Secondary Logo

Institutional members access full text with Ovid®

Machine learning–based prediction of clinical pain using multimodal neuroimaging and autonomic metrics

Lee, Jeungchana; Mawla, Ishtiaqa; Kim, Jieuna,b; Loggia, Marco L.a; Ortiz, Anaa; Jung, Changjina,b; Chan, Suk-Taka; Gerber, Jessicaa; Schmithorst, Vincent J.c; Edwards, Robert R.d; Wasan, Ajay D.e; Berna, Chantalf; Kong, Jiana,g; Kaptchuk, Ted J.h; Gollub, Randy L.a,g; Rosen, Bruce R.a; Napadow, Vitalya,d,*

doi: 10.1097/j.pain.0000000000001417
Research Paper
Buy
SDC

Although self-report pain ratings are the gold standard in clinical pain assessment, they are inherently subjective in nature and significantly influenced by multidimensional contextual variables. Although objective biomarkers for pain could substantially aid pain diagnosis and development of novel therapies, reliable markers for clinical pain have been elusive. In this study, individualized physical maneuvers were used to exacerbate clinical pain in patients with chronic low back pain (N = 53), thereby experimentally producing lower and higher pain states. Multivariate machine-learning models were then built from brain imaging (resting-state blood-oxygenation-level-dependent and arterial spin labeling functional imaging) and autonomic activity (heart rate variability) features to predict within-patient clinical pain intensity states (ie, lower vs higher pain) and were then applied to predict between-patient clinical pain ratings with independent training and testing data sets. Within-patient classification between lower and higher clinical pain intensity states showed best performance (accuracy = 92.45%, area under the curve = 0.97) when all 3 multimodal parameters were combined. Between-patient prediction of clinical pain intensity using independent training and testing data sets also demonstrated significant prediction across pain ratings using the combined model (Pearson's r = 0.63). Classification of increased pain was weighted by elevated cerebral blood flow in the thalamus, and prefrontal and posterior cingulate cortices, and increased primary somatosensory connectivity to frontoinsular cortex. Our machine-learning approach introduces a model with putative biomarkers for clinical pain and multiple clinical applications alongside self-report, from pain assessment in noncommunicative patients to identification of objective pain endophenotypes that can be used in future longitudinal research aimed at discovery of new approaches to combat chronic pain.

A machine learning–based model used multimodal neuroimaging and autonomic metrics obtained from patients with chronic pain to accurately classify and predict different clinical pain intensity states.

aDepartment of Radiology, Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital, Harvard Medical School, Charlestown, MA, United States

bDivision of Clinical Research, Korea Institute of Oriental Medicine, Daejeon, Korea

cDepartment of Pediatric Radiology, Children's Hospital of Pittsburgh of UPMC and University of Pittsburgh School of Medicine, Pittsburgh, PA, United States

dDepartment of Anesthesiology, Perioperative and Pain Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, United States

eDepartment of Anesthesiology, Center for Pain Research, University of Pittsburgh, Pittsburgh, PA, United States

fDepartment of Anesthesiology, Pain Center, Lausanne University Hospital (CHUV), Lausanne, Switzerland

gDepartment of Psychiatry, Massachusetts General Hospital, Harvard Medical School, Boston, MA, United States

hProgram of Placebo Studies and the Therapeutic Encounter, Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA, United States

Corresponding author. Address: Martinos Center for Biomedical Imaging, Building 149, Suite 2301, Charlestown, MA 02129, United States. Tel.: +1-617-724-3402; fax: +1-617-726-7422. E-mail address: vitaly@mgh.harvard.edu (V. Napadow).

Sponsorships or competing interests that may be relevant to content are disclosed at the end of this article.

Supplemental digital content is available for this article. Direct URL citations appear in the printed text and are provided in the HTML and PDF versions of this article on the journal's Web site (www.painjournalonline.com).

J. Lee and I. Mawla contributed equally to this work.

Received July 13, 2018

Accepted October 09, 2018

© 2019 International Association for the Study of Pain
You currently do not have access to this article

To access this article:

Note: If your society membership provides full-access, you may need to login on your society website