딥러닝 기반 항생제 내성균 감염 예측 = Antibiotics-Resistant Bacteria Infection Prediction Based on Deep Learning

다국어 초록 (Multilingual Abstract)

The World Health Organization (WHO) and other government agencies aroundthe world have warned against antibiotic-resistant bacteria due to abuse of antibiotics and are strengthening their care and monitoring to prevent infection. However, it is highly necessary to develop an expeditious and accurate prediction and estimating method for preemptive measures. Because it takes several days to cultivate the infecting bacteria to identify the infection, quarantine and contact are not effective to prevent spread of infection. In this study, the disease diagnosis and antibiotic prescriptions included in Electronic Health Records were embedded through neural embedding model and matrix factorization, and deep learning based classification predictive model was proposed. The f1-score of the deep learning model increased from 0.525 to 0.617when embedding information on disease and antibiotics, whichare the main causes of antibiotic resistance, added to the patient’s basic information and hospital use information. And deep learning model outperformed the traditional machine hospital use information. And deep learning model outperformed the traditional machine learning models.As a result of analyzing the characteristics of antibiotic resistant patients, resistant patients were more likely to use antibiotics in J01 than nonresistant patients who were diagnosed with the same diseases and were prescribed 6.3 times more than DDD.

국문 초록 (Abstract)

세계보건기구(WHO)를 비롯해 세계 각국의 정부기관은 항생제 오남용에 따른 항생제 내성균 감염에 대해 심각하게 경고하며 이를 예방하기 위한 관리와 감시를 강화하고 있다. 하지만 감염을 확인하기 위한 감염균 배양에 수일의 시간이 소요되면서 격리와 접촉주의를 통한 감염 확산 방지 효과가 떨어져 선제적 조치를 위한 신속하고 정확한 예측 및 추정방법이 요구되고 있다. 본 연구는 Electronic Health Records에 포함된 질병 진단내역과 항생제 처방내역을 neural embedding model과 matrix factorization을 통해 embedding 하였고, 이를 활용한 딥러닝 기반 분류 예측 모형을 제안하였다. 항생제 내성균 감염의 주요 원인인 질병과 항생제 정보를 embedding 하여 환자의 기본정보와 병원이용 정보에 추가했을 때 딥러닝 예측 모형의 f1-score는 0.525에서 0.617로 상승하였고, 딥러닝 모형은 Super Learner와 같은 기존 기계학습 모형보다 더 나은 성능을 보여주었다. 항생제 내성균 감염환자의 특성을 분석한 결과, 감염환자는 동일한 질병을진단받은 비감염환자에 비교해 J01 계열 항생제 사용이 많았고 WHO 권고기준(DDD)을 크게 벗어나는 오남용 청구사례가 6.3배 이상 높게 나타났으며 항생제 오남용과 항생제 내성균 감염 간의 높은 연관성이 발견되었다.

참고문헌 (Reference)

1 송재훈, "항생제 내성의 국내 현황 및 대책" 대한내과학회 77 (77): 143-151, 2009

2 김록영, "입원 환자 표본 개발에 관한 연구: 국민건강보험 청구자료를 중심으로" 한국보건행정학회 23 (23): 152-161, 2013

3 박선희, "의료기관에서의 다제내성균 관리" 대한의사협회 61 (61): 26-35, 2018

4 노준호, "워드넷 기반 특징 추상화를 통한 웹문서 자동분류시스템의 성능향상" 한국전자거래학회 18 (18): 95-110, 2013

5 최재원, "개인화 추천시스템의 사용자 평가에 대한 통합적 접근 : 시스템 성과와 사용자 태도를 기반으로" 한국전자거래학회 17 (17): 85-103, 2012

6 Kim, Y. H., "The Forecast of Future Technology Based on Deep Learning" 219-220, 2015

7 Polley, E. C., "Super Learner in Prediction" U.C. Berkeley Division of Biostatistics 1-19, 2010

8 Van der Laan, M. J., "Super Learner" 6 (6): 2007

9 Omlin, C. W., "Stable Encoding of Large Finite-State Automata in Recurrent Neural Networks with Sigmoid Discriminants" 8 (8): 675-696, 1996

10 Rajkomar, A., "Scalable and accurate deep learning with electronic health records" 1 (1): 18-, 2018

11 Xu, X., "Review of classical dimensionality reduction and sample selection methods for large-scale data processing" 328 : 5-15, 2019

12 Moradigaravand, D., "Prediction of antibiotic resistance in Escherichia coli from large-scale pan-genome data" 14 (14): 1-17, 2018

13 Gao, X. W., "Prediction of Multidrug-Resistant TB from CT Pulmonary Images Based on Deep Learning Techniques" 15 (15): 4326-4335, 2018

14 Martinez, J. L., "Predicting antibiotic resistance" 5 (5): 958-956, 2007

15 Socher, R., "Parsing Natural Scenes and Natural Language with Recursive Neural Networks" Omnipress 129-136, 2011

16 Levy, O., "Neural Word Embedding As Implicit Matrix Factorization" MIT Press 2 : 2177-2185, 2014

17 Jensen, P. B., "Mining electronic health records: towards better research applications and clinical care" 13 (13): 395-, 2012

18 Zhang, M., "Matrix Factorization meets Social Network Embedding for Rating Prediction" Springer 121-129, 2018

19 Koren, Y., "Matrix Factorization Techniques for Recommender Systems" 42 (42): 30-37, 2009

20 Fonarev, A., "Matrix Factorization Methods For Training Embeddings"

21 Ho, J. C., "Marble:High-throughput Phenotyping from Electronic Health Records via Sparse Nonnegative Tensor Factorization" ACM 115-124, 2014

22 Yang, Y., "Machine learning for healthcare technologies" IET 203-226, 2016

23 Ho, J. C., "Limestone: High-throughput candidate phenotype generation via tensor factorization" 52 : 199-211, 2014

24 Dumais, S. T., "Latent semantic analysis" 38 (38): 188-230, 2004

25 A Medium Corporation, "I’ll tell you why Deep Learning is so popular and in demand"

26 Gamallo, P., "Is Singular Value Decomposition Useful for Word Similarity Extraction?" 45 (45): 95-119, 2011

27 Krizhevsky, A., "ImageNet Classification with Deep Convolutional Neural Networks" Curran Associates Inc 1 : 1097-1105, 2012

28 Liang, D., "Factorization Meets the Item Embedding: Regularizing Matrix Factorization with Item Co-occurrence" ACM 59-66, 2016

29 Bullinaria, J. A., "Extracting semantic representations from word co-occurrence statistics: stop-lists, stemming, and SVD" 44 (44): 890-907, 2012

30 Mikolov, T., "Distributed Representations of Words and Phrases and Their Compositionality" Curran Associates Inc 2 : 3111-3119, 2013

31 Arango-Argoty, G., "DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data" 6 (6): 23-, 2018

32 Young, S., "Deep super learner: A deep ensemble for classification problems" 84-95, 2018

33 Chen, M. L., "Deep Learning Predicts Tuberculosis Drug Resistance Status from Whole-Genome Sequencing Data"

34 Xiang, T., "Computational Phenotyping of Two-Person Interactions Reveals Differential Neural Response to Depth-of-Thought" 8 (8): e1002841-, 2012

35 Chung, J., "Combination therapy with polymyxin B and netropsin against clinical isolates of multidrug-resistant Acinetobacter baumannii" 6 : 28168-, 2016

36 Purushotham, S., "Benchmark of Deep Learning Models on Large Healthcare MIMIC Datasets"

37 Mcadam, A. J., "Antibiotic Resistance:How Serious Is the Problem, and What Can Be Done?" 58 (58): 1182-1186, 2012

38 Santos, R. P., "Active Surveillance Cultures and Contact Precautions for Control of Multidrug-Resistant Organisms-Ethical Considerations" 47 (47): 110-116, 2008