Use of artificial intelligence, or machine learning, to assess dermoscopic images of skin lesions to detect melanoma has in several retrospective studies shown high levels of diagnostic accuracy on par with, or even outperforming, experienced dermatologists. However, the enthusiasm around these algorithms has not yet been matched by prospective clinical trials performed in authentic clinical settings. In several European countries, including Sweden, the initial clinical assessment of suspected skin cancer is principally conducted in the primary health care setting by primary care physicians; with or without access to teledermoscopic support from dermatology clinics. To determine the diagnostic performance of an artificial intelligence-based clinical decision support tool for cutaneous melanoma detection, operated by a smartphone application (app), when used prospectively by primary care physicians to assess skin lesions of concern due to some degree of melanoma suspicion. This prospective, multicentre, clinical trial was conducted at 36 primary care centres in Sweden. The physicians used the smartphone app on skin lesions of concern by photographing them dermoscopically, which resulted in a dichotomous decision support text regarding evidence for melanoma. Regardless of the app outcome, all lesions underwent standard diagnostic procedure, by surgical excision or referral to dermatologist. After completed investigation, lesion diagnoses were collected from the patients’ medical records and compared to app outcome and other lesion data. In total, 253 lesions of concern in 228 patients were included, of which 21 proved to be melanomas, with 11 thin invasive melanomas and 10 melanomas in situ. The app’s accuracy (95% confidence interval) in identifying melanomas was reflected in an area under the receiver operating characteristic (AUROC) curve of 0.960 (0.928-0.980), corresponding to a maximum sensitivity and specificity of 95.2% and 84.5%, respectively. For invasive melanomas alone, the AUROC was 0.988 (0.965–0.997), corresponding to a maximum sensitivity and specificity of 100% and 92.6%, respectively. The clinical decision support tool evaluated in this investigation showed high diagnostic accuracy when used prospectively on primary care patients, which could add significant clinical value for primary care physicians in assessing skin lesions to detect melanoma. ClinicalTrials.gov Identifier: NCT05172232

Actinic keratosis is the most common actinic lesion in fair-skinned populations. It is accepted as an indicator of actinic skin damage and as an occasional precursor of squamous cell carcinoma. The aim of this study was to investigate, in a cohort of patients with a diagnosis of actinic keratosis, the relative risk of developing skin cancer during a follow-up period of 10 years. This registry-based cohort study compared a cohort of 2,893 individuals in south-eastern Sweden, who were diagnosed with actinic keratosis during the period 2000 to 2004, with a matched-control cohort of 14,668 individuals without actinic keratosis during the same inclusion period. The subjects were followed for 10 years to identify skin cancer development in both cohorts. Hazard ratios with 95% confidence intervals (95% CI) were used as risk measures. Individuals in the actinic keratosis cohort had a markedly higher risk for all skin cancer forms compared with the control cohort (hazard ratio (HR) 5.1, 95% CI 4.7?5.6). The relative risk was highest for developing squamous cell carcinoma (SCC) (HR 7.7, 95% CI 6.7?8.8) and somewhat lower for basal cell carcinoma (BCC) (HR 4.4, 95% CI 4.1?5.0) and malignant melanoma (MM) (HR 2.7 (2.1?3.6). Patients with a diagnosis of actinic keratosis were found to be at increased risk of developing SCC, BCC and MM in the 10 years following diagnosis of actinic keratosis. In conclusion, a diagnosis of actinic keratosis, even in the absence of documentation of other features of chronic sun exposure, is a marker of increased risk of skin cancer, which should be addressed with individually directed preventive advice.

The incidence of skin cancer is increasing worldwide, mostly because of increasing exposure to ultraviolet (UV) radiation from the sun. The Sun Exposure and Protection Index (SEPI) questionnaire, developed in Linköping and validated in Sweden and Australia, is used to map sun habits, sun protection behaviour, and readiness to increase sun protection. We sought to examine differences in sun habits or sun protection behaviour and propensity to increase sun protection, based on SEPI as related to self-estimated skin UV sensitivity according to the Fitzpatrick classification. The study population comprised students at Linköping University, who were asked to complete the SEPI questionnaire. We examined differences in sun habits and sun protection behaviour according to skin type and gender. Individuals with lower UV sensitivity had significantly riskier sun habits and sun protection behaviour and were significantly less likely to increase sun protection. Women spent significantly more time tanning than men, more time in the midday sun, used sunscreen more frequently, and were more likely to seek the shade for sun protection. Individuals with higher UV sensitivity were significantly more likely to increase sun protection; individuals with low UV sensitivity tended to have a riskier attitude to sunbathing. In conclusion, self-estimated skin type and gender are important factors influencing sun exposure habits and sun protection behaviour.

Background: Differentiating between pneumonia and acute bronchitis is often difficult in primary care. There is no consensus regarding clinical decision rules for pneumonia, and guidelines differ between countries. Use of diagnostic tests and change of management over time is not known.Aim: To calculate the proportion of diagnostic tests in the management of lower respiratory tract infections (LRTIs) in a low antibiotic prescribing country, and to evaluate if the use and prescription pattern has changed over time.Design & setting: A register-based study on data from electronic health records from January 2006 to December 2014 in the Kronoberg county of south east Sweden.Method: Data regarding use of C-reactive protein (CRP), chest x-rays (CXRs), microbiological tests, and antibiotic prescriptions were assessed for patients aged 18–79 years, with the diagnosis pneumonia, acute bronchitis, or cough.Results: A total of 54 229 sickness episodes were analysed. Use of CRP increased during the study period from 61.3% to 77.5% for patients with pneumonia (P<0.001), and from 53.4% to 65.7% for patients with acute bronchitis (P<0.001). Use of CXR increased for patients with acute bronchitis from 3.1% to 5.1% (P<0.001). Use of microbiological tests increased for patients with pneumonia, from 1.8% to 5.1% (P<0.001). The antibiotic prescription rate decreased from 18.6 to 8.2 per 1000 inhabitants per year for patients with acute bronchitis, but did not change for patients with pneumonia.Conclusion: Use of CRP and microbiological tests in the diagnostics of LRTIs increased despite the fact that the incidence of pneumonia and acute bronchitis was stable.