Motivos dermatológicos de consulta en atención primaria. Análisis de la demanda derivada

Castillo-Arenas, E.; Garrido, V. Reyes; Serrano‐Ortega, S.

doi:10.1016/j.ad.2013.10.003

Cited by 36 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…It has been reported that the diagnosis of dermatological tumor lesions at the primary care level, by non-dermatologist physicians, currently exhibits low sensitivity (approximately 20%) and up to 94% specificity, alongside poor agreement. Coupled with extended referral periods and treatment initiation, malignant skin lesions have emerged as a significant health issue due to underdiagnosis [ 39 ]. Consequently, the results obtained in this study could enhance early diagnosis at the primary level by facilitating image processing of lesions through their fractal dimension.…”

Section: Discussionmentioning

confidence: 99%

Development, Application and Utility of a Machine Learning Approach for Melanoma and Non-Melanoma Lesion Classification Using Counting Box Fractal Dimension

Romero-Morelos,

Herrera-López,

González-Yebra

2024

Diagnostics

View full text Add to dashboard Cite

The diagnosis and identification of melanoma are not always accurate, even for experienced dermatologists. Histopathology continues to be the gold standard, assessing specific parameters such as the Breslow index. However, it remains invasive and may lack effectiveness. Therefore, leveraging mathematical modeling and informatics has been a pursuit of diagnostic methods favoring early detection. Fractality, a mathematical parameter quantifying complexity and irregularity, has proven useful in melanoma diagnosis. Nonetheless, no studies have implemented this metric to feed artificial intelligence algorithms for the automatic classification of dermatological lesions, including melanoma. Hence, this study aimed to determine the combined utility of fractal dimension and unsupervised low-computational-requirements machine learning models in classifying melanoma and non-melanoma lesions. We analyzed 39,270 dermatological lesions obtained from the International Skin Imaging Collaboration. Box-counting fractal dimensions were calculated for these lesions. Fractal values were used to implement classification methods by unsupervised machine learning based on principal component analysis and iterated K-means (100 iterations). A clear separation was observed, using only fractal dimension values, between benign or malignant lesions (sensibility 72.4% and specificity 50.1%) and melanoma or non-melanoma lesions (sensibility 72.8% and specificity 50%) and subsequently, the classification quality based on the machine learning model was ≈80% for both benign and malignant or melanoma and non-melanoma lesions. However, the grouping of metastatic melanoma versus non-metastatic melanoma was less effective, probably due to the small sample size included in MM lesions. Nevertheless, we could suggest a decision algorithm based on fractal dimension for dermatological lesion discrimination. On the other hand, it was also determined that the fractal dimension is sufficient to generate unsupervised artificial intelligence models that allow for a more efficient classification of dermatological lesions.

show abstract

Section: Discussionmentioning

confidence: 99%

Development, Application and Utility of a Machine Learning Approach for Melanoma and Non-Melanoma Lesion Classification Using Counting Box Fractal Dimension

Romero-Morelos,

Herrera-López,

González-Yebra

2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…Em uma análise de 755 pacientes realizada na Espanha, a principal razão para o encaminhamento foi a avaliação diagnóstica, correspondendo a 52,5%. As fichas que não continham um diagnóstico específico representaram 22,2%, em 25% delas não havia descrição do diagnóstico e apenas 18,1% continham uma descrição adequada de doença 18 .…”

Section: Discussionunclassified

“…Além disso, os médicos da APS demonstraram estar mais qualificados para descartar uma determinada condição de pele do que estabelecer um diagnóstico clínico preciso. Os autores sugerem que os médicos da APS devem receber conhecimento e treinamento de habilidades para melhorar o controle das dermatoses, especialmente o câncer de pele, devido ao seu impacto 18 .…”

Section: Discussionunclassified

Qualidade dos encaminhamentos da atenção primária a um serviço de dermatologia

Barszcz,

Baroni,

Dornelles

et al. 2023

Cad. saúde colet.

View full text Add to dashboard Cite

Resumo Introdução Queixas dermatológicas são frequentes e em sua maioria são avaliadas por médicos não especialistas. Objetivo Analisar a proporção de pacientes encaminhados para dermatologia que poderiam ter sido tratados na Atenção Primária à Saúde e o grau de concordância entre o diagnóstico de encaminhamento do médico da Atenção Primária à Saúde e o diagnóstico do dermatologista. Método Estudo retrospectivo com abordagem quantitativa, com dados coletados de 194 prontuários, entre 2014 e 2015. O grau de concordância foi analisado pelo coeficiente Kappa, com significância de 5%. Resultados A média de idade foi 46,7 anos (dp = 17,9), sendo a maioria mulheres. Os diagnósticos de encaminhamento mais frequentes relatados pelos médicos da Atenção Primária à Saúde foram doenças eritemato-descamativas (8,0%) e câncer de pele (6,0%). Em 40,3% dos casos não havia o preenchimento do diagnóstico de encaminhamento. Os diagnósticos mais frequentes relatados pelo dermatologista foram lesões pré-malignas (15,6%) e tumores benignos (12,4%). A proporção de pacientes encaminhados que poderia ter sido tratada na Atenção Primária à Saúde foi de 37,1%. O grau de concordância Kappa foi moderado. Conclusão Os resultados sugerem dificuldades no diagnóstico das dermatopatias que foram referenciadas ao serviço de dermatologia.

show abstract

“…Skin diseases are among the most prevalent reasons for seeking health care, varying between 5.5% and 22.5%. Most are not life-threatening; however, the psychosocial, economic, and occupational impact of these diseases is considered to be equal to or greater than other chronic pathologies [1]. In particular, 25% of dermatologic pathologies can even cause disability [2].…”

Section: Introductionmentioning

confidence: 99%

Clinical Application of Pharmacogenetic Markers in the Treatment of Dermatologic Pathologies

et al. 2021

View full text Add to dashboard Cite

Dermatologic pathologies are the fourth most common cause of non-fatal disease worldwide; however, they produce a psychosocial, economic, and occupational impact equal to or greater than other chronic conditions. The most prevalent are actinic keratosis, followed by basal-cell carcinoma, in a lesser proportion acne vulgaris, psoriasis, and hidradenitis suppurativa, among others, and more rarely dermatitis herpetiformis. To treat actinic keratosis and basal-cell carcinoma, 5-fluorouracil (5-FU) 0.5% is administered topically with good results, although in certain patients it produces severe toxicity. On the other hand, dapsone is a drug commonly used in inflammatory skin conditions such as dermatitis herpetiformis; however, it occasionally causes hemolytic anemia. Additionally, biologic drugs indicated for the treatment of moderate-to-severe psoriasis and hidradenitis suppurativa have proved to be effective and safe; nevertheless, a small percentage of patients do not respond to treatment with biologics in the long term or they are ineffective. This interindividual variability in response may be due to alterations in genes that encode proteins involved in the pathologic environment of the disease or the mechanism of action of the medication. Pharmacogenetics studies the relationship between genetic variations and drug response, which is useful for the early identification of non-responsive patients and those with a higher risk of developing toxicity upon treatment. This review describes the pharmacogenetic recommendations with the strongest evidence at present for the treatments used in dermatology, highlighting those included in clinical practice guides. Currently, we could only find pharmacogenetic clinical guidelines for 5-FU. However, the summary of product characteristics for dapsone contains a pharmacogenetic recommendation from the United States Food and Drug Administration. Finally, there is an enormous amount of information from pharmacogenetic studies in patients with dermatologic pathologies (mainly psoriasis) treated with biologic therapies, but they need to be validated in order to be included in clinical practice guides.

show abstract

Motivos dermatológicos de consulta en atención primaria. Análisis de la demanda derivada

Cited by 36 publications

References 10 publications

Development, Application and Utility of a Machine Learning Approach for Melanoma and Non-Melanoma Lesion Classification Using Counting Box Fractal Dimension

Development, Application and Utility of a Machine Learning Approach for Melanoma and Non-Melanoma Lesion Classification Using Counting Box Fractal Dimension

Qualidade dos encaminhamentos da atenção primária a um serviço de dermatologia

Clinical Application of Pharmacogenetic Markers in the Treatment of Dermatologic Pathologies

Contact Info

Product

Resources

About