Extracorporeal membrane oxygenation (ECMO) procedures may result in emergencies requiring the intervention of a perfusionist. However, their arrival results in waiting times that put patients at risk. Hence, nursing staff should be remotely supported using augmented reality (AR) in troubleshooting to improve patient safety. In this study, we aimed to investigate the usability of AR glasses HMT-1 and HoloLens 2 for remote support during ECMO and to determine the user acceptance of AR in intensive care. Ten nurses tested both glasses in a user test in randomized order under perfusionist guidance to rectify the three ECMO emergencies: a signal alert, a pump failure and reduced blood flow. An investigator rated their skills using a 3-step scheme, and success rates were calculated from the ratings and compared using the Wilcoxon test (α =.05). AR acceptance was assessed using the System Usability Scale (SUS) and User Experience Questionnaire (UEQ). We recorded 12 and 21 use errors with HMT-1 and HoloLens 2, respectively. However, significantly fewer use errors occurred with the HMT-1 than with HoloLens 2 (Z = -1786, p = .046, n = 80) when troubleshooting the pump failure. Most participants rated HoloLens 2 as more suitable. AR acceptance was rated as good with a SUS score of 72 (± 11). UEQ ratings for attractiveness, dependability, stimulation, novelty, and efficiency were excellent or good, while perspicuity was rated below average. The results indicate that both AR glasses are suitable for remote support; however, improvements to increase efficiency and patient safety in intensive care are necessary.

Accurate survival prediction in breast cancer remains a key challenge in oncology, requiring models that can integrate diverse clinical, molecular, and imaging data sources to guide breast cancer management. While recent deep learning models have explored multimodal integration for cancer survival prediction, their generalizability to unseen data remains limited. In this study, we developed and optimized unimodal and multimodal models for breast cancer survival prediction, systematically assessing our optimized early and late integration strategies and their impact on out-of-sample generalization performance. We integrated clinical variables, somatic mutations, RNA expression, copy number variation, miRNA expression, and histopathology images from The Cancer Genome Atlas breast cancer dataset. Across all modality combinations, late fusion models consistently outperformed early fusion approaches and late and intermediate benchmark methods, with the combination of omics and clinical data yielding the highest test-set concordance indices. Explainability analyses showed that our models captured biologically relevant features associated with patient survival. These findings highlight the value of late-fusion multimodal deep learning frameworks for robust and explainable survival prediction in breast cancer.

Influenza A virus (IAV) is a highly adaptable pathogen that poses a significant threat to human health. Genomic surveillance of IAVs is complex due to their broad host range, zoonotic potential, and rapid evolution. Strategies based on codon preference analysis have been successfully employed for the discrimination of IAVs with different host specificity in the past. Hence, monitoring changes in codon usage offers a promising strategy for tracking IAVs' host range and identifying significant epidemiological events. In this study, we developed a computational workflow for the stratification of IAVs based on codon usage profiles by analysing recent IAV-associated epidemiological emergencies: 1) the 2009 H1N1 pandemic in North America, 2) the H7N9 epidemic in China (2013-2017), and 3) the long-term circulation of H5N1 in domestic birds and its subsequent spillover to dairy cows. We explore the application of codon usage metrics for capturing patterns of viral diversification and expand previous related findings in the field. Our results uncovered important differences in genomic features, which are not always reflected in the clade-based nomenclature. Interestingly, a reduced set of amino acids and associated codons was sufficient to summarize salient patterns of IAV genomes across the 3 paradigmatic cases herein considered, suggesting shared evolutionary signatures across IAV serotypes. Codon usage-based stratification effectively highlighted key epidemiological events and enabled detailed comparisons of genomic features across IAV serotypes. The approach developed in this work provides a scalable framework for IAV genomic surveillance, offering insights into viral evolution and shared patterns of codon usage preferences. Its general applicability makes it suitable for extending to other Influenza A serotypes, particularly those for which available genomic data are limited or a reference nomenclature is not established.

Monoclonal antibodies targeting HER2, a receptor overexpressed in certain cancer cells, have greatly improved the treatment of HER2-positive cancers. In addition, anti-HER2 antibodies play a critical role in diagnostic applications, enabling accurate detection of HER2 expression levels. Advancing antibody-based therapies and diagnostic tools require a thorough understanding of binding interactions, but it remains challenging due to complex antibody protein structure and its flexibility, particularly within their complementarity-determining regions. In this study we utilized LightDock, a molecular docking tool simulating protein-protein interactions which can incorporate flexibility that allows the in silico analysis of flexible proteins like antibody. Using LightDock we investigated interaction sites between the recently developed by our group anti-HER2 antibodies and their specific antigen HER2 protein. Despite the high variability in the obtained results, a statistics-based approach identified two recurring HER2 regions as potential binding sites and functionally relevant areas in receptor biology. This variability in predicted docking interfaces reflects the inherent complexity of antibody-antigen interactions. This structure based docking approach provides a cost-effective method to analyze antibody-protein interactions and offers preliminary insight into possible epitopes targeted by the novel anti-HER2 antibodies. However, our data indicates that at this time point further validation using experimental techniques will be beneficial to refine and increase the accuracy of the results obtained in silico. This report highlights the value of the computational docking in antibody-protein interaction studies, demonstrating significant potential with present and upcoming advancements in computer-based approaches.

Many clinically significant health conditions in older adults are underreported or only recorded in unstructured health records. These records, however, contain valuable information for patient care and prognosis. This study utilized 10.6 million free-text entries from the electronic health records of 102,525 patients aged 50–80 across various care settings in Finland from 2010 to 2022. A deep learning-based natural language processing model was employed to perform named entity recognition (NER) to identify falls, incontinence, loneliness, and mobility limitations from the free-text entries. The performance of the NER models was evaluated by precision, recall and F1 scores. Diagnostic codes for incontinence and falls were collected for comparisons. Cox regression models were used to assess the predictive value of the identified conditions for all-cause mortality. The NER models demonstrated excellent performance with recall, precision and F1 scores greater than 0.80 across the health conditions. Compared to diagnostic codes, NER identified greater numbers of falls (31987 vs 4090) and incontinence (7059 vs 3873) onsets and yielded greater hazard ratios for all-cause mortality: 1.31 vs 1.04 for falls and 1.99 vs 0.65 for incontinence. Deep learning-based NER models present new opportunities to identify vulnerable patients in free text health records.

Federated learning (FL)-a distributed machine learning that offers collaborative training of global models across multiple clients. FL has been considered for the design and development of many FL systems in various domains. Hence, we present a comprehensive survey and analysis of existing FL systems, drawing insights from more than 250 articles published in 2019-2024. Our review elucidates the functioning of FL systems, particularly in comparison with alternative distributed learning approaches. Considering the healthcare domain as an example, we define the building blocks of a typical FL healthcare system, including system architecture, federation scale, data partitioning, open-source frameworks, ML models, and aggregation algorithms. Furthermore, we identify and discuss key challenges associated with the design and implementation of FL systems within the healthcare sector while outlining the directions of future research. In general, through systematic categorization and analysis of existing FL systems, we offer insights to design efficient, accurate, and privacy-preserving healthcare applications using cutting-edge FL techniques.

Recent advancements in biologics production using CHO cells have been partly driven by improved understanding of how variations in the cell culture environment influence cellular metabolism, productivity, and the attributes of the final product. In-silico models serve a valuable role in mapping the effects of various process parameters and media changes on cellular response. Advances in technologies such as data-driven analysis, self-learning systems, and digital twins are reinforcing progress toward smart manufacturing, enabling the real-time control of production processes. Furthermore, kinetic, and constraint-based mechanistic modeling, combined with omics approaches, are becoming increasingly incorporated into the bioprocess development and manufacturing innovation ecosystem. In this review, we cover CHO central metabolism as a foundation for mechanistic modeling and extend the discussion to include various mechanistic modeling approaches, highlighting the incorporation of glycosylation and secretory pathways. Multi-omics approaches provide a deeper understanding of intracellular processes and the dynamic interactions between product quality and pathways. In parallel, to achieve the Industry 4.0 vision of digitalization and machine learning techniques are finding wider adoption in biopharmaceutical development. We discuss the potential applications of these techniques for predictions, inference, optimization, and control. The role of big data analytics and artificial intelligence methods in reinforcing progress towards smart manufacturing and enabling real-time control of production processes is discussed. Finally, we summarize the application of machine learning and hybrid models to CHO bioprocesses, aiming to develop and manufacture drugs more efficiently and at a lower cost for patients.

This study investigates the potential of 1H NMR spectroscopy for predicting key chemical and sensory attributes in olive oil. By integrating NMR data with traditional chemical analyses and sensory evaluation, we developed multivariate models to evaluate the predictive power of NMR spectra coupled with machine learning algorithms for 50 distinct olive oil quality parameters, including physicochemical properties, fatty acid composition, total polyphenols, tocopherols, and sensory attributes. We applied Random Forest regression models to correlate NMR spectra with these parameters, achieving promising results, particularly for predicting major fatty acids, total polyphenols, and tocopherols. We have also found the collected data to be highly effective in classifying olive cultivars and the years of harvest. Our findings highlight the potential of NMR spectroscopy as a rapid, non-destructive, and environmentally friendly tool for olive oil quality assessment. This study introduces a novel approach that combines machine learning with 1H NMR spectral analysis to correlate analytical data for predicting essential qualitative parameters in olive oil. By leveraging 1H NMR spectra as predictive proxies, this methodology offers a promising alternative to traditional assessment techniques, enabling rapid determination of several parameters related to chemical composition, sensory attributes, and geographical origin of olive oil samples.