Evaluation of the National Swiss Skin Cancer Screening Campaign 2013: Do We Do the Right Thing

Basic principles of artificial intelligence in dermatology explained using melanoma

The use of artificial intelligence (AI) continues to establish itself in the most diverse areas of medicine at an increasingly fast pace. Nevertheless, many healthcare professionals lack the basic technical understanding of how this technology works, which severely limits its application in clinical settings and research. Thus, we would like to discuss the functioning and classification of AI using melanoma as an example in this review to build an understanding of the technology behind AI. For this purpose, elaborate illustrations are used that quickly reveal the technology involved. Previous reviews tend to focus on the potential applications of AI, thereby missing the opportunity to develop a deeper understanding of the subject matter that is so important for clinical application. Malignant melanoma has become a significant burden for healthcare systems. If discovered early, a better prognosis can be expected, which is why skin cancer screening has become increasingly popular and is supported by health insurance. The number of experts remains finite, reducing their availability and leading to longer waiting times. Therefore, innovative ideas need to be implemented to provide the necessary care. Thus, machine learning offers the ability to recognize melanomas from images at a level comparable to experienced dermatologists under optimized conditions.

Grundprinzipien der künstlichen Intelligenz in der Dermatologie erklärt am Beispiel des Melanoms

Der Einsatz von künstlicher Intelligenz (KI) setzt sich in den verschiedensten Bereichen der Medizin immer schneller durch. Dennoch fehlt vielen medizinischen Kollegen das technische Grundverständnis für die Funktionsweise dieser Technologie, was ihre Anwendung in Klinik und Forschung stark einschränkt. Daher möchten wir in dieser Übersichtsarbeit die Funktionsweise und Klassifizierung der KI am Beispiel des Melanoms erörtern, um ein Verständnis für die Technologie hinter der KI zu schaffen. Dazu werden ausführliche Illustrationen verwendet, die die Technologie schnell erklären. Bisherige Übersichten konzentrieren sich eher auf die potenziellen Anwendungen der KI und verpassen die Gelegenheit, ein tieferes Verständnis für die Materie herauszuarbeiten, das für die klinische Anwendung so wichtig ist. Das maligne Melanom ist zu einer erheblichen Belastung für die Gesundheitssysteme geworden. Bei frühzeitiger Entdeckung ist eine bessere Prognose zu erwarten, weshalb das Hautkrebs‐Screening immer populärer und von den Krankenkassen unterstützt wird. Die Zahl der Fachärzte ist jedoch begrenzt, was ihre Verfügbarkeit einschränkt und zu längeren Wartezeiten führt. Daher müssen innovative Ideen umgesetzt werden, um die notwendige Versorgung zu gewährleisten. Das maschinelle Lernen bietet die Möglichkeit, Melanome auf Bildern zu erkennen, und zwar auf einem Niveau, das mit dem von erfahrenen Dermatologen – unter optimierten Bedingungen – vergleichbar ist.

Overdiagnosis in malignant melanoma: a scoping review

OBJECTIVES

We aimed to systematically identify and scrutinise published empirical evidence about overdiagnosis in malignant melanoma and examine how frequent overdiagnosis of melanoma is and whether this is related to different types of interventions or diagnostic technologies.

DESIGN AND SETTING

Empirical studies that discussed overdiagnosis in malignant melanoma were eligible, including qualitative and quantitative studies in any type of population, age group and geographical location. We excluded studies that did not include empirical data, studies that only mentioned 'overdiagnosis' without addressing it further and studies that used the term overdiagnosis for cases of misdiagnosis or false positives.We developed the search strategy in cooperation with an information specialist. We searched five databases on 21 April 2022: MEDLINE, Embase, CINAHL, PsycINFO and Cochrane Library.This scoping review adheres to The JBI methodology and Prefered Reporting Items for Systematic Reviews and Meta-analyses extension for Scoping reviews (PRISMA-ScR). Two reviewers independently screened titles, abstracts and full texts for inclusion and extracted data from the included studies. The data extracted include study characteristics, population details, research question, the context and the study's main results.

RESULTS

Our search resulted in 1134 potentially relevant studies. 35 studies were included: 29 register studies, 3 cohort studies, 1 case-control study, 1 survey study and 1 randomised controlled trial. Most register studies examined trends in melanoma incidence and/or mortality and found a significant increase in incidence between 0.39% and 6.6% annually and a little or no increase in mortality. Three cohort studies and one case-control study showed that skin screening was associated with increased detection of melanoma; especially in situ or thin invasive melanoma. Three studies estimated the degree of overdiagnosis which ranged from 29% to 60%.

CONCLUSIONS

Epidemiological data suggest a high degree of overdiagnosis in malignant melanoma. Studies that examined the association between skin screening and malignant melanoma all found increased detection of melanomas, mostly thin and in situ melanomas, which raises concern about overdiagnosis.

Skin cancer screening in Switzerland: Cross-sectional trends (1997-2012) in socioeconomic inequalities

INTRODUCTION

Skin cancer is one of the most common malignancies. Despite controversy over its efficacy, skin cancer screening has become widespread although socioeconomic screening inequalities have been documented. Switzerland has the highest rate of melanoma in Europe but Swiss trends in skin cancer screening and social disparities have not been investigated. This study aims to evaluate trends in skin cancer screening and its association with socioeconomic indicators in Switzerland between 1997 and 2012.

METHOD

We used data from four waves (from 1997 to 2012) of the population-based Swiss Health Interview Survey. Multivariable Poisson regressions with robust variance were used to estimate weighted prevalence ratio (PR) and 95% Confidence Intervals (CI) adjusting for demographics, health status and use of healthcare.

RESULTS

This study included 60,764 participants with a mean age of 49.1 years (standard deviation (SD) 17.2) and 53.6% of women. Between 1997 and 2012, the weighted prevalence of ever life-time skin examination and skin examination in the current year increased by 38.2% and 35.3% respectively (p-value <0.001). Participants with a lower education level, lower income and living in non-metropolitan areas were less often screened than their counterparts. Educational differences in ever life-time skin examination increased over time (p-value for trend = 0.036).

CONCLUSION

While skin cancer screening prevalence in Switzerland increased from 1997 to 2012, most social inequalities persisted over time and educational inequalities increased. Dermatologists should be alerted that populations with lower education should be given special attention.