Document Type

Article

Publication Date

3-11-2021

Identifier/URL

136361492 (Orcid)

Abstract

Patients with sickle cell disease (SCD) experience lifelong struggles with both chronic and acute pain, often requiring medical interventMaion. Pain can be managed with medications, but dosages must balance the goal of pain mitigation against the risks of tolerance, addiction and other adverse effects. Setting appropriate dosages requires knowledge of a patient's subjective pain, but collecting pain reports from patients can be difficult for clinicians and disruptive for patients, and is only possible when patients are awake and communicative. Here we investigate methods for estimating SCD patients' pain levels indirectly using vital signs that are routinely collected and documented in medical records. Using machine learning, we develop both sequential and non-sequential probabilistic models that can be used to infer pain levels or changes in pain from sequences of these physiological measures. We demonstrate that these models outperform null models and that objective physiological data can be used to inform estimates for subjective pain. Author summary: Understanding subjective human pain remains a major challenge. If objective data could be used in place of reported pain levels, it could reduce patient burdens and enable the collection of much larger data sets that could deepen our understanding of causes of pain and allow for accurate forecasting and more effective pain management. Here we apply two machine learning approaches to data from patients with sickle cell disease, who often experience debilitating pain crises. Using vital sign data routinely collected in hospital settings including respiratory rate, heart rate, and blood pressure and amidst the real-world challenges of irregular timing, missing data, and inter-patient variation, we demonstrate that these models outperform baseline models in estimating subjective pain, distinguishing between typical and atypical pain levels, and detecting changes in pain. Once trained, these types of models could be used to improve pain estimates in real time in the absence of direct pain reports.

Comments

This work is licensed under CC BY 4.0

DOI

10.1371/journal.pcbi.1008542

Download


Share

COinS