Vroegdetectie van huidtumoren in het tijdperk van artificiële intelligentie: zijn we er klaar voor?

Early detection of skin tumors in the age of artificial intelligence: are we ready for it? Artificial intelligence (AI) is rapidly evolving and is increasingly being applied in dermatology, particularly in the early detection of skin tumors. Given the high and increasing incidence of skin cancer and the pressure on specialized care, AI is often proposed as a tool to improve the efficiency of detection and triage. Applications span multiple levels, including risk-based triage on population-level, support for non-dermatologists, and decision support for dermatologists, notably through monitoring of high-risk patients. At the same time, important limitations remain. The performance of AI systems varies significantly depending on the clinical context, image quality, and device used. Smartphone applications used by laypersons for self-assessment of skin-lesion photographs remain insufficiently reliable in real-world conditions, as both image acquisition and diagnostic sensitivity and specificity may be suboptimal. False-positive results may lead to unnecessary anxiety, additional consultations and overdiagnosis, while false-negative results carry clinical risks. There is also a risk that clinicians adopt errors generated by AI systems due to increased trust in the technology. Within the European context, the implementation of AI is further shaped by regulatory frameworks such as the General Data Protection Regulation, the Medical Device Regulation, and the EU AI Act. The AI Act entered into force in 2024 and becomes applicable in phases; for medical AI it may apply alongside the Medical Device Regulation. This highlights that the use of AI entails not only technological, but also clinical and legal responsibility. A critical and stepwise integration of AI into dermatological practice is essential, including clinical validation, user training, and post-deployment performance monitoring. Without adequate understanding of its capabilities and limitations, there is a risk of inefficient and potentially suboptimal care delivery.

Authors

Publication Details

Journal
Tijdschrift voor Geneeskunde
Published
2026-11-18
DOI
https://doi.org/10.47671/tvg.82.26.052
Primary Topic
Cutaneous Melanoma Detection and Management
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Vroegdetectie van huidtumoren in het tijdperk van artificiële intelligentie: zijn we er klaar voor?

L. Verhulst, M. Vandaele, L. Vandebuerie
1 links
Tijdschrift voor Geneeskunde
Cutaneous Melanoma Detection and Management
article

Vroegdetectie van huidtumoren in het tijdperk van artificiële intelligentie: zijn we er klaar voor?

L. Verhulst, M. Vandaele, L. Vandebuerie
article en

Abstract

Early detection of skin tumors in the age of artificial intelligence: are we ready for it? Artificial intelligence (AI) is rapidly evolving and is increasingly being applied in dermatology, particularly in the early detection of skin tumors. Given the high and increasing incidence of skin cancer and the pressure on specialized care, AI is often proposed as a tool to improve the efficiency of detection and triage. Applications span multiple levels, including risk-based triage on population-level, support for non-dermatologists, and decision support for dermatologists, notably through monitoring of high-risk patients. At the same time, important limitations remain. The performance of AI systems varies significantly depending on the clinical context, image quality, and device used. Smartphone applications used by laypersons for self-assessment of skin-lesion photographs remain insufficiently reliable in real-world conditions, as both image acquisition and diagnostic sensitivity and specificity may be suboptimal. False-positive results may lead to unnecessary anxiety, additional consultations and overdiagnosis, while false-negative results carry clinical risks. There is also a risk that clinicians adopt errors generated by AI systems due to increased trust in the technology. Within the European context, the implementation of AI is further shaped by regulatory frameworks such as the General Data Protection Regulation, the Medical Device Regulation, and the EU AI Act. The AI Act entered into force in 2024 and becomes applicable in phases; for medical AI it may apply alongside the Medical Device Regulation. This highlights that the use of AI entails not only technological, but also clinical and legal responsibility. A critical and stepwise integration of AI into dermatological practice is essential, including clinical validation, user training, and post-deployment performance monitoring. Without adequate understanding of its capabilities and limitations, there is a risk of inefficient and potentially suboptimal care delivery.

Tijdschrift voor Geneeskunde
Good health and well-being
Cutaneous Melanoma Detection and Management
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon