30988 research outputs found
Sort by
Scrum mastereiden kokemuksia ketteristä menetelmistä sosiaali- ja terveydenhuollon digitaalisten palveluiden kehittämisessä
No full textArtificial intelligence in drug design: why a ‘one-size-fits-all’ approach remains out of reach
No full textIntroduction
Advances in artificial intelligence (AI) have transformed the drug design and discovery process, introducing novel methods that can reduce costs, increase success rates, and shorten development timelines. However, due to the complexity and multifactorial nature of this process, no single AI approach is likely to be universally effective.
Areas covered
This review summarizes progress made over the past five years toward diverse drug development goals using AI tools. It also discusses the main challenges that inhibit the development and adoption of a broad AI solution in this field.
Expert opinion
Despite major advancements, AI fails to reach its full potential due to issues related to data quality, model complexity, computational costs, and organizational barriers. At present, the effectiveness of any AI approach heavily depends on its application. Ultimately, while the world strives for a general-purpose AI, no method in drug discovery can yet be considered universally applicable, and rather than relying on a one-size-fits-all solution, individual trade-offs and research objectives need to be carefully aligned to harness AI’s potential in drug discovery
Determining radiologists' reporting times based on imaging report databases and digital image archive logs
No full textHealthcare services use in transition: The perspective of patients with epilepsy or multiple sclerosis
No full textImpact of Scaling Peak Oxygen Uptake for Body Size and Composition to Assess Cardiometabolic Risk in Children
No full textPurpose
This study measured associations of peak oxygen uptake (V̇O2peak) with cardiometabolic risk factors and quantified cardiometabolic risk misclassification when scaling V̇O2peak for body size and composition, comparing population-specific and universal V̇O2peak cut-points.
Methods
In a population sample of 332 Finnish children (164 girls, 9-11 years), V̇O2peak was determined using a maximal cycle ergometer test and scaled for body mass (BM) and lean mass (LM) using ratio and allometric methods. A continuous cardiometabolic risk score was calculated from age- and sex-specific z-scores of traditional risk factors, with ‘increased risk’ defined as ≥1 standard deviation above the mean. Receiver operating characteristics curves assessed the ability of V̇O2peak to classify children at increased risk. Associations between V̇O2peak and cardiometabolic risk factors were measured using linear regression analyses. The type and extent of misclassification were calculated by comparing rank differences between allometric and ratio-scaled V̇O2peak, using directly measured cardiometabolic risk vs. V̇O2peak cut-points. Population-specific cut-points based on previously reported cut-points in this sample were compared with universal cut-points from existing meta-analyses.
Results
Scaling using LM, or allometric methods, attenuated associations between V̇O2peak and cardiometabolic risk factors. V̇O2peak scaled by LM-1, BM-0.49, or LM-1.04 demonstrated poor ability to classify increased cardiometabolic risk, whilst V̇O2peak scaled by BM-1 had the highest classification ability in girls and boys (AUC = 0.875 and 0.690 respectively, p < 0.01). Universal cut-points produced fewer false positive classifications than population-specific cut-points.
Conclusions
V̇O2peak appropriately scaled for body size and composition may have limited ability to distinguish cardiometabolic risk in children, with diminished associations with cardiometabolic risk factors. Screening for cardiometabolic risk in children using V̇O2peak ratio-scaled by BM may reflect body size, rather than fitness
A Portable Measurement System Based on Nanomembranes for Pollutant Detection in Water
No full textThis work presents the design, the development and the experimental validation of a portable, low-cost sensing system for the detection of waterborne pollutants. The proposed system is based on Electrochemical Impedance Spectroscopy and PPF+Ni nanomembrane sensors. Designed in response to the increasing demand for in situ water quality monitoring, the system integrates a simplified, scalable EIS acquisition architecture compatible with microcontroller-based platforms. The sensing configuration utilises the voltage divider principle, ensuring simplicity in signal conditioning by allowing compatibility with different electrode types through passive impedance matching. In addition, new merit figures have been proposed and implemented to analyse the measures. The proposed platform was experimentally characterised for its measurement stability, accuracy and environmental robustness. Sensitivity tests using benzoquinone as a target analyte demonstrated the capability of detecting concentrations as low as 0.1 mM with a monotonic response over increasing concentrations. A comparative study with a commercial electrochemical system (PalmSens4) under identical conditions highlighted the higher resolution and practical advantages of the proposed method despite operating with a lower impedance range. Additionally, the system exhibited reliable discrimination across tested concentrations and greater adaptability for integration into field-deployable environmental monitoring platforms. Future developments will focus on optimising selectivity through new sensor materials and analytical modelling of uncertainty propagation in the analysis based on defined figures of merit
