Chatbot Performance in Defining and Differentiating Palliative Care, Supportive Care, Hospice Care.

CONTEXT: Artificial intelligence (AI) chatbot platforms are increasingly used by patients as sources of information. However, there is limited data on the performance of these platforms, especially regarding palliative care terms. OBJECTIVES: We evaluated the accuracy, comprehensiveness, reliability, and readability of three AI platforms in defining and differentiating "palliative care," "supportive care," and "hospice care." METHODS: We asked ChatGPT, Microsoft Bing Chat, Google Bard to define and differentiate "palliative care," "supportive care," and "hospice care" and provide three references. Outputs were randomized and assessed by six blinded palliative care physicians using 0-10 scales (10 = best) for accuracy, comprehensiveness, and reliability. Readability was assessed using Flesch Kincaid Grade Level and Flesch Reading Ease scores. RESULTS: The mean (SD) accuracy scores for ChatGPT, Bard, and Bing Chat were 9.1 (1.3), 8.7 (1.5), and 8.2 (1.7), respectively; for comprehensiveness, the scores for the three platforms were 8.7 (1.5), 8.1 (1.9), and 5.6 (2.0), respectively; for reliability, the scores were 6.3 (2.5), 3.2 (3.1), and 7.1 (2.4), respectively. Despite generally high accuracy, we identified some major errors (e.g., Bard stated that supportive care had "the goal of prolonging life or even achieving a cure"). We found several major omissions, particularly with Bing Chat (e.g., no mention of interdisciplinary teams in palliative care or hospice care). References were often unreliable. Readability scores did not meet recommended levels for patient educational materials. CONCLUSION: We identified important concerns regarding the accuracy, comprehensiveness, reliability, and readability of outputs from AI platforms. Further research is needed to improve their performance.

Referral Criteria to Specialist Palliative Care for People with Advanced Chronic Kidney Disease: A Systematic Review.

CONTEXT: People with advanced chronic kidney disease (CKD) have significant morbidity, yet for many, access to palliative care occurs late, if at all. OBJECTIVES: This study sought to examine criteria for referral to specialist palliative care for adults with advanced CKD with a view to improving use of these essential services. METHODS: Systematic review of studies detailing referral criteria to palliative care in advanced CKD conducted and reported according to the Preferred Reporting Items for Systematic Reviews and Meta Analyses (PRISMA) guideline and registered (PROSPERO: CRD42021230751). DATA SOURCES: Electronic databases (Ovid, MEDLINE, Ovid Embase, and PubMed) were used to identify potential studies, which were subjected to double review, data extraction, thematic coding, and descriptive analyses. RESULTS: Searches yielded 650 unique titles ultimately resulting in 56 studies addressing referral criteria to specialist palliative care in advanced CKD. Of 10 categories of referral criteria, most commonly discussed were: Critical times of treatment decision making (n = 23, 41%); physical or emotional symptoms (n = 22, 39%); limited prognosis (n = 18, 32%); patient age and comorbidities (n = 18, 32%); category of CKD/ biochemical criteria (n = 13, 23%); functional decline (n = 13, 23); psychosocial needs (n = 9, 16%); future care planning (n = 9, 16%); anticipated decline in illness course (n = 8, 14%); and hospital use (n = 8, 14%). CONCLUSION: Clinicians consider referral to specialist palliative care for a wide range of reasons, with many related to care needs. As palliative care continues to integrate with nephrology, our findings represent a key step towards developing consensus criteria to standardize referral for patients with chronic kidney diseases.

Criteria for Referral of Patients With Advanced Heart Failure for Specialized Palliative Care.

BACKGROUND: Patients with advanced heart failure have substantial supportive care needs. Specialist palliative care can be beneficial, but it is unclear who is most appropriate for referral and when patients should be referred. OBJECTIVES: We conducted a Delphi study of international experts to identify consensus referral criteria for specialist palliative care for patients with advanced heart failure. METHODS: Clinicians from 5 continents with expertise in the integration of cardiology and palliative care were asked to rate 34 disease-based, 24 needs-based, and 9 time-based criteria over 3 rounds. Consensus was defined a priori as ≥70% agreement. A criterion was coded as major if the experts endorsed that meeting that criterion alone was adequate to justify a referral. RESULTS: The response rate was 44 of 46 (96%), 41 of 46 (89%), and 43 of 46 (93%) in the first, second, and third rounds, respectively. Panelists reached consensus on 25 major criteria for specialist palliative care referral. The 25 major criteria were categorized under 6 topics, including "advanced/refractory heart failure, comorbidities, and complications" (eg, cardiac cachexia, cardiorenal syndrome) (n = 8), "advanced heart failure therapies" (eg, chronic inotropes, precardiac transplant) (n = 4), "hospital utilization" (eg, emergency room visits, hospitalization) (n = 2), "prognostic estimate" (n = 1), "symptom burden/distress" (eg, severe physical/emotional/spiritual distress) (n = 6), and "decision making/social support" (eg, goals-of-care discussions) (n = 4). The majority (68%) of major criteria had ≥90% agreement. CONCLUSIONS: International experts reached consensus on a large number of criteria for referral to specialist palliative care. With further validation, these criteria may be useful for standardizing palliative care access in the inpatient and/or outpatient settings.

Referral criteria to specialist palliative care for patients with dementia: A systematic review.

BACKGROUND: Patients with dementia often have significant symptom burden and a progressive course of functional deterioration. Specialist palliative care referral may be helpful, but it is unclear who and when patients should be referred. We conducted a systematic review of the literature to examine referral criteria for palliative care among patients with dementia. METHODS: We searched Ovid MEDLINE, Ovid Embase, Ovid PsycInfo, Cochrane Library, PubMed, and CINAHL databases for articles from inception to December 3, 2019, related to specialist palliative care referral for dementia. Two investigators independently reviewed the citations for inclusion, extracted the referral criteria, and categorized them thematically. RESULTS: Of the 1788 citations, 59 articles were included in the final sample. We identified 13 categories of referral criteria, including 6 disease-based and 7 needs-based criteria. The most commonly discussed criterion was "dementia stage" (n = 43, 73%), followed by "new diagnosis of dementia" (n = 17, 29%), "medical complications of dementia" (n = 12, 20%), "prognosis" (n = 11, 19%), and "physical symptoms" (n = 11, 19%). Under dementia stage, 37/44 (84%) articles recommended a palliative care referral for advanced dementia. Pneumonia (n = 6, 10%), fall/fracture (n = 4, 7%), and decubitus ulcers (n = 4, 7%) were most commonly discussed complications to trigger a referral. Under prognosis, the time frame for referral varied from <2 years of life expectancy to <6 months. 3 (5%) of articles recommended "surprise question" as a potential trigger. CONCLUSIONS: This systematic review highlighted the lack of consensus regarding referral criteria for palliative care in patients with dementia and the need to identify timely triggers to standardize referral.

Referral criteria to palliative care for patients with respiratory disease: a systematic review.

AIMS: Advanced nonmalignant respiratory diseases are associated with significant patient morbidity, yet access to palliative care occurs late, if at all. Our aim was to examine referral criteria for palliative care among patients with advanced nonmalignant respiratory disease, with a view to developing a standardised set of referral criteria. METHODS: We performed a systematic review of all studies reporting on referral criteria to palliative care in advanced nonmalignant respiratory disease, with a focus on chronic obstructive pulmonary disease and interstitial lung disease. The systematic review was conducted and reported according to the PRISMA guidelines, and was undertaken using electronic databases (Ovid, MEDLINE, Ovid Embase and PubMed). RESULTS: Searches yielded 2052 unique titles, which were screened for eligibility and resulted in 62 studies addressing referral criteria to palliative care in advanced nonmalignant respiratory disease. Of 18 categories put forward for referral to palliative care, the most commonly discussed factors were hospital use (69% of papers), indicators of poor respiratory status (47%), physical and emotional symptoms (37%), functional decline (29%), need for advanced respiratory therapies (27%), and disease progression (26%). CONCLUSION: Clinicians consider referral to specialist palliative care for a wide range of disease- and needs-based criteria. Our findings highlight the need to standardise palliative care access by developing consensus referral criteria for patients with advanced nonmalignant respiratory illnesses.

Referral Criteria to Palliative Care for Patients With Heart Failure: A Systematic Review.

BACKGROUND: Patients with heart failure have significant symptom burden, care needs, and often a progressive course to end-stage disease. Palliative care referrals may be helpful but it is currently unclear when patients should be referred and by whom. We conducted a systematic review of the literature to examine referral criteria for palliative care among patients with heart failure. METHODS: We searched Ovid, MEDLINE, Ovid Embase, and PubMed databases for articles in the English language from the inception of databases to January 17, 2019 related to palliative care referral in patients with heart failure. Two investigators independently reviewed each citation for inclusion and then extracted the referral criteria. Referral criteria were then categorized thematically. RESULTS: Of the 1199 citations in our initial search, 102 articles were included in the final sample. We identified 18 categories of referral criteria, including 7 needs-based criteria and 10 disease-based criteria. The most commonly discussed criterion was physical or emotional symptoms (n=51 [50%]), followed by cardiac stage (n=46 [45%]), hospital utilization (n=38 [37%]), prognosis (n=37 [36%]), and advanced cardiac therapies (n=36 [35%]). Under cardiac stage, 31 (30%) articles suggested New York Heart Association functional class ≥III and 12 (12%) recommended New York Heart Association class ≥IV as cutoffs for referral. Prognosis of ≤1 year was mentioned in 21 (21%) articles as a potential trigger; few other criteria had specific cutoffs. CONCLUSIONS: This systematic review highlighted the lack of consensus regarding referral criteria for the involvement of palliative care in patients with heart failure. Further research is needed to identify appropriate and timely triggers for palliative care referral.