当前位置: X-MOL 学术Med. Biol. Eng. Comput. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Medical expert system for low back pain management: design issues and conflict resolution with Bayesian network.
Medical & Biological Engineering & Computing ( IF 2.6 ) Pub Date : 2020-09-07 , DOI: 10.1007/s11517-020-02222-9
Debarpita Santra 1 , Jyotsna Kumar Mandal 1 , Swapan Kumar Basu 2 , Subrata Goswami 3
Affiliation  

The paper focuses on the development of a reliable medical expert system for diagnosis of low back pain (LBP) by proposing an efficient frame-based knowledge representation scheme and a suitable resolution logic with conflicts in outcomes being resolved using Bayesian network. Considering that LBP is classified into many diseases based on different pain generators, the proposed methodology infers non-conflicting LBP diseases sorted according to their chances of occurrence. A satisfactory clinical efficacy (average relative error − 0.09, recall 74.44%, precision 76.67%, accuracy 71.11%, and F1-score 73.88%) of the proposed methodology has been found after validating the design with empirically selected thirty LBP patient cases. Constraining that an inferred disease having chance of occurrence, prior to pathological investigations, below 0.75 (as set by four pain specialists) is not accepted clinically; the design can correctly identify, on average, 74.44% of actual diagnosis; and 76.67% of inferred diagnosis is included in actual diagnosis. With the predicted chance of occurrence being lower than 0.75 by a fraction of 0.09 on average, the proposed design performs well for 73.88% cases detecting 71.11% inferred outcomes as accurate. The design offers homogeneity to the actual outcomes, with the chi-squared static being calculated as 11.08 having 12 as degree of freedom.



中文翻译:

腰痛管理医学专家系统:贝叶斯网络的设计问题和冲突解决。

本文着重于通过提出一种有效的基于框架的知识表示方案和合适的解决逻辑来开发用于诊断腰痛 (LBP) 的可靠医学专家系统,其中使用贝叶斯网络解决结果冲突。考虑到 LBP 根据不同的疼痛发生器分为多种疾病,所提出的方法推断非冲突的 LBP 疾病根据其发生的机会进行分类。令人满意的临床疗效(平均相对误差 - 0.09,召回率 74.44%,精确度 76.67%,准确度 71.11%,F在用经验选择的 30 个 LBP 患者病例验证设计后,发现了所提出的方法的 1 分(73.88%)。临床上不接受在病理调查之前有机会发生的推断疾病低于 0.75(由四名疼痛专家设定);该设计可以正确识别平均74.44%的实际诊断;76.67%的推断诊断包含在实际诊断中。由于预测的发生几率低于 0.75,平均为 0.09 的一小部分,因此所提出的设计在 73.88% 的情况下表现良好,检测到 71.11% 的推断结果为准确。该设计为实际结果提供了同质性,卡方静力计算为 11.08,自由度为 12。

更新日期:2020-09-08
down
wechat
bug