Automatic recognition of symptom severity from psychiatric evaluation records
Automatic recognition of symptom severity from psychiatric evaluation records
复制标题
DOI：
10.1016/j.jbi.2017.05.020
复制
发表时间：
2017-11-01
影响因子：
4.5
通讯作者：
Harabagiu, Sanda M.
中科院分区：
文献类型：
--
作者：
Goodwin, Travis R.;Maldonado, Ramon;Harabagiu, Sanda M.
本文提出了一种自动识别症状严重程度的新方法，该方法使用精神病学评估记录的自然语言处理来提取特征，并通过机器学习技术进行处理，为CEGS/N-GRID的2016年精神病学挑战RDoC中评估的每条记录分配严重程度分数。自然语言处理技术侧重于(a)识别问答中表达的话语信息；(b)确定与精神障碍有关的医学概念；(c)解释否定的作用。机器学习技术依赖于以下假设：(1)患者阳性效价症状的严重程度存在于潜在的连续谱上；(2)心理评估记录中记录的所有患者的回答和叙述都由患者在该谱上的潜在严重程度评分提供信息。这些假设激发了我们自动识别心理症状严重程度的两步机器学习框架。第一步，从每条记录中推断出潜在连续严重程度评分；在第二步中，严重性分数被映射到CEGS/N-GRID挑战中使用的四个离散严重性级别之一。我们评估了三种推断与每条记录相关的潜在严重程度评分的方法：(i)点向脊回归；（ii）基于成对比较的分类；（iii）结合点回归和两两分类器的混合方法。第二步使用层叠支持向量机（SVM）分类器树实现。虽然官方评估结果表明这三种方法都很有前景，但混合方法不仅优于两两方法和点向方法，而且在所有提交的CEGS/N-GRID挑战中，其标准化MAE得分为84.093%（数值越高，性能越好），在所有提交的材料中表现第二高。这些评估结果使我们能够观察到，对于这项任务，考虑两两信息可以产生比点回归更准确的严重性分数-一种在其他系统中广泛用于分配严重性分数的方法。此外，我们的分析表明，在确定离散严重级别方面，使用级联支持向量机树优于传统的支持向量机分类方法。(C) 2017年Elsevier Inc.出版。
This paper presents a novel method for automatically recognizing symptom severity by using natural language processing of psychiatric evaluation records to extract features that are processed by machine learning techniques to assign a severity score to each record evaluated in the 2016 RDoC for Psychiatry Challenge from CEGS/N-GRID. The natural language processing techniques focused on (a) discerning the discourse information expressed in questions and answers; (b) identifying medical concepts that relate to mental disorders; and (c) accounting for the role of negation. The machine learning techniques rely on the assumptions that (1) the severity of a patient's positive valence symptoms exists on a latent continuous spectrum and (2) all the patient's answers and narratives documented in the psychological evaluation records are informed by the patient's latent severity score along this spectrum. These assumptions motivated our two-step machine learning framework for automatically recognizing psychological symptom severity. In the first step, the latent continuous severity score is inferred from each record; in the second step, the severity score is mapped to one of the four discrete severity levels used in the CEGS/N-GRID challenge. We evaluated three methods for inferring the latent severity score associated with each record: (i) pointwise ridge regression; (ii) pairwise comparison-based classification; and (iii) a hybrid approach combining pointwise regression and the pairwise classifier. The second step was implemented using a tree of cascading support vector machine (SVM) classifiers. While the official evaluation results indicate that all three methods are promising, the hybrid approach not only outperformed the pairwise and pointwise methods, but also produced the second highest performance of all submissions to the CEGS/N-GRID challenge with a normalized MAE score of 84.093% (where higher numbers indicate better performance). These evaluation results enabled us to observe that, for this task, considering pairwise information can produce more accurate severity scores than pointwise regression - an approach widely used in other systems for assigning severity scores. Moreover, our analysis indicates that using a cascading SVM tree outperforms traditional SVM classification methods for the purpose of determining discrete severity levels. (C) 2017 Published by Elsevier Inc.