Use of Machine Learning and Lay Care Coaches to Increase Advance Care Planning Conversations for Patients With Metastatic Cancer

Facilitated Advance Care Planning Interventions: A Narrative Review

Introduction: Multiple interventions have been designed to employ facilitators to address gaps in Advance Care Planning (ACP). Objective: To collect and review available evidence related to facilitated ACP interventions. Methods/Design: Narrative review using a previously described framework for scoping reviews. We searched PubMed using structured criteria and report synthesized themes detailing the design, target populations, methods, and outcome measurements for interventions in which a facilitator-who may or may not be clinical staff-engaged a patient and/or a patient's caregiver in some part of the ACP process. Results: Of 1492 articles discovered on our search, 28 met the inclusion criteria. Twelve (42.9%) studies utilized a nurse facilitator, two (7.1%) utilized trained social workers, and one (3.6%) embedded multiple facilitators. The remaining 13 (46.4%) utilized facilitators from other various professional and community backgrounds, such as lay navigators, care coordinators, and peer mentors. Twenty-five (89.2%) studies included patients with serious or chronic illness, at the end-of-life, or having a high risk of need for medical care. Four (14.3%) articles focused on marginalized populations. Intervention settings varied notably across studies. Eighteen (64.3%) integrated interventions into existing clinical workflows. Primary outcomes were measured in one of three ways: documentation in the Electronic Health Record (EHR) (25.0%); questionnaires, scales, patient reports, or non-EHR documentation (64.3%); or multiple measures (10.7%). Twenty-three (82.1%) of the studies were determined a success by study authors. Conclusion: We identified a variety of key characteristics that can be modified to target facilitated ACP interventions towards gaps in current applications of ACP.

Barriers and Strategies to Effective Serious Illness Communication for Patients with End-Stage Liver Disease in the Intensive Care Setting

Background: Patients with end-stage liver disease (ESLD) often require Intensive Care Unit (ICU) admission during the disease trajectory, but aggressive medical treatment has not resulted in increased quality of life for patients or caregivers. Methods: This narrative review synthesizes relevant data thematically exploring the current state of serious illness communication in the ICU with identification of barriers and potential strategies to improve performance. We provide a conceptual model underscoring the importance of providing comprehensible disease and prognosis knowledge, eliciting patient values and aligning these values with available goals of care options through a series of discussions. Achieving effective serious illness communication supports the delivery of goal concordant care (care aligned with the patient's stated values) and improved quality of life. Results: General barriers to effective serious illness communication include lack of outpatient serious illness communication discussions; formalized provider training, literacy and culturally appropriate patient-directed serious illness communication tools; and unoptimized electronic health records. ESLD-specific barriers to effective serious illness communication include stigma, discussing the uncertainty of prognosis and provider discomfort with serious illness communication. Evidence-based strategies to address general barriers include using the Ask-Tell-Ask communication framework; clinician training to discuss patients' goals and expectations; PREPARE for Your Care literacy and culturally appropriate written and online tools for patients, caregivers, and clinicians; and standardization of documentation in the electronic health record. Evidence-based strategies to address ESLD-specific barriers include practicing with empathy; using the "Best-Case, Worst Case" prognostic framework; and developing interdisciplinary solutions in the ICU. Conclusion: Improving clinician training, providing patients and caregivers easy-to-understand communication tools, standardizing EHR documentation, and improving interdisciplinary communication, including palliative care, may increase goal concordant care and quality of life for critically ill patients with ESLD.

Equity in Using Artificial Intelligence Mortality Predictions to Target Goals of Care Documentation

BACKGROUND

Artificial intelligence (AI) algorithms are increasingly used to target patients with elevated mortality risk scores for goals-of-care (GOC) conversations.

OBJECTIVE

To evaluate the association between the presence or absence of AI-generated mortality risk scores with GOC documentation.

DESIGN

Retrospective cross-sectional study at one large academic medical center between July 2021 and December 2022.

PARTICIPANTS

Hospitalized adult patients with AI-defined Serious Illness Risk Indicator (SIRI) scores indicating > 30% 90-day mortality risk (defined as "elevated" SIRI) or no SIRI scores due to insufficient data.

INTERVENTION

A targeted intervention to increase GOC documentation for patients with AI-generated scores predicting elevated risk of mortality.

MAIN MEASURES

Odds ratios comparing GOC documentation for patients with elevated or no SIRI scores with similar severity of illness using propensity score matching and risk-adjusted mixed-effects logistic regression.

KEY RESULTS

Among 13,710 patients with elevated (n = 3643, 27%) or no (n = 10,067, 73%) SIRI scores, the median age was 64 years (SD 18). Twenty-five percent were non-White, 18% had Medicaid, 43% were admitted to an intensive care unit, and 11% died during admission. Patients lacking SIRI scores were more likely to be younger (median 60 vs. 72 years, p < 0.0001), be non-White (29% vs. 13%, p < 0.0001), and have Medicaid (22% vs. 9%, p < 0.0001). Patients with elevated versus no SIRI scores were more likely to have GOC documentation in the unmatched (aOR 2.5, p < 0.0001) and propensity-matched cohorts (aOR 2.1, p < 0.0001).

CONCLUSIONS

Using AI predictions of mortality to target GOC documentation may create differences in documentation prevalence between patients with and without AI mortality prediction scores with similar severity of illness. These finding suggest using AI to target GOC documentation may have the unintended consequence of disadvantaging severely ill patients lacking AI-generated scores from receiving targeted GOC documentation, including patients who are more likely to be non-White and have Medicaid insurance.

Why and How to Integrate Early Palliative Care Into Cutting-Edge Personalized Cancer Care

Early palliative care, palliative care integrated with oncology care early in the course of illness, has myriad benefits for patients and their caregivers, including improved quality of life, reduced physical and psychological symptom burden, enhanced prognostic awareness, and reduced health care utilization at the end of life. Although ASCO and others recommend early palliative care for all patients with advanced cancer, widespread implementation of early palliative care has not been realized because of barriers such as insufficient reimbursement and a palliative care workforce shortage. Investigators have recently tested several implementation strategies to overcome these barriers, including triggers for palliative care consultations, telehealth delivery, navigator-delivered interventions, and primary palliative care interventions. More research is needed to identify mechanisms to distribute palliative care optimally and equitably. Simultaneously, the transformation of the oncology treatment landscape has led to shifts in the supportive care needs of patients and caregivers, who may experience longer, uncertain trajectories of cancer. Now, palliative care also plays a clear role in the care of patients with hematologic malignancies and may be beneficial for patients undergoing phase I clinical trials and their caregivers. Further research and clinical guidance regarding how to balance the risks and benefits of opioid therapy and safely manage cancer-related pain across this wide range of settings are urgently needed. The strengths of early palliative care in supporting patients' and caregivers' coping and centering decisions on their goals and values remain valuable in the care of patients receiving cutting-edge personalized cancer care.

Tumor Is Not the Only Target: Ensuring Equitable Person-Centered Supportive Care in the Era of Precision Medicine

Communication in oncology has always been challenging. The new era of precision oncology creates prognostic uncertainty. Still, person-centered care requires attention to people and their care needs. Living with cancer portends an experience that is life-altering, no matter what the outcome. Supporting patients and families through this unique experience requires careful attention, honed skills, an understanding of process and balance measures of innovation, and recognizing that supportive care is a foundational element of cancer medicine, rather than an either-or approach, an and-with approach that emphasizes the regular integration of palliative care (PC), geriatric oncology, and skilled communication.

Machine Learning to Allocate Palliative Care Consultations During Cancer Treatment

PURPOSE

For patients with advanced cancer, early consultations with palliative care (PC) specialists reduce costs, improve quality of life, and prolong survival. However, capacity limitations prevent all patients from receiving PC shortly after diagnosis. We evaluated whether a prognostic machine learning system could promote early PC, given existing capacity.

METHODS

Using population-level administrative data in Ontario, Canada, we assembled a cohort of patients with incurable cancer who received palliative-intent systemic therapy between July 1, 2014, and December 30, 2019. We developed a machine learning system that predicted death within 1 year of each treatment using demographics, cancer characteristics, treatments, symptoms, laboratory values, and history of acute care admissions. We trained the system in patients who started treatment before July 1, 2017, and evaluated the potential impact of the system on PC in subsequent patients.

RESULTS

Among 560,210 treatments received by 54,628 patients, death occurred within 1 year of 45.2% of treatments. The machine learning system recommended the same number of PC consultations observed with usual care at the 60.0% 1-year risk of death, with a first-alarm positive predictive value of 69.7% and an outcome-level sensitivity of 74.9%. Compared with usual care, system-guided care could increase early PC by 8.5% overall (95% CI, 7.5 to 9.5; P < .001) and by 15.3% (95% CI, 13.9 to 16.6; P < .001) among patients who live 6 months beyond their first treatment, without requiring more PC consultations in total or substantially increasing PC among patients with a prognosis exceeding 2 years.

CONCLUSION

Prognostic machine learning systems could increase early PC despite existing resource constraints. These results demonstrate an urgent need to deploy and evaluate prognostic systems in real-time clinical practice to increase access to early PC.

ChatGPT as a Source of Patient Information for Lumbar Spinal Fusion and Laminectomy: A Comparative Analysis Against Google Web Search

STUDY DESIGN

Retrospective Observational Study.

OBJECTIVE

The objective of this study was to assess the utility of ChatGPT, an artificial intelligence chatbot, in providing patient information for lumbar spinal fusion and lumbar laminectomy in comparison with the Google search engine.

SUMMARY OF BACKGROUND DATA

ChatGPT, an artificial intelligence chatbot with seemingly unlimited functionality, may present an alternative to a Google web search for patients seeking information about medical questions. With widespread misinformation and suboptimal quality of online health information, it is imperative to assess ChatGPT as a resource for this purpose.

METHODS

The first 10 frequently asked questions (FAQs) related to the search terms "lumbar spinal fusion" and "lumbar laminectomy" were extracted from Google and ChatGPT. Responses to shared questions were compared regarding length and readability, using the Flesch Reading Ease score and Flesch-Kincaid Grade Level. Numerical FAQs from Google were replicated in ChatGPT.

RESULTS

Two of 10 (20%) questions for both lumbar spinal fusion and lumbar laminectomy were asked similarly between ChatGPT and Google. Compared with Google, ChatGPT's responses were lengthier (340.0 vs. 159.3 words) and of lower readability (Flesch Reading Ease score: 34.0 vs. 58.2; Flesch-Kincaid grade level: 11.6 vs. 8.8). Subjectively, we evaluated these responses to be accurate and adequately nonspecific. Each response concluded with a recommendation to discuss further with a health care provider. Over half of the numerical questions from Google produced a varying or nonnumerical response in ChatGPT.

CONCLUSIONS

FAQs and responses regarding lumbar spinal fusion and lumbar laminectomy were highly variable between Google and ChatGPT. While ChatGPT may be able to produce relatively accurate responses in select questions, its role remains as a supplement or starting point to a consultation with a physician, not as a replacement, and should be taken with caution until its functionality can be validated.

Lessons Learned from a Multi-Site, Team-Based Serious Illness Care Program Implementation at an Academic Medical Center

Background: Patients with serious illness benefit from conversations to share prognosis and explore goals and values. To address this, we implemented Ariadne Labs' Serious Illness Care Program (SICP) at Stanford Health Care. Objective: Improve quantity, timing, and quality of serious illness conversations. Methods: Initial implementation followed Ariadne Labs' SICP framework. We later incorporated a team-based approach that included nonphysician care team members. Outcomes included number of patients with documented conversations according to clinician role and practice location. Machine learning algorithms were used in some settings to identify eligible patients. Results: Ambulatory oncology and hospital medicine were our largest implementation sites, engaging 4707 and 642 unique patients in conversations, respectively. Clinicians across eight disciplines engaged in these conversations. Identified barriers that included leadership engagement, complex workflows, and patient identification. Conclusion: Several factors contributed to successful SICP implementation across clinical sites: innovative clinical workflows, machine learning based predictive algorithms, and nonphysician care team member engagement.

Integrating Artificial Intelligence and Machine Learning Into Cancer Clinical Trials

The practice of oncology requires analyzing and synthesizing abundant data. From the patient's workup to determine eligibility to the therapies received to the post-treatment surveillance, practitioners must constantly juggle, evaluate, and weigh decision-making based on their best understanding of information at hand. These complex, multifactorial decisions have a tremendous opportunity to benefit from data-driven machine learning (ML) methods to drive opportunities in artificial intelligence (AI). Within the past 5 years, we have seen AI move from simply a promising opportunity to being used in prospective trials. Here, we review recent efforts of AI in clinical trials that have moved the needle towards improved prediction of actionable outcomes, such as predicting acute care visits, short term mortality, and pathologic extranodal extension. We then pause and reflect on how these AI models ask a different question than traditional statistics models that readers may be more familiar with; how then should readers conceptualize and interpret AI models that they are not as familiar with. We end with what we believe are promising future opportunities for AI in oncology, with an eye towards allowing the data to inform us through unsupervised learning and generative models, rather than asking AI to perform specific functions.

Cancer Informatics for Cancer Centers: Sharing Ideas on How to Build an Artificial Intelligence-Ready Informatics Ecosystem for Radiation Oncology

In August 2022, the Cancer Informatics for Cancer Centers brought together cancer informatics leaders for its biannual symposium, Precision Medicine Applications in Radiation Oncology, co-chaired by Quynh-Thu Le, MD (Stanford University), and Walter J. Curran, MD (GenesisCare). Over the course of 3 days, presenters discussed a range of topics relevant to radiation oncology and the cancer informatics community more broadly, including biomarker development, decision support algorithms, novel imaging tools, theranostics, and artificial intelligence (AI) for the radiotherapy workflow. Since the symposium, there has been an impressive shift in the promise and potential for integration of AI in clinical care, accelerated in large part by major advances in generative AI. AI is now poised more than ever to revolutionize cancer care. Radiation oncology is a field that uses and generates a large amount of digital data and is therefore likely to be one of the first fields to be transformed by AI. As experts in the collection, management, and analysis of these data, the informatics community will take a leading role in ensuring that radiation oncology is prepared to take full advantage of these technological advances. In this report, we provide highlights from the symposium, which took place in Santa Barbara, California, from August 29 to 31, 2022. We discuss lessons learned from the symposium for data acquisition, management, representation, and sharing, and put these themes into context to prepare radiation oncology for the successful and safe integration of AI and informatics technologies.

Improving serious illness communication: a qualitative study of clinical culture

OBJECTIVE

Communication about patients' values, goals, and prognosis in serious illness (serious illness communication) is a cornerstone of person-centered care yet difficult to implement in practice. As part of Serious Illness Care Program implementation in five health systems, we studied the clinical culture-related factors that supported or impeded improvement in serious illness conversations.

METHODS

Qualitative analysis of semi-structured interviews of clinical leaders, implementation teams, and frontline champions.

RESULTS

We completed 30 interviews across palliative care, oncology, primary care, and hospital medicine. Participants identified four culture-related domains that influenced serious illness communication improvement: (1) clinical paradigms; (2) interprofessional empowerment; (3) perceived conversation impact; (4) practice norms. Changes in clinicians' beliefs, attitudes, and behaviors in these domains supported values and goals conversations, including: shifting paradigms about serious illness communication from 'end-of-life planning' to 'knowing and honoring what matters most to patients;' improvements in psychological safety that empowered advanced practice clinicians, nurses and social workers to take expanded roles; experiencing benefits of earlier values and goals conversations; shifting from avoidant norms to integration norms in which earlier serious illness discussions became part of routine processes. Culture-related inhibitors included: beliefs that conversations are about dying or withdrawing care; attitudes that serious illness communication is the physician's job; discomfort managing emotions; lack of reliable processes.

CONCLUSIONS

Aspects of clinical culture, such as paradigms about serious illness communication and inter-professional empowerment, are linked to successful adoption of serious illness communication. Further research is warranted to identify effective strategies to enhance clinical culture and drive clinician practice change.