Author Correction: A machine learning approach to leveraging electronic health records for enhanced omics analysis
Related Articles
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.
Comprehensive multi-omics analysis of breast cancer reveals distinct long-term prognostic subtypes
Breast cancer (BC) is a leading cause of cancer-related death worldwide. The diverse nature and heterogeneous biology of BC pose challenges for survival prediction, as patients with similar diagnoses often respond differently to treatment. Clinically relevant BC intrinsic subtypes have been established through gene expression profiling and are implemented in the clinic. While these intrinsic subtypes show a significant association with clinical outcomes, their long-term survival prediction beyond 5 years often deviates from expected clinical outcomes. This study aimed to identify naturally occurring long-term prognostic subgroups of BC based on an integrated multi-omics analysis. This study incorporates a clinical cohort of 335 untreated BC patients from the Oslo2 study with long-term follow-up (>12 years). Multi-Omics Factor Analysis (MOFA+) was employed to integrate transcriptomic, proteomic, and metabolomic data obtained from the tumor tissues. Our analysis revealed three prominent multi-omics clusters of BC patients with significantly different long-term prognoses (p = 0.005). The multi-omics clusters were validated in two independent large cohorts, METABRIC and TCGA. Importantly, a lack of prognostic association to long-term follow-up above 12 years in the previously established intrinsic subtypes was shown for these cohorts. Through a systems-biology approach, we identified varying enrichment levels of cell-cycle and immune-related pathways among the prognostic clusters. Integrated multi-omics analysis of BC revealed three distinct clusters with unique clinical and biological characteristics. Notably, these multi-omics clusters displayed robust associations with long-term survival, outperforming the established intrinsic subtypes.
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.
Machine learning empowered coherent Raman imaging and analysis for biomedical applications
In situ and in vivo visualization and analysis of functional, endogenous biomolecules in living systems have generated a pivotal impact in our comprehension of biology and medicine. An increasingly adopted approach involves the utilization of molecular vibrational spectroscopy, which delivers notable advantages such as label-free imaging, high spectral density, high sensitivity, and molecule specificity. Nonetheless, analyzing and processing the intricate, multi-dimensional imaging data to extract interpretable and actionable information poses a fundamental obstacle. In contrast to conventional multivariate methods, machine learning has recently gained considerable attention for its capability of discerning essential features from massive datasets. Here, we present a comprehensive review of the latest advancements in the application of machine learning in the molecular spectroscopic imaging fields. We also discuss notable attributes of spectroscopic imaging modalities and explore their broader impact on other imaging techniques.
Understanding learning through uncertainty and bias
Learning allows humans and other animals to make predictions about the environment that facilitate adaptive behavior. Casting learning as predictive inference can shed light on normative cognitive mechanisms that improve predictions under uncertainty. Drawing on normative learning models, we illustrate how learning should be adjusted to different sources of uncertainty, including perceptual uncertainty, risk, and uncertainty due to environmental changes. Such models explain many hallmarks of human learning in terms of specific statistical considerations that come into play when updating predictions under uncertainty. However, humans also display systematic learning biases that deviate from normative models, as studied in computational psychiatry. Some biases can be explained as normative inference conditioned on inaccurate prior assumptions about the environment, while others reflect approximations to Bayesian inference aimed at reducing cognitive demands. These biases offer insights into cognitive mechanisms underlying learning and how they might go awry in psychiatric illness.
Responses