The detection of hospitalized patients at risk of testing positive to multi-drug resistant bacteria using MOCA-I, a rule-based "white-box" classification algorithm for medical data.
Data mining
Drug resistance
Electronic health records
Infection control
Information systems
Multiple
Supervised machine learning
Journal
International journal of medical informatics
ISSN: 1872-8243
Titre abrégé: Int J Med Inform
Pays: Ireland
ID NLM: 9711057
Informations de publication
Date de publication:
10 2020
10 2020
Historique:
received:
31
01
2020
revised:
19
07
2020
accepted:
25
07
2020
pubmed:
28
8
2020
medline:
22
12
2020
entrez:
28
8
2020
Statut:
ppublish
Résumé
Multi-drug resistant (MDR) bacteria are a major health concern. In this retrospective study, a rule-based classification algorithm, MOCA-I (Multi-Objective Classification Algorithm for Imbalanced data) is used to identify hospitalized patients at risk of testing positive for multidrug-resistant (MDR) bacteria, including Methicillin-resistant Staphylococcus aureus (MRSA), before or during their stay. Applied to a data set of 48,945 hospital stays (including known cases of carriage) with up to 16,325 attributes per stay, MOCA-I generated alert rules for risk of carriage or infection. A risk score was then computed from each stay according to the triggered rules.Recall and precision curves were plotted. The classification can be focused on specifically detecting high risk of having a positive test, or identifying large numbers of at-risk patients by modulating the risk score cut-off level. For a risk score above 0.85,recall (sensitivity) is 62 % with 69 % precision (confidence) for MDR bacteria, recall is 58 % with 88 % precision for MRSA. In addition, MOCA-I identifies 38 and 21 cases of previously unknown MDR and MRSA respectively. MOCA-I generates medically pertinent alert rules. This classification algorithm can be used to detect patients with high risk of testing positive to MDR bacteria (including MRSA). Classification can be modulated by appropriately setting the risk score cut-off level to favor specific detection of small numbers of patients at very high risk or identification of large numbers of patients at risk. MOCA-I can thus contribute to more adapted treatments and preventive measures from admission, depending on the clinical setting or management strategy.
Sections du résumé
BACKGROUND
Multi-drug resistant (MDR) bacteria are a major health concern. In this retrospective study, a rule-based classification algorithm, MOCA-I (Multi-Objective Classification Algorithm for Imbalanced data) is used to identify hospitalized patients at risk of testing positive for multidrug-resistant (MDR) bacteria, including Methicillin-resistant Staphylococcus aureus (MRSA), before or during their stay.
METHODS
Applied to a data set of 48,945 hospital stays (including known cases of carriage) with up to 16,325 attributes per stay, MOCA-I generated alert rules for risk of carriage or infection. A risk score was then computed from each stay according to the triggered rules.Recall and precision curves were plotted.
RESULTS
The classification can be focused on specifically detecting high risk of having a positive test, or identifying large numbers of at-risk patients by modulating the risk score cut-off level. For a risk score above 0.85,recall (sensitivity) is 62 % with 69 % precision (confidence) for MDR bacteria, recall is 58 % with 88 % precision for MRSA. In addition, MOCA-I identifies 38 and 21 cases of previously unknown MDR and MRSA respectively.
CONCLUSIONS
MOCA-I generates medically pertinent alert rules. This classification algorithm can be used to detect patients with high risk of testing positive to MDR bacteria (including MRSA). Classification can be modulated by appropriately setting the risk score cut-off level to favor specific detection of small numbers of patients at very high risk or identification of large numbers of patients at risk. MOCA-I can thus contribute to more adapted treatments and preventive measures from admission, depending on the clinical setting or management strategy.
Identifiants
pubmed: 32853975
pii: S1386-5056(20)30146-5
doi: 10.1016/j.ijmedinf.2020.104242
pii:
doi:
Substances chimiques
Anti-Bacterial Agents
0
Pharmaceutical Preparations
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
104242Informations de copyright
Copyright © 2020 Elsevier B.V. All rights reserved.