Predictive Models for Palliative Care Needs of Advanced Cancer Patients Receiving Chemotherapy.

CONTEXT: Early palliative care is recommended within eight-week of diagnosing advanced cancer. Although guidelines suggest routine screening to identify cancer patients who could benefit from palliative care, implementing screening can be challenging due to understaffing and time constraints. OBJECTIVES: To develop and evaluate machine learning models for predicting specialist palliative care needs in advanced cancer patients undergoing chemotherapy, and to investigate if predictive models could substitute screening tools. METHODS: We conducted a retrospective cohort study using supervised machine learning. The study included patients aged 18 or older, diagnosed with metastatic or stage IV cancer, who underwent chemotherapy and distress screening at a designated cancer hospital in Japan from April 1, 2018, to March 31, 2023. Specialist palliative care needs were assessed based on distress screening scores and expert evaluations. Data sources were hospital's cancer registry, health claims database, and nursing admission records. The predictive model was developed using XGBoost, a machine learning algorithm. RESULTS: Out of the 1878 included patients, 561 were analyzed. Among them, 114 (20.3%) exhibited needs for specialist palliative care. After under-sampling to address data imbalance, the models achieved an Area Under the Curve (AUC) of 0.89 with 95.8% sensitivity and a specificity of 71.9%. After feature selection, the model retained five variables, including the patient-reported pain score, and showcased an 0.82 AUC. CONCLUSION: Our models could forecast specialist palliative care needs for advanced cancer patients on chemotherapy. Using five variables as predictors could replace screening tools and has the potential to contribute to earlier palliative care.

Quality indicators for palliative care in intensive care units: a systematic review.

BACKGROUND: Establishing appropriate quality assessment indicators for palliative care in intensive care units (ICUs) is vital. This systematic review summarizes the existing quality indicators (QIs) for palliative care in ICUs. It assesses the methodological quality of QI development to pave the way for more valid QIs. METHODS: A literature search was conducted using MEDLINE, PsycINFO, CINAHL, Cochrane databases, and the Ichushi-web database for Japanese literature for all studies published until November 2021. The included QIs were drawn from the National Consensus Project for Quality Palliative Care (NCP) and the Donabedian model of quality. Methodological quality was assessed based on the appraisal of indicators through the research and evaluation tool. RESULTS: Five studies were included, from which 109 indicators were extracted: 78% were process indicators, 5% were outcome indicators, and 17% were structure indicators. The most common indicators addressed the palliative care domain of "ethical and legal aspects of care" (n=38, 30%). Another distinctive feature of some indicators was a focus on supporting ICU staff. Regarding methodological quality, the "scientific evidence" varied (11-89%). Most of the data on QI measures and data sources were obtained from a review of electronic medical records (EMRs). Administrative data also provided a few measurable indicators. CONCLUSIONS: Out of all the QIs covered in this review, most were process indicators, and only a few were outcome indicators. Ethical and legal aspects of care and support for the ICU staff emerged as unique to palliative care. Although the existing QIs can be used for palliative care in ICUs, more specific indicators are urgently needed. Continuous quality assessment and improvement, as well as the addition of more palliative care practices in ICUs, would provide further evidence and help develop valid QIs.

Needs-based triggers for timely referral to palliative care for older adults severely affected by noncancer conditions: a systematic review and narrative synthesis.

BACKGROUND: Older people with noncancer conditions are less likely to be referred to palliative care services due to the inherent uncertain disease trajectory and a lack of standardised referral criteria. For older adults with noncancer conditions where prognostic estimation is unpredictable, needs-based criteria are likely more suitable. Eligibility criteria for participation in clinical trials on palliative care could inform a needs-based criteria. This review aimed to identify and synthesise eligibility criteria for trials in palliative care to construct a needs-based set of triggers for timely referral to palliative care for older adults severely affected by noncancer conditions. METHODS: A systematic narrative review of published trials of palliative care service level interventions for older adults with noncancer conditions. Electronic databases Medline, Embase, CINAHL, PsycINFO, CENTRAL, and ClinicalTrials.gov. were searched from inception to June 2022. We included all types of randomised controlled trials. We selected trials that reported eligibility criteria for palliative care involvement for older adults with noncancer conditions, where > 50% of the population was aged ≥ 65 years. The methodological quality of the included studies was assessed using a revised Cochrane risk-of-bias tool for randomized trials. Descriptive analysis and narrative synthesis provided descriptions of the patterns and appraised the applicability of included trial eligibility criteria to identify patients likely to benefit from receiving palliative care. RESULTS: 27 randomised controlled trials met eligibility out of 9,584 papers. We identified six major domains of trial eligibility criteria in three categories, needs-based, time-based and medical history-based criteria. Needs-based criteria were composed of symptoms, functional status, and quality of life criteria. The major trial eligibility criteria were diagnostic criteria (n = 26, 96%), followed by medical history-based criteria (n = 15, 56%), and physical and psychological symptom criteria (n = 14, 52%). CONCLUSION: For older adults severely affected by noncancer conditions, decisions about providing palliative care should be based on the present needs related to symptoms, functional status, and quality of life. Further research is needed to examine how the needs-based triggers can be operationalized as referral criteria in clinical settings and develop international consensus on referral criteria for older adults with noncancer conditions.