In Electronic Health Records (EHRs), much of valuable information regarding patients’ conditions is embedded in free text format. Natural language processing (NLP) techniques have been developed to extract clinical information from free text. One challenge faced in clinical NLP is that the meaning of clinical entities is heavily affected by modifiers such as negation. A negation detection algorithm, NegEx, applies a simplistic approach that has been shown to be powerful in clinical NLP. However, due to the failure to consider the contextual relationship between words within a sentence, NegEx fails to correctly capture the negation status of concepts in complex sentences. Incorrect negation assignment could cause inaccurate diagnosis of patients’ condition or contaminated study cohorts. We developed a negation algorithm called DEEPEN to decrease NegEx’s false positives by taking into account the dependency relationship between negation words and concepts within a sentence using Stanford dependency parser. The system was developed and tested using EHR data from Indiana University (IU) and it was further evaluated on Mayo Clinic dataset to assess its generalizability. The evaluation results demonstrate DEEPEN, which incorporates dependency parsing into NegEx, can reduce the number of incorrect negation assignment for patients with positive findings, and therefore improve the identification of patients with the target clinical findings in EHRs.

NLP is an effective tool to automatically identify patients with pancreatic cysts based on electronic medical records (EMR). This highly accurate system can help capture patients 'at-risk' of pancreatic cancer in a registry.

Active countercircling on a rotating platform for 15 min causes individuals to involuntarily circle in the same direction when they step in place on firm ground. This is referred to as podokinetic after-rotation (PKAR). It is unclear how interjecting brief periods of visual or haptic inputs for a stable orientation reference affects PKAR. The authors studied this issue in 16 healthy individuals who participated in three sessions each. Following active countercircling, participants attempted to step in place for 30 min on firm ground. In two of three sessions, participants received full visual input or made fingertip contact with a stationary object for 30 s during 30 min of ongoing PKAR. All participants slowed or stopped rotating during the presence of visual or haptic inputs and resumed PKAR after removal of these inputs. Exponential functions fitted to angular trunk velocity versus time plots revealed no significant differences across conditions (p > .05). The preservation of PKAR after brief exposure to a visual or haptic reference is consistent with a slowly decaying velocity storage that is not reset or dumped after exposure to conflicting visual or haptic cues.