Diagnostic ability of general practitioners and dermatologists in discriminating pigmented skin lesions

doi:10.1067/mjd.2001.113442

Journal of the American Academy of Dermatology

Volume 44, Issue 6, June 2001, Pages 979-986

https://doi.org/10.1067/mjd.2001.113442 Get rights and content

Abstract

Background: Early recognition of melanoma is the key in preventing metastatic disease. Objective: The aim of this study was to evaluate diagnostic ability of general practitioners (GPs) and dermatologists concerning pigmented skin lesions in general and melanoma in particular. We also investigated whether the diagnostic ability of GPs changed after a lecture on melanoma. Methods: A test set of 13 pigmented skin lesions on 35-mm color slides was presented to 160 GPs and 60 dermatologists during educational courses. Results: GPs correctly evaluated biologic behavior of the pigmented skin lesions in 72% of the evaluations. In 71% of these evaluations they correctly identified the lesions. The proportion of lesions correctly identified was positively correlated with the frequency of pigmented skin lesions in everyday practice. Dermatologists made a correct identification of the lesions in 88% of all evaluations, and they correctly evaluated biologic behavior in 94% of these. Recognition of melanoma was proportional to melanoma exposure in everyday practice. Thick melanomas were better recognized than thin melanomas in both physician groups. After a lecture on melanoma, sensitivity of GPs to recognize malignant disease increased from 72% to 84%, without a significant decrease in specificity. The proportion of lesions correctly identified also rose significantly (66% vs 52%). (J Am Acad Dermatol 2001;44:979-86.)

Section snippets

Methods

During 1998, a health education program on melanoma was launched for GPs in the province of East-Flanders, Belgium. The objective was to bring an update on risk groups, clinical aspects, differential diagnosis, and management of melanoma by organizing lectures on this topic. Their capacity to diagnose pigmented skin lesions was tested concurrently before and after the course. In May 1997 an invitation was addressed to all 67 GP educational groups (representing 1956 GPs) of the province. Eight

Results

There are important differences between dermatologists and GPs as to the frequency with which they are asked advice for pigmented skin lesions (Table I). Whereas 95% of the dermatologists are consulted for a pigmented lesion at least once a week and more than half of them even daily, only 18% of the GPs are presented a pigmented lesion once in a week. For most GPs (61%) such advice is asked only once every week to 2 months. Similarly the frequency of melanoma cases seen in general practice is

Discussion

The ability of physicians to recognize pigmented skin lesions and melanoma can be investigated either prospectively, retrospectively, or in an experimental setting. In the prospective setting, usually a screening program, the clinical diagnosis is compared with the eventual outcome (eg, biopsy result, patient registered in a cancer registry).4, 5, 6 Follow-up of these patients is usually elaborate, especially of those in whom no suspect lesions were noted. Hence there is a danger of

References (28)

FHJ Rampen et al.
Melanoma/skin cancer screening clinics: experiences in the Netherlands
J Am Acad Dermatol
(1991)
R Marks et al.
Who removes pigmented lesions? A study of the ratio of melanoma to other benign pigmented tumors removed by different categories of physicians in Australia in 1989 and 1994
J Am Acad Dermatol
(1997)
FHJ Rampen et al.
False-negative findings in skin cancer and melanoma screening
J Am Acad Dermatol
(1995)
BR Cassileth et al.
How well do physicians recognize melanoma and other problem lesions?
J Am Acad Dermatol
(1986)
BA Solomon et al.
Quality of care: issue or oversight in health care reform?
J Am Acad Dermatol
(1996)
BR Cassileth et al.
Patient and physician delay in melanoma diagnosis
J Am Acad Dermatol
(1988)
RA Clark et al.
The cost of initiating appropriate therapy for skin diseases: a comparison of dermatologists and family physicians
J Am Acad Dermatol
(1983)
H Pehamberger et al.
In vivo epiluminescence microscopy: improvement in the early diagnosis of melanoma
J Invest Dermatol
(1993)
AC Lightstone et al.
Diagnostic accuracy: a new approach to its evaluation
Arch Dermatol
(1965)
CM Grin et al.
Accuracy in the clinical diagnosis of malignant melanoma
Arch Dermatol
(1990)

JD Whited et al.

Diagnostic accuracy and precision in assessing dermatologic disease: problem or promise?

Arch Dermatol

(1997)

HK Koh et al.

Evaluation of melanoma/skin cancer screening in Massachusetts: preliminary results

Cancer

(1990)

MJM De Rooij et al.

Skin cancer screening focusing on melanoma yields more selective attendance

Arch Dermatol

(1995)

SW. Becker

Pitfalls in the diagnosis and treatment of melanoma

Arch Dermatol

(1954)

Cited by (85)

Non-tumorous facial pigmentation classification based on multi-view convolutional neural network with attention mechanism
2022, Neurocomputing
Diagnosis of non-tumorous facial pigmentation is an important and difficult issue in the field of dermatology (For example, chloasma and freckles are too similar to distinguish, but they often appear at the same time). In this paper, different from other studies, we used images with nine different forms (views) to comprehensively diagnose these diseases for the first time. In detail, firstly, we collected and published the first multi-view non-tumorous facial pigmentation (MVNFP) dataset provided as the benchmark for classification and segmentation problems: MVNFP, where each face consists of 9 images: 1) Standard Image, 2) Polarization Image, 3) Oil Secretion Image, 4) Sunshine Damage Image, 5) Pigmentation Image, 6) Physiological Aging Image, 7) Sensitive Image, 8) Brown Image, 9) Pigmentation Trend Image. MVNFP has a total of 10,719 images, 5 categories which brings great convenience for the follow-up research. Secondly, to make full use of the informations behind these images described from different views, we use multi-view convolutional neural network to diagnose these indistinguishable diseases. In addition, we introduced the attention mechanisms, and at the same time deeply studied the many influencing factors of multi-view non-tumorous facial pigmentation diagnosis. All experimental results show our method has achieved state-of-the-art results on the MVNFP dataset. Code and MVNFP dataset are released at: https://github.com/sunshiding/MVNFP.git.
Classification of non-tumorous skin pigmentation disorders using voting based probabilistic linear discriminant analysis
2018, Computers in Biology and Medicine
Non-tumorous skin pigmentation disorders can have a huge negative emotional impact on patients. The correct diagnosis of these disorders is essential for proper treatments to be instituted. In this paper, we present a computerized method for classifying five non-tumorous skin pigmentation disorders (i.e., freckles, lentigines, Hori's nevus, melasma and nevus of Ota) based on probabilistic linear discriminant analysis (PLDA). To address the large within-class variance problem with pigmentation images, a voting based PLDA (V-PLDA) approach is proposed. The proposed V-PLDA method is tested on a dataset that contains 150 real-world images taken from patients. It is shown that the proposed V-PLDA method obtains significantly higher classification accuracy (4% or more with p< 0.001 in the analysis of variance (ANOVA) test) than the original PLDA method, as well as several state-of-the-art image classification methods. To the authors' best knowledge, this is the first study that focuses on the non-tumorous skin pigmentation image classification problem. Therefore, this paper could provide a benchmark for subsequent research on this topic. Additionally, the proposed V-PLDA method demonstrates promising performance in clinical applications related to skin pigmentation disorders.
Recognition and initial management of melanoma by general practitioners: A survey in a rural French area with low medical density
2018, Presse Medicale
Les cancers cutanés sont très fréquents, visibles sur peau, le médecin généraliste (MG) est en première ligne pour décider de la prise en charge : reconnaître la malignité et adresser le plus souvent au spécialiste pour l’exérèse, ou considérer que la lésion est bénigne et proposer une surveillance clinique. La faible densité médicale en région Centre Val de Loire rend l’accès au MG et au dermatologue difficile. Notre étude avait pour objectif d’évaluer la pratique des MG du Cher dans le dépistage des cancers cutanés de manière générale, et du mélanome en particulier.
Nous avons adressé en novembre 2015 un questionnaire à tous les MG du département du Cher (soit 204 questionnaires) afin de connaître leur pratique du dépistage des cancers cutanés. Le questionnaire était divisé en deux parties : une première composée de 23 items avec une majorité de questions fermées sur le mélanome, une deuxième comportant une série de 10 cas cliniques (4 mélanomes, 1 basocellulaire tatoué, 4 nævus, 1 kératose séborrhéique). Les MG devaient répondre à 3 questions identiques pour chaque cas : diagnostic, degré de certitude (de 0 à 10), attitude pratique (exérèse, surveillance, recours au dermatologue ou au chirurgien). Leurs réponses étaient anonymes. Le critère de jugement principal était de savoir si les MG avaient une conduite adaptée devant une tumeur cutanée.
Nous avons reçu 72 réponses (taux de réponse de 35 %). Trente-huit médecins (53 %) avaient une attitude adaptée face aux 5 lésions malignes, et 18 médecins (25 %) une attitude adaptée dans 4 cas sur 5. La méthode ABCDE était connue de 58 % des répondeurs, le vilain petit canard de 19 %. Les MG ne se sentaient pas très à l’aise pour dépister un mélanome : sur une échelle croissante (de 0 = pas à l’aise du tout à 10 = très à l’aise) la moyenne était de 4,2 avec une médiane à 5 (valeurs extrêmes 0–10). Ils exprimaient un fort besoin de formation sur ce thème : sur une échelle croissante de 0 à 10, la moyenne était à 7,9 pour une médiane à 8 (extrêmes 3–10). L’âge, le mode d’exercice (seul ou en groupe), le nombre de consultations quotidiennes, le niveau de connaissance des facteurs de risque de développer un mélanome et le degré d’aisance ressentie pour le diagnostic du mélanome n’étaient pas associés significativement à une attitude plus ou moins adaptée. Les principales difficultés étaient le manque de temps et la difficulté croissante d’accès au dermatologue. La mise en place d’un accès facilité par télé-dermatologie était sollicitée par 89 % des répondeurs.
Les MG ont une conduite pratique souvent adaptée dans la prise en charge initiale des tumeurs cutanées. Les principales difficultés identifiées étaient le manque de temps et la difficulté croissante d’accès au dermatologue. La mise en place d’un accès facilité par télé-dermatologie pourrait faciliter la prise en charge plus rapide du mélanome.
Cutaneous cancers are very common, easily visible on skin. The general practitioner (GP) is in the front line to manage the lesions. He has to recognize malignancy and refer most often to the specialist for excision, or consider that the lesion is benign and in ambiguous cases, offer clinical monitoring. The current low medical density in the Centre Val de Loire area makes access to general practitioners (GP) and dermatologists harder. The aim of this study was to evaluate GPs’ everyday practice in cutaneous cancers screening in general, and particularly in melanoma screening, in a rural region of France.
We sent a questionnaire on November 24th 2015 to all GPs of the Cher department (204 questionnaires), to assess their knowledge and practice of melanoma. The questionnaire comprised 2 parts: the first part was composed of 23 items with a majority of questions focused on melanoma and the second part consisted of clinical cases including 5 benign cutaneous tumors, 4 melanomas and 1 pigmented basal cell carcinoma. GP's were asked to answer in each case: diagnosis, degree of certainty (from 0 to 10), practical attitude (excision, referral to dermatologist or surgeon or surveillance). Their answers were anonymous. The primary endpoint was whether medical decision regarding each case was appropriate, i.e. removal of malignant lesion or referral for removal, and reassurance or surveillance in benign lesions.
The response rate was 35% (72 responses). Thirty-eight GPs (53%) had an appropriate management facing the 5 malignant lesions, 18 GP (25%) had an appropriate management in 4 out of 5 cases. The ABCDE rule was known by 58% of responders, the ugly duckling sign of 19%. GPs did not feel comfortable with melanoma: on a growing scale (from 0 = not comfortable at all to 10 = very comfortable) the average was 4.2 with a median at 5 (range 0–10). They expressed a strong need for training on this topic: on a scale increasing from 0 to 10, the average was 7.9 for a median to 8 (range 3–10). Knowledge about melanoma risk factors, and the level of ease dealing with screening of melanoma was not significantly associated with a better management. The main difficulties were lack of time and the increasing difficulty of access to dermatologist. Fast and easy access by teledermatology was solicited by 89% of GPs.
GPs had often appropriate management of skin cancer. The major obstacles to skin's cancer screening were the lack of time and difficult access to dermatologists. The setting-up of an easier access with teledermatology was requested by 89% of responders, and should improve early detection of melanoma.
Palpation as a useful diagnostic tool for skin lesions
2014, Journal of Plastic, Reconstructive and Aesthetic Surgery
Early identification and accurate diagnosis of malignant pigmented skin lesions is essential for effective management and cost containment. The aim was to investigate the additional value of tactile descriptive information from lesion palpation on the diagnostic accuracy of pigmented skin lesions by medical students using computer-driven learning.
Sixth year medical students (n = 152) from the University of Adelaide were invited to participate in an online teaching module on pigmented skin lesions. Users were asked to describe, diagnose and manage 15 pigmented skin lesions in three separate case studies based on pertinent clinical history and visual images of the lesions. Tactile descriptive information was then provided and users were asked to reflect on their diagnosis and management.
A total of 66 (43%) of the sixth year students successfully completed the online module. Diagnostic accuracy improved significantly with the provision of tactile descriptive information for seborrhoeic keratosis (p = 0.012), basal cell carcinoma (p = 0.001), squamous cell carcinoma (p = 0.02), and dysplastic naevi (p = 0.035). Tactile descriptive information was stated by 23% of medical students to be important in the clinical diagnosis of pigmented skin lesion. Students managed all malignant pigmented skin lesions with either appropriate biopsy or specialist referral.
Palpation information about skin lesions offers useful information for improvement of diagnostic accuracy in an online computer learning setting for medical students.
Artificial Intelligence Algorithms for Benign vs. Malignant Dermoscopic Skin Lesion Image Classification
2023, Bioengineering
Evaluation of primary care physicians' competence in selective skin tumour triage after short versus long dermoscopy training: a randomized non-inferiority trial
2023, Journal of the European Academy of Dermatology and Venereology

View all citing articles on Scopus

^☆: Supported by the Fund for Scientific Research-Flanders (Belgium) (F.W.O. G.0106.96).

^☆☆: Reprint requests: Jean-Marie Naeyaert, Department of Dermatology, University Hospital Gent, De Pintelaan 185, 9000 Gent, Belgium.

^★: J Am Acad Dermatol 2001;44:979-86

View full text

ReportsDiagnostic ability of general practitioners and dermatologists in discriminating pigmented skin lesions☆,☆☆,★

Abstract

Section snippets

Methods

Results

Discussion

J Am Acad Dermatol

J Am Acad Dermatol

J Am Acad Dermatol

J Am Acad Dermatol

J Am Acad Dermatol

J Am Acad Dermatol

J Am Acad Dermatol

J Invest Dermatol

Diagnostic accuracy: a new approach to its evaluation

Arch Dermatol

Accuracy in the clinical diagnosis of malignant melanoma

Arch Dermatol

Diagnostic accuracy and precision in assessing dermatologic disease: problem or promise?

Arch Dermatol

Evaluation of melanoma/skin cancer screening in Massachusetts: preliminary results

Cancer

Skin cancer screening focusing on melanoma yields more selective attendance

Arch Dermatol

Pitfalls in the diagnosis and treatment of melanoma

Arch Dermatol

Reports
Diagnostic ability of general practitioners and dermatologists in discriminating pigmented skin lesions☆,☆☆,★