Advance Care Planning in Serious Illness: A Narrative Review.

CONTEXT: Advance care planning (ACP) intends to support person-centered medical decision-making by eliciting patient preferences. Research has not identified significant associations between ACP and goal-concordant end-of-life care, leading to justified scientific debate regarding ACP utility. OBJECTIVE: To delineate ACP's potential benefits and missed opportunities and identify an evidence-informed, clinically relevant path ahead for ACP in serious illness. METHODS: We conducted a narrative review merging the best available ACP empirical data, grey literature, and emergent scholarly discourse using a snowball search of PubMed, Medline, and Google Scholar (2000-2022). Findings were informed by our team's interprofessional clinical and research expertise in serious illness care. RESULTS: Early ACP practices were largely tied to mandated document completion, potentially failing to capture the holistic preferences of patients and surrogates. ACP models focused on serious illness communication rather than documentation show promising patient and clinician results. Ideally, ACP would lead to goal-concordant care even amid the unpredictability of serious illness trajectories. But ACP might also provide a false sense of security that patients' wishes will be honored and revisited at end-of-life. An iterative, 'building block' framework to integrate ACP throughout serious illness is provided alongside clinical practice, research, and policy recommendations. CONCLUSIONS: We advocate a balanced approach to ACP, recognizing empirical deficits while acknowledging potential benefits and ethical imperatives (e.g., fostering clinician-patient trust and shared decision-making). We support prioritizing patient/surrogate-centered outcomes with more robust measures to account for interpersonal clinician-patient variables that likely inform ACP efficacy and may better evaluate information gleaned during serious illness encounters.

Development and Validation of a Deep Learning Algorithm for Mortality Prediction in Selecting Patients With Dementia for Earlier Palliative Care Interventions.

Importance: Early palliative care interventions drive high-value care but currently are underused. Health care professionals face challenges in identifying patients who may benefit from palliative care. Objective: To develop a deep learning algorithm using longitudinal electronic health records to predict mortality risk as a proxy indicator for identifying patients with dementia who may benefit from palliative care. Design, Setting, and Participants: In this retrospective cohort study, 6-month, 1-year, and 2-year mortality prediction models with recurrent neural networks used patient demographic information and topics generated from clinical notes within Partners HealthCare System, an integrated health care delivery system in Boston, Massachusetts. This study included 26 921 adult patients with dementia who visited the health care system from January 1, 2011, through December 31, 2017. The models were trained using a data set of 24 229 patients and validated using another data set of 2692 patients. Data were analyzed from September 18, 2018, to May 15, 2019. Main Outcomes and Measures: The area under the receiver operating characteristic curve (AUC) for 6-month and 1- and 2-year mortality prediction models and the factors contributing to the predictions. Results: The study cohort included 26 921 patients (16 263 women [60.4%]; mean [SD] age, 74.6 [13.5] years). For the 24 229 patients in the training data set, mean (SD) age was 74.8 (13.2) years and 14 632 (60.4%) were women. For the 2692 patients in the validation data set, mean (SD) age was 75.0 (12.6) years and 1631 (60.6%) were women. The 6-month model reached an AUC of 0.978 (95% CI, 0.977-0.978); the 1-year model, 0.956 (95% CI, 0.955-0.956); and the 2-year model, 0.943 (95% CI, 0.942-0.944). The top-ranked latent topics associated with 6-month and 1- and 2-year mortality in patients with dementia include palliative and end-of-life care, cognitive function, delirium, testing of cholesterol levels, cancer, pain, use of health care services, arthritis, nutritional status, skin care, family meeting, shock, respiratory failure, and swallowing function. Conclusions and Relevance: A deep learning algorithm based on patient demographic information and longitudinal clinical notes appeared to show promising results in predicting mortality among patients with dementia in different time frames. Further research is necessary to determine the feasibility of applying this algorithm in clinical settings for identifying unmet palliative care needs earlier.