ABSTRACT
[This corrects the article DOI: 10.3389/fpain.2023.1177070.].
ABSTRACT
Introduction: Chronic musculoskeletal pain is a prevalent condition impacting around 20% of people globally; resulting in patients living with pain, fatigue, restricted social and employment capacity, and reduced quality of life. Interdisciplinary multimodal pain treatment programs have been shown to provide positive outcomes by supporting patients modify their behavior and improve pain management through focusing attention on specific patient valued goals rather than fighting pain. Methods: Given the complex nature of chronic pain there is no single clinical measure to assess outcomes from multimodal pain programs. Using Centre for Integral Rehabilitation data from 2019-2021 (n = 2,364), we developed a multidimensional machine learning framework of 13 outcome measures across 5 clinically relevant domains including activity/disability, pain, fatigue, coping and quality of life. Machine learning models for each endpoint were separately trained using the most important 30 of 55 demographic and baseline variables based on minimum redundancy maximum relevance feature selection. Five-fold cross validation identified best performing algorithms which were rerun on deidentified source data to verify prognostic accuracy. Results: Individual algorithm performance ranged from 0.49 to 0.65 AUC reflecting characteristic outcome variation across patients, and unbalanced training data with high positive proportions of up to 86% for some measures. As expected, no single outcome provided a reliable indicator, however the complete set of algorithms established a stratified prognostic patient profile. Patient level validation achieved consistent prognostic assessment of outcomes for 75.3% of the study group (n = 1,953). Clinician review of a sample of predicted negative patients (n = 81) independently confirmed algorithm accuracy and suggests the prognostic profile is potentially valuable for patient selection and goal setting. Discussion: These results indicate that although no single algorithm was individually conclusive, the complete stratified profile consistently identified patient outcomes. Our predictive profile provides promising positive contribution for clinicians and patients to assist with personalized assessment and goal setting, program engagement and improved patient outcomes.
ABSTRACT
BACKGROUND: The use of extracorporeal membrane oxygenation (ECMO) in refractory cardiac arrest (ECPR) has increased exponentially. ECPR is a resource intensive service and its cost effectiveness has yet to be demonstrated. We sought to complete a cost analysis with modelling of cost effectiveness and quality of life outcomes. We sought to complete a cost analysis with modelling of cost effectiveness and quality of life outcomes of patients who have undergone ECPR. METHODS: Using data on all extracorporeal cardiopulmonary resuscitation (ECPR) patients at two ECMO centres in Sydney, Australia; we completed a costing analysis of ECPR patients. A Markov model of cost, quality of life and survival outcomes was developed to examine cost per QALY estimates and incremental cost effectiveness ratios (ICERs). Probabilistic sensitivity analysis (PSA) was completed to assess the probability of cost effectiveness for base case and variations. RESULTS: Sixty-two consecutive ECPR patients were analysed; mean age of 51.9 ± 13.6 years, 38 (61%) were in hospital cardiac arrests (IHCA). Twenty-five patients (40%) survived to hospital discharge; all with a cerebral performance category (CPC) of 1 or 2. The mean cost per ECPR patient was AUD 75,165 (50,535; ±AUD 75,737). Over 10 years ECPR was estimated to add a mean gain of 3.0 Quality Adjusted Life Years (QALYs) per patient with an incremental cost effectiveness ratio (ICER) of AUD 25,212 (16,890) per QALY, increasing to 4.0 QALYs and an ICER of AUD 18,829 (12,614) over a 15-year survival scenario. Mean cost per QALY did not differ significantly by OHCA or IHCA. CONCLUSIONS: ECMO support for refractory cardiac arrests is cost effective and compares favourably to accepted cost effectiveness thresholds.
