Knowledge-Infused Abstractive Summarization of Clinical Diagnostic Interviews: Framework Development Study.

BACKGROUND: In clinical diagnostic interviews, mental health professionals (MHPs) implement a care practice that involves asking open questions (eg, "What do you want from your life?" "What have you tried before to bring change in your life?") while listening empathetically to patients. During these interviews, MHPs attempted to build a trusting human-centered relationship while collecting data necessary for professional medical and psychiatric care. Often, because of the social stigma of mental health disorders, patient discomfort in discussing their presenting problem may add additional complexities and nuances to the language they use, that is, hidden signals among noisy content. Therefore, a focused, well-formed, and elaborative summary of clinical interviews is critical to MHPs in making informed decisions by enabling a more profound exploration of a patient's behavior, especially when it endangers life. OBJECTIVE: The aim of this study is to propose an unsupervised, knowledge-infused abstractive summarization (KiAS) approach that generates summaries to enable MHPs to perform a well-informed follow-up with patients to improve the existing summarization methods built on frequency heuristics by creating more informative summaries. METHODS: Our approach incorporated domain knowledge from the Patient Health Questionnaire-9 lexicon into an integer linear programming framework that optimizes linguistic quality and informativeness. We used 3 baseline approaches: extractive summarization using the SumBasic algorithm, abstractive summarization using integer linear programming without the infusion of knowledge, and abstraction over extractive summarization to evaluate the performance of KiAS. The capability of KiAS on the Distress Analysis Interview Corpus-Wizard of Oz data set was demonstrated through interpretable qualitative and quantitative evaluations. RESULTS: KiAS generates summaries (7 sentences on average) that capture informative questions and responses exchanged during long (58 sentences on average), ambiguous, and sparse clinical diagnostic interviews. The summaries generated using KiAS improved upon the 3 baselines by 23.3%, 4.4%, 2.5%, and 2.2% for thematic overlap, Flesch Reading Ease, contextual similarity, and Jensen Shannon divergence, respectively. On the Recall-Oriented Understudy for Gisting Evaluation-2 and Recall-Oriented Understudy for Gisting Evaluation-L metrics, KiAS showed an improvement of 61% and 49%, respectively. We validated the quality of the generated summaries through visual inspection and substantial interrater agreement from MHPs. CONCLUSIONS: Our collaborator MHPs observed the potential utility and significant impact of KiAS in leveraging valuable but voluminous communications that take place outside of normally scheduled clinical appointments. This study shows promise in generating semantically relevant summaries that will help MHPs make informed decisions about patient status.

Analyzing and learning the language for different types of harassment.

THIS ARTICLE USES WORDS OR LANGUAGE THAT IS CONSIDERED PROFANE, VULGAR, OR OFFENSIVE BY SOME READERS. The presence of a significant amount of harassment in user-generated content and its negative impact calls for robust automatic detection approaches. This requires the identification of different types of harassment. Earlier work has classified harassing language in terms of hurtfulness, abusiveness, sentiment, and profanity. However, to identify and understand harassment more accurately, it is essential to determine the contextual type that captures the interrelated conditions in which harassing language occurs. In this paper we introduce the notion of contextual type in harassment by distinguishing between five contextual types: (i) sexual, (ii) racial, (iii) appearance-related, (iv) intellectual and (v) political. We utilize an annotated corpus from Twitter distinguishing these types of harassment. We study the context of each kind to shed light on the linguistic meaning, interpretation, and distribution, with results from two lines of investigation: an extensive linguistic analysis, and the statistical distribution of uni-grams. We then build type- aware classifiers to automate the identification of type-specific harassment. Our experiments demonstrate that these classifiers provide competitive accuracy for identifying and analyzing harassment on social media. We present extensive discussion and significant observations about the effectiveness of type-aware classifiers using a detailed comparison setup, providing insight into the role of type-dependent features.

Sentinels of Breach: Lexical Choice as a Measure of Urgency in Social Media.

Objective This paper identifies general properties of language style in social media to help identify areas of need in disasters. Background In the search for metrics of need in social media data, much of the existing literature ignores processes of language usage. Psychological concepts, such as narrative breach, Gricean maxims, and lexical marking in cognition, may assist the recovery of disaster-relevant metrics from altered patterns of word prevalence. Method We analyzed several hundred thousand location-specific microblogs from Twitter for Hurricane Sandy, Oklahoma tornadoes, and the Boston Marathon bombing along with a fantasy football control corpus, examining the relative frequency of words in 36 antonym pairs. We compared the ratio of words within these pairs to the corresponding ratios recovered from an online word norm database. Results Partial rank correlation values between observed antonym ratios demonstrate consistent patterns across disasters. For Hurricane Sandy data, 25 antonym pairs have moderate to large effect sizes for discrepancies between observed and normative ratios. Across disasters, 7 pairs are stable and meet effect size criteria. Sentiment analysis, supplementary word frequency counts with respect to disaster proximity, and examples support a "breach" account for the observed results. Conclusion Lexical choice between antonyms, only somewhat related to sentiment, suggests that social media capture wide-ranging breaches of normal functioning. Application Antonym selection contributes to screening tools based on language style for identifying relevant content and quantifying disruption using social media without the a priori specification of content keywords.

Navigating the Decision Space: Shared Medical Decision Making as Distributed Cognition.

Despite increasing prominence, little is known about the cognitive processes underlying shared decision making. To investigate these processes, we conceptualize shared decision making as a form of distributed cognition. We introduce a Decision Space Model to identify physical and social influences on decision making. Using field observations and interviews, we demonstrate that patients and physicians in both acute and chronic care consider these influences when identifying the need for a decision, searching for decision parameters, making actionable decisions Based on the distribution of access to information and actions, we then identify four related patterns: physician dominated; physician-defined, patient-made; patient-defined, physician-made; and patient-dominated decisions. Results suggests that (a) decision making is necessarily distributed between physicians and patients, (b) differential access to information and action over time requires participants to transform a distributed task into a shared decision, and (c) adverse outcomes may result from failures to integrate physician and patient reasoning. Our analysis unifies disparate findings in the medical decision-making literature and has implications for improving care and medical training.

The impact of medical record technologies on collaboration in emergency medicine.

PURPOSE: Electronic medical records (EMR) promise potential benefits for the practice of medical care. However, individual technologies such as EMR must interact with the work system as a whole - including people, technology and work practices - to enable or hinder the coordination of dynamic work demands. Based on this extended perspective, we address in this paper how support technologies (should) impact the coordination of work across multiple agents, controlling a dynamic domain with multiple, interacting processes. The technology we address is the medical record and the dynamic domain is emergency medicine as it is practiced in the U.S. METHOD: We performed 500 hours of naturalistic observations of physicians in two different hospital emergency departments in the Midwestern U.S differing in their reliance on paper or electronic medical records. RESULTS AND CONCLUSIONS: An analysis of work practice across the two hospitals revealed the role of medical records in facilitating or hindering the coordination of time sensitive and context dependent distributed work, as well as the specific influence of EMR. Recognizing that work practice compensates for the limitations of technology, we suggest four requirements for the design of EMR to promote workplace efficiency: facilitation of locally customized data presentations; support for integration of hitherto fragmented record systems and data formats; support for effective multi-user coordination of control tasks; and guidance for standardizing a level of detail in planning and documenting care.

Everyday expertise: cognitive demands in diabetes selfmanagement.

OBJECTIVE: To assess the relationship between decision making and successful diabetes self-management. BACKGROUND: Patients with type II diabetes make routine but critical self-management decisions. METHOD: We conducted cognitive task analysis interviews with 18 patients to examine problem detection, functional relationships, problem-solving strategies, and types of knowledge used to make self-management decisions. We expected that these decision processes would be related to behavioral adherence and glycemic control. RESULTS: Verbal reports displaying problem detection skills, knowledge of functional relationships, and effective problem-solving strategies were all related to better adherence. Problem detection skill was linked to greater glycemic control. Participants differed in declarative and applied knowledge. CONCLUSION: Diabetes self-management draws on the same cognitive skills found in experts from diverse professional domains. Considering diabetes self-management as a form of expertise may support adherence. APPLICATION: Human factors approaches that support professional expertise may be useful for the decision making of patients with diabetes and other chronic diseases.