Temporal Relation Extraction in Clinical Texts

Unstructured data in electronic health records, represented by clinical texts, are a vast source of healthcare information because they describe a patient's journey, including clinical findings, procedures, and information about the continuity of care. The publication of several studies on temporal relation extraction from clinical texts during the last decade and the realization of multiple shared tasks highlight the importance of this research theme. Therefore, we propose a review of temporal relation extraction in clinical texts. We analyzed 105 articles and verified that relations between events and document creation time, a coarse temporality type, were addressed with traditional machine learning–based models with few recent initiatives to push the state-of-the-art with deep learning–based models. For temporal relations between entities (event and temporal expressions) in the document, factors such as dataset imbalance because of candidate pair generation and task complexity directly affect the system's performance. The state-of-the-art resides on attention-based models, with contextualized word representations being fine-tuned for temporal relation extraction. However, further experiments and advances in the research topic are required until real-time clinical domain applications are released. Furthermore, most of the publications mainly reside on the same dataset, hindering the need for new annotation projects that provide datasets for different medical specialties, clinical text types, and even languages.

“Until I Know It’s Safe for Me”: The Role of Timing in COVID-19 Vaccine Decision-Making and Vaccine Hesitancy

Managing the COVID-19 pandemic—and other communicable diseases—involves broad societal uptake of vaccines. As has been demonstrated, however, vaccine uptake is often uneven and incomplete across populations. This is a substantial challenge that must be addressed by public health efforts. To this point, significant research has focused on demographic and attitudinal correlates with vaccine hesitancy to understand uptake patterns. In this study, however, we advance understandings of individual decision-making processes involved in vaccine uptake through a mixed-methods investigation of the role of timing in COVID-19 vaccine choices. In the first step, a survey experiment, we find the timing of vaccine rollout (i.e., when a vaccine becomes available to the respondent) has a significant impact on public decision-making. Not only is there a higher level of acceptance when the vaccine becomes available at a later time, but delayed availability is correlated with both lower levels of ‘desire to wait’ and ‘total rejection’ of the vaccine. In a second step, we explore associated qualitative data, finding that temporal expressions (i.e., professing a desire to wait) can serve as a proxy for underlying non-temporal rationales, like concerns around safety, efficacy, personal situations, or altruism. By identifying these patterns, as well as the complexities of underlying factors, through a mixed-methods investigation, we can inform better vaccine-related policy and public messaging, as well as enhance our understanding of how individuals make decisions about vaccines in the context of COVID-19.

Extraction of Temporal Structures for Clinical Events in Unlabeled Free-Text Electronic Health Records in Russian

The important information about a patient is often stored in a free-form text to describe the events in the patient’s medical history. In this work, we propose and evaluate a hybrid approach based on rules and syntactical analysis to normalise temporal expressions and assess uncertainty depending on the remoteness of the event. A dataset of 500 sentences was manually labelled to measure the accuracy. On this dataset, the accuracy of extracting temporal expressions is 95,5%, and the accuracy of normalization is 94%. The event extraction accuracy is 74.80%. The essential advantage of this work is the implementation of the considered approach for the non-English language where NLP tools are limited.

Some temporal expressions in early Southern Min play scripts

Drawing on the data in early Southern Min play scripts, this paper explores temporal expressions—in particular temporal adverbials—which bear on the issues of their grammatical categories and syntactic placement. Considerable space is devoted to clarifying two kinds of distinctions of temporal adverbials on the strength of attested examples. A distinction is made between deictic temporal adverbials and determiner phrase-derived temporal adverbials. Similarly, durative adverbials are shown to behave differently from punctual adverbials. Finally, I argue that the metonymic semantic shift of deictic temporal adverbials denoting tomorrow and yesterday/the day before yesterday is grounded in the constraint of proximity to the deictic center of today in connection with the backdrop of diachronic development.

THE SPACES OF MYTH IN KAZUO ISHIGURO’S THE REMAINS OF THE DAY: EXPLORING THE INTERSECTIONS OF MEMORY AND HISTORY

Kazuo Ishiguro’s The Remains of the Day (1989) reconstructs the experiences of an ageing butler, Stevens, trapped within the confined space of the house he has served in for many years. The contours of memory are drawn along the spatial dimensions of the house which serve as a space of contestation between traditional values and emergent cultural beliefs in the post-war period. Physical modifications on the architecture produce continuities and alterations within the subject, who inhabits the space. This paper seeks to explore the dynamics of remembering and forgetting which are determined by the sites of memory and which trace historical changes as well as shifts in identity politics in Ishiguro’s novel. The paper critically assesses the idea of space, its functional dimension and mythic commemoration in relation to a symbolic historical past. It examines the development of subjectivity through the expansion of memory embodied in material form and the complex relationship between history and myth-making, which complicates individual identity. This paper further proposes that these spatio-temporal expressions can be understood as not only confined to the individual but may be extended to the domain of public memory and contextualized in a post-war British cultural politics of grief.

The categorical use of a continuous time representation

The abstract concept of time is mentally represented as a spatially oriented line, with the past associated with the left space and the future associated with the right. Although the line is supposed to be continuous, most available evidence is also consistent with a categorical representation that only discriminates between past and future. The aim of the present study was to test the continuous or categorical nature of the mental timeline. Italian participants judged the temporal reference of 20 temporal expressions by pressing keys on either the left or the right. In Experiment 1 (N = 32), all words were presented at the center of the screen. In Experiment 2 (N = 32), each word was presented on the screen in a central, left, or right position. In Experiment 3 (N = 32), all text was mirror-reversed. In all experiments, participants were asked to place the 20 temporal expressions on a 10-cm line. The results showed a clear Spatial–TEmporal Association of Response Codes (STEARC) effect which did not vary in strength depending on the location of the temporal expressions on the line. However, there was also a clear Distance effect: latencies were slower for words that were closer to the present than further away. We conclude that the mental timeline is a continuous representation that can be used in a categorical way when an explicit past vs. future discrimination is required by the task.

Aberrant Temporal-Spatial Complexity of Intrinsic Fluctuations in Major Depression

Accumulating evidence suggested that the brain is highly dynamic, thus investigation of brain dynamics especially in brain connectivity would provide crucial information that stationary functional connectivity could miss. This study investigated temporal expressions of spatial modes within the default mode network (DMN), salience network (SN) and cognitive control network (CCN) using a reliable data-driven co-activation pattern (CAP) analysis. We found reduced number of CAPs, as well as transitions between different CAPs of the DMN and CCN, in patients with MDD. These results suggested reduced variability and flexibility of these two brain networks in the patients. By contrast, we also found increased number of CAPs of the SN in the patients, indicating enhanced variability of the SN in individuals with MDD. In addition, the patients were characterized by prominent activation of mPFC and insula. More importantly, we showed that our findings were robust and reproducible with another independent data set. Our findings suggest that functional connectivity in the patients may not be simply attenuated or potentiated, but just alternating faster or slower among more complex patterns. The aberrant temporal-spatial complexity of intrinsic fluctuations reflects functional diaschisis of resting-state networks as characteristic of patients with MDD.