Artificial-intelligence-based risk prediction and mechanism discovery for atrial fibrillation using heart beat-to-beat intervals.

BACKGROUND: Early diagnosis of atrial fibrillation (AF) is important for preventing stroke and other complications. Predicting AF risk in advance can improve early diagnostic efficiency. Deep learning has been used for disease risk prediction; however, it lacks adherence to evidence-based medicine standards. Identifying the underlying mechanisms behind disease risk prediction is important and required. METHODS: We developed an explainable deep learning model called HBBI-AI to predict AF risk using only heart beat-to-beat intervals (HBBIs) during sinus rhythm. We proposed a possible AF mechanism based on the model's explainability and verified this conjecture using confirmed AF risk factors while also examining new AF risk factors. Finally, we investigated the changes in clinicians' ability to predict AF risk using only HBBIs before and after learning the model's explainability. FINDINGS: HBBI-AI consistently performed well across large in-house and external public datasets. HBBIs with large changes or extreme stability were critical predictors for increased AF risk, and the underlying cause was autonomic imbalance. We verified various AF risk factors and discovered that autonomic imbalance was associated with all these factors. Finally, cardiologists effectively understood and learned from these findings to improve their abilities in AF risk prediction. CONCLUSIONS: HBBI-AI effectively predicted AF risk using only HBBI information through evaluating autonomic imbalance. Autonomic imbalance may play an important role in many risk factors of AF rather than in a limited number of risk factors. FUNDING: This study was supported in part by the National Key R&D Program and the National Natural Science Foundation of China.

Biomedical research models in the science of fracture healing - Pitfalls & promises.

Development of intervention strategies to stimulate fracture healing has long been a focus of musculoskeletal research. Considerable investment in empirical research has led to the discovery of several genes and signaling pathways that are involved in skeletal development and regeneration. However, there are currently very few biologic interventions that can efficiently be used to enhance fracture healing in clinical practice. This translational barrier is due in part to experimental barriers to mechanism discovery. Animal models, biomechanical models, finite element models, and mathematical models are a few examples of models that aid in the discovery of mechanisms. Understanding the advantages, limitations, and specialized uses of each model type is critical to our ability to interpret mechanistic insights from such research and to help bridge the translation gap between pre-clinical research and clinical practice. In this review, we look at specific modeling methods used in the study of the fracture healing mechanism. We also discuss the strength and limitations to translation of each method, hopefully leading to a better understanding of how we can use models to advance the study of fracture healing.

Xenopus: Driving the Discovery of Novel Genes in Patient Disease and Their Underlying Pathological Mechanisms Relevant for Organogenesis.

Frog model organisms have been appreciated for their utility in exploring physiological phenomena for nearly a century. Now, a vibrant community of biologists that utilize this model organism has poised Xenopus to serve as a high throughput vertebrate organism to model patient-driven genetic diseases. This has facilitated the investigation of effects of patient mutations on specific organs and signaling pathways. This approach promises a rapid investigation into novel mechanisms that disrupt normal organ morphology and function. Considering that many disease states are still interrogated in vitro to determine relevant biological processes for further study, the prospect of interrogating genetic disease in Xenopus in vivo is an attractive alternative. This model may more closely capture important aspects of the pathology under investigation such as cellular micro environments and local forces relevant to a specific organ's development and homeostasis. This review aims to highlight recent methodological advances that allow investigation of genetic disease in organ-specific contexts in Xenopus as well as provide examples of how these methods have led to the identification of novel mechanisms and pathways important for understanding human disease.

The role of orientation experiments in discovering mechanisms.

Many types of experiments have been recognized in the literature. One important type we discuss in this article is the orientation experiment. While orientation experiments are like other types of experiments in that they are tests for causal relevance, they also have other qualities. One important (but not the only) goal of these experiments is to offer a rough, qualitative characterization of the mechanism responsible for a capacity of interest, effectively constraining future research. This makes them particularly useful during the early stages of investigation, when an explanandum-phenomenon has just been identified and several (often competing) hypotheses as to the qualitative character of the mechanism responsible for it are proposed. We illustrate our claims, and explicate a number of additional aims that orientation experiments can sometimes serve, by considering three case studies from different era's, namely the discovery of the mechanisms responsible for i) the capacity of eels to produce numbing sensations (17th and 18th century), ii) puerperal fever in Semmelweis' Vienna Maternity Hospital (19th century), and iii) the capacity of pigeons to home (20th century).