Med Data Quest, Inc., 505 Coast Blvd S Ste 300, La Jolla, CA 92037, United States.
Department of Electrical and Computer Engineering, UCSD, 9500 Gilman Drive, La Jolla, CA 92093, United States.
J Biomed Inform. 2017 Nov;75S:S105-S111. doi: 10.1016/j.jbi.2017.05.015. Epub 2017 May 22.
In this paper, we present our system as submitted in the CEGS N-GRID 2016 task 2 RDoC classification competition. The task was to determine symptom severity (0-3) in a domain for a patient based on the text provided in his/her initial psychiatric evaluation. We first preprocessed the psychiatry notes into a semi-structured questionnaire and transformed the short answers into either numerical, binary, or categorical features. We further trained weak Support Vector Regressors (SVR) for each verbose answer and combined regressors' output with other features to feed into the final gradient tree boosting classifier with resampling of individual notes. Our best submission achieved a macro-averaged Mean Absolute Error of 0.439, which translates to a normalized score of 81.75%.
在本文中，我们展示了我们在 CEGS N-GRID 2016 任务 2 RDoC 分类竞赛中提交的系统。该任务是根据患者初始精神评估中提供的文本，确定其在某个领域的症状严重程度（0-3）。我们首先将精神病学笔记预处理为半结构化问卷，并将简短的答案转换为数字、二进制或分类特征。我们进一步为每个冗长的答案训练了弱支持向量回归器（SVR），并将回归器的输出与其他特征结合起来，输入到最终的梯度树提升分类器中，并对各个笔记进行重采样。我们的最佳提交结果的宏观平均绝对误差为 0.439，这相当于归一化分数为 81.75%。
