Clinical performance of AI-integrated risk assessment pooling reveals cost savings even at high prevalence of COVID-19.

Individual testing of samples is time- and cost-intensive, particularly during an ongoing pandemic. Better practical alternatives to individual testing can significantly decrease the burden of disease on the healthcare system. Herein, we presented the clinical validation of Segtnan™ on 3929 patients. Segtnan™ is available as a mobile application entailing an AI-integrated personalized risk assessment approach with a novel data-driven equation for pooling of biological samples. The AI was selected from a comparison between 15 machine learning classifiers (highest accuracy = 80.14%) and a feed-forward neural network with an accuracy of 81.38% in predicting the rRT-PCR test results based on a designed survey with minimal clinical questions. Furthermore, we derived a novel pool-size equation from the pooling data of 54 published original studies. The results demonstrated testing capacity increase of 750%, 60%, and 5% at prevalence rates of 0.05%, 22%, and 50%, respectively. Compared to Dorfman's method, our novel equation saved more tests significantly at high prevalence, i.e., 28% (p = 0.006), 40% (p = 0.00001), and 66% (p = 0.02). Lastly, we illustrated the feasibility of the Segtnan™ usage in clinically complex settings like emergency and psychiatric departments.

Plasma levels of multiple cardiovascular- and inflammation-related proteins analysed for associations with disease activity and anti-cyclic citrullinated peptide status in active early rheumatoid arthritis.

OBJECTIVES: To compare plasma levels of 92 cardiovascular- and inflammation-related proteins (CIRPs) and to analyse for associations with anti-cyclic citrullinated peptide (anti-CCP) status and disease activity in early and treatment-naive rheumatoid arthritis (RA). METHODS: Olink CVD-III-panel was used to measure 92 CIRP plasma levels in 180 early, treatment-naive, and highly inflamed RA patients from the OPERA trial. CIRP plasma levels as well as correlation between CIRP plasma levels and RA disease activity were compared between anti-CCP groups. CIRP level-based hierarchical cluster analysis was performed in each anti-CCP group separately. RESULTS: The study included 117 anti-CCP-positive and 63 anti-CCP-negative RA patients. Among the 92 CIRPs measured, the levels of chitotriosidase-1 (CHIT1) and tyrosine-protein-phosphatase non-receptor-type substrate-1 (SHPS-1) were increased and those of metalloproteinase inhibitor-4 (TIMP-4) decreased in the anti-CCP-negative group compared to anti-CCP-positive group. The strongest associations with RA disease activity were found for interleukin-2 receptor-subunit-alpha (IL2-RA) and E-selectin levels in the anti-CCP-negative group and for C-C-motif chemokine-16 levels (CCL16) in the anti-CCP-positive group. None of the differences passed the Hochberg sequential multiplicity test, however, the CIPRs were interacting and thus the prerequisites of the Hochberg procedure were not fulfilled. CIRP level-based cluster analysis identified two patient clusters in both anti-CCP groups. Demographic and clinical characteristics were similar in the two clusters for each anti-CCP group. CONCLUSIONS: In active and early RA, the findings regarding CHIT1, SHPS-1 TIMP-4, IL2-RA, E-selectin, and CCL16 differed between the two anti-CCP groups. In addition, we identified two patient clusters that were independent of the anti-CCP status.

MS2AI: automated repurposing of public peptide LC-MS data for machine learning applications.

MOTIVATION: Liquid-chromatography mass-spectrometry (LC-MS) is the established standard for analyzing the proteome in biological samples by identification and quantification of thousands of proteins. Machine learning (ML) promises to considerably improve the analysis of the resulting data, however, there is yet to be any tool that mediates the path from raw data to modern ML applications. More specifically, ML applications are currently hampered by three major limitations: (i) absence of balanced training data with large sample size; (ii) unclear definition of sufficiently information-rich data representations for e.g. peptide identification; (iii) lack of benchmarking of ML methods on specific LC-MS problems. RESULTS: We created the MS2AI pipeline that automates the process of gathering vast quantities of MS data for large-scale ML applications. The software retrieves raw data from either in-house sources or from the proteomics identifications database, PRIDE. Subsequently, the raw data are stored in a standardized format amenable for ML, encompassing MS1/MS2 spectra and peptide identifications. This tool bridges the gap between MS and AI, and to this effect we also present an ML application in the form of a convolutional neural network for the identification of oxidized peptides. AVAILABILITY AND IMPLEMENTATION: An open-source implementation of the software can be found at https://gitlab.com/roettgerlab/ms2ai. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.