Managing knowledge in neuroscience

Natural Language Processing Applications in the Clinical Neurosciences: A Machine Learning Augmented Systematic Review

Natural language processing (NLP), a domain of artificial intelligence (AI) that models human language, has been used in medicine to automate diagnostics, detect adverse events, support decision making and predict clinical outcomes. However, applications to the clinical neurosciences appear to be limited. NLP has matured with the implementation of deep transformer models (e.g., XLNet, BERT, T5, and RoBERTa) and transfer learning. The objectives of this study were to (1) systematically review NLP applications in the clinical neurosciences, and (2) explore NLP analysis to facilitate literature synthesis, providing clear examples to demonstrate the potential capabilities of these technologies for a clinical audience. Our NLP analysis consisted of keyword identification, text summarization and document classification. A total of 48 articles met inclusion criteria. NLP has been applied in the clinical neurosciences to facilitate literature synthesis, data extraction, patient identification, automated clinical reporting and outcome prediction. The number of publications applying NLP has increased rapidly over the past five years. Document classifiers trained to differentiate included and excluded articles demonstrated moderate performance (XLNet AUC = 0.66, BERT AUC = 0.59, RoBERTa AUC = 0.62). The T5 transformer model generated acceptable abstract summaries. The application of NLP has the potential to enhance research and practice in the clinical neurosciences.

Bridging the Brain and Data Sciences

Brain scientists are now capable of collecting more data in a single experiment than researchers a generation ago might have collected over an entire career. Indeed, the brain itself seems to thirst for more and more data. Such digital information not only comprises individual studies but is also increasingly shared and made openly available for secondary, confirmatory, and/or combined analyses. Numerous web resources now exist containing data across spatiotemporal scales. Data processing workflow technologies running via cloud-enabled computing infrastructures allow for large-scale processing. Such a move toward greater openness is fundamentally changing how brain science results are communicated and linked to available raw data and processed results. Ethical, professional, and motivational issues challenge the whole-scale commitment to data-driven neuroscience. Nevertheless, fueled by government investments into primary brain data collection coupled with increased sharing and community pressure challenging the dominant publishing model, large-scale brain and data science is here to stay.

Workflow and atlas system for brain-wide mapping of axonal connectivity in rat

Detailed knowledge about the anatomical organization of axonal connections is important for understanding normal functions of brain systems and disease-related dysfunctions. Such connectivity data are typically generated in neuroanatomical tract-tracing experiments in which specific axonal connections are visualized in histological sections. Since journal publications typically only accommodate restricted data descriptions and example images, literature search is a cumbersome way to retrieve overviews of brain connectivity. To explore more efficient ways of mapping, analyzing, and sharing detailed axonal connectivity data from the rodent brain, we have implemented a workflow for data production and developed an atlas system tailored for online presentation of axonal tracing data. The system is available online through the Rodent Brain WorkBench (www.rbwb.org; Whole Brain Connectivity Atlas) and holds experimental metadata and high-resolution images of histological sections from experiments in which axonal tracers were injected in the primary somatosensory cortex. We here present the workflow and the data system, and exemplify how the online image repository can be used to map different aspects of the brain-wide connectivity of the rat primary somatosensory cortex, including not only presence of connections but also morphology, densities, and spatial organization. The accuracy of the approach is validated by comparing results generated with our system with findings reported in previous publications. The present study is a contribution to a systematic mapping of rodent brain connections and represents a starting point for further large-scale mapping efforts.