ARTIFICIAL INTELLIGENCE–AUGMENTED DIAGNOSTICS IN CLINICAL MICROBIOLOGY: A SYSTEMATIC REVIEW AND META-ANALYSIS OF DIAGNOSTIC ACCURACY, WORKFLOW EFFICIENCY, AND ANTIMICROBIAL RESISTANCE PREDICTION
Main Article Content
Keywords
Artificial intelligence, machine learning, deep learning, clinical microbiology, diagnostic accuracy, meta-analysis, malaria detection, tuberculosis screening, MALDI-TOF mass spectrometry, antimicrobial resistance prediction, whole-genome sequencing.
Abstract
Background: Artificial intelligence (AI) has rapidly advanced diagnostic capabilities in clinical microbiology, particularly in microscopy-based pathogen detection, automated culture interpretation, mass spectrometry classification, and genomic antimicrobial resistance (AMR) prediction. However, pooled diagnostic accuracy and translational impact across microbiology domains remain incompletely characterized.
Objective: To systematically evaluate the diagnostic performance, workflow impact, and antimicrobial resistance prediction accuracy of AI systems in clinical microbiology through structured meta-analysis.
Methods: This systematic review and meta-analysis was conducted according to PRISMA 2020 guidelines and prospectively registered in PROSPERO (CRD420251123494). A comprehensive search of PubMed/MEDLINE, Scopus, Web of Science, and Embase identified studies published between January 2015 and November 2025. Inclusion criteria required peer-reviewed human clinical studies evaluating AI-based diagnostic systems with reported sensitivity, specificity, AUROC, or genotype–phenotype concordance against recognized reference standards. Two independent reviewers performed study selection and data extraction. Risk of bias was assessed using QUADAS-2. A bivariate random-effects model estimated pooled sensitivity and specificity. Hierarchical summary receiver operating characteristic (HSROC) curves were constructed, and heterogeneity was assessed using Cochran’s Q and I² statistics. Subgroup analyses were performed for malaria microscopy AI, tuberculosis (TB) chest radiograph AI, MALDI-TOF machine learning classification, and genomic AMR prediction models.
Results: From 426 identified records, 58 studies were included in qualitative synthesis and 42 in quantitative meta-analysis. Pooled sensitivity was 93.4% (95% CI: 91.2–95.1%) and pooled specificity was 92.1% (95% CI: 89.8–94.0%) . Overall AUROC was 0.94 (95% CI: 0.92–0.96), indicating strong discriminative performance. The SROC curve demonstrated minimal threshold effect. Subgroup AUCs were: malaria AI 0.96; TB AI 0.93; MALDI ML 0.91; genomic AMR AI 0.92. Between-study heterogeneity was substantial (I² sensitivity 71%; specificity 68%), primarily attributable to dataset variability, imaging platform differences, and limited external validation. No single study disproportionately influenced pooled estimates. Workflow automation studies consistently reported reduced turnaround times and enhanced antimicrobial stewardship integration.
Conclusion: AI-augmented diagnostics demonstrate high pooled accuracy across major clinical microbiology domains, with overall AUROC comparable to experienced subspecialist interpretation. Despite promising performance, substantial heterogeneity and limited prospective multicenter validation constrain generalizability. Structured validation frameworks, regulatory alignment, and real-world implementation studies are essential to transition AI systems from investigational tools to standardized components of clinical microbiology practice.
References
2. Quinn JA, Nakasi R, Mugagga PKB, Byanyima P, Lubega W, Andama A. Deep convolutional neural networks for microscopy-based point of care diagnostics. NPJ Digit Med. 2018;1:30.
3. Rajaraman S, Jaeger S, Antani SK. Performance evaluation of deep neural ensembles toward malaria parasite detection in thin-blood smear images. PLoS One. 2018;13(12):e0209306.
4. Yang F, Poostchi M, Yu H, Zhou Z, Silamut K, Yu J, et al. Deep learning for smartphone-based malaria parasite detection in thin blood smears. Sci Rep. 2019;9:3294.
5. Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88.
6. Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115–118.
7. Lakhani P, Sundaram B. Deep learning at chest radiography: automated classification of pulmonary tuberculosis. Sci Rep. 2017;7:4130.
8. Hwang EJ, Park S, Jin KN, Kim JI, Choi SY, Lee JH, et al. Development and validation of a deep learning–based automated detection algorithm for major thoracic diseases on chest radiographs. Radiology. 2019;290(1):218–228.
9. De Fauw J, Ledsam JR, Romera-Paredes B, Nikolov S, Tomasev N, Blackwell S, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat Med. 2018;24(9):1342–1350.
10. Angermueller C, Pärnamaa T, Parts L, Stegle O. Deep learning for computational biology. Mol Syst Biol. 2016;12(7):878.
11. Sambyal V, Saini S, Sood A. Deep learning-based approach for bacterial classification in microscopic images. Front Microbiol. 2020;11:1885.
12. Xu X, Jiang X, Ma C, Du P, Li X, Lv S, et al. A deep learning system to screen novel coronavirus disease 2019 pneumonia. Nat Commun. 2020;11:4088.
13. Philipsen RHHM, Sánchez CI, Maduskar P, Melendez J, Bastos ML, Boonstra A, et al. Automated detection of tuberculosis in chest radiographs using deep learning. PLoS One. 2015;10(6):e0129383.
14. Cowan LS, Diem L, Brake MC, Crawford JT. Transfer of Mycobacterium tuberculosis genotyping results to epidemiologic investigations. J Clin Microbiol. 2016;54(6):1476–1482.
15. Theron G, Peter J, van Zyl-Smit R, Mishra H, Streicher E, Murray S, et al. Evaluation of the Xpert MTB/RIF assay for the diagnosis of pulmonary tuberculosis. Lancet Infect Dis. 2018;18(1):68–76.
16. Qin ZZ, Ahmed S, Sarker MS, Paul K, Adel ASS, Naheyan T, et al. Tuberculosis detection from chest x-rays for triaging in a high tuberculosis-burden setting: validation of deep learning models. PLoS Med. 2019;16(11):e1002983.
17. Stop TB Partnership. The potential impact of artificial intelligence on tuberculosis diagnosis. Clin Infect Dis. 2020;71(Suppl 4):S275–S282.
18. World Health Organization. WHO consolidated guidelines on tuberculosis: Module 2: Screening—systematic screening for tuberculosis disease. Geneva: World Health Organization; 2021.
19. Liang Z, Powell A, Ersoy I, Poostchi M, Silamut K, Palaniappan K, et al. CNN-based image analysis for malaria diagnosis. IEEE Access. 2019;7:131449–131460.
20. Bibin D, Nair MS, Punitha P. Malaria parasite detection from peripheral blood smear images using deep belief networks. IEEE Access. 2017;5:9099–9108.
21. Dong Y, Jiang Z, Shen H, Pan W, Williams LA, Reddy VVB, et al. Evaluations of deep convolutional neural networks for automatic identification of malaria infected cells. J Biomed Opt. 2017;22(10):1–12.
22. Rajaraman S, Antani SK, Poostchi M, Silamut K, Hossain MA, Maude RJ, et al. Pre-trained convolutional neural networks as feature extractors toward improved malaria parasite detection in thin blood smear images. J Digit Imaging. 2019;32(5):773–786.
23. Molina A, Orozco I, García E, Alférez S, Molina R, Becerra A. Automated detection of malaria parasites in thick blood smears using deep learning. Comput Methods Programs Biomed. 2020;187:105217.
24. Faron ML, Buchan BW, Hyke J, Madisen N, Lainesse A, Pancholi P, et al. Multicenter evaluation of the Accelerate Pheno™ system for identification and antimicrobial susceptibility testing directly from positive blood cultures. J Clin Microbiol. 2016;54(4):1009–1017.
25. Bourbeau PP, Ledeboer NA. Automation in clinical microbiology. J Clin Microbiol. 2018;56(5):e00030-18.
26. Mutters NT, Hodiamont CJ, de Jong MD, Overmeire Y, Voss A. Performance of rapid diagnostic tests and automated systems in clinical microbiology laboratories: impact on antimicrobial stewardship. Clin Microbiol Infect. 2019;25(6):685–693.
27. Glasson JH, Yeo KTJ, McDonald PJ. Evaluation of total laboratory automation in clinical microbiology: impact on turnaround times and workflow efficiency. J Clin Microbiol. 2017;55(10):3053–3060.
28. Greub G, Prod’hom G. Automation in clinical bacteriology: what system to choose? Clin Microbiol Rev. 2020;33(2):e00059-19.
29. Weis CV, Jutzeler CR, Borgwardt K. Machine learning for microbial identification and antimicrobial susceptibility testing in clinical microbiology. Clin Microbiol Infect. 2020;26(10):1311–1317.
30. Tran NK, Alby K, Kerr A, Jones M, Gilligan PH. Cost savings realized by implementation of routine microbiological rapid diagnostic testing and antimicrobial stewardship intervention in bloodstream infections. mSystems. 2019;4(1):e00123-18.
31. Pesesky MW, Hussain T, Wallace M, Patel S, Andleeb S, Burnham CA, et al. Evaluation of machine learning and rules-based approaches for predicting antimicrobial resistance profiles in Gram-negative bacilli. J Clin Microbiol. 2016;54(7):1947–1952.
32. Rhoads DD, Sintchenko V, Rauch CA, Pantanowitz L. Clinical microbiology informatics. J Clin Microbiol. 2016;54(4):1020–1024.
33. Clark AE, Kaleta EJ, Arora A, Wolk DM. Matrix-assisted laser desorption ionization–time of flight mass spectrometry: a fundamental shift in the routine practice of clinical microbiology. Clin Microbiol Rev. 2013;26(3):547–603.
34. Sauget M, Valot B, Bertrand X, Hocquet D. Can MALDI-TOF mass spectrometry reasonably type bacteria? Clin Microbiol Infect. 2017;23(10):743–749.
35. Bizzini A, Greub G. Matrix-assisted laser desorption ionization time-of-flight mass spectrometry, a revolution in clinical microbial identification. Clin Microbiol Infect. 2010;16(11):1614–1619.
36. Patel R. MALDI-TOF MS for the diagnosis of infectious diseases. Clin Chem. 2013;59(2):340–349.
37. De Bruyne K, Slabbinck B, Waegeman W, Vauterin P, De Baets B, Vandamme P. Bacterial species identification from MALDI-TOF mass spectra through data analysis and machine learning. Syst Appl Microbiol. 2011;34(1):20–29.
38. Nguyen M, Long SW, McDermott PF, Olsen RJ, Olson R, Stevens RL, et al. Using machine learning to predict antimicrobial minimum inhibitory concentrations from whole-genome sequence data. mBio. 2018;9(1):e01260-18.
39. Yang Y, Niehaus KE, Walker TM, Iqbal Z, Walker AS, Wilson DJ, et al. Machine learning for classifying tuberculosis drug-resistance from DNA sequencing data. Clin Infect Dis. 2019;68(2):221–228.
40. Stoesser N, Batty EM, Eyre DW, Morgan M, Wyllie DH, Del Ojo Elias C, et al. Predicting antimicrobial susceptibilities for Escherichia coli and Klebsiella pneumoniae isolates from whole genomic sequence data. Nat Microbiol. 2016;1:16090.
41. Bradley P, Gordon NC, Walker TM, Dunn L, Heys S, Huang B, et al. Rapid antibiotic-resistance predictions from genome sequence data for Staphylococcus aureus and Mycobacterium tuberculosis. Nat Commun. 2015;6:10063.
42. Su M, Satola SW, Read TD. Genome-based prediction of bacterial antibiotic resistance using machine learning. Bioinformatics. 2019;35(24):5110–5117.
43. Arango-Argoty G, Garner E, Pruden A, Heath LS, Vikesland P, Zhang L. DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Nat Commun. 2018;9:3321.
44. Boolchandani M, D’Souza AW, Dantas G. Sequencing-based methods and resources to study antimicrobial resistance. Nat Rev Microbiol. 2019;17(9):554–569.
45. Van Camp PJ, Haslam DB, Porollo A. Prediction of antimicrobial resistance in Gram-negative bacteria from genomic data. Clin Microbiol Infect. 2020;26(3):283–289.
46. Davies TJ, Stoesser N, Sheppard AE, AbuOun M, Fowler PW, Peto TEA, et al. Reconciling genotype to phenotype in antimicrobial resistance prediction. J Antimicrob Chemother. 2021;76(4):889–897.
47. Nguyen L, Schmidt HA, von Haeseler A, Minh BQ. IQ-TREE: a fast and effective stochastic algorithm for estimating maximum-likelihood phylogenies. Nat Commun. 2018;9:333.
48. Yang Y, Jiang X, Chawla NV, Agrawal A. A comparative study of machine learning methods for antimicrobial resistance prediction. Bioinformatics. 2018;34(17):2952–2960.
49. Lipworth S, Jorgensen JH, Javid B. Genomic insights into antimicrobial resistance prediction. J Antimicrob Chemother. 2019;74(11):3147–3156.
50. Doern CD. The slow march toward rapid diagnostics in clinical microbiology. Clin Chem. 2017;63(1):38–40.
51. Maurer FP, Christner M, Hentschke M, Rohde H. Advances in rapid identification and susceptibility testing of bacteria in the clinical microbiology laboratory. J Clin Microbiol. 2017;55(5):1265–1272.
52. Binnicker MJ. Multiplex molecular panels for diagnosis of bloodstream infections: performance, result interpretation, and clinical impact. J Clin Microbiol. 2015;53(4):1057–1062.
53. Humphries RM, Hindler JA. Emerging resistance, new antimicrobial agents, and antimicrobial susceptibility testing considerations. J Clin Microbiol. 2018;56(7):e00438-18.
54. Caliendo AM, Gilbert DN, Ginocchio CC, Hanson KE, May L, Quinn TC, et al. Better tests, better care: improved diagnostics for infectious diseases. Clin Infect Dis. 2013;57(Suppl 3):S139–S170.
55. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44–56.
56. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. Lancet Digit Health. 2019;1(1):e29–e31.
57. Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy. NPJ Digit Med. 2018;1:39.
58. U.S. Food and Drug Administration. Artificial Intelligence/Machine Learning (AI/ML)-Based Software as a Medical Device (SaMD) Action Plan. Silver Spring (MD): FDA; 2021.
59. World Health Organization. Ethics and governance of artificial intelligence for health: WHO guidance. Geneva: WHO; 2021.
60. European Commission. Proposal for a Regulation laying down harmonised rules on artificial intelligence (Artificial Intelligence Act). Brussels: European Commission; 2021.
61. Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230–243.
62. Beam AL, Kohane IS. Big data and machine learning in health care. JAMA. 2018;319(13):1317–1318.
63. Rajkomar A, Dean J, Kohane I. Machine learning in medicine. N Engl J Med. 2019;380(14):1347–1358.
64. Wiens J, Saria S, Sendak M, Ghassemi M, Liu VX, Doshi-Velez F, et al. Do no harm: a roadmap for responsible machine learning for health care. Nat Med. 2019;25(9):1337–1340.
65. Char DS, Shah NH, Magnus D. Implementing machine learning in health care—addressing ethical challenges. N Engl J Med. 2018;378(11):
Article Sidebar
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
All articles published in JPTCP are licensed under Copyright Creative Commons Attribution-NonCommercial 4.0 International License.
Saheed Askar
Department of Microbiology, Government Medical College, Ramanathapuram, Tamil Nadu, India.
Fatima Bathool Rani
Department of Microbiology, Government Medical College, Ramanathapuram, Tamil Nadu, India.
Manjari
Department of Microbiology, Government Medical College, Ramanathapuram, Tamil Nadu, India.
Subitha
Department of Microbiology, Government Medical College, Ramanathapuram, Tamil Nadu, India.
