Machine learning clinical decision support for interdisciplinary multimodal chronic musculoskeletal pain treatment

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.

Simple acute phase protein score to predict long-term survival in patients with acute myeloid leukemia

High levels of acute phase reactants can be associated with adverse outcome in patients with various solid tumor types. For patients with acute myeloid leukemia (AML), this correlation is unknown. We retrospectively investigated the prognostic value of pretreatment acute phase protein levels in 282 consecutive newly diagnosed AML patients undergoing at least one cycle of intensive induction chemotherapy. We applied a new score integrating pre-treatment C-reactive protein (CRP), fibrinogen, and albumin levels termed the CFA ratio, and we stratified patients into two groups: Patients with a CFA ratio below 3.06 had decisively better progression-free (26.2 vs 7.7 months; P < .001), disease-free (56.4 vs 8.7 months; P < .001), and overall survival (61.2 vs 13.8 months; P < .001). Results remained significant when adjusting for confounders including European Leukemia Network risk group. Early mortality also tended to be lower in the low CFA ratio group. Finally, patients with lower modified Glasgow prognostic score (mGPS) similarly had better outcome. In conclusion, our data suggest that an elevated CFA ratio as well as a high mGPS are associated with adverse outcome in patients with newly diagnosed AML undergoing intensive induction. These parameters should undergo prospective evaluation for their contribution to risk profiling in AML patients.