The Temperature Feature of ChatGPT: Modifying Creativity for Clinical Research.

More clinicians and researchers are exploring uses for large language model chatbots, such as ChatGPT, for research, dissemination, and educational purposes. Therefore, it becomes increasingly relevant to consider the full potential of this tool, including the special features that are currently available through the application programming interface. One of these features is a variable called temperature, which changes the degree to which randomness is involved in the model's generated output. This is of particular interest to clinicians and researchers. By lowering this variable, one can generate more consistent outputs; by increasing it, one can receive more creative responses. For clinicians and researchers who are exploring these tools for a variety of tasks, the ability to tailor outputs to be less creative may be beneficial for work that demands consistency. Additionally, access to more creative text generation may enable scientific authors to describe their research in more general language and potentially connect with a broader public through social media. In this viewpoint, we present the temperature feature, discuss potential uses, and provide some examples.

Bolstering Advance Care Planning Measurement Using Natural Language Processing.

Despite its growth as a clinical activity and research topic, the complex dynamic nature of advance care planning (ACP) has posed serious challenges for researchers hoping to quantitatively measure it. Methods for measurement have traditionally depended on lengthy manual chart abstractions or static documents (e.g., advance directive forms) even though completion of such documents is only one aspect of ACP. Natural language processing (NLP), in the form of an assisted electronic health record (EHR) review, is a technological advancement that may help researchers better measure ACP activity. In this article, we aim to show how NLP-assisted EHR review supports more accurate and robust measurement of ACP. We do so by presenting three example applications that illustrate how using NLP for this purpose supports (1) measurement in research, (2) detailed insights into ACP in quality improvement, and (3) identification of current limitations of ACP in clinical settings.

Development of a keyword library for capturing PRO-CTCAE-focused "symptom talk" in oncology conversations.

Objectives: As computational methods for detecting symptoms can help us better attend to patient suffering, the objectives of this study were to develop and evaluate the performance of a natural language processing keyword library for detecting symptom talk, and to describe symptom communication within our dataset to generate insights for future model building. Materials and Methods: This was a secondary analysis of 121 transcribed outpatient oncology conversations from the Communication in Oncologist-Patient Encounters trial. Through an iterative process of identifying symptom expressions via inductive and deductive techniques, we generated a library of keywords relevant to the Patient-Reported Outcome version of the Common Terminology Criteria for Adverse Events (PRO-CTCAE) framework from 90 conversations, and tested the library on 31 additional transcripts. To contextualize symptom expressions and the nature of misclassifications, we qualitatively analyzed 450 mislabeled and properly labeled symptom-positive turns. Results: The final library, comprising 1320 terms, identified symptom talk among conversation turns with an F1 of 0.82 against a PRO-CTCAE-focused gold standard, and an F1 of 0.61 against a broad gold standard. Qualitative observations suggest that physical symptoms are more easily detected than psychological symptoms (eg, anxiety), and ambiguity persists throughout symptom communication. Discussion: This rudimentary keyword library captures most PRO-CTCAE-focused symptom talk, but the ambiguity of symptom speech limits the utility of rule-based methods alone, and limits to generalizability must be considered. Conclusion: Our findings highlight opportunities for more advanced computational models to detect symptom expressions from transcribed clinical conversations. Future improvements in speech-to-text could enable real-time detection at scale.

Acceptability of a Serious Illness Conversation Guide to Black Americans: Results from a focus group and oncology pilot study.

OBJECTIVES: Serious illness conversations (SICs) can improve the experience and well-being of patients with advanced cancer. A structured Serious Illness Conversation Guide (SICG) has been shown to improve oncology patient outcomes but was developed and tested in a predominantly White population. To help address disparities in advanced cancer care, we aimed to assess the acceptability of the SICG among African Americans with advanced cancer and their clinicians. METHODS: A two-phase study conducted in Charleston, SC, included focus groups to gather perspectives on the SICG in Black Americans and a single-arm pilot study of a revised SICG with surveys and qualitative exit interviews to evaluate patient and clinician perspectives. We used descriptive analysis of survey results and thematic analysis of qualitative data. RESULTS: Community-based and patient focus group participants (N = 20) reported that a simulated conversation using an adapted SICG built connection, promoted control, and fostered consideration of religious faith and family. Black patients with advanced cancer (N = 23) reported that SICG-guided conversations were acceptable, helpful, and promoted conversations with loved ones. Oncologists found conversations feasible to implement and skill-building, and also identified opportunities for training and implementation that could support meeting the needs of their patients with low health literacy. An adapted SICG includes language to assess the strength and affirm the clinician-patient relationship. SIGNIFICANCE OF RESULTS: An adapted structured communication tool to facilitate SIC, the SICG, appears acceptable to Black Americans with advanced cancer and seems feasible for use by oncology clinicians working with this population. Further testing in other marginalized populations may address disparities in advanced cancer care.

21st Century Cures Act: ethical recommendations for new patient-facing products.

BACKGROUND: Recent legislation ensuring patient access to their electronic health records represents a promising national commitment to patient empowerment. Access and interoperability rules seek to empower individuals as well as increase opportunities for data sharing by hospitals, apps, and other parties for research and innovation. However, there are trade-offs between data accessibility and oversight. Some third-party apps may not be covered by federal regulations, and receiving records directly from individuals may render some services in possession of health data. To promote consumer trust, these services should follow ethical standards regardless of regulatory status. ACTIONABLE PRINCIPLES: This Perspective proposes 3 actionable principles, grounded in medical ethics, for services making use of health data: services should (1) provide informed, dynamic, regular consent, including control over data sharing, (2) promote inclusivity and equity, and (3) intentionally focus on consumer trust and the perception of value in the service provided.

Patient Preference for Telehealth Background Shapes Impressions of Physicians and Information Recall: A Randomized Experiment.

Introduction: Telehealth is increasing rapidly as a health care delivery platform, but we lack empirical evidence regarding how telehealth environments can affect patient experiences. The present research determined how physician's telehealth backgrounds affect various patient outcomes. Methods: Participants viewed a 30-s video of a physician with one of six different virtual backgrounds and reported various socioemotional and cognitive responses to the mock telehealth experience. Results: Although the telehealth background manipulation did not impact participants' socioemotional or cognitive responses, participants' subjective perceptions of the telehealth backgrounds were related to important clinical outcomes, such as their ability to remember critical information from the appointment and overall satisfaction with the experience. Discussion: Telehealth environments may result in tradeoffs between patient experience, subjective impressions of clinicians, and information recall. Conclusions: A physician's telehealth background can have measurable impact on patients' telehealth experiences, suggesting a need for careful background selection and design.

"I think that she would have wanted. . .": Qualitative interviews with bereaved caregivers reveal complexity in measuring goal-concordant care at the end of life.

BACKGROUND: Experts consider goal-concordant care an important healthcare outcome for individuals with serious illness. Despite their relationship to the patient and knowledge about the patient's wishes and values, little is known about bereaved family caregivers' perceptions of how end-of-life care aligns with patient goals and preferences. AIM: To understand caregivers' perceptions about patients' care experiences, the extent to which care was perceived as goal-concordant, and the factors that contextualized the end-of-life care experience. DESIGN: Qualitative interview study employing a semi-structured interview guide based on the National Health and Aging Trends Survey end-of-life planning module. Template analysis was used to identify themes. SETTING/PARTICIPANTS: Nineteen recently bereaved family caregivers of people with serious illness in two academic medical centers in the Northeastern United States. RESULTS: Most caregivers reported goal-concordant care, though many also recalled experiences of goal discordance. Three themes characterized care perceptions and related to perceived quality: communication, relationships and humanistic care, and care transitions. Within communication, caregivers described the importance of clear communication, inadequate prognostic communication, and information gaps that undermined caregiver confidence in decision making. Patient-clinician relationships enriched care and were considered higher-quality when felt to be humanistic. Finally, care transitions impacted goal discordance when marked by logistical barriers, a need to establish relationships with new providers, inadequate information transfer, and poor care coordination. CONCLUSIONS: Bereaved caregivers commonly rated care as goal-concordant while also identifying areas of disappointing and low-quality care. Communication, relationships and humanistic care, and care transitions are modifiable quality improvement targets for patients with advanced cancer.

Epidemiology of Connectional Silence in specialist serious illness conversations.

CONTEXT: Human connection can reduce suffering and facilitate meaningful decision-making amid the often terrifying experience of hospitalization for advanced cancer. Some conversational pauses indicate human connection, but we know little about their prevalence, distribution or association with outcomes. PURPOSE: To describe the epidemiology of Connectional Silence during serious illness conversations in advanced cancer. METHODS: We audio-recorded 226 inpatient palliative care consultations at two academic centers. We identified pauses lasting 2+ seconds and distinguished Connectional Silences from other pauses, sub-categorized as either Invitational (ICS) or Emotional (ECS). We identified treatment decisional status pre-consultation from medical records and post-consultation via clinicians. Patients self-reported quality-of-life before and one day after consultation. RESULTS: Among all 6769 two-second silences, we observed 328 (4.8%) ECS and 240 (3.5%) ICS. ECS prevalence was associated with decisions favoring fewer disease-focused treatments (ORadj: 2.12; 95% CI: 1.12, 4.06). Earlier conversational ECS was associated with improved quality-of-life (p = 0.01). ICS prevalence was associated with clinicians' prognosis expectations. CONCLUSIONS: Connectional Silences during specialist serious illness conversations are associated with decision-making and improved patient quality-of-life. Further work is necessary to evaluate potential causal relationships. PRACTICE IMPLICATIONS: Pauses offer important opportunities to advance the science of human connection in serious illness decision-making.

A Framework for Anti-Racist Publication in Palliative Care: Structures, Processes, and Outcomes.

Systemic or structural racism describes an embedded pattern of explicit and implicit racial biases that, through policy and action, systematically confer advantage to white people and disadvantage Black, indigenous, and other people of color. Hospice and palliative care journals participate in this broader system of racial discrimination. Building on palliative care's explicit focus on patients' goals and values, which may in and of itself comprise a form of social justice in healthcare, palliative care journals and their publishers have an opportunity to lead others in cultivating anti-racist practices and explicitly promoting equity. The publication life cycle of submission and solicitation, manuscript peer-review, and publication provide a framework for examining the structures, processes, and outcomes by which palliative care and other journals might address systemic racism. We describe the current academic publishing landscape, which diminishes the voices and experiences of racial and ethnic minority patients and undermines the careers of under-represented scholars. We then propose reforms that we believe will improve publication equity and quality as well as healthcare outcomes. These include an Equity in Publication checklist, solicitation of manuscripts on equity-relevant topics, promotion of scholars through editorial structures and peer review processes, and a standard Equity Rating for publications. Greater efforts to include non-dominant voices in every aspect of publication, through appropriate recognition of their scholarship and remuneration for their efforts, will drive equity in health outcomes. By pursuing an anti-racist and equity-focused publishing agenda, hospice and palliative medicine journals and their publishers have an opportunity to transform healthcare.

Conversational stories & self organizing maps: Innovations for the scalable study of uncertainty in healthcare communication.

BACKGROUND: Understanding uncertainty in participatory decision-making requires scientific attention to interaction between what actually happens when patients, families and clinicians engage one another in conversation and the multi-level contexts in which these occur. Achieving this understanding will require conceptually grounded and scalable methods for use in large samples of people representing diversity in cultures, speaking and decision-making norms, and clinical situations. DISCUSSION: Here, we focus on serious illness and describe Conversational Stories as a scalable and conceptually grounded framework for characterizing uncertainty expression in these clinical contexts. Using actual conversations from a large direct-observation cohort study, we demonstrate how natural language processing and unsupervised machine learning methods can reveal underlying types of uncertainty stories in serious illness conversations. CONCLUSIONS: Conversational Storytelling offers a meaningful analytic framework for scalable computational methods to study uncertainty in healthcare conversations.

Epidemiology of Fear, Sadness, and Anger Expression in Palliative Care Conversations.

CONTEXT: Advancing the science of serious illness communication requires methods for measuring characteristics of conversations in large studies. Understanding which characteristics predict clinically important outcomes can help prioritize attention to scalable measure development. OBJECTIVES: To understand whether audibly recognizable expressions of distressing emotion during palliative care serious illness conversations are associated with ratings of patient experience or six-month enrollment in hospice. METHODS: We audiorecorded initial palliative care consultations involving 231 hospitalized people with advanced cancer at two large academic medical centers. We coded conversations for expressions of fear, anger, and sadness. We examined the distribution of these expressions and their association with pre/post ratings of feeling heard and understood and six-month hospice enrollment after the consultation. RESULTS: Nearly six in 10 conversations included at least one audible expression of distressing emotion (59%; 137 of 231). Among conversations with such an expression, fear was the most prevalent (72%; 98 of 137) followed by sadness (50%; 69 of 137) and anger (45%; 62 of 137). Anger expression was associated with more disease-focused end-of-life treatment preferences, pre/post consultation improvement in feeling heard and understood and lower six-month hospice enrollment. Fear was strongly associated with preconsultation patient ratings of shorter survival expectations. Sadness did not exhibit strong association with patient descriptors or outcomes. CONCLUSION: Fear, anger, and sadness are commonly expressed in hospital-based palliative care consultations with people who have advanced cancer. Anger is an epidemiologically useful predictor of important clinical outcomes.

Story Arcs in Serious Illness: Natural Language Processing features of Palliative Care Conversations.

OBJECTIVE: Serious illness conversations are complex clinical narratives that remain poorly understood. Natural Language Processing (NLP) offers new approaches for identifying hidden patterns within the lexicon of stories that may reveal insights about the taxonomy of serious illness conversations. METHODS: We analyzed verbatim transcripts from 354 consultations involving 231 patients and 45 palliative care clinicians from the Palliative Care Communication Research Initiative. We stratified each conversation into deciles of "narrative time" based on word counts. We used standard NLP analyses to examine the frequency and distribution of words and phrases indicating temporal reference, illness terminology, sentiment and modal verbs (indicating possibility/desirability). RESULTS: Temporal references shifted steadily from talking about the past to talking about the future over deciles of narrative time. Conversations progressed incrementally from "sadder" to "happier" lexicon; reduction in illness terminology accounted substantially for this pattern. We observed the following sequence in peak frequency over narrative time: symptom terms, treatment terms, prognosis terms and modal verbs indicating possibility. CONCLUSIONS: NLP methods can identify narrative arcs in serious illness conversations. PRACTICE IMPLICATIONS: Fully automating NLP methods will allow for efficient, large scale and real time measurement of serious illness conversations for research, education and system re-design.

Identifying Connectional Silence in Palliative Care Consultations: A Tandem Machine-Learning and Human Coding Method.

Background: Systematic measurement of conversational features in the natural clinical setting is essential to better understand, disseminate, and incentivize high quality serious illness communication. Advances in machine-learning (ML) classification of human speech offer exceptional opportunity to complement human coding (HC) methods for measurement in large scale studies. Objectives: To test the reliability, efficiency, and sensitivity of a tandem ML-HC method for identifying one feature of clinical importance in serious illness conversations: Connectional Silence. Design: This was a cross-sectional analysis of 354 audio-recorded inpatient palliative care consultations from the Palliative Care Communication Research Initiative multisite cohort study. Setting/Subjects: Hospitalized people with advanced cancer. Measurements: We created 1000 brief audio "clips" of randomly selected moments predicted by a screening ML algorithm to be two-second or longer pauses in conversation. Each clip included 10 seconds of speaking before and 5 seconds after each pause. Two HCs independently evaluated each clip for Connectional Silence as operationalized from conceptual taxonomies of silence in serious illness conversations. HCs also evaluated 100 minutes from 10 additional conversations having unique speakers to identify how frequently the ML screening algorithm missed episodes of Connectional Silence. Results:Connectional Silences were rare (5.5%) among all two-second or longer pauses in palliative care conversations. Tandem ML-HC demonstrated strong reliability (kappa 0.62; 95% confidence interval: 0.47-0.76). HC alone required 61% more time than the Tandem ML-HC method. No Connectional Silences were missed by the ML screening algorithm. Conclusions: Tandem ML-HC methods are reliable, efficient, and sensitive for identifying Connectional Silence in serious illness conversations.

Automated Detection of Conversational Pauses from Audio Recordings of Serious Illness Conversations in Natural Hospital Settings.

OBJECTIVE: Automating conversation analysis in the natural clinical setting is essential to scale serious illness communication research to samples that are large enough for traditional epidemiological studies. Our objective is to automate the identification of pauses in conversations because these are important linguistic targets for evaluating dynamics of speaker involvement and turn-taking, listening and human connection, or distraction and disengagement. DESIGN: We used 354 audio recordings of serious illness conversations from the multisite Palliative Care Communication Research Initiative cohort study. SETTING/SUBJECTS: Hospitalized people with advanced cancer seen by the palliative care team. MEASUREMENTS: We developed a Random Forest machine learning (ML) algorithm to detect Conversational Pauses of two seconds or longer. We triple-coded 261 minutes of audio with human coders to establish a gold standard for evaluating ML performance characteristics. RESULTS: ML automatically identified Conversational Pauses with a sensitivity of 90.5 and a specificity of 94.5. CONCLUSIONS: ML is a valid method for automatically identifying Conversational Pauses in the natural acoustic setting of inpatient serious illness conversations.