{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T13:01:48Z","timestamp":1792242108023,"version":"4.4.0"},"reference-count":58,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T00:00:00Z","timestamp":1776038400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005047","name":"Natural Science Foundation of Liaoning Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>In the intensive care unit (ICU), antibiotics often begin under extreme uncertainty. Fever, leukocytosis, hypotension, and organ dysfunction may signal bacterial infection, but the same findings are common with aspiration, post-operative inflammation, drug reactions, or sterile systemic inflammation. Cultures take time and their yield falls after antibiotics. Rapid molecular tests and metagenomics can add actionable information, but they also raise the burden of interpreting complex results. Microscopy is one of the few inputs that can shift management within minutes to hours: Gram-stain patterns from positive blood-culture bottles, respiratory specimens, cerebrospinal fluid, and wound material can reshape initial coverage and support early de-escalation when negative. Tissue and cytology help distinguish invasion from key mimics. The gap is consistency-reads vary across observers, workflows differ, and results do not always translate into reliable bedside actions. This review focuses on infectious-disease artificial intelligence (AI) as ICU bedside decision support, rather than as a survey of models. Using ICU sepsis as the primary use case-and neurocritical care as a challenging setting where sedation, brain injury, and noninfectious inflammation often mimic infection-we separate evidence into pathogen signals and host-response signals. We then map both streams to six decisions over the first 72 hours: start now versus pause, choose initial spectrum, reassess and narrow, escalate diagnostics and source control, act on high-risk resistance or invasive pathogens, and stop safely. We summarize where AI is most credible today (Gram-stain assistance, culture-plate triage, urine-culture screening, infection-focused digital pathology, host-response classifiers, and selected metagenomics) and what makes outputs actionable: calibrated probabilities, explicit confidence with safe deferral when uncertain, validation across hospitals and instruments, and endpoints tied to stewardship and safety (time to appropriate therapy, antibiotic days, de-escalation within 72 hours, missed bacteremia). Evidence was updated through February 28, 2026.<\/jats:p>","DOI":"10.3389\/frai.2026.1807400","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:45:44Z","timestamp":1776059144000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["From microscopy to antimicrobial decisions: a clinically grounded roadmap for critical care infectious diseases"],"prefix":"10.3389","volume":"9","author":[{"given":"Hui-Ling","family":"Qu","sequence":"first","affiliation":[{"name":"Department of Neurology, The General Hospital of Northern Theater Command","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia-Nan","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The General Hospital of Northern Theater Command","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The General Hospital of Northern Theater Command","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi-Meng","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The General Hospital of Northern Theater Command","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao-Bin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Neurosurgery, The General Hospital of Northern Theater Command","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shi-Da","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Laboratory Medicine, The People's Hospital of Liaoning Province","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.jnlssr.2024.06.001","article-title":"Exploring the risks of automation bias in healthcare artificial intelligence applications: a bowtie analysis","volume":"5","author":"Abdelwanis","year":"2024","journal-title":"J. Saf. Sci. Resilience"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3990","DOI":"10.1038\/s41598-025-88545-9","article-title":"Validation of histopathology general-purpose large models through whole slide image retrieval","volume":"15","author":"Alfasly","year":"2025","journal-title":"Sci. Rep"},{"key":"B3","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1373\/clinchem.2017.274522","article-title":"Clinical microbiology is growing up: the total laboratory automation revolution","volume":"65","author":"Bailey","year":"2019","journal-title":"Clin. Chem"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e51","DOI":"10.1093\/cid\/ciw118","article-title":"Implementing an antibiotic stewardship program: guidelines by the infectious diseases society of America and the society for healthcare epidemiology of America","volume":"62","author":"Barlam","year":"2016","journal-title":"Clin. Infect. Dis"},{"key":"B5","doi-asserted-by":"publisher","first-page":"106565","DOI":"10.1016\/j.jinf.2025.106565","article-title":"Improved pathogen identification in sepsis or septic shock by clinical metagenomic sequencing","volume":"91","author":"Brenner","year":"2025","journal-title":"J. Infect"},{"key":"B6","doi-asserted-by":"publisher","first-page":"104397","DOI":"10.1016\/j.jbi.2023.104397","article-title":"Meaningful time-related aspects of alerts in clinical decision support tools: a unified approach","volume":"143","author":"Canovas-Segura","year":"2023","journal-title":"J. Biomed. Inform"},{"key":"B7","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1186\/s12916-025-04340-3","article-title":"Navigating fairness aspects of clinical prediction models","volume":"23","author":"Chakradeo","year":"2025","journal-title":"BMC Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1172","DOI":"10.1093\/jamia\/ocae060","article-title":"Unmasking bias in artificial intelligence: a systematic review of bias detection and mitigation strategies in electronic health record-based models","volume":"31","author":"Chen","year":"","journal-title":"J. Am. Med. Inform. Assoc"},{"key":"B9","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1038\/s41591-024-02857-3","article-title":"Towards a general-purpose foundation model for computational pathology (UNI)","volume":"30","author":"Chen","year":"","journal-title":"Nat. Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1093\/cid\/ciab672","article-title":"Advancing diagnostic stewardship for healthcare-associated infections, antibiotic resistance, and sepsis","volume":"74","author":"Curren","year":"2022","journal-title":"Clin. Infect. Dis"},{"key":"B11","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1016\/S1473-3099(16)00053-0","article-title":"Efficacy and safety of procalcitonin guidance in reducing the duration of antibiotic treatment in critically ill patients: a randomized, controlled, open-label trial","volume":"16","author":"de Jong","year":"2016","journal-title":"Lancet Infect. Dis"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e01804","DOI":"10.1128\/jcm.01804-24","article-title":"Proceedings of the clinical microbiology open 2024: artificial intelligence applications in clinical microbiology","volume":"63","author":"Dien Bard","year":"2024","journal-title":"J. Clin. Microbiol"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3749","DOI":"10.1038\/s41591-025-03982-3","article-title":"A multimodal whole-slide foundation model for pathology","volume":"31","author":"Ding","year":"2025","journal-title":"Nat. Med"},{"key":"B14","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/s00134-024-07772-2","article-title":"Inhale wp3, a multicenter, open-label, pragmatic randomised controlled trial assessing the impact of rapid, icu-based, syndromic pcr, versus standard-of-care on antibiotic stewardship and clinical outcomes in hospital-acquired and ventilator-associated pneumonia","volume":"51","author":"Enne","year":"2025","journal-title":"Intensive Care Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s00134-021-06506-y","article-title":"Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021","volume":"47","author":"Evans","year":"2021","journal-title":"Intensive Care Med"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e01683","DOI":"10.1128\/JCM.01683-19","article-title":"Evaluation of the wasplab segregation software to automatically analyze urine cultures using routine blood and macconkey agars","volume":"58","author":"Faron","year":"2020","journal-title":"J. Clin. Microbiol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The tripod-llm reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat. Med"},{"key":"B18","first-page":"2151","article-title":"\u201cSelectivenet: a deep neural network with an integrated reject option,\u201d","author":"Geifman","year":"2019","journal-title":"Proceedings of the 36th International Conference on Machine Learning (ICML 2019)"},{"key":"B19","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1007\/s00134-024-07450-3","article-title":"Tired of \"alarm fatigue\" in the intensive care unit: taking a fresh path to solutions using mental load theory","volume":"50","author":"Goldart","year":"2024","journal-title":"Intensive Care Med"},{"key":"B20","doi-asserted-by":"publisher","first-page":"e2013","DOI":"10.1016\/S2214-109X(25)00356-0","article-title":"Global, regional, and national sepsis incidence and mortality, 1990-2021: a systematic analysis for the global burden of disease study 2021","volume":"13","author":"Gray","year":"2025","journal-title":"Lancet Glob. Health"},{"key":"B21","article-title":"\u201cGood machine learning practice for medical device development: guiding principles,\u201d","author":"Group","year":"2025","journal-title":"Technical Report IMDRF\/AIML WG\/N88 FINAL:2025"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e16843","DOI":"10.2196\/16843","article-title":"Deep learning frameworks for rapid gram stain image data interpretation: protocol for a retrospective data analysis","volume":"9","author":"Kim","year":"2020","journal-title":"JMIR Res. Protoc"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2808","DOI":"10.3390\/biomedicines10112808","article-title":"Rapid convolutional neural networks for gram-stained image classification at inference time on mobile devices: from transfer learning to optimization","volume":"10","author":"Kim","year":"2022","journal-title":"Biomedicines"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1589","DOI":"10.1097\/01.CCM.0000217961.75225.E9","article-title":"Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock","volume":"34","author":"Kumar","year":"2006","journal-title":"Crit. Care Med"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1136\/bmj.m3164","article-title":"Reporting guidelines for clinical trials of artificial intelligence interventions: the consort-AI extension","volume":"26","author":"Liu","year":"2020","journal-title":"Nat. Med"},{"key":"B26","doi-asserted-by":"publisher","first-page":"e01514","DOI":"10.1128\/jcm.01514-24","article-title":"A novel framework for the automated characterization of gram-stained blood culture slides using a large-scale vision transformer","volume":"63","author":"McMahon","year":"2025","journal-title":"J. Clin. Microbiol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1188684","DOI":"10.3389\/fcimb.2023.1188684","article-title":"Laboratory automation, informatics, and artificial intelligence: current and future perspectives in clinical microbiology","volume":"13","author":"Mencacci","year":"2023","journal-title":"Front. Cell. Infect. Microbiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e200029","DOI":"10.1148\/ryai.2020200029","article-title":"Checklist for artificial intelligence in medical imaging (claim): a guide for authors","volume":"2","author":"Mongan","year":"2020","journal-title":"Radiol Artif Intell"},{"key":"B29","doi-asserted-by":"publisher","first-page":"e082505","DOI":"10.1136\/bmj-2024-082505","article-title":"Probast+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-025-01516-3","article-title":"Benchmarking foundation models as feature extractors for weakly-supervised computational pathology","author":"Neidlinger","year":"2025","journal-title":"Nat. Biomed. Eng"},{"key":"B31","doi-asserted-by":"publisher","first-page":"5212","DOI":"10.1038\/s41598-022-09264-z","article-title":"Generation of microbial colonies dataset with deep learning style transfer","volume":"12","author":"Paw\u0142owski","year":"2022","journal-title":"Sci. Rep"},{"key":"B32","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1093\/cid\/ciae234","article-title":"Rapid diagnostic tests and antimicrobial stewardship programs for the management of bloodstream infection: what is their relative contribution to improving clinical outcomes? A systematic review and network meta-analysis","volume":"79","author":"Peri","year":"2024","journal-title":"Clin. Infect. Dis"},{"key":"B33","doi-asserted-by":"crossref","first-page":"1351","DOI":"10.1038\/s41591-020-1037-7","article-title":"Spirit-AI extension: guidance for clinical trial protocols for artificial intelligence interventions","volume":"26","author":"Rivera","year":"2020","journal-title":"Nat. Med"},{"key":"B34","doi-asserted-by":"publisher","first-page":"4119","DOI":"10.1038\/s41591-025-03964-5","article-title":"A consensus blood transcriptomic approach for sepsis","volume":"31","author":"Scicluna","year":"2025","journal-title":"Nat. Med"},{"key":"B35","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1056\/NEJMoa1703058","article-title":"Time to treatment and mortality during mandated emergency care for sepsis","volume":"376","author":"Seymour","year":"2017","journal-title":"N. Engl. J. Med"},{"key":"B36","doi-asserted-by":"publisher","first-page":"779","DOI":"10.1080\/14737159.2019.1658524","article-title":"Making diagnostic clinical microbiology faster, better, and more resilient: the case for host response-based diagnosis","volume":"19","author":"Shean","year":"2019","journal-title":"Expert Rev. Mol. Diagn"},{"key":"B37","doi-asserted-by":"publisher","first-page":"20289","DOI":"10.1007\/s11042-025-20742-0","article-title":"Vision transformer based bacteria classification model for gram-stained direct smear images","volume":"84","author":"Shwetha","year":"2025","journal-title":"Multimed. Tools Appl"},{"key":"B38","doi-asserted-by":"publisher","first-page":"6303","DOI":"10.1038\/s41467-023-42563-1","article-title":"Hierarchical AI enables global interpretation of culture plates in the era of digital microbiology","volume":"14","author":"Signoroni","year":"2023","journal-title":"Nat. Commun"},{"key":"B39","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (sepsis-3)","volume":"315","author":"Singer","year":"2016","journal-title":"JAMA"},{"key":"B40","doi-asserted-by":"publisher","first-page":"e01521","DOI":"10.1128\/JCM.01521-17","article-title":"Automated interpretation of blood culture gram stains by use of a deep convolutional neural network","volume":"56","author":"Smith","year":"2018","journal-title":"J. Clin. Microbiol"},{"key":"B41","doi-asserted-by":"publisher","first-page":"3283","DOI":"10.1038\/s41591-025-03953-8","article-title":"The stard-AI reporting guideline for diagnostic accuracy studies using artificial intelligence","volume":"31","author":"Sounderajah","year":"2025","journal-title":"Nat. Med"},{"key":"B42","doi-asserted-by":"publisher","first-page":"3989","DOI":"10.1038\/s41591-025-04005-x","article-title":"Unlocking host response signatures in sepsis and critical illnesses","volume":"31","author":"Stevens","year":"2025","journal-title":"Nat. Med"},{"key":"B43","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1001\/jamainternmed.2017.1938","article-title":"Association of adverse events with antibiotic use in hospitalized patients","volume":"177","author":"Tamma","year":"2017","journal-title":"JAMA Intern. Med"},{"key":"B44","doi-asserted-by":"publisher","first-page":"e240300","DOI":"10.1148\/ryai.240300","article-title":"Checklist for artificial intelligence in medical imaging (claim): 2024 update. Radiol. Artif","volume":"6","author":"Tejani","year":"2024","journal-title":"Intell"},{"key":"B45","doi-asserted-by":"publisher","first-page":"1710412","DOI":"10.3389\/fcimb.2025.1710412","article-title":"Cost-effectiveness analysis of metagenomic next-generation sequencing versus traditional bacterial cultures for postoperative central nervous system infections in critical care settings: a prospective pilot study","volume":"15","author":"Tian","year":"2025","journal-title":"Front. Cell. Infect. Microbiol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1093\/cid\/ciw649","article-title":"The effect of molecular rapid diagnostic testing on clinical outcomes in bloodstream infections: a systematic review and meta-analysis","volume":"64","author":"Timbrook","year":"2017","journal-title":"Clin. Infect. Dis"},{"key":"B47","doi-asserted-by":"publisher","first-page":"e02153","DOI":"10.1128\/spectrum.02153-23","article-title":"Conversion of a classical microbiology laboratory to a total automation laboratory enhanced by the application of lean principles","volume":"12","author":"Trigueiro","year":"2024","journal-title":"Microbiol. Spectr"},{"key":"B48","doi-asserted-by":"publisher","first-page":"e070904","DOI":"10.1136\/bmj-2022-070904","article-title":"Decide-AI: a checklist for the early stage clinical evaluation of AI-driven decision support tools","volume":"377","author":"Vasey","year":"2022","journal-title":"BMJ"},{"key":"B49","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","article-title":"Net-benefit curve analysis: a novel method for evaluating prediction models","volume":"26","author":"Vickers","year":"2006","journal-title":"Med. Decis. Making"},{"key":"B50","doi-asserted-by":"publisher","first-page":"104683","DOI":"10.1016\/j.jbi.2024.104683","article-title":"Assessing racial bias in healthcare predictive models: practical lessons from an empirical evaluation of 30-day hospital readmission models","volume":"156","author":"Wang","year":"2024","journal-title":"J. Biomed. Inform"},{"key":"B51","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.cmi.2024.12.007","article-title":"Performance of molecular tests for diagnosis of bloodstream infections in the clinical setting: a systematic literature review and meta-analysis","volume":"31","author":"Wang","year":"2025","journal-title":"Clin. Microbiol. Infect"},{"key":"B52","doi-asserted-by":"publisher","first-page":"2327","DOI":"10.1056\/NEJMoa1803396","article-title":"Clinical metagenomic sequencing for diagnosis of meningitis and encephalitis","volume":"380","author":"Wilson","year":"2019","journal-title":"N. Engl. J. Med"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1065","DOI":"10.1001\/jamainternmed.2021.2626","article-title":"External validation of a widely implemented proprietary sepsis prediction model in hospitalized patients","volume":"181","author":"Wong","year":"2021","journal-title":"JAMA Intern. Med"},{"key":"B54","volume-title":"Global Antimicrobial Resistance and Use Surveillance System (GLASS) Report: 2022","year":"2022"},{"key":"B55","article-title":"\u201cGuidelines on the clinical management of sepsis,\u201d","volume-title":"Technical Report","year":"2024"},{"key":"B56","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1186\/s12967-025-06332-6","article-title":"Impact of metagenomics next-generation sequencing on etiological diagnosis and early outcomes in sepsis","volume":"23","author":"Xu","year":"2025","journal-title":"J. Transl. Med"},{"key":"B57","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1038\/s41586-024-07441-w","article-title":"A whole-slide foundation model for digital pathology from real-world data (prov-gigapath)","volume":"630","author":"Xu","year":"2024","journal-title":"Nature"},{"key":"B58","doi-asserted-by":"publisher","first-page":"100004","DOI":"10.1016\/j.ibmed.2020.100004","volume":"2","author":"Zhou","year":"2020"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1807400\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T05:45:46Z","timestamp":1776059146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1807400\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":58,"alternative-id":["10.3389\/frai.2026.1807400"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1807400","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,13]]},"article-number":"1807400"}}