Applying Machine Learning Techniques to the Audit of Antimicrobial Prophylaxis

被引:4
|
作者
Shi, Zhi-Yuan [1 ,2 ,3 ]
Hon, Jau-Shin [1 ]
Cheng, Chen-Yang [4 ]
Chiang, Hsiu-Tzy [5 ]
Huang, Hui-Mei [6 ]
机构
[1] Tunghai Univ, Dept Ind Engn & Enterprise Informat, Taichung 407, Taiwan
[2] Taichung Vet Gen Hosp, Infect Control Ctr, Taichung 407, Taiwan
[3] Natl Yang Ming Chiao Tung Univ, Sch Med, Taipei 106, Taiwan
[4] Natl Taipei Univ Technol, Dept Ind Engn & Management, Taipei 106, Taiwan
[5] Mackay Mem Hosp, Infect Control Ctr, Taipei 10449, Taiwan
[6] Taichung Vet Gen Hosp, Dept Nursing, Taichung 407, Taiwan
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 05期
关键词
antimicrobial prophylaxis; machine learning; Auto-WEKA; multilayer perceptron; decision tree; bagging; SMOTE; SURGICAL SITE INFECTION;
D O I
10.3390/app12052586
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
High rates of inappropriate use of surgical antimicrobial prophylaxis were reported in many countries. Auditing the prophylactic antimicrobial use in enormous medical records by manual review is labor-intensive and time-consuming. The purpose of this study is to develop accurate and efficient machine learning models for auditing appropriate surgical antimicrobial prophylaxis. The supervised machine learning classifiers (Auto-WEKA, multilayer perceptron, decision tree, SimpleLogistic, Bagging, and AdaBoost) were applied to an antimicrobial prophylaxis dataset, which contained 601 instances with 26 attributes. Multilayer perceptron, SimpleLogistic selected by Auto-WEKA, and decision tree algorithms had outstanding discrimination with weighted average AUC > 0.97. The Bagging and SMOTE algorithms could improve the predictive performance of decision tree against imbalanced datasets. Although with better performance measures, multilayer perceptron and Auto-WEKA took more execution time as compared with that of other algorithms. Multilayer perceptron, SimpleLogistic, and decision tree algorithms have outstanding performance measures for identifying the appropriateness of surgical prophylaxis. The efficient models developed by machine learning can be used to assist the antimicrobial stewardship team in the audit of surgical antimicrobial prophylaxis. In future research, we still have the challenges and opportunities of enriching our datasets with more useful clinical information to improve the performance of the algorithms.
引用
收藏
页数:17
相关论文
共 50 条
  • [1] Applying Machine Learning Techniques for Environmental Reporting
    Kotsiantis, S.
    Kanellopoulos, D.
    [J]. NCM 2008 : 4TH INTERNATIONAL CONFERENCE ON NETWORKED COMPUTING AND ADVANCED INFORMATION MANAGEMENT, VOL 1, PROCEEDINGS, 2008, : 217 - 223
  • [2] Intrusion detection applying machine learning to Solaris audit data
    Endler, D
    [J]. 14TH ANNUAL COMPUTER SECURITY APPLICATIONS CONFERENCE, PROCEEDINGS, 1998, : 268 - 279
  • [3] Audit of quality of perioperative antimicrobial prophylaxis
    Salih Hosoglu
    Selda Aslan
    Serife Akalin
    Vuslat Bosnak
    [J]. Pharmacy World & Science, 2009, 31 : 14 - 17
  • [4] On applying machine learning techniques for design pattern detection
    Zanoni, Marco
    Fontana, Francesca Arcelli
    Stella, Fabio
    [J]. JOURNAL OF SYSTEMS AND SOFTWARE, 2015, 103 : 102 - 117
  • [5] Applying machine learning techniques to automating XML markup
    Akhtar, S
    Reilly, RG
    Dunnion, J
    [J]. MLMTA'03: INTERNATIONAL CONFERENCE ON MACHINE LEARNING; MODELS, TECHNOLOGIES AND APPLICATIONS, 2003, : 56 - 61
  • [6] Applying Machine Learning Techniques to Identify Damaged Potatoes
    Osipov, Aleksey
    Filimonov, Andrey
    Suvorov, Stanislav
    [J]. ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING (ICAISC 2021), PT I, 2021, 12854 : 193 - 201
  • [7] Audit of quality of perioperative antimicrobial prophylaxis
    Hosoglu, Salih
    Aslan, Selda
    Akalin, Serife
    Bosnak, Vuslat
    [J]. PHARMACY WORLD & SCIENCE, 2009, 31 (01): : 14 - 17
  • [8] Applying Machine Learning Techniques for Email Reply Prediction
    Ayodele, Taiwo
    Zhou, Shikun
    Khusainov, Rinat
    [J]. WORLD CONGRESS ON ENGINEERING 2009, VOLS I AND II, 2009, : 31 - 36
  • [9] AUDIT OF ANTIMICROBIAL PROPHYLAXIS ON A UROLOGICAL WARD
    HEKSTER, YA
    BOEREMA, JBJ
    [J]. PHARMACEUTISCH WEEKBLAD-SCIENTIFIC EDITION, 1984, 6 (06) : 273 - 273
  • [10] Applying Machine Learning Techniques for Speech Emotion Recognition
    Tarunika, K.
    Pradeeba, R. B.
    Aruna, P.
    [J]. 2018 9TH INTERNATIONAL CONFERENCE ON COMPUTING, COMMUNICATION AND NETWORKING TECHNOLOGIES (ICCCNT), 2018,