發(fā)布時(shí)間：2018-06-22 18:40

  本文選題：數(shù)據(jù)挖掘 + 隱含狄利克雷分布�。� 參考：《計(jì)算機(jī)應(yīng)用》2017年S1期

【摘要】：當(dāng)前對(duì)中醫(yī)學(xué)的懷疑關(guān)鍵在于其缺少科學(xué)數(shù)據(jù)的支撐,因此,把中醫(yī)診療的過(guò)程數(shù)據(jù)化十分重要。針對(duì)該問(wèn)題提出一種數(shù)據(jù)驅(qū)動(dòng)的中醫(yī)診療方法,基于對(duì)醫(yī)案中病癥和對(duì)應(yīng)處方的隱語(yǔ)義分析,找出隱含病機(jī),發(fā)現(xiàn)隱含病機(jī)與病癥和藥物間存在的關(guān)系,建立了一個(gè)基于傳統(tǒng)中醫(yī)醫(yī)案挖掘的多內(nèi)容隱含狄利克雷分布(LDA)模型�；谀Ｐ偷慕Y(jié)果,提出根據(jù)癥狀推薦藥物的算法,并且建立了基于隱語(yǔ)義模型的中醫(yī)在線輔助診療系統(tǒng)。通過(guò)實(shí)驗(yàn)評(píng)估推薦算法的有效性,在精度、召回率方面均好于基線方法。中醫(yī)在線輔助診療系統(tǒng)能提供數(shù)據(jù)驅(qū)動(dòng)的診療結(jié)果輔助中醫(yī)師診療,幫助中醫(yī)更準(zhǔn)確、全面、智能地制定科學(xué)的治療方案。
[Abstract]:At present, the key to the doubt of TCM lies in its lack of scientific data, so it is very important to digitize the process of TCM diagnosis and treatment. To solve this problem, a data-driven method of TCM diagnosis and treatment was proposed. Based on the implicit semantic analysis of symptoms and corresponding prescriptions in medical records, the underlying pathogenesis was found, and the relationship between hidden pathogenesis and symptoms and drugs was found. A multi-content implicit Delikley distribution (LDA) model based on traditional Chinese medicine case mining is established. Based on the results of the model, an algorithm for recommending drugs according to symptoms is proposed, and an online Chinese medicine diagnosis and treatment system based on implicit semantic model is established. The effectiveness of the recommendation algorithm is evaluated experimentally, and the accuracy and recall rate are better than the baseline method. Chinese medicine online assistant diagnosis and treatment system can provide data-driven diagnosis and treatment results to assist traditional Chinese medicine doctors to make more accurate, comprehensive and intelligent scientific treatment plan.
，

本文編號(hào)：2053816