The poor performance of apps assessing skin cancer risk

Morley, Jessica; Floridi, Luciano; Goldacre, Ben

doi:10.1136/bmj.m428

Cited by 8 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consistent with previous studies focusing on mHealth in general, a lack of perceived usefulness and trustworthiness, concerns over privacy and perceived high costs appeared to be important barriers to adoption 25,33,34 . However, we also identified new (sub‐)barriers that seem to be unique to skin cancer, in which a perceived lack of screening accuracy is most prominent 18,35 . The expectations regarding the required minimal levels of accuracy seem to vary, ranging from GP‐level skin cancer detection accuracy up to flawless screening capabilities.…”

Section: Discussionsupporting

confidence: 83%

“… 25 , 33 , 34 However, we also identified new (sub‐)barriers that seem to be unique to skin cancer, in which a perceived lack of screening accuracy is most prominent. 18 , 35 The expectations regarding the required minimal levels of accuracy seem to vary, ranging from GP‐level skin cancer detection accuracy up to flawless screening capabilities.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Views on mobile health apps for skin cancer screening in the general population: an in‐depth qualitative exploration of perceived barriers and facilitators*

et al. 2021

View full text Add to dashboard Cite

The Department of Dermatology of the Erasmus MC Cancer Institute has received an unrestricted research grant from SkinVision. T.N. serves on the SkinVision advisory board and has equity in the company. Data availability statementThe data that support the findings of this study are available on reasonable request from the corresponding author. The data are not publicly available due to privacy or ethical restrictions.

show abstract

Section: Discussionsupporting

confidence: 83%

Section: Discussionmentioning

confidence: 99%

Views on mobile health apps for skin cancer screening in the general population: an in‐depth qualitative exploration of perceived barriers and facilitators*

et al. 2021

View full text Add to dashboard Cite

show abstract

“…[26][27][28] Teledermoscopy could offer another way to preselect specific lesions in need of early-access consultation. [29][30][31][32][33]…”

Section: Discussionmentioning

confidence: 99%

“…Unfortunately at this moment existing smartphone applications using AI systems for diagnosis do not seem ready for such use in daily practice, although this field is rapidly evolving 26–28 . Teledermoscopy could offer another way to preselect specific lesions in need of early‐access consultation 29–33 …”

Section: Discussionmentioning

confidence: 99%

Lesion‐directed screening to optimize skin cancer detection in dermatology practice: an observational study

Mylle

Coile

Maele

et al. 2021

Acad Dermatol Venereol

View full text Add to dashboard Cite

Background Early detection of skin cancer is still a major challenge in dermatology practice today. While surveillance programs are offered to high-risk patients, systematic total-body examination (TBE) in the general population is not cost-effective. In the past, we demonstrated that a lesion-directed screening (LDS) in the general population delivered similar detection rates to TBE and was less time-consuming.Objectives To study whether a lesion-directed early-access consultation can optimize skin cancer detection in dermatology practice.Methods In this observational study, we offered an early-access consultation in patients contacting the dermatology department concerning 1 or 2 lesions of concern meeting predefined criteria. Results 342 persons were seen at the dermatology department after triage by phone. Skin cancer detection rate was 13.2% (4.1% for melanoma). If advised/referred by a doctor skin cancer detection rate was 23.6% (9% for melanoma).With a history of skin cancer, detection rate was 24.3% (4.3% for melanoma). In patients with no referral and a negative history of skin cancer, detection rate was 7.7% (1.7% for melanoma), which is at least triple the rates reported by population-based screening programs. In patients in whom the index lesion was benign, worry of having skin cancer had decreased significantly by the end of the consultation. Additional total-body examination in these patients had low additional detection rate (0.5%) and a high number of unnecessary excisions (number needed to excise 13).Conclusions An early-access dermatology consultation for LDS after triage by phone resulted in high overall skin cancer and melanoma detection rates. Our data indicate that performing TBE is especially useful if the index lesion is suspicious. In addition to surveillance programs in high-risk patients, LDS may be a way to optimize skin cancer detection in the general population and use available time more efficiently in daily dermatology practice.

show abstract

“…Multiple examples of bizarre and unlikely conclusions have been demonstrated, including lower leg pain and breathlessness being diagnosed as a Charcot’s joint and asthma. Recently, The BMJ published a systematic review of AI based skin checking apps currently available to the public, which found that they were dangerously inaccurate2 and inadequately regulated 3…”

mentioning

confidence: 99%