1
|
Pinto-de-Sá R, Sousa-Pinto B, Costa-de-Oliveira S. Brave New World of Artificial Intelligence: Its Use in Antimicrobial Stewardship-A Systematic Review. Antibiotics (Basel) 2024; 13:307. [PMID: 38666983 PMCID: PMC11047419 DOI: 10.3390/antibiotics13040307] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/20/2024] [Revised: 03/24/2024] [Accepted: 03/25/2024] [Indexed: 04/29/2024] Open
Abstract
Antimicrobial resistance (AMR) is a growing public health problem in the One Health dimension. Artificial intelligence (AI) is emerging in healthcare, since it is helpful to deal with large amounts of data and as a prediction tool. This systematic review explores the use of AI in antimicrobial stewardship programs (ASPs) and summarizes the predictive performance of machine learning (ML) algorithms, compared with clinical decisions, in inpatients and outpatients who need antimicrobial prescriptions. This review includes eighteen observational studies from PubMed, Scopus, and Web of Science. The exclusion criteria comprised studies conducted only in vitro, not addressing infectious diseases, or not referencing the use of AI models as predictors. Data such as study type, year of publication, number of patients, study objective, ML algorithms used, features, and predictors were extracted from the included publications. All studies concluded that ML algorithms were useful to assist antimicrobial stewardship teams in multiple tasks such as identifying inappropriate prescribing practices, choosing the appropriate antibiotic therapy, or predicting AMR. The most extracted performance metric was AUC, which ranged from 0.64 to 0.992. Despite the risks and ethical concerns that AI raises, it can play a positive and promising role in ASP.
Collapse
Affiliation(s)
- Rafaela Pinto-de-Sá
- Division of Microbiology, Department of Pathology, Faculty of Medicine, University of Porto, Alameda Prof. Hernâni Monteiro, 4200-319 Porto, Portugal;
| | - Bernardo Sousa-Pinto
- Department of Community Medicine, Information and Health Decision Sciences, Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal;
- Center for Health Technology and Services Research—CINTESIS@RISE, Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal
| | - Sofia Costa-de-Oliveira
- Division of Microbiology, Department of Pathology, Faculty of Medicine, University of Porto, Alameda Prof. Hernâni Monteiro, 4200-319 Porto, Portugal;
- Center for Health Technology and Services Research—CINTESIS@RISE, Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal
| |
Collapse
|
2
|
Ramezani M, Takian A, Bakhtiari A, Rabiee HR, Ghazanfari S, Sazgarnejad S. Research agenda for using artificial intelligence in health governance: interpretive scoping review and framework. BioData Min 2023; 16:31. [PMID: 37904172 PMCID: PMC10617108 DOI: 10.1186/s13040-023-00346-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 10/07/2023] [Indexed: 11/01/2023] Open
Abstract
BACKGROUND The governance of health systems is complex in nature due to several intertwined and multi-dimensional factors contributing to it. Recent challenges of health systems reflect the need for innovative approaches that can minimize adverse consequences of policies. Hence, there is compelling evidence of a distinct outlook on the health ecosystem using artificial intelligence (AI). Therefore, this study aimed to investigate the roles of AI and its applications in health system governance through an interpretive scoping review of current evidence. METHOD This study intended to offer a research agenda and framework for the applications of AI in health systems governance. To include shreds of evidence with a greater focus on the application of AI in health governance from different perspectives, we searched the published literature from 2000 to 2023 through PubMed, Scopus, and Web of Science Databases. RESULTS Our findings showed that integrating AI capabilities into health systems governance has the potential to influence three cardinal dimensions of health. These include social determinants of health, elements of governance, and health system tasks and goals. AI paves the way for strengthening the health system's governance through various aspects, i.e., intelligence innovations, flexible boundaries, multidimensional analysis, new insights, and cognition modifications to the health ecosystem area. CONCLUSION AI is expected to be seen as a tool with new applications and capabilities, with the potential to change each component of governance in the health ecosystem, which can eventually help achieve health-related goals.
Collapse
Affiliation(s)
- Maryam Ramezani
- Department of Health Management, Policy and Economics, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran
- Health Equity Research Centre (HERC), Tehran University of Medical Sciences, Tehran, Iran
| | - Amirhossein Takian
- Department of Health Management, Policy and Economics, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran.
- Health Equity Research Centre (HERC), Tehran University of Medical Sciences, Tehran, Iran.
- Department of Global Health and Public Policy, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran.
| | - Ahad Bakhtiari
- Health Equity Research Centre (HERC), Tehran University of Medical Sciences, Tehran, Iran
| | - Hamid R Rabiee
- Department of Computer Engineering, Sharif University of Technology, Tehran, Iran
| | - Sadegh Ghazanfari
- Department of Health Management, Policy and Economics, School of Public Health, Tehran University of Medical Sciences, Tehran, Iran
| | - Saharnaz Sazgarnejad
- School of Public Health, Tehran University of Medical Sciences, Tehran, Iran
- School of Medicine, Tehran University of Medical Sciences, Tehran, Iran
| |
Collapse
|
3
|
Tran Quoc V, Nguyen Thi Ngoc D, Nguyen Hoang T, Vu Thi H, Tong Duc M, Do Pham Nguyet T, Nguyen Van T, Ho Ngoc D, Vu Son G, Bui Duc T. Predicting Antibiotic Resistance in ICUs Patients by Applying Machine Learning in Vietnam. Infect Drug Resist 2023; 16:5535-5546. [PMID: 37638070 PMCID: PMC10460201 DOI: 10.2147/idr.s415885] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2023] [Accepted: 08/16/2023] [Indexed: 08/29/2023] Open
Abstract
Introduction Artificial Intelligence (AI) and machine learning (ML) are used extensively in HICs to detect and control antibiotic resistance (AMR) in laboratories and clinical institutions. ML is designed to predict outcome variables using an algorithm to enable "machines" to learn the "rules" from the data. ML is increasingly being applied in intensive care units to identify AMR and to assist empiric antibiotic therapy. This study aimed to evaluate the performance of ML models for predicting AMR bacteria and resistance to antibiotics in two Vietnamese hospitals. Patients and Methods A cross-sectional study combined with retrospective was conducted from 1st January 2020 to 30th June 2022. Five models were developed to predict antibiotic resistance of bacterial infections of ICU patients. Two datasets were prepared to predict AMR bacteria and antibiotics with ML models. The performance of the prediction models was evaluated by various indicators (sensitivity, specificity, precision, accuracy, F1-score, PRC, AuROC, and NormMCC) to determine the optimal time point for data selection. Python version 3.8 was used for statistical analyses. Results The accuracy, F1-score, AuROC, and normMMC of LightGBM, XGBoost, and Random Forest models were higher than those of other models in both datasets. In both datasets 1 and 2, accuracy, F1-score, AuROC and normMCC of the XGBoost model were the highest among five models (from 0.890 to 1.000). Only Random Forest models had specificity scores higher than 0.850. High scores of sensitivity, accuracy, precision, F1-score, and normMCC indicated that the models were making accurate predictions for datasets 1 and 2. Conclusion XGBoost, LightGBM, and Random Forest were the best-performed machine learning models to predict antibiotic resistance of bacterial infections of ICUs patients using the patients' EMRs.
Collapse
Affiliation(s)
- Viet Tran Quoc
- Intensive Care Unit, Military Hospital 175, Ho Chi Minh City, Vietnam
| | - Dung Nguyen Thi Ngoc
- Department of Military Science and Training, Military Hospital 175, Ho Chi Minh City, Vietnam
- Hanoi University of Public Health, Hanoi, Vietnam
| | - Trung Nguyen Hoang
- Department of Military Hygiene, Vietnam Military Medical University, Hanoi, Vietnam
| | - Hoa Vu Thi
- Department of Military Hygiene, Vietnam Military Medical University, Hanoi, Vietnam
| | - Minh Tong Duc
- Department of Military Hygiene, Vietnam Military Medical University, Hanoi, Vietnam
| | - Thanh Do Pham Nguyet
- Department of Military Science and Training, Military Hospital 175, Ho Chi Minh City, Vietnam
| | - Thanh Nguyen Van
- Department of General Planning, Military Hospital 175, Ho Chi Minh City, Vietnam
| | - Diep Ho Ngoc
- Department of Military Science and Training, Military Hospital 175, Ho Chi Minh City, Vietnam
| | - Giang Vu Son
- Department of Personnel, Military Hospital 175, Ho Chi Minh City, Vietnam
| | - Thanh Bui Duc
- Institute of Trauma and Orthopedics, Military hospital 175, Ho Chi Minh City, Vietnam
| |
Collapse
|
4
|
Cai T, Anceschi U, Prata F, Collini L, Brugnolli A, Migno S, Rizzo M, Liguori G, Gallelli L, Wagenlehner FME, Johansen TEB, Montanari L, Palmieri A, Tascini C. Artificial Intelligence Can Guide Antibiotic Choice in Recurrent UTIs and Become an Important Aid to Improve Antimicrobial Stewardship. Antibiotics (Basel) 2023; 12:antibiotics12020375. [PMID: 36830285 PMCID: PMC9952599 DOI: 10.3390/antibiotics12020375] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2023] [Revised: 01/29/2023] [Accepted: 02/06/2023] [Indexed: 02/15/2023] Open
Abstract
BACKGROUND A correct approach to recurrent urinary tract infections (rUTIs) is an important pillar of antimicrobial stewardship. We aim to define an Artificial Neural Network (ANN) for predicting the clinical efficacy of the empiric antimicrobial treatment in women with rUTIs. METHODS We extracted clinical and microbiological data from 1043 women. We trained an ANN on 725 patients and validated it on 318. RESULTS The ANN showed a sensitivity of 87.8% and specificity of 97.3% in predicting the clinical efficacy of empirical therapy. The previous use of fluoroquinolones (HR = 4.23; p = 0.008) and cephalosporins (HR = 2.81; p = 0.003) as well as the presence of Escherichia coli with resistance against cotrimoxazole (HR = 3.54; p = 0.001) have been identified as the most important variables affecting the ANN output decision predicting the fluoroquinolones-based therapy failure. A previous isolation of Escherichia coli with resistance against fosfomycin (HR = 2.67; p = 0.001) and amoxicillin-clavulanic acid (HR = 1.94; p = 0.001) seems to be the most influential variable affecting the output decision predicting the cephalosporins- and cotrimoxazole-based therapy failure. The previously mentioned Escherichia coli with resistance against cotrimoxazole (HR = 2.35; p < 0.001) and amoxicillin-clavulanic acid (HR = 3.41; p = 0.007) seems to be the most influential variable affecting the output decision predicting the fosfomycin-based therapy failure. CONCLUSIONS ANNs seem to be an interesting tool to guide the antimicrobial choice in the management of rUTIs at the point of care.
Collapse
Affiliation(s)
- Tommaso Cai
- Department of Urology, Santa Chiara Regional Hospital, 38123 Trento, Italy
- Institute of Clinical Medicine, University of Oslo, 0315 Oslo, Norway
- Correspondence:
| | - Umberto Anceschi
- IRCCS “Regina Elena” National Cancer Institute, 00144 Rome, Italy
| | - Francesco Prata
- Department of Urology, Campus Bio-Medico University of Rome, 00128 Rome, Italy
| | - Lucia Collini
- Department of Microbiology, Santa Chiara Regional Hospital, 38123 Trento, Italy
| | - Anna Brugnolli
- Centre of Higher Education for Health Sciences, 38122 Trento, Italy
| | - Serena Migno
- Department of Gynecology and Obstetrics, Santa Chiara Regional Hospital, 38123 Trento, Italy
| | - Michele Rizzo
- Department of Urology, University of Trieste, 34127 Trieste, Italy
| | - Giovanni Liguori
- Department of Urology, University of Trieste, 34127 Trieste, Italy
| | - Luca Gallelli
- Department of Health Science, School of Medicine, University of Catanzaro, 88100 Catanzaro, Italy
| | - Florian M. E. Wagenlehner
- Clinic for Urology, Pediatric Urology and Andrology, Justus Liebig University, 35390 Giessen, Germany
| | - Truls E. Bjerklund Johansen
- Institute of Clinical Medicine, University of Oslo, 0315 Oslo, Norway
- Department of Urology, Oslo University Hospital, 0315 Oslo, Norway
- Institute of Clinical Medicine, University of Aarhus, 8000 Aarhus, Denmark
| | - Luca Montanari
- Department of Medicine (DAME), Infectious Diseases Clinic, University of Udine, 33100 Udine, Italy
| | - Alessandro Palmieri
- Department of Urology, University of Naples Federico II, 80138 Naples, Italy
| | - Carlo Tascini
- Department of Medicine (DAME), Infectious Diseases Clinic, University of Udine, 33100 Udine, Italy
| |
Collapse
|
5
|
Amin D, Garzón-Orjuela N, Garcia Pereira A, Parveen S, Vornhagen H, Vellinga A. Artificial intelligence to improve antimicrobial prescribing: A protocol for a systematic review. HRB Open Res 2022. [DOI: 10.12688/hrbopenres.13582.1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022] Open
Abstract
Introduction: The inappropriate use of antimicrobials is a threat to their effectiveness and often results in antimicrobial resistance (AMR) and difficult to treat infections. Different methods have been implemented to control AMR, and in recent years, artificial intelligence (AI) has been used to improve antimicrobial prescribing. However, there is insufficient information about the contribution of AI in improving antimicrobial prescribing. This systematic review aims to determine whether the use of AI can improve antimicrobial prescribing for human patients. Methods: Observational studies that examine the potential or actual use of AI in improving antimicrobial prescribing cited in IEEE Xplore, ScienceDirect, Scopus, Web of Science, OVID, EMBASE and ACM will be included in this systematic review. There will be no restriction on language, nor the setting (i.e.: primary care or hospital) nor the time when the studies included were conducted. The primary outcome of this systematic review is the relative reduction in prescribed antimicrobials, while the secondary outcome is the relative reduction in patients’ consultations, whether for infection recurrence or worsening of symptoms. Data will be meta-analyzed with a Random Effects Model. The I2 statistic for heterogeneity will be calculated and the Newcastle Ottawa Scale Tool will be used to assess risk of bias. Dissemination: The results will be disseminated through a peer-reviewed publication and scientific sessions. PROSPERO Registration: This protocol has been registered in PROSPERO online database (CRD42022329049; 14 May 2022).
Collapse
|
6
|
Iskandar K, Molinier L, Hallit S, Sartelli M, Hardcastle TC, Haque M, Lugova H, Dhingra S, Sharma P, Islam S, Mohammed I, Naina Mohamed I, Hanna PA, Hajj SE, Jamaluddin NAH, Salameh P, Roques C. Surveillance of antimicrobial resistance in low- and middle-income countries: a scattered picture. Antimicrob Resist Infect Control 2021; 10:63. [PMID: 33789754 PMCID: PMC8011122 DOI: 10.1186/s13756-021-00931-w] [Citation(s) in RCA: 113] [Impact Index Per Article: 37.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2020] [Accepted: 03/22/2021] [Indexed: 01/07/2023] Open
Abstract
Data on comprehensive population-based surveillance of antimicrobial resistance is lacking. In low- and middle-income countries, the challenges are high due to weak laboratory capacity, poor health systems governance, lack of health information systems, and limited resources. Developing countries struggle with political and social dilemma, and bear a high health and economic burden of communicable diseases. Available data are fragmented and lack representativeness which limits their use to advice health policy makers and orientate the efficient allocation of funding and financial resources on programs to mitigate resistance. Low-quality data means soaring rates of antimicrobial resistance and the inability to track and map the spread of resistance, detect early outbreaks, and set national health policy to tackle resistance. Here, we review the barriers and limitations of conducting effective antimicrobial resistance surveillance, and we highlight multiple incremental approaches that may offer opportunities to strengthen population-based surveillance if tailored to the context of each country.
Collapse
Affiliation(s)
- Katia Iskandar
- Department of Mathématiques Informatique et Télécommunications, Université Toulouse III, Paul Sabatier, INSERM, UMR 1027, 31000, Toulouse, France.
- INSPECT-LB, Institut National de Santé Publique, d'Épidémiologie Clinique et de Toxicologie-Liban, Beirut, 6573-14, Lebanon.
- Faculty of Pharmacy, Lebanese University, Mount Lebanon, Lebanon.
| | - Laurent Molinier
- Faculté de Médecine, Equipe constitutive du CERPOP, UMR1295, unité mixte INSERM, Université Paul Sabatier Toulouse III, 31000, Toulouse, France
| | - Souheil Hallit
- INSPECT-LB, Institut National de Santé Publique, d'Épidémiologie Clinique et de Toxicologie-Liban, Beirut, 6573-14, Lebanon
- Faculty of Medicine and Medical Sciences, Holy Spirit University of Kaslik (USEK), Jounieh, Lebanon
| | - Massimo Sartelli
- Department of Surgery, University of Macerata, 62100, Macerata, Italy
| | - Timothy Craig Hardcastle
- Department of Trauma Service, Inkosi Albert Luthuli Central Hospital, Durban, 4091, South Africa
- Department of Surgery, Nelson Mandela School of Clinical Medicine, University of KwaZulu-Natal, Congela, 4041, Durban, South Africa
| | - Mainul Haque
- Unit of Pharmacology, Faculty of Medicine and Defence Health, Universiti Pertahanan Nasional Malaysia (National Defence University of Malaysia), Kem Perdana Sungai Besi, 57000, Malaysia
| | - Halyna Lugova
- Faculty of Medicine and Defence Health, National Defence University of Malaysia, 57000, Kuala Lumpur, Malaysia
| | - Sameer Dhingra
- Department of Pharmacy Practice, National Institute of Pharmaceutical Education and Research (NIPER) Hajipur, Bihar, India
| | - Paras Sharma
- Department of Pharmacognosy, BVM College of Pharmacy, Gwalior, India
| | - Salequl Islam
- Department of Microbiology, Jahangirnagar University, Savar, Dhaka-1342, Bangladesh
| | - Irfan Mohammed
- Department of Restorative Dentistry, Federal University of Pelotas School of Dentistry, Pelotas, RS, 96020-010, Brazil
| | - Isa Naina Mohamed
- Pharmacoepidemiology and Drug Safety Unit, Pharmacology Department, Medical Faculty, Universiti Kebangsaan Malaysia, Jalan Yaacob Latif, Kuala Lumpur, Malaysia
| | - Pierre Abi Hanna
- Faculty of Pharmacy, Lebanese University, Mount Lebanon, Lebanon
| | - Said El Hajj
- Department of Medicine, Lebanese University, Beirut, Lebanon
| | - Nurul Adilla Hayat Jamaluddin
- Pharmacoepidemiology and Drug Safety Unit, Pharmacology Department, Medical Faculty, Universiti Kebangsaan Malaysia, Jalan Yaacob Latif, Kuala Lumpur, Malaysia
| | - Pascale Salameh
- INSPECT-LB, Institut National de Santé Publique, d'Épidémiologie Clinique et de Toxicologie-Liban, Beirut, 6573-14, Lebanon
- Department of Medicine, Lebanese University, Beirut, Lebanon
- Faculty of Medicine, University of Nicosia, Nicosia, Cyprus
| | - Christine Roques
- Department of Bactériologie-Hygiène, Centre Hospitalier Universitaire, Hôpital Purpan, 31330, Toulouse, France
- Department of Bioprocédés et Systèmes Microbiens, Laboratoire de Génie Chimique, Université Paul Sabatier Toulouse III, UMR 5503, 31330, Toulouse, France
| |
Collapse
|
7
|
Vandenberg O, Martiny D, Rochas O, van Belkum A, Kozlakidis Z. Considerations for diagnostic COVID-19 tests. Nat Rev Microbiol 2021; 19:171-183. [PMID: 33057203 PMCID: PMC7556561 DOI: 10.1038/s41579-020-00461-z] [Citation(s) in RCA: 438] [Impact Index Per Article: 146.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 09/17/2020] [Indexed: 02/07/2023]
Abstract
During the early phase of the coronavirus disease 2019 (COVID-19) pandemic, design, development, validation, verification and implementation of diagnostic tests were actively addressed by a large number of diagnostic test manufacturers. Hundreds of molecular tests and immunoassays were rapidly developed, albeit many still await clinical validation and formal approval. In this Review, we summarize the crucial role of diagnostic tests during the first global wave of COVID-19. We explore the technical and implementation problems encountered during this early phase in the pandemic, and try to define future directions for the progressive and better use of (syndromic) diagnostics during a possible resurgence of COVID-19 in future global waves or regional outbreaks. Continuous global improvement in diagnostic test preparedness is essential for more rapid detection of patients, possibly at the point of care, and for optimized prevention and treatment, in both industrialized countries and low-resource settings.
Collapse
Affiliation(s)
- Olivier Vandenberg
- Innovation and Business Development Unit, Laboratoire Hospitalier Universtaire de Bruxelles - Universitair Laboratorium Brussel, Université Libre de Bruxelles, Brussels, Belgium.
- Center for Environmental Health and Occupational Health, School of Public Health, Université Libre de Bruxelles, Brussels, Belgium.
- Division of Infection and Immunity, Faculty of Medical Sciences, University College London, London, UK.
| | - Delphine Martiny
- Department of Microbiology, Laboratoire Hospitalier Universtaire de Bruxelles - Universitair Laboratorium Brussel, Université Libre de Bruxelles, Brussels, Belgium
| | - Olivier Rochas
- Strategic Intelligence, Corporate Business Development, bioMérieux, Chemin de L'Orme, France
| | - Alex van Belkum
- Open Innovation and Partnerships, bioMérieux, La Balme Les Grottes, France.
| | - Zisis Kozlakidis
- Laboratory Services and Biobank Group, International Agency for Research on Cancer, World Health Organization, Lyon, France
| |
Collapse
|
8
|
Lv J, Deng S, Zhang L. A review of artificial intelligence applications for antimicrobial resistance. BIOSAFETY AND HEALTH 2021. [DOI: 10.1016/j.bsheal.2020.08.003] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/20/2022] Open
|
9
|
PARGT: a software tool for predicting antimicrobial resistance in bacteria. Sci Rep 2020; 10:11033. [PMID: 32620856 PMCID: PMC7335159 DOI: 10.1038/s41598-020-67949-9] [Citation(s) in RCA: 14] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2020] [Accepted: 06/16/2020] [Indexed: 11/08/2022] Open
Abstract
With the ever-increasing availability of whole-genome sequences, machine-learning approaches can be used as an alternative to traditional alignment-based methods for identifying new antimicrobial-resistance genes. Such approaches are especially helpful when pathogens cannot be cultured in the lab. In previous work, we proposed a game-theory-based feature evaluation algorithm. When using the protein characteristics identified by this algorithm, called ‘features’ in machine learning, our model accurately identified antimicrobial resistance (AMR) genes in Gram-negative bacteria. Here we extend our study to Gram-positive bacteria showing that coupling game-theory-identified features with machine learning achieved classification accuracies between 87% and 90% for genes encoding resistance to the antibiotics bacitracin and vancomycin. Importantly, we present a standalone software tool that implements the game-theory algorithm and machine-learning model used in these studies.
Collapse
|