For event detection, statistical machine learning (ML) methods consistently showed superior performance. While ML and rule based methods seemed to detect temporal expressions equally well, the best systems overwhelmingly adopted a rule based approach for value normalization. For temporal relation classification, the systems using hybrid approaches that combined ML and heuristics based methods produced the best results.

No abstract

Temporal information in clinical narratives plays an important role in patients’ diagnosis, treatment and prognosis. In order to represent narrative information accurately, medical natural language processing (MLP) systems need to correctly identify and interpret temporal information. To promote research in this area, the Informatics for Integrating Biology and the Bedside (i2b2) project developed a temporally annotated corpus of clinical narratives. This corpus contains 310 de-identified discharge summaries, with annotations of clinical events, temporal expressions and temporal relations. This paper describes the process followed for the development of this corpus and discusses annotation guideline development, annotation methodology, and corpus quality.

This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .

We formulate the RI-TIMEX normalization problem as a pair of multi-label classification problems. Considering only RI-TIMEX extraction and normalization, the system achieves statistically significant improvement over the RI-TIMEX results of the best systems in the 2012 i2b2 challenge.

Cerebral autoregulation is defined as the mechanism by which constant cerebral blood flow is maintained despite changes of arterial blood pressure, and arterial blood pressure represents the principle aspect of cerebral autoregulation. The impairment of cerebral autoregulation is reported to be involved in several diseases. However, the concept, mechanisms, and pathological dysfunction of cerebral autoregulation are beyond full comprehension. Nitric oxide control and sympathetic control are main contributors to cerebral autoregulation. Although impaired cerebral autoregulation after nitric oxide inhibition or sympathetic ganglia blockade is reported, managing the inhibition or blockade can have negative consequences and needs further exploration. Additionally, impaired cerebral autoregulation following subarachnoid hemorrhage and traumatic brain injury has been proven by several descriptive studies, although without corresponding explanations. As the most important mechanisms of cerebral autoregulation, the changes of nitric oxide and sympathetic stimulation play significant roles in these insults. Therefore, the in-depth researches of nitric oxide and sympathetic nerve in cerebral autoregulation may help to develop new therapeutic targets.

We discuss automatic creation of medical reports from ASR-generated patient-doctor conversational transcripts using an end-to-end neural summarization approach.We explore both recurrent neural network (RNN) and Transformer-based sequence-to-sequence architectures for summarizing medical conversations. We have incorporated enhancements to these architectures, such as the pointer-generator network that facilitates copying parts of the conversations to the reports, and a hierarchical RNN encoder that makes RNN training three times faster with long inputs. A comparison of the relative improvements from the different model architectures over an oracle extractive baseline is provided on a dataset of 800k orthopedic encounters. Consistent with observations in literature for machine translation and related tasks, we find the Transformer models outperform RNN in accuracy, while taking less than half the time to train. Significantly large wins over a strong oracle baseline indicate that sequenceto-sequence modeling is a promising approach for automatic generation of medical reports, in the presence of data at scale.

Objectives Loneliness is considered to be a crucial factor in mental health of elderly people. However, the effects of loneliness on behavioral and psychological symptoms of dementia (BPSD) have not been fully examined. The aim of this study was to investigate whether loneliness in patients with dementia is related to BPSD. Methods A total of 152 patients with dementia were assessed using the Neuropsychiatric Inventory (NPI‐12) and the revised University of California at Los Angeles (UCLA) loneliness scale. Spearman correlation analysis and Mann–Whitney U‐tests were used to examine factors associated with the revised UCLA loneliness scale. Logistic regression analysis with a forced entry method was performed to identify risk factors for BPSD. Results The revised UCLA loneliness scale score was not significantly associated with age, years of education, mini‐mental state examination (MMSE) score, gender, living status, visual impairment, hearing impairment, and marital status. However, this score was a significant predictor of NPI delusion and hallucination subscale scores and Geriatric Depression Scale‐15 score. The MMSE score was a significant predictor of NPI anxiety and apathy subscale scores. Conclusions Loneliness is a risk factor for BPSD, especially for depressive symptoms and psychosis. Paying attention to loneliness in patients with dementia will help medical staff to intervene in psychiatric symptoms of these patients at an early stage.