An Acoustical and Lexical Machine-Learning Pipeline to Identify Connectional Silences.

Context: Developing scalable methods for conversation analytics is essential for health care communication science and quality improvement. Purpose: To assess the feasibility of automating the identification of a conversational feature, Connectional Silence, which is associated with important patient outcomes. Methods: Using audio recordings from the Palliative Care Communication Research Initiative cohort study, we develop and test an automated measurement pipeline comprising three machine-learning (ML) tools-a random forest algorithm and a custom convolutional neural network that operate in parallel on audio recordings, and subsequently a natural language processing algorithm that uses brief excerpts of automated speech-to-text transcripts. Results: Our ML pipeline identified Connectional Silence with an overall sensitivity of 84% and specificity of 92%. For Emotional and Invitational subtypes, we observed sensitivities of 68% and 67%, and specificities of 95% and 97%, respectively. Conclusion: These findings support the capacity for coordinated and complementary ML methods to fully automate the identification of Connectional Silence in natural hospital-based clinical conversations.

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.

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.