Detecting goals of care conversations in clinical notes with active learning.

OBJECTIVE: Goals of care (GOC) discussions are an increasingly used quality metric in serious illness care and research. Wide variation in documentation practices within the Electronic Health Record (EHR) presents challenges for reliable measurement of GOC discussions. Novel natural language processing approaches are needed to capture GOC discussions documented in real-world samples of seriously ill hospitalized patients' EHR notes, a corpus with a very low event prevalence. METHODS: To automatically detect sentences documenting GOC discussions outside of dedicated GOC note types, we proposed an ensemble of classifiers aggregating the predictions of rule-based, feature-based, and three transformers-based classifiers. We trained our classifier on 600 manually annotated EHR notes among patients with serious illnesses. Our corpus exhibited an extremely imbalanced ratio between sentences discussing GOC and sentences that do not. This ratio challenges standard supervision methods to train a classifier. Therefore, we trained our classifier with active learning. RESULTS: Using active learning, we reduced the annotation cost to fine-tune our ensemble by 70% while improving its performance in our test set of 176 EHR notes, with 0.557 F1-score for sentence classification and 0.629 for note classification. CONCLUSION: When classifying notes, with a true positive rate of 72% (13/18) and false positive rate of 8% (13/158), our performance may be sufficient for deploying our classifier in the EHR to facilitate bedside clinicians' access to GOC conversations documented outside of dedicated notes types, without overburdening clinicians with false positives. Improvements are needed before using it to enrich trial populations or as an outcome measure.

Rhetoric of research: a call for renaming the clinical research partnership.

OBJECTIVE: Research cannot advance without the voluntary participation of human participants. SUMMARY OF ARGUMENTS: Full participation of research participants is often restrained by the traditional research framework, which relegates them to a predefined participant role and allows them only quasi-scripted opportunities to contribute to research processes and outcomes. Terms commonly used to refer to research participants do not reflect their significant role or send a clear message about their value. The authors propose a shift from 'patient participant' to 'participant partner.' Recognition of the true partnership between the participant and the research team, from the consent process to the trial's end, will encourage and enable fuller participation. CONCLUSION: Changing the rhetoric of research in the labelling of research participants will require dialogue. 'Respect for persons' demands it, and the research process will be better for it.

Everyday Ethics or Deference to Expertise: Experiences of Pediatric Palliative Care Teams with Ethics Consultancy.

Background: Little is known about the extent to which pediatric palliative care (PPC) clinicians are engaged in ethics consults or how they perceive interactions with ethics consultants. Objective: Describe the extent to which PPC team members serve in pediatric health care ethics (PHCE) consultancy roles and to describe their experiences interacting with pediatric ethic consultant services. Design: Online survey distributed to members of the American Academy of Pediatrics and American Academy of Hospice and Palliative Care pediatric and ethics section and special interest groups in the United States. Results: Eighty-six responses were obtained (response rate 45%) from PPC teams in 70 different children's hospitals located in 34 states. Almost all (97%) reported a functional ethics consult service such that PPC is not expected to meet the ethics need of the institution. A person involved on the PPC team also performed ethics consults in half (49%) of the settings, predominantly the PPC physician. Most respondents who perceive PPC teams engage in ethics-relevant work as part of their everyday PPC work. Formal ethics training was lacking among PPC members involved in ethics consults with few ethics degrees (15%), certifications (6%), or fellowships (2%). Discord (67%), conflict (49%), limitations to treatment (48%), and distress (41%) were cited as the most frequent reasons for which PPC teams consult ethics. PPC respondents identified role clarity, coordinated engagement, timely presence, and open communication as strong PHCE consultant practices. Conclusions: PPC team members performing ethics consults may benefit from additional ethics education and training. Further research is warranted to delineate scope of ethics consultancy relevant to PPC and role clarity.