Case-based reasoning: application of an Artificial Intelligence system in the management of common musculoskeletal pain complaints (Preprint)

Author:

Granviken FredrikORCID,Vasseljen OttarORCID,Bach KerstinORCID,Jaiswal AmarORCID,Meisingset IngebrigtORCID

Abstract

BACKGROUND

Applying group-level evidence from guidelines to individual patients is challenging due to the great variation in symptoms in patients with musculoskeletal (MSK) pain complaints. A problem-solving method in artificial intelligence (AI), case-based reasoning (CBR), where new problems are solved based on experiences from past similar problems, might offer guidance in such situations.

OBJECTIVE

The objective of this study was to use CBR to build an AI system for decision support in musculoskeletal (MSK) pain patients seeking physiotherapy care. The paper describes the development of the CBR system and demonstrates the system’s ability to identify similar patients.

METHODS

Data from physiotherapy patients in primary care of Norway were collected to build a case base for the CBR system. We used the local-global principle in CBR to identify similar patients. The global similarity measures consisted of prognostic attributes, weighted in terms of prognostic importance and choice of treatment. For the local similarity measures, the degree of similarity within each attribute, was based on minimal clinically important difference and expert knowledge. The CBR system’s ability to identify similar patients was assessed by comparing the similarity scores of all patients in the case base with the scores on an established screening tool (The short form Örebro Musculoskeletal Pain Screening Questionnaire (ÖMSPQ)) and an outcome measure (The Musculoskeletal Health Questionnaire (MSK-HQ)) used in MSK pain.

RESULTS

The original case base contained 105 patients with MSK pain (mean age 46 years (SD 15); 73% women). The CBR system consisted of 29 weighted attributes with local similarities. When comparing the similarity scores for all patients in the case base, one at a time, with the ÖMSPQ and MSK-HQ, the most similar patients had a mean absolute difference from the query patient of 9.3 points (95% CI, 8.0-10.6 points) on the ÖMSPQ and a mean absolute difference of 5.6 points (95% CI, 4.6-6.6 points) on the MSK-HQ. For both ÖMSPQ and MSK-HQ, the absolute score difference increased as the rank of most similar patients decreased.

CONCLUSIONS

This paper describes the development of a CBR system for MSK pain in primary care. The CBR system identified similar patients according to an established screening tool and an outcome measure for patients with MSK pain.

Publisher

JMIR Publications Inc.

Cited by 2 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3