Automated Assessment of Patients' Self-Narratives for Posttraumatic Stress Disorder Screening Using Natural Language Processing and Text Mining.

Patients' narratives about traumatic experiences and symptoms are useful in clinical screening and diagnostic procedures. In this study, we presented an automated assessment system to screen patients for posttraumatic stress disorder via a natural language processing and text-mining approach. Four machine-learning algorithms-including decision tree, naive Bayes, support vector machine, and an alternative classification approach called the product score model-were used in combination with n-gram representation models to identify patterns between verbal features in self-narratives and psychiatric diagnoses.

Towards an in vitro model mimicking the foreign body response: tailoring the surface properties of biomaterials to modulate extracellular matrix.

Despite various studies to minimize host reaction following a biomaterial implantation, an appealing strategy in regenerative medicine is to actively use such an immune response to trigger and control tissue regeneration. We have developed an in vitro model to modulate the host response by tuning biomaterials' surface properties through surface modifications techniques as a new strategy for tissue regeneration applications. Results showed tunable surface topography, roughness, wettability, and chemistry by varying treatment type and exposure, allowing for the first time to correlate the effect of these surface properties on cell attachment, morphology, strength and proliferation, as well as proinflammatory (IL-1β, IL-6) and antiinflammatory cytokines (TGF-β1, IL-10) secreted in medium, and protein expression of collagen and elastin.