Accuracy of a smartphone application for triage of skin lesions based on machine learning algorithms.

BACKGROUND: Machine learning algorithms achieve expert-level accuracy in skin lesion classification based on clinical images. However, it is not yet shown whether these algorithms could have high accuracy when embedded in a smartphone app, where image quality is lower and there is high variability in image taking scenarios by users. In the past, these applications were criticized due to lack of accuracy. OBJECTIVE: In this study, we evaluate the accuracy of the newest version of a smartphone application (SA) for risk assessment of skin lesions. METHODS: This SA uses a machine learning algorithm to compute a risk rating. The algorithm is trained on 131 873 images taken by 31 449 users in multiple countries between January 2016 and August 2018 and rated for risk by dermatologists. To evaluate the sensitivity of the algorithm, we use 285 histopathologically validated skin cancer cases (including 138 malignant melanomas), from two previously published clinical studies (195 cases) and from the SA user database (90 cases). We calculate the specificity on a separate set from the SA user database containing 6000 clinically validated benign cases. RESULTS: The algorithm scored a 95.1% (95% CI, 91.9-97.3%) sensitivity in detecting (pre)malignant conditions (93% for malignant melanoma and 97% for keratinocyte carcinomas and precursors). This level of sensitivity was achieved with a 78.3% (95% CI, 77.2-79.3%) specificity. CONCLUSIONS: This SA provides a high sensitivity to detect skin cancer; however, there is still room for improvement in terms of specificity. Future studies are needed to assess the impact of this SA on the health systems and its users.

Clinical and immunological aspects and outcome of a Brazilian cohort of 414 patients with systemic lupus erythematosus (SLE): comparison between childhood-onset, adult-onset, and late-onset SLE.

The clinical expression of systemic lupus erythematosus (SLE) is influenced by genetic and environmental factors and therefore varies between ethnicities. Information on the epidemiology of SLE in Brazil is scarce and practically limited to studies conducted in socioeconomically developed regions (South and Southeast). The objective of this study was to describe the clinical and immunological aspects and outcome of a cohort of patients with SLE treated at a university hospital in northeastern Brazil and compare patterns related to age at onset: childhood (cSLE), adult (aSLE), and late (lSLE). A random sample of 414 records (women: 93.5%) were reviewed. The mean age at SLE onset and the mean disease duration were 28.9 ± 10.9 years and 10.2 ± 6.6 years, respectively. Most patients had aSLE (n = 338; 81.6%), followed by cSLE (n = 60; 14.5%) and lSLE (n = 16; 3.9%). The female/male ratio was 6.5:1 in cSLE and 16.8:1 in aSLE; in lSLE, all patients were female (p = 0.05). During follow-up, the cSLE group presented higher rates of nephritis (70% vs. 52.9% vs. 12.5%; p = 0.0001) and leuko/lymphopenia (61.7% vs. 43.8% vs. 56.2%; p = 0.02). No significant differences were found for anti-dsDNA, anti-Sm, and antiphospholipid antibodies. Treatment with immunosuppressants was significantly more common, and higher doses of prednisone were used, in cSLE. The prevalence of cardiovascular diseases were more frequent in lSLE (p = 0.03). No significant differences were found between the three groups with regard to mean damage accrual (SDI), remission, and mortality. Although cSLE presented higher rates of nephritis and leuko/lymphopenia, more frequent use of immunosuppressants and higher prednisone doses than aSLE and lSLE, the three groups did not differ significantly with regard to damage accrual, remission, and mortality.

Cost-effectiveness of prostate cancer screening: a simulation study based on ERSPC data.

BACKGROUND: The results of the European Randomized Study of Screening for Prostate Cancer (ERSPC) trial showed a statistically significant 29% prostate cancer mortality reduction for the men screened in the intervention arm and a 23% negative impact on the life-years gained because of quality of life. However, alternative prostate-specific antigen (PSA) screening strategies for the population may exist, optimizing the effects on mortality reduction, quality of life, overdiagnosis, and costs. METHODS: Based on data of the ERSPC trial, we predicted the numbers of prostate cancers diagnosed, prostate cancer deaths averted, life-years and quality-adjusted life-years (QALY) gained, and cost-effectiveness of 68 screening strategies starting at age 55 years, with a PSA threshold of 3, using microsimulation modeling. The screening strategies varied by age to stop screening and screening interval (one to 14 years or once in a lifetime screens), and therefore number of tests. RESULTS: Screening at short intervals of three years or less was more cost-effective than using longer intervals. Screening at ages 55 to 59 years with two-year intervals had an incremental cost-effectiveness ratio of $73000 per QALY gained and was considered optimal. With this strategy, lifetime prostate cancer mortality reduction was predicted as 13%, and 33% of the screen-detected cancers were overdiagnosed. When better quality of life for the post-treatment period could be achieved, an older age of 65 to 72 years for ending screening was obtained. CONCLUSION: Prostate cancer screening can be cost-effective when it is limited to two or three screens between ages 55 to 59 years. Screening above age 63 years is less cost-effective because of loss of QALYs because of overdiagnosis.

Protein phosphorylation during the process of interaction of Toxoplasma gondii with host cells.

Previous studies have shown that tachyzoites of Toxoplasma gondii were able to penetrate into macrophages using two mechanisms: phagocytosis and active penetration. We show here that previous incubation of the macrophages or the parasites with staurosporine, a wide range inhibitor of protein kinases, tyrfostin and genistein, specific inhibitors of tyrosine kinases, significantly interfered with the process of parasite-macrophage interaction. Staurosporine treatment induced the formation of many filopodium-like surface projections of the macrophages and markedly increased the attachment of the tachyzoites to the cell surface. Genistein inhibited about 50% penetration of T. gondii into macrophages. Previous incubation of tachyzoites with genistein also significantly inhibited their attachment to and penetration into the macrophages. Confocal laser scanning microscopy was used to locate phosphoproteins in macrophages interacting with tachyzoites. Antiphosphotyrosine antibodies labeled the surface of macrophages, but not L929 cells, incubated in presence of T. gondii, even those cells did not show associated parasites. Anti phosphotyrosine, phosphothreonine and phosphoserine antibodies labeled the region surrounding the parasitophorous vacuoles. These observations suggest that protein phosphorylation is a key event in the process of T. gondii-host cell interaction.

The peripheral vesicles of trophozoites of the primitive protozoan Giardia lamblia may correspond to early and late endosomes and to lysosomes.

Giardia lamblia, a primitive eukaryotic cell, lacks organelles such as mitochondria, peroxisomes, and a typical Golgi complex and presents a system of vesicles located below the plasma membrane. We used fluorescence and electron microscopy to better characterize the peripheral vesicles. Incubation of living cells with acridine orange showed that the peripheral vesicles correspond to an acidic compartment. Incubation with lucifer yellow, and with horseradish peroxidase, showed labeling of the peripheral vesicles even after several hours. Acid phosphatase was localized in the endoplasmic reticulum and in most of the peripheral vesicles. On the other hand, glucose 6-phosphatase, an endoplasmic reticulum marker, was observed in the endoplasmic reticulum cisternae and in some peripheral vesicles. A similar labeling pattern was observed using the zinc iodide technique, which reveals SH-containing proteins. Three-dimensional reconstruction and electron microscopy tomography of cells stained for acid phosphatase and glucose-6-phosphatase revealed the connection between some vesicles and profiles of the endoplasmic reticulum. Taken together, our observations suggest that trophozoites of G. lamblia present an endosomal-lysosomal system concentrated in a single system, the peripheral vesicles, which may represent an ancient organellar system that later on subdivided into compartments such as early and late endosomes and lysosomes.

Early events related with the behaviour of Trypanosoma cruzi within an endocytic vacuole in mouse peritoneal macrophages.

Transmission electron microscopy was used to analyse the process of interaction of Trypanosoma cruzi with resident and activated mouse peritoneal macrophages. Initially, the parasites are located within a membrane-bounded endocytic vacuole. Lysosomes from the host cell fuse and discharge their content into the parasite-containing vacuole, as visualized by localization of horseradish peroxidase and acid phosphatase activity. Acridine orange was used to label secondary lysosomes in order to quantify the process of lysosome-phagosome fusion by fluorescence microscopy. The fusion index was higher for amastigote than for epimastigote and trypomastigote forms. Images were obtained showing that a few hours after ingestion of trypomastigote forms by the macrophages there is progressive disruption of the membrane lining the vacuole, until its complete disappearance.

Surface charge of resident, elicited, and activated mouse peritoneal macrophages.

The surface charge of resident, thioglycollate-elicited, and Trypanosoma cruzi-activated mouse peritoneal macrophages was analyzed using cell electrophoresis. All macrophages had a net negative surface charge. Activated macrophages had a lower zeta potential and a higher isoelectrophoretic point than resident and elicited macrophages. The populations of resident, elicited, and activated macrophages were heterogeneous in terms of surface charge. The analysis of the effect of the pH of the solution in which the macrophages were suspended on their cellular electrophoretic mobility (EPM) indicated that their surface contained both positively and negatively charged dissociating groups. The contribution of sialic acid residues to the surface charge was determined by analyzing the effect of neuraminidase treatment on the EPM of the cells. Activated macrophages possessed more sialic acid residues exposed on their surface, and sensitive to the neuraminidase from Clostridium perfringens, than resident and elicited macrophages. Treatment of the cells with the neuraminidase from Vibrio cholerae, however, reduced the surface charge of all macrophages in about the same extent. Macrophages had their mean EPM reduced when incubated in the presence of Ca++, suggesting that some cell surface anionogenic sites have Ca++-binding capacity.