RESUMO
PURPOSE: Machine learning (ML) algorithms that incorporate routinely collected patient-reported outcomes (PROs) alongside electronic health record (EHR) variables may improve prediction of short-term mortality and facilitate earlier supportive and palliative care for patients with cancer. METHODS: We trained and validated two-phase ML algorithms that incorporated standard PRO assessments alongside approximately 200 routinely collected EHR variables, among patients with medical oncology encounters at a tertiary academic oncology and a community oncology practice. RESULTS: Among 12,350 patients, 5,870 (47.5%) completed PRO assessments. Compared with EHR- and PRO-only algorithms, the EHR + PRO model improved predictive performance in both tertiary oncology (EHR + PRO v EHR v PRO: area under the curve [AUC] 0.86 [0.85-0.87] v 0.82 [0.81-0.83] v 0.74 [0.74-0.74]) and community oncology (area under the curve 0.89 [0.88-0.90] v 0.86 [0.85-0.88] v 0.77 [0.76-0.79]) practices. CONCLUSION: Routinely collected PROs contain added prognostic information not captured by an EHR-based ML mortality risk algorithm. Augmenting an EHR-based algorithm with PROs resulted in a more accurate and clinically relevant model, which can facilitate earlier and targeted supportive care for patients with cancer.
Assuntos
Registros Eletrônicos de Saúde , Neoplasias , Humanos , Medidas de Resultados Relatados pelo Paciente , Cuidados Paliativos , Aprendizado de Máquina , Neoplasias/diagnóstico , Neoplasias/terapiaRESUMO
BACKGROUND: Subjective stress is a well-documented predictor of early smoking relapse, yet our understanding of stress and tobacco use is limited by reliance on self-reported measures of stress. We utilized a validated functional neuroimaging paradigm to examine whether stress exposure during early abstinence alters objective measures of brain function. METHODS: Seventy-five participants underwent blood oxygen level dependent (BOLD) functional magnetic resonance imaging (fMRI) during the Montreal Imaging Stress Task (MIST) on two occasions: once during smoking satiety and once following biochemically confirmed 24-hour abstinence (order counterbalanced). The primary outcome measure was brain response during stress (vs. control) blocks of the MIST, assessed using whole-brain analysis corrected for multiple comparisons using clusters determined by Z ≥ 3.1. RESULTS: Abstinence (vs. satiety) was associated with significantly increased activation in the left inferior frontal gyrus, a brain region associated with inhibitory control. Abstinence-induced change in brain response to stress was positively associated with change in self-reported stress. CONCLUSIONS: This study provides objective evidence that the brain response to stress is altered during the first 24 hours of a quit attempt compared to smoking satiety. IMPLICATIONS: These results point to the potential value of inoculating smokers with stress management training prior to a quit attempt.