Dermatologist-like explainable AI enhances trust and confidence in diagnosing melanoma

Artificial intelligence (AI) systems have been shown to help dermatologists diagnose melanoma more accurately, however they lack transparency, hindering user acceptance. Explainable AI (XAI) methods can help to increase transparency, yet often lack precise, domain-specific explanations. Moreover, the impact of XAI methods on dermatologists' decisions has not yet been evaluated. Building upon previous research, we introduce an XAI system that provides precise and domain-specific explanations alongside its differential diagnoses of melanomas and nevi. Through a three-phase study, we assess its impact on dermatologists' diagnostic accuracy, diagnostic confidence, and trust in the XAI-support. Our results show strong alignment between XAI and dermatologist explanations. We also show that dermatologists' confidence in their diagnoses, and their trust in the support system significantly increase with XAI compared to conventional AI. This study highlights dermatologists' willingness to adopt such XAI systems, promoting future use in the clinic.

Tungiasis in the Sanumás Amerindians in the Amazon Rainforest, Brazil: Prevalence, Intensity and Morbidity

BACKGROUND

Tungiasis is a disease associated with extreme poverty. We aimed to evaluate the prevalence of tungiasis in six different settlements of the Sanumás indigenous community in a remote area in the Auaris region, Yanomami territory, Brazil.

METHODS

We conducted an observational study to detect clinical and epidemiological factors associated with tungiasis using a cross-sectional strategy and multivariate logistic regression. Soil analysis was performed by visual and microscopic methods.

RESULTS

We examined 555 persons, 45 of whom had active tungiasis; 18 cases were classified as mild, 16 as moderate and 11 as severe. The disease was significantly more prevalent in children than in adults (odds ratio (OR) 15.77; 95% confidence interval (CI) = 5.34-67.91; p < 0.001). Soil infestation was significantly related to the occurrence of human tungiasis (OR = 12.29; 95% CI = 3.75-45.88). The sex and GPS location of the houses were not related to the occurrence of tungiasis.

CONCLUSIONS

We conclude that tungiasis is an important problem in the Sanumás community, especially for children. We suggest that interruption of the off-host transmission cycle, together with regular treatment [human and animal interventions], must be prioritized to achieve control of tungiasis in indigenous populations.

Non-tuberculous cutaneous mycobacterioses

Non-tuberculous mycobacteriosis, previously known as atypical, anonymous, opportunistic, or unclassified mycobacteriosis, refers to pathogenic mycobacterioses other than those caused by Mycobacterium tuberculosis and Mycobacterium leprae. These mycobacteria are known for their environmental distribution, mainly in water and soil. The incidence of non-tuberculous mycobacteriosis has been increasing in all countries and skin infections are being increasingly studied, mainly with the increase in immunosuppressive conditions and the development of new medications that affect immunological function. In the present article, a detailed narrative review of the literature is carried out to study the main non-tuberculous mycobacteriosis that cause diseases of the skin and appendages. The article also aims to present a historical context, followed by epidemiological, microbiological, and clinical characteristics of these diseases. Practical considerations about the diagnosis and treatment of non-tuberculous mycobacteriosis are detailed.