A predictive coding model of the N400.

The N400 event-related component has been widely used to investigate the neural mechanisms underlying real-time language comprehension. However, despite decades of research, there is still no unifying theory that can explain both its temporal dynamics and functional properties. In this work, we show that predictive coding - a biologically plausible algorithm for approximating Bayesian inference - offers a promising framework for characterizing the N400. Using an implemented predictive coding computational model, we demonstrate how the N400 can be formalized as the lexico-semantic prediction error produced as the brain infers meaning from the linguistic form of incoming words. We show that the magnitude of lexico-semantic prediction error mirrors the functional sensitivity of the N400 to various lexical variables, priming, contextual effects, as well as their higher-order interactions. We further show that the dynamics of the predictive coding algorithm provides a natural explanation for the temporal dynamics of the N400, and a biologically plausible link to neural activity. Together, these findings directly situate the N400 within the broader context of predictive coding research. More generally, they raise the possibility that the brain may use the same computational mechanism for inference across linguistic and non-linguistic domains.

Leveraging interpretable machine learning algorithms to predict postoperative patient outcomes on mobile devices.

Setting patient and family expectations for postoperative outcomes is an important aspect of care, a cornerstone of which is accurate, personalized, and explainable risk estimation. Modern machine learning offers a plethora of models that can effectively capture the complex, nonlinear contributions of preoperative risk factors to the surgical patient's overall risk. However, most of these models produce risk estimates that are not interpretable, which compromises trust in these systems, renders them unaccountable, and limits their widespread adoption. Recent developments in machine learning have been successful at creating risk calculators that address this gap, producing explainable risk estimates without compromising accuracy. In this work, we describe how the state of the art in postoperative risk estimation addresses the shortcomings of older methods, and how they have been applied in a clinical setting. We conclude with a discussion of the potential of machine learning models to be systematically integrated in health care more broadly and future prospects beyond passive risk prediction.