Creating a Learning Health System in a Cancer Center: Generalizability of an Electronic Health Record Phenotype for Advanced Solid Cancer.

PURPOSE: To test the generalizability of an electronic health record (EHR) phenotype for patients with advanced solid cancer, which was previously developed in a single cancer center. METHODS: We compared an algorithm to identify patients with advanced solid cancer from a random sample of patients with active cancer in the Veterans Health Administration (VA) and an academic cancer center with a human-coded reference standard between January 1, 2016, and December 31, 2019. RESULTS: Compared with the human-coded reference standard, the algorithm had high specificity (93%; 95% CI, 87 to 99 and 97%; 95% CI, 93 to 100) and reasonable sensitivity (85%; 95% CI, 76 to 94 and 87%; 95% CI, 77 to 97) in the VA and academic cancer center populations, respectively. Patients with advanced cancer (compared with those with active nonadvanced cancer) had higher mortality at the VA and academic cancer center (29.2% and 17.0% 6-month mortality v 6.8% and 3.5%), respectively. CONCLUSION: This EHR phenotype can be used to measure and improve the quality of palliative care for patients with advanced cancer within and across health care settings.

Investigating Data Diversity and Model Robustness of AI Applications in Palliative Care and Hospice: Protocol for Scoping Review.

BACKGROUND: Artificial intelligence (AI) has become a pivotal element in health care, leading to significant advancements across various medical domains, including palliative care and hospice services. These services focus on improving the quality of life for patients with life-limiting illnesses, and AI's ability to process complex datasets can enhance decision-making and personalize care in these sensitive settings. However, incorporating AI into palliative and hospice care requires careful examination to ensure it reflects the multifaceted nature of these settings. OBJECTIVE: This scoping review aims to systematically map the landscape of AI in palliative care and hospice settings, focusing on the data diversity and model robustness. The goal is to understand AI's role, its clinical integration, and the transparency of its development, ultimately providing a foundation for developing AI applications that adhere to established ethical guidelines and principles. METHODS: Our scoping review involves six stages: (1) identifying the research question; (2) identifying relevant studies; (3) study selection; (4) charting the data; (5) collating, summarizing, and reporting the results; and (6) consulting with stakeholders. Searches were conducted across databases including MEDLINE through PubMed, Embase.com, IEEE Xplore, ClinicalTrials.gov, and Web of Science Core Collection, covering studies from the inception of each database up to November 1, 2023. We used a comprehensive set of search terms to capture relevant studies, and non-English records were excluded if their abstracts were not in English. Data extraction will follow a systematic approach, and stakeholder consultations will refine the findings. RESULTS: The electronic database searches conducted in November 2023 resulted in 4614 studies. After removing duplicates, 330 studies were selected for full-text review to determine their eligibility based on predefined criteria. The extracted data will be organized into a table to aid in crafting a narrative summary. The review is expected to be completed by May 2025. CONCLUSIONS: This scoping review will advance the understanding of AI in palliative care and hospice, focusing on data diversity and model robustness. It will identify gaps and guide future research, contributing to the development of ethically responsible and effective AI applications in these settings. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/56353.

Timing and content of serious illness conversations for patients with advanced heart failure in a specialty-aligned palliative care service.

BACKGROUND: Patients with advanced heart failure (AHF) desire communication around values and goals prior to treatment decisions. OBJECTIVES: To evaluate the timing and content of the first serious illness communication (SI conversation) for patients with AHF after referral to a specialist palliative care (PC) team (HeartPal). METHODS: In this retrospective cohort study, we used electronic health records to identify patients referred to HeartPal and their first SI conversations at a tertiary care hospital between October 2018 and September 2021. We used natural language processing and predetermined codes to quantify prevalence of prior goals of care conversations by the cardiology team within six months preceding the HeartPal consultation and the prevalence of hopes, fears, and seven conversation content codes. Consecutive SI conversations and patient outcomes were followed until March 2022. RESULTS: Of 468 patients (mean age: 64 years, 72 % male, 66 % referred for goals of care conversation), 25.2 % had prior documented goals of care conversations preceding the HeartPal consultation. During the study period, 206 (44.0 %) patients died (median time from initial SI conversation to death: 65 days, IQR 206) and 43.2 % engaged in multiple SI conversations before death. SI conversation analysis (n = 324) revealed that patients hoped to "be at home" (74.1 %, n = 240), "be independent" (65.7 %, n = 213) and "live as long as possible" (53.4 %, n = 173). Conversation content included goals of care (83.0 %), strengths (83.0 %), decision-making (79.3 %), spirituality (71.0 %), coping (52.2 %), and prognostic communication (43.5 %). CONCLUSION: Specialist PC service provides documentation of goals and values and offers longitudinal follow-up for patients with AHF.

Using Oncology Treatment Pathway Data to Evaluate Serious Illness Communication, Care Utilization, and End-of-Life Care for Patients With Cancer.

PURPOSE: Oncology treatment pathways provide decision support and encourage guideline adherence. Pathway data combined with electronic health record (EHR) data can identify patient populations with poor prognoses, low serious illness conversation (SIC) rates, and high acute care utilization that may benefit from targeted interventions. PATIENTS AND METHODS: We conducted a retrospective cohort analysis among adults with cancer treated at seven affiliated sites of the Dana-Farber Cancer Institute (DFCI) who had navigations within 21 treatment pathways between July 29, 2019, and March 8, 2023. DFCI clinicians previously identified pathway nodes with an estimated survival less than 1 year, termed poor prognosis (PP) nodes. We combined pathway data with EHR data to calculate the median overall survival (OS) and proportion of patients with SICs, acute care utilization (hospitalizations and emergency department visits), and outpatient palliative care 6 months after treatment node navigation for all, PP, and nonpoor prognosis (nPP) nodes. SICs were identified using the EHR advanced care planning (ACP) tab. RESULTS: There were 15,261 navigations for 10,203 patients (median age 66 years, 55% female, 85% White). The median OS was 13.8 months for all nodes, 7.8 months for PP nodes, and 21.0 months for nPP nodes. The ACP section of the EHR rate 6 months after navigation was 19.6% for PP nodes versus 11.0% for nPP nodes. There was substantial intragroup variability in OS and SIC rates among all nodes. SICs were recorded in the ACP tab for only 34.3% of decedents. Patients who navigated to PP nodes had higher levels of acute care utilization and palliative care encounters. CONCLUSION: Treatment pathway data enabled identification of patient populations with poor prognoses, low SIC rates, and high acute care utilization.

Harnessing Natural Language Processing to Assess Quality of End-of-Life Care for Children With Cancer.

PURPOSE: Data on end-of-life care (EOLC) quality, assessed through evidence-based quality measures (QMs), are difficult to obtain. Natural language processing (NLP) enables efficient quality measurement and is not yet used for children with serious illness. We sought to validate a pediatric-specific EOLC-QM keyword library and evaluate EOLC-QM attainment among childhood cancer decedents. METHODS: In a single-center cohort of children with cancer who died between 2014 and 2022, we piloted a rule-based NLP approach to examine the content of clinical notes in the last 6 months of life. We identified documented discussions of five EOLC-QMs: goals of care, limitations to life-sustaining treatments (LLST), hospice, palliative care consultation, and preferred location of death. We assessed performance of NLP methods, compared with gold standard manual chart review. We then used NLP to characterize proportions of decedents with documented EOLC-QM discussions and timing of first documentation relative to death. RESULTS: Among 101 decedents, nearly half were minorities (Hispanic/Latinx [24%], non-Hispanic Black/African American [20%]), female (48%), or diagnosed with solid tumors (43%). Through iterative refinement, our keyword library achieved robust performance statistics (for all EOLC-QMs, F1 score = 1.0). Most decedents had documented discussions regarding goals of care (83%), LLST (83%), and hospice (74%). Fewer decedents had documented discussions regarding palliative care consultation (49%) or preferred location of death (36%). For all five EOLC-QMs, first documentation occurred, on average, >30 days before death. CONCLUSION: A high proportion of decedents attained specified EOLC-QMs more than 30 days before death. Our findings indicate that NLP is a feasible approach to measuring quality of care for children with cancer at the end of life and is ripe for multi-center research and quality improvement.

Telemedicine-based serious illness conversations, healthcare utilization, and end of life care among patients with advanced lung cancer.

PURPOSE: Little is known about serious illness conversations (SIC) conducted during telemedicine visits and their impact on end-of-life (EOL) outcomes for patients with advanced cancer. PATIENTS AND METHODS: We conducted a retrospective analysis telemedicine visits for patients with metastatic lung cancer conducted during the first surge of the COVID-19 pandemic (October 3, 2020-October 6, 2020). We used natural language processing (NLP) to characterize documentation of SIC domains (ie, goals of care [GOC], limitation of life-sustaining treatment [LLST], prognostic awareness [PA], palliative care [PC], and hospice). We used unadjusted logistic regression to evaluate factors associated with SIC documentation and the relationship between SIC documentation and EOL outcomes. RESULTS: The study included 634 telemedicine visits across 360 patients. Documentation of at least one SIC domain was present in 188 (29.7%) visits with GOC and PA being the most discussed domains. Family presence (odds ratio [OR], 1.66; P = .004), progressive or newly diagnosed disease (OR, 5.42; P < .000), age ≥ 70 (OR, 1.80; P = .009), and male sex (OR, 2.23; P < .000) were associated with a greater likelihood of discussing ≥ 1 SIC domain. Of the 61 patients who died within 12 months of the study period, having ≥ 1 SIC domain discussed was associated with a lower likelihood of hospitalization in the last 30 days of life (OR, 0.27; P = .020). CONCLUSION: In this study of telehealth visits, we identified important factors associated with an increased likelihood of having documentation of an SIC and demonstrated that SIC documentation correlated with lower likelihood of hospitalization at EOL.

Content Analysis of Serious Illness Conversation Documentation: Structured vs. Free-Text Information.

CONTEXT: Clear, accessible, and thorough documentation of serious illness conversations helps ensure that critical information patients share with clinicians is reflected in their future care. OBJECTIVES: We sought to characterize and compare serious illness conversations recorded in two different ways in the electronic health record to better understand patterns of serious illness conversation documentation. METHODS: We performed content analysis of serious illness conversations documented in the electronic health record, whether documented via structured tab or free-text clinical notes, for patients (n = 150) with advanced cancer who started a treatment associated with a poor prognosis between October 2020 and June 2022. A multidisciplinary team iteratively developed a codebook to classify serious illness conversation content (e.g., goals/hopes) on a preliminary sample (n = 30), and two researchers performed mixed deductive-inductive coding on the remaining data (n = 120). We reviewed documentation from 34 patients with serious illness conversations documentation in the structured tab only, 43 with documentation in only free-text clinical notes, and 44 with documentation of both types. We then compared content between documentation types. RESULTS: Information documented more frequently in structured tabs included fears/worries and illness understanding; clinical notes more often included treatment preferences, deliberations surrounding advance directives, function, and trade-offs. Qualitative insights highlight a range of length and detail across documentation types, and suggest notable authorship by palliative and social work clinicians. CONCLUSION: How serious illness conversations are documented in the electronic health record may impact the content captured. Future quality improvement efforts should seek to consolidate documentation sources to improve care and information retention.

Feasibility and acceptability of a nurse-led telehealth intervention (BOLSTER) to support patients with peritoneal carcinomatosis and their caregivers: A pilot randomized clinical trial.

OBJECTIVE: Patients with advanced gynecologic (GYN) and gastrointestinal (GI) cancers frequently develop peritoneal carcinomatosis (PC), which limits prognosis and diminishes health-related quality of life (HRQoL). Palliative procedures may improve PC symptoms, yet patients and caregivers report feeling unprepared to manage ostomies, catheters, and other complex needs. Our objectives were to (1) assess the feasibility of an efficacy trial of a nurse-led telehealth intervention (BOLSTER) for patients with PC and their caregivers; and (2) assess BOLSTER's acceptability, potential to improve patients' HRQoL and self-efficacy, and potential impact on advance care planning (ACP). METHODS: Pilot feasibility RCT. Recently hospitalized adults with advanced GYN and GI cancers, PC, and a new complex care need and their caregivers were randomized 1:1 to BOLSTER or enhanced discharge planning (EDP). We defined feasibility as a ≥ 50% approach-to-consent ratio and acceptability as ≥70% satisfaction with BOLSTER. We assessed patients' HRQoL and self-efficacy at baseline and six weeks, then compared the proportion experiencing meaningful improvements by arm. ACP documentation was identified using natural language processing. RESULTS: We consented 77% of approached patients. In the BOLSTER arm, 91.0% of patients and 100.0% of caregivers were satisfied. Compared to EDP, more patients receiving BOLSTER experienced improvements in HRQoL (68.4% vs. 40.0%) and self-efficacy for managing symptoms (78.9% vs. 35.0%) and treatment (52.9% vs. 42.9%). The BOLSTER arm had more ACP documentation. CONCLUSIONS: BOLSTER is a feasible and acceptable intervention with the potential to improve patients' HRQoL and promote ACP. An efficacy trial comparing BOLSTER to usual care is underway. TRIAL REGISTRATION: ClinicalTrials.gov: NCT03367247; PI: Wright.

A Comparison of Palliative Care Delivery between Ethnically Chinese and Non-Chinese Canadians in the Last Year of Life.

BACKGROUND: Ethnically Chinese adults in Canada and the United States face multiple barriers in accessing equitable, culturally respectful care at the end-of-life. Palliative care (PC) is committed to supporting patients and families in achieving goal-concordant, high-quality serious illness care. Yet, current PC delivery may be culturally misaligned. Therefore, understanding ethnically Chinese patients' use of palliative care may uncover modifiable factors to sustained inequities at the end-of-life. OBJECTIVE: To compare the use and delivery of PC in the last year of life between ethnically Chinese and non-Chinese adults. DESIGN: Population-based cohort study. PARTICIPANTS: All Ontario adults who died between January 1st, 2012, and October 31st, 2022, in Ontario, Canada. EXPOSURES: Chinese ethnicity. MAIN MEASURES: Elements of physician-delivered PC, including model of care (generalist; specialist; mixed), timing and location of initiation, and type of palliative care physician at initial consultation. KEY RESULTS: The final study cohort included 527,700 non-Chinese (50.8% female, 77.9 ± 13.0 mean age, 13.0% rural residence) and 13,587 ethnically Chinese (50.8% female, 79.2 ± 13.6 mean age, 0.6% rural residence) adults. Chinese ethnicity was associated with higher likelihoods of using specialist (adjusted odds ratio [aOR] 1.53, 95%CI 1.46-1.60) and mixed (aOR 1.32, 95%CI 1.26-1.38) over generalist models of PC, compared to non-Chinese patients. Chinese ethnicity was also associated with a higher likelihood of PC initiation in the last 30 days of life (aOR 1.07, 95%CI 1.03-1.11), in the hospital setting (aOR 1.24, 95%CI 1.18-1.30), and by specialist PC physicians (aOR 1.33, 95%CI 1.28-1.38). CONCLUSIONS: Chinese ethnicity was associated with a higher likelihood of mixed and specialist models of PC delivery in the last year of life compared to adults who were non-Chinese. These observed differences may be due to later initiation of PC in hospital settings, and potential differences in unmeasured needs that suggest opportunities to initiate early, community-based PC to support ethnically Chinese patients with serious illness.

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.

Role matters in understanding 'quality' in palliative care: a qualitative analysis of patient, caregiver and practitioner perspectives.

OBJECTIVES: To compare the discussions from two panels on the concept of palliative care quality for patients with advanced cancer, exploring the priorities reflected in each group's perspectives. DESIGN: We convened two RAND-UCLA appropriateness panel discussions on palliative care quality in advanced cancer. Discussions were audio-recorded and transcribed verbatim. Panel transcripts were analysed thematically using a matrix approach to examine perceptions and experiences of quality. SETTING: Discussions were framed within the context of advanced cancer care and palliative care. PARTICIPANTS: The patient-caregiver panel had 9 patients with current or a history of cancer and caregivers, and the practitioner panel had 10 expert practitioners representing fields of oncology, primary care, social work, palliative care, nursing, pain management and ethics. RESULTS: Our analysis identified three thematic categories for understanding quality common across both groups and nine subthemes within those categories. At the highest level, quality was conceived as: (1) the patient and caregiver experience of care, (2) technical competence and (3) the structure of health system. Among the subthemes, four were present in only one of the two group's discussions: 'purpose and action' was specific to the patient-caregiver panel, whereas 'adhering to best medical practice', 'mitigating unintended consequences and side effects', and 'health system resources and costs' were specific to the practitioner panel. CONCLUSIONS: While both panels aligned on the three key domains of quality, the particular dimensions through which they perceived quality varied in relation to their experience and role as a professional provider of care versus recipient of healthcare services. These differences suggest the importance of adopting a collaborative approach to quality measurement and improvement so that the values of all interested parties are represented in improvement efforts.

Assessing performance of Geriatric Surgery Verification Program preoperative communication standards in spine surgery.

BACKGROUND: To assess performance of the American College of Surgeons Geriatric Surgery Verification (GSV) Program preoperative communication standards in older patients undergoing high risk spine surgery. METHODS: We performed an external validation of a natural language processing (NLP) method for identifying documentation meeting GSV communication standards. We then applied this method to a retrospective cohort of patients aged 65 and older who underwent spinal fusion procedures between January 2018-December 2020 in a large healthcare system in Massachusetts. Our primary outcome of interest was fulfillment of GSV communication domains: overall health goals, treatment goals, and patient-centered outcomes. Factors associated with the fulfillment of at least one domain were assessed using Poisson regression to adjust for confounding. RESULTS: External validation of the NLP method had a sensitivity of 88.6% and specificity of 99.0%. Our study population included 1294 patients, of whom only 0.8% (n = 10) patients contained documentation of all three GSV domains, and 33.7% (n = 436) had documentation fulfilling at least one GSV domain. The GSV domain with lowest frequency of documentation was overall health goals, with only 35 (2.7%) of patients meeting this requirement. Adjusted analysis suggested that patients with a Charlson comorbidity score of one or more had higher fulfillment of GSV criteria (CCI 1-3: prevalence rate ratio (PRR) 1.8, 95% confidence interval (CI) 1.5-2.1; CCI >3: PRR 1.5, 95% CI 1.2-1.9). CONCLUSION: A paucity of geriatric patients undergoing spine surgery had preoperative documentation consistent with GSV standards. Given that spine surgery is one of the highest risk surgeries in older adults and GSV standards are relevant to all surgical specialties, wider promulgation of these standards is warranted.

What Patients Facing Cancer and Caregivers Want From Communication in Times of Crisis: A Qualitative Study in the Early Months of the COVID-19 Pandemic.

BACKGROUND: Interpersonal communication is a cornerstone of patient-centered care. We aimed to identify what patients with cancer and caregivers may want from communication during a public health crisis. METHODS: We interviewed 15 patients (8 Veteran, 7 non-Veteran) and caregivers from regionally, racially, and ethnically diverse backgrounds across the US about serious illness care and quality of care during the COVID-19 pandemic Using an iterative, inductive and deductive process, 2 coders analyzed content associated with the code "Communication," which appeared 71 times, and identified 5 themes. RESULTS: Participants identified as White (10), Latino/a (3), Asian (1), and Black (1). (1) Help patients and caregivers prepare for care during crisis by communicating medical information directly and proactively. (2) Explain how a crisis might influence medical recommendations and impact on recovery from illness. (3) Use key messengers to improve communication between primary teams, patients, and caregivers. (4) Include caregivers and families in communication when they cannot be physically present. (5) Foster bidirectional communication with patients and families to engage them in shared decision-making during a vulnerable time. CONCLUSION: Communication is critical during a public health crisis yet overwhelmed clinicians may not be able to communicate effectively. Communicating with caregivers and family, transparent and timely communication, ensuring diverse providers are on the same page, and effective listening are known gaps even before the COVID-19 pandemic. Clinicians may need quick interventions, like education about goals of care, to remind them about what seriously ill patients and their caregivers want from communication and offer patient-centered care during crises.

Video Intervention and Goals-of-Care Documentation in Hospitalized Older Adults: The VIDEO-PCE Randomized Clinical Trial.

Importance: Despite the benefits of goals-of-care (GOC) communication, many hospitalized individuals never communicate their goals or preferences to clinicians. Objective: To assess whether a GOC video intervention delivered by palliative care educators (PCEs) increased the rate of GOC documentation. Design, Setting, and Participants: This pragmatic, stepped-wedge cluster randomized clinical trial included patients aged 65 years or older admitted to 1 of 14 units at 2 urban hospitals in New York and Boston from July 1, 2021, to October 31, 2022. Intervention: The intervention involved PCEs (social workers and nurses trained in GOC communication) facilitating GOC conversations with patients and/or their decision-makers using a library of brief, certified video decision aids available in 29 languages. Patients in the control period received usual care. Main Outcome and Measures: The primary outcome was GOC documentation, which included any documentation of a goals conversation, limitation of life-sustaining treatment, palliative care, hospice, or time-limited trials and was obtained by natural language processing. Results: A total of 10 802 patients (mean [SD] age, 78 [8] years; 51.6% male) were admitted to 1 of 14 hospital units. Goals-of-care documentation during the intervention phase occurred among 3744 of 6023 patients (62.2%) compared with 2396 of 4779 patients (50.1%) in the usual care phase (P < .001). Proportions of documented GOC discussions for Black or African American individuals (865 of 1376 [62.9%] vs 596 of 1125 [53.0%]), Hispanic or Latino individuals (311 of 548 [56.8%] vs 218 of 451 [48.3%]), non-English speakers (586 of 1059 [55.3%] vs 405 of 863 [46.9%]), and people living with Alzheimer disease and related dementias (520 of 681 [76.4%] vs 355 of 570 [62.3%]) were greater during the intervention phase compared with the usual care phase. Conclusions and Relevance: In this stepped-wedge cluster randomized clinical trial of older adults, a GOC video intervention delivered by PCEs resulted in higher rates of GOC documentation compared with usual care, including among Black or African American individuals, Hispanic or Latino individuals, non-English speakers, and people living with Alzheimer disease and related dementias. The findings suggest that this form of patient-centered care delivery may be a beneficial decision support tool. Trial Registration: ClinicalTrials.gov Identifier: NCT04857060.

Depression care quality among patients with solid tumor cancers detected to have depression in Veterans Health Administration primary care clinics.

Patients with cancer, especially advanced cancer, experience depression at high rates. We aimed to evaluate the quality of depression care received by patients with solid tumor cancer and advanced solid tumor cancer in Veterans Affairs (VA) primary care clinics. This is a retrospective cohort study of patients seen in 82 VA primary care clinics who newly screened positive for depression on the Patient Health Questionnaire (PHQ-2). Outcomes included timely follow-up within 84 or 180 days (3+ mental health specialty, 3+ psychotherapy, or 3+ primary care visits with depression diagnosis codes) and minimum treatment within 1 year (60+ days antidepressants prescribed, 4+ mental health specialty visits, or 3+ psychotherapy visits). 608,042 individuals were seen in VA primary care clinics during this period; 49,839 patients (8.2%) had solid tumor cancer and 9,278 (1.5%) had advanced or poor-prognosis solid tumor cancer. For 686 observations of patients with cancer and new depression, rates of appropriate follow-up were 22.3% within 84 days and 38.2% within 180 days. For 73 observations of patients with advanced or poor-prognosis cancer and new depression, rates of appropriate follow-up were 21.9% within 84 days and 34.3% within 180 days. Rates of minimum treatment within 1 year were 68.4% and 64.4% for patients with cancer and patients with advanced or poor-prognosis cancer, respectively. Quality of timely depression management is low in patients with solid tumor cancers. Even in health systems with well-integrated mental health services, care gaps remain for patients with cancer and depression. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Forms or Free-Text? Measuring Advance Care Planning Activity Using Electronic Health Records.

Advance care planning (ACP) discussions seek to guide future serious illness care. These discussions may be recorded in the electronic health record by documentation in clinical notes, structured forms and directives, and physician orders. Yet, most studies of ACP prevalence have only examined structured electronic health record elements and ignored data existing in notes. We sought to investigate the relative comprehensiveness and accuracy of ACP documentation from structured and unstructured electronic health record data sources. We evaluated structured and unstructured ACP documentation present in the electronic health records of 435 patients with cancer drawn from three separate healthcare systems. We extracted structured ACP documentation by manually annotating written documents and forms scanned into the electronic health record. We coded unstructured ACP documentation using a rule-based natural language processing software that identified ACP keywords within clinical notes and was subsequently reviewed for accuracy. The unstructured approach identified more instances of ACP documentation (238, 54.7% of patients) than the structured ACP approach (187, 42.9% of patients). Additionally, 16.6% of all patients with structured ACP documentation only had documents that were judged as misclassified, incomplete, blank, unavailable, or a duplicate of a previously entered erroneous document. ACP documents scanned into electronic health records represent a limited view of ACP activity. Research and measures of clinical practice with ACP should incorporate information from unstructured data.

Mitigating bias in AI at the point of care.

Promoting equity in AI in health care requires addressing biases at cli nical implementation.

Integrating Patient and Expert Perspectives to Conceptualize High-Quality Palliative Cancer Care for Symptoms in the US Veterans Health Administration: A Qualitative Study.

Quality measurement is typically the domain of clinical experts and health system leaders; patient/caregiver perspectives are rarely solicited. We aimed to describe and integrate clinician and patient/caregiver conceptualizations of high-quality palliative symptom care for patients receiving care for advanced cancer within the US Veterans Health Administration in the context of existing quality measures. We conducted a secondary qualitative analysis of transcripts from prioritization discussions of process quality measures relevant to cancer palliative care. These discussions occurred during 2 modified RAND-UCLA appropriateness panels: a panel of 10 palliative care clinical expert stakeholders (7 physicians, 2 nurses, 1 social worker) and a panel of 9 patients/caregivers with cancer experience. Discussions were recorded, transcribed, and independently double-coded using an a priori logical framework. Content analysis was used to identify subthemes within codes and axial coding was used to identify crosscutting themes. Patients/caregivers and clinical experts contributed important perspectives to 3 crosscutting themes. First, proactive elicitation of symptoms is critical. Patients/caregivers especially emphasized importance of comprehensive and proactive screening and assessment, especially for pain and mental health. Second, screening and assessment alone is not enough; information elicited from patients must inform care. Measuring screening/assessment and management care processes separately has important limitations. Lastly, high-quality symptom management can be broadly defined if it is patient-centered; high-quality care takes an individualized approach and might include non-medical or non-pharmacological symptom management. Integrating the perspectives of clinical experts and patients/caregivers is critical for health systems to consider as they design and implement quality measures for palliative cancer care.