New AI-algorithms on smartphones to detect skin cancer in a clinical setting-A validation study.

BACKGROUND AND OBJECTIVES: The incidence of skin cancer is rising worldwide and there is medical need to optimize its early detection. This study was conducted to determine the diagnostic and risk-assessment accuracy of two new diagnosis-based neural networks (analyze and detect), which comply with the CE-criteria, in evaluating the malignant potential of various skin lesions on a smartphone. Of note, the intention of our study was to evaluate the performance of these medical products in a clinical setting for the first time. METHODS: This was a prospective, single-center clinical study at one tertiary referral center in Graz, Austria. Patients, who were either scheduled for preventive skin examination or removal of at least one skin lesion were eligible for participation. Patients were assessed by at least two dermatologists and by the integrated algorithms on different mobile phones. The lesions to be recorded were randomly selected by the dermatologists. The diagnosis of the algorithm was stated as correct if it matched the diagnosis of the two dermatologists or the histology (if available). The histology was the reference standard, however, if both clinicians considered a lesion as being benign no histology was performed and the dermatologists were stated as reference standard. RESULTS: A total of 238 patients with 1171 lesions (86 female; 36.13%) with an average age of 66.19 (SD = 17.05) was included. Sensitivity and specificity of the detect algorithm were 96.4% (CI 93.94-98.85) and 94.85% (CI 92.46-97.23); for the analyze algorithm a sensitivity of 95.35% (CI 93.45-97.25) and a specificity of 90.32% (CI 88.1-92.54) were achieved. DISCUSSION: The studied neural networks succeeded analyzing the risk of skin lesions with a high diagnostic accuracy showing that they are sufficient tools in calculating the probability of a skin lesion being malignant. In conjunction with the wide spread use of smartphones this new AI approach opens the opportunity for a higher early detection rate of skin cancer with consecutive lower epidemiological burden of metastatic cancer and reducing health care costs. This neural network moreover facilitates the empowerment of patients, especially in regions with a low density of medical doctors. REGISTRATION: Approved and registered at the ethics committee of the Medical University of Graz, Austria (Approval number: 30-199 ex 17/18).

Nitric Oxide-Related Biological Pathways in Patients with Major Depression.

BACKGROUND: Major depression is a well-known risk factor for cardiovascular diseases and increased mortality following myocardial infarction. However, biomarkers of depression and increased cardiovascular risk are still missing. The aim of this prospective study was to evaluate, whether nitric-oxide (NO) related factors for endothelial dysfunction, such as global arginine bioavailability, arginase activity, L-arginine/ADMA ratio and the arginine metabolites asymmetric dimethylarginine (ADMA) and symmetric dimethylarginine (SDMA) might be biomarkers for depression-induced cardiovascular risk. METHODS: In 71 in-patients with major depression and 48 healthy controls the Global Arginine Bioavailability Ratio (GABR), arginase activity (arginine/ornithine ratio), the L-arginine/ADMA ratio, ADMA, and SDMA were determined by high-pressure liquid chromatography. Psychiatric and laboratory assessments were obtained at baseline at the time of in-patient admittance and at the time of hospital discharge. RESULTS: The ADMA concentrations in patients with major depression were significantly elevated and the SDMA concentrations were significantly decreased in comparison with the healthy controls. Even after a first improvement of depression, ADMA and SDMA levels remained nearly unchanged. In addition, after a first improvement of depression at the time of hospital discharge, a significant decrease in arginase activity, an increased L-arginine/ADMA ratio and a trend for increased global arginine bioavailability were observed. CONCLUSIONS: Our study results are evidence that in patients with major depression ADMA and SDMA might be biomarkers to indicate an increased cardiovascular threat due to depression-triggered NO reduction. GABR, the L-arginine/ADMA ratio and arginase activity might be indicators of therapy success and increased NO production after remission.

Recoil velocities from equal-mass binary-black-hole mergers.

The final evolution of a binary-black-hole system gives rise to a recoil velocity if an asymmetry is present in the emitted gravitational radiation. Measurements of this effect for nonspinning binaries with unequal masses have pointed out that kick velocities approximately 175 km/s can be reached for a mass ratio approximately 0.36. However, a larger recoil can be obtained for equal-mass binaries if the asymmetry is provided by the spins. Using two independent methods we show that the merger of such binaries yields velocities as large as approximately 440 km/s for black holes having unequal spins that are antialigned and parallel to the orbital angular momentum.

Gravitational-wave extraction from an inspiraling configuration of merging black holes.

We present new ideas for evolving black holes through a computational grid without excision, which enable accurate and stable evolutions of binary black hole systems with the accurate determination of gravitational waveforms directly from the wave zone region. Rather than excising the black hole interiors, our approach follows the "puncture" treatment of black holes, but utilizing a new gauge condition which allows the black holes to move successfully through the computational domain. We apply these techniques to an inspiraling binary, modeling the radiation generated during the final plunge and ringdown. We demonstrate convergence of the waveforms and good conservation of mass-energy, with just over 3% of the system's mass converted to gravitational radiation.