Search

Objective: To challenge clinicians and informaticians to learn about potential sources of bias in medical machine learning models through investigation of data and predictions from an open-source severity of illness score., Methods: Over a two-day period (total elapsed time approximately 28 hours), we conducted a datathon that challenged interdisciplinary teams to investigate potential sources of bias in the Global Open Source Severity of Illness Score. Teams were invited to develop hypotheses, to use tools of their choosing to identify potential sources of bias, and to provide a final report., Results: Five teams participated, three of which included both informaticians and clinicians. Most (4/5) used Python for analyses, the remaining team used R. Common analysis themes included relationship of the GOSSIS-1 prediction score with demographics and care related variables; relationships between demographics and outcomes; calibration and factors related to the context of care; and the impact of missingness. Representativeness of the population, differences in calibration and model performance among groups, and differences in performance across hospital settings were identified as possible sources of bias., Discussion: Datathons are a promising approach for challenging developers and users to explore questions relating to unrecognized biases in medical machine learning algorithms.

The goal of this study was the development of a bioartificial nerve guide to induce axonal regeneration in the peripheral nervous system (PNS). In this in vitro study, the ability of a novel, 3-dimensional (3D), highly oriented, cross-linked porcine collagen scaffold to promote directed axonal growth has been studied. Collagen nerve guides with longitudinal guidance channels were manufactured using a series of chemical and mechanical treatments with a patented unidirectional freezing process, followed by freeze-drying (pore sizes 20-50 microm). Hemisected rat dorsal root ganglia (DRG) were positioned such that neural and non-neural elements could migrate into the collagen scaffold. After 21 days, S100-positive Schwann cells (SCs) migrated into the scaffold and aligned within the guidance channels in a columnar fashion, resembling "Bands of Büngner." Neurofilament-positive axons (mean length +/- SD 756 microm +/- 318 microm, maximum 1496 microm) from DRG neurons entered the scaffold where the growth within the guidance channels was closely associated with the oriented SCs. This study confirmed the importance of SCs in the regeneration process (neurotrophic theory). The alignment of SCs within the guidance channels supported directional axonal growth (contact guidance theory). The microstructural properties of the scaffold (open, porous, longitudinal pore channels) and the in vitro data after DRG loading (axonal regeneration along migrated and columnar-aligned SCs resembling "Band of Büngner") suggest that this novel oriented 3D collagen scaffold serves as a basis for future experimental regeneration studies in the PNS.