Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool

BackgroundLow back pain (LBP) presents with diverse manifestations, necessitating personalized treatment approaches that recognize various phenotypes within the same diagnosis, which could be achieved through precision medicine. Although prediction strategies have been explor...

Full description

Saved in:
Bibliographic Details
Main Authors: Anabela C Areias, Robert G Moulder, Maria Molinos, Dora Janela, Virgílio Bento, Carolina Moreira, Vijay Yanamadala, Steven P Cohen, Fernando Dias Correia, Fabíola Costa
Format: Article
Language:English
Published: JMIR Publications 2024-11-01
Series:JMIR Medical Informatics
Online Access:https://medinform.jmir.org/2024/1/e64806
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846162955696078848
author Anabela C Areias
Robert G Moulder
Maria Molinos
Dora Janela
Virgílio Bento
Carolina Moreira
Vijay Yanamadala
Steven P Cohen
Fernando Dias Correia
Fabíola Costa
author_facet Anabela C Areias
Robert G Moulder
Maria Molinos
Dora Janela
Virgílio Bento
Carolina Moreira
Vijay Yanamadala
Steven P Cohen
Fernando Dias Correia
Fabíola Costa
author_sort Anabela C Areias
collection DOAJ
description BackgroundLow back pain (LBP) presents with diverse manifestations, necessitating personalized treatment approaches that recognize various phenotypes within the same diagnosis, which could be achieved through precision medicine. Although prediction strategies have been explored, including those employing artificial intelligence (AI), they still lack scalability and real-time capabilities. Digital care programs (DCPs) facilitate seamless data collection through the Internet of Things and cloud storage, creating an ideal environment for developing and implementing an AI predictive tool to assist clinicians in dynamically optimizing treatment. ObjectiveThis study aims to develop an AI tool that continuously assists physical therapists in predicting an individual’s potential for achieving clinically significant pain relief by the end of the program. A secondary aim was to identify predictors of pain nonresponse to guide treatment adjustments. MethodsData collected actively (eg, demographic and clinical information) and passively in real-time (eg, range of motion, exercise performance, and socioeconomic data from public data sources) from 6125 patients enrolled in a remote digital musculoskeletal intervention program were stored in the cloud. Two machine learning techniques, recurrent neural networks (RNNs) and light gradient boosting machine (LightGBM), continuously analyzed session updates up to session 7 to predict the likelihood of achieving significant pain relief at the program end. Model performance was assessed using the area under the receiver operating characteristic curve (ROC-AUC), precision-recall curves, specificity, and sensitivity. Model explainability was assessed using SHapley Additive exPlanations values. ResultsAt each session, the model provided a prediction about the potential of being a pain responder, with performance improving over time (P<.001). By session 7, the RNN achieved an ROC-AUC of 0.70 (95% CI 0.65-0.71), and the LightGBM achieved an ROC-AUC of 0.71 (95% CI 0.67-0.72). Both models demonstrated high specificity in scenarios prioritizing high precision. The key predictive features were pain-associated domains, exercise performance, motivation, and compliance, informing continuous treatment adjustments to maximize response rates. ConclusionsThis study underscores the potential of an AI predictive tool within a DCP to enhance the management of LBP, supporting physical therapists in redirecting care pathways early and throughout the treatment course. This approach is particularly important for addressing the heterogeneous phenotypes observed in LBP. Trial RegistrationClinicalTrials.gov NCT04092946; https://clinicaltrials.gov/ct2/show/NCT04092946 and NCT05417685; https://clinicaltrials.gov/ct2/show/NCT05417685
format Article
id doaj-art-1ce3caeff5ab4f9fb804e1ea4f0c48bc
institution Kabale University
issn 2291-9694
language English
publishDate 2024-11-01
publisher JMIR Publications
record_format Article
series JMIR Medical Informatics
spelling doaj-art-1ce3caeff5ab4f9fb804e1ea4f0c48bc2024-11-19T21:04:23ZengJMIR PublicationsJMIR Medical Informatics2291-96942024-11-0112e6480610.2196/64806Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction ToolAnabela C Areiashttps://orcid.org/0000-0002-1807-7386Robert G Moulderhttps://orcid.org/0000-0001-7504-9560Maria Molinoshttps://orcid.org/0000-0002-9679-4639Dora Janelahttps://orcid.org/0000-0002-8440-2044Virgílio Bentohttps://orcid.org/0000-0001-6025-8511Carolina Moreirahttps://orcid.org/0000-0001-8781-1823Vijay Yanamadalahttps://orcid.org/0000-0002-2456-5888Steven P Cohenhttps://orcid.org/0000-0001-5928-2127Fernando Dias Correiahttps://orcid.org/0000-0001-8028-926XFabíola Costahttps://orcid.org/0000-0001-8981-7049 BackgroundLow back pain (LBP) presents with diverse manifestations, necessitating personalized treatment approaches that recognize various phenotypes within the same diagnosis, which could be achieved through precision medicine. Although prediction strategies have been explored, including those employing artificial intelligence (AI), they still lack scalability and real-time capabilities. Digital care programs (DCPs) facilitate seamless data collection through the Internet of Things and cloud storage, creating an ideal environment for developing and implementing an AI predictive tool to assist clinicians in dynamically optimizing treatment. ObjectiveThis study aims to develop an AI tool that continuously assists physical therapists in predicting an individual’s potential for achieving clinically significant pain relief by the end of the program. A secondary aim was to identify predictors of pain nonresponse to guide treatment adjustments. MethodsData collected actively (eg, demographic and clinical information) and passively in real-time (eg, range of motion, exercise performance, and socioeconomic data from public data sources) from 6125 patients enrolled in a remote digital musculoskeletal intervention program were stored in the cloud. Two machine learning techniques, recurrent neural networks (RNNs) and light gradient boosting machine (LightGBM), continuously analyzed session updates up to session 7 to predict the likelihood of achieving significant pain relief at the program end. Model performance was assessed using the area under the receiver operating characteristic curve (ROC-AUC), precision-recall curves, specificity, and sensitivity. Model explainability was assessed using SHapley Additive exPlanations values. ResultsAt each session, the model provided a prediction about the potential of being a pain responder, with performance improving over time (P<.001). By session 7, the RNN achieved an ROC-AUC of 0.70 (95% CI 0.65-0.71), and the LightGBM achieved an ROC-AUC of 0.71 (95% CI 0.67-0.72). Both models demonstrated high specificity in scenarios prioritizing high precision. The key predictive features were pain-associated domains, exercise performance, motivation, and compliance, informing continuous treatment adjustments to maximize response rates. ConclusionsThis study underscores the potential of an AI predictive tool within a DCP to enhance the management of LBP, supporting physical therapists in redirecting care pathways early and throughout the treatment course. This approach is particularly important for addressing the heterogeneous phenotypes observed in LBP. Trial RegistrationClinicalTrials.gov NCT04092946; https://clinicaltrials.gov/ct2/show/NCT04092946 and NCT05417685; https://clinicaltrials.gov/ct2/show/NCT05417685https://medinform.jmir.org/2024/1/e64806
spellingShingle Anabela C Areias
Robert G Moulder
Maria Molinos
Dora Janela
Virgílio Bento
Carolina Moreira
Vijay Yanamadala
Steven P Cohen
Fernando Dias Correia
Fabíola Costa
Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
JMIR Medical Informatics
title Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
title_full Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
title_fullStr Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
title_full_unstemmed Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
title_short Predicting Pain Response to a Remote Musculoskeletal Care Program for Low Back Pain Management: Development of a Prediction Tool
title_sort predicting pain response to a remote musculoskeletal care program for low back pain management development of a prediction tool
url https://medinform.jmir.org/2024/1/e64806
work_keys_str_mv AT anabelacareias predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT robertgmoulder predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT mariamolinos predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT dorajanela predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT virgiliobento predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT carolinamoreira predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT vijayyanamadala predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT stevenpcohen predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT fernandodiascorreia predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool
AT fabiolacosta predictingpainresponsetoaremotemusculoskeletalcareprogramforlowbackpainmanagementdevelopmentofapredictiontool