Predictive cardio-omics: translating single-cell multiomics into tools for personalized medicine
Related Articles
Algorithmic personalization: a study of knowledge gaps and digital media literacy
Understanding personalized content and its societal implications is critical in the digital media era. This article introduces a novel information-analytical system designed to evaluate the level of knowledge among different social classes regarding personalized content in the digital media ecosystem. Utilizing data from 1213 Czech respondents, we employ fuzzy logic and multidimensional membership functions for an in-depth evaluation of the populace’s awareness. It categorizes population knowledge on personalization processes, their preferences, and trust levels and advocates control mechanisms over online content. The research reveals significant insights into demographic disparities in digital media literacy, emphasizing the urgent need for targeted educational programs. This paper presents a pioneering methodological framework and lays the groundwork for future investigations into personalized media services’ ethical considerations and socio-political dynamics. Our study contributes to the broader discourse on media literacy, algorithmic understanding, and protecting informational self-determination in the digital age.
Early cardio-oncology intervention in thoracic radiotherapy: prospective single-arm pilot study
While there is increasing recognition of the morbidity of cardiovascular disease in cancer survivors, including accelerated atherosclerosis following thoracic radiotherapy, patients are frequently under-optimized for cardiovascular risk.
A machine learning approach to leveraging electronic health records for enhanced omics analysis
Omics studies produce a large number of measurements, enabling the development, validation and interpretation of systems-level biological models. Large cohorts are required to power these complex models; yet, the cohort size remains limited due to clinical and budgetary constraints. We introduce clinical and omics multimodal analysis enhanced with transfer learning (COMET), a machine learning framework that incorporates large, observational electronic health record databases and transfer learning to improve the analysis of small datasets from omics studies. By pretraining on electronic health record data and adaptively blending both early and late fusion strategies, COMET overcomes the limitations of existing multimodal machine learning methods. Using two independent datasets, we showed that COMET improved the predictive modelling performance and biological discovery compared with the analysis of omics data with traditional methods. By incorporating electronic health record data into omics analyses, COMET enables more precise patient classifications, beyond the simplistic binary reduction to cases and controls. This framework can be broadly applied to the analysis of multimodal omics studies and reveals more powerful biological insights from limited cohort sizes.
Engineering bone/cartilage organoids: strategy, progress, and application
The concept and development of bone/cartilage organoids are rapidly gaining momentum, providing opportunities for both fundamental and translational research in bone biology. Bone/cartilage organoids, essentially miniature bone/cartilage tissues grown in vitro, enable the study of complex cellular interactions, biological processes, and disease pathology in a representative and controlled environment. This review provides a comprehensive and up-to-date overview of the field, focusing on the strategies for bone/cartilage organoid construction strategies, progresses in the research, and potential applications. We delve into the significance of selecting appropriate cells, matrix gels, cytokines/inducers, and construction techniques. Moreover, we explore the role of bone/cartilage organoids in advancing our understanding of bone/cartilage reconstruction, disease modeling, drug screening, disease prevention, and treatment strategies. While acknowledging the potential of these organoids, we discuss the inherent challenges and limitations in the field and propose potential solutions, including the use of bioprinting for organoid induction, AI for improved screening processes, and the exploration of assembloids for more complex, multicellular bone/cartilage organoids models. We believe that with continuous refinement and standardization, bone/cartilage organoids can profoundly impact patient-specific therapeutic interventions and lead the way in regenerative medicine.
Predictive learning as the basis of the testing effect
A prominent learning phenomenon is the testing effect, meaning that testing enhances retention more than studying. Emergent frameworks propose fundamental (Hebbian and predictive) learning principles as its basis. Predictive learning posits that learning occurs based on the contrast (error) between a prediction and the feedback on that prediction (prediction error). Here, we propose that in testing (but not studying) scenarios, participants predict potential answers, and its contrast with the subsequent feedback yields a prediction error, which facilitates testing-based learning. To investigate this, we developed an associative memory network incorporating Hebbian and/or predictive learning, together with an experimental design where human participants studied or tested English-Swahili word pairs followed by recognition. Three behavioral experiments (N = 80, 81, 62) showed robust testing effects when feedback was provided. Model fitting (of 10 different models) suggested that only models incorporating predictive learning can account for the breadth of data associated with the testing effect. Our data and model suggest that predictive learning underlies the testing effect.
Responses