; the time left to complete the test set appeared in the top right corner. The images could be enlarged to fill the browser window.…”

Section: Testing Sessionmentioning

confidence: 99%

“…Correct diagnosis and timely surgical removal are the mainstay of melanoma treatment. [1][2][3][4] Dermoscopy is a non-invasive method demonstrated to enhance skin-lesion diagnosis. [5][6][7] Many dermoscopic algorithms and checklists have been proposed to improve the accuracy of early melanoma (EM) diagnosis and avoid inappropriate removal through a more standardized approach.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Validation of an integrated dermoscopic scoring method in an European teledermoscopy web platform: the iDScore project for early detection of melanoma

Tognetti

Cevenini

Moscarella

et al. 2019

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background Although live and teledermoscopic examination has been successfully used to achieve non‐invasive diagnosis of melanocytic skin lesions (MSLs), early melanoma (EM) and atypical nevi (AN) continue to be a challenge, and none of the various algorithms proposed have been sufficiently accurate. We designed a scoring classifier diagnostic method, the iDScore that combines clinical data of the patient with dermoscopic features of the MSL. Objective To test the accuracy of the iDScore in differentiating EM from AN in a teledermoscopy setting and to compare it with intuitive diagnosis, the ABCD rule and the seven‐point checklist. Materials and methods A dedicated teledermoscopy web platform was designed. This involved the following: (i) collecting a large integrated clinical–historical–dermoscopic data set of difficult MSLs from eight European dermatology centres; (ii) online testing, education and training in using the iDScore. A total of 904 images were combined with age, sex, lesion diameter and body site data and evaluated on the platform by 111 participants with four levels of skill in dermoscopy. Each testing session consisted of 30 blind cases to examine consecutively by the above four methods. ‘Management decisions’ and personal participant data were also recorded. Results iDScore‐aided diagnosis achieved satisfactory diagnostic accuracy for all lesions, irrespective of centre of affiliation, showing an average AUC of 0.776 in all participant testing sessions. All skill groups improved their accuracy by 10–16% with respect to intuitive diagnosis and the other methods, showing high concordance and avoiding wrong management decisions. Conclusion We demonstrated the validity of the iDScore method for managing suspicious MSLs in a large multicentric data set and a teledermoscopic setting. The platform designed for the iDScore project provides ready support for physicians of any dermoscopy skill level and is useful for education and training.

show abstract

Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions

Marsden²,

et al. 2019

View full text Add to dashboard Cite

IMPORTANCE A high proportion of suspicious pigmented skin lesions referred for investigation are benign. Techniques to improve the accuracy of melanoma diagnoses throughout the patient pathway are needed to reduce the pressure on secondary care and pathology services. OBJECTIVE To determine the accuracy of an artificial intelligence algorithm in identifying melanoma in dermoscopic images of lesions taken with smartphone and digital single-lens reflex (DSLR) cameras. DESIGN, SETTING, AND PARTICIPANTS This prospective, multicenter, single-arm, masked diagnostic trial took place in dermatology and plastic surgery clinics in 7 UK hospitals. Dermoscopic images of suspicious and control skin lesions from 514 patients with at least 1 suspicious pigmented skin lesion scheduled for biopsy were captured on 3 different cameras. Data were collected from January 2017 to July 2018. Clinicians and the Deep Ensemble for Recognition of Malignancy, a deterministic artificial intelligence algorithm trained to identify melanoma in dermoscopic images of pigmented skin lesions using deep learning techniques, assessed the likelihood of melanoma. Initial data analysis was conducted in September 2018; further analysis was conducted from February 2019 to August 2019. INTERVENTIONS Clinician and algorithmic assessment of melanoma.MAIN OUTCOMES AND MEASURES Area under the receiver operating characteristic curve (AUROC), sensitivity, and specificity of the algorithmic and specialist assessment, determined using histopathology diagnosis as the criterion standard. RESULTSThe study population of 514 patients included 279 women (55.7%) and 484 white patients (96.8%), with a mean (SD) age of 52.1 (18.6) years. A total of 1550 images of skin lesions were included in the analysis (551 [35.6%] biopsied lesions; 999 [64.4%] control lesions); 286 images (18.6%) were used to train the algorithm, and a further 849 (54.8%) images were missing or unsuitable for analysis. Of the biopsied lesions that were assessed by the algorithm and specialists, 125 (22.7%) were diagnosed as melanoma. Of these, 77 (16.7%) were used for the primary analysis.The algorithm achieved an AUROC of 90.1% (95% CI, 86.3%-94.0%) for biopsied lesions and 95.8% (95% CI, 94.1%-97.6%) for all lesions using iPhone 6s images; an AUROC of 85.8% (95% CI, 81.0%-90.7%) for biopsied lesions and 93.8% (95% CI, 91.4%-96.2%) for all lesions using Galaxy S6 images; and an AUROC of 86.9% (95% CI, 80.8%-93.0%) for biopsied lesions and 91.8% (95% CI, 87.5%-96.1%) for all lesions using DSLR camera images. At 100% sensitivity, the algorithm achieved (continued) Key Points Question How accurate is an artificial intelligence-based melanoma detection algorithm, which analyzes dermoscopic images taken by smartphone and digital single-lens reflex cameras, compared with clinical assessment and histopathological diagnosis? Findings In this diagnostic study, 1550 images of suspicious and benign skin lesions were analyzed by an artificial intelligence algorithm. When compared with histopathological diagnosis, ...

show abstract

Teledermatology for diagnosing skin cancer in adults

Abstract: Trusted evidence. Informed decisions. Better health.

Cited by 113 publications

References 251 publications

Live interactive teledermatology compared to in‐person care – a systematic review

Live interactive teledermatology compared to in‐person care – a systematic review

Validation of an integrated dermoscopic scoring method in an European teledermoscopy web platform: the iDScore project for early detection of melanoma

Assessment of Accuracy of an Artificial Intelligence Algorithm to Detect Melanoma in Images of Skin Lesions

Contact Info

Product

Resources

About