{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T10:50:39Z","timestamp":1785408639585,"version":"3.56.0"},"reference-count":31,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T00:00:00Z","timestamp":1781481600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100007700","name":"Carol Davila University of Medicine and Pharmacy","doi-asserted-by":"crossref","award":["28567"],"award-info":[{"award-number":["28567"]}],"id":[{"id":"10.13039\/501100007700","id-type":"DOI","asserted-by":"crossref"}]},{"award":["28567"],"award-info":[{"award-number":["28567"]}],"id":[{"id":"https:\/\/ror.org\/04fm87419","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Medical Sciences"],"abstract":"<jats:p>Objectives: When a Candida species is identified in an ICU patient, susceptibility results are typically available in 24\u201372 h. In this study, we built a machine learning model using four variables available at identification to estimate resistance probability in real time. Methods: We analysed 747 fungal isolates from 725 ICU patients (January 2021\u2013March 2026). We trained and compared a Random Forest and a Logistic Regression model, evaluating both with temporal cross-validation, permutation feature importance, three-category (S\/I\/R) prediction, and calibration analysis. Results: Multidrug resistance doubled from 24.5% (2021) to 51.1% (2025), and Candida auris grew eight-fold in three years. Random Forest reached AUC 0.885 on the held-out test set and 0.848 on prospective 2024\u20132025 data (Brier score 0.093). Species identity and drug choice together explained 87% of predictive signal. Local C. albicans fluconazole resistance (~16%) far exceeded the ECMM European figure of 0%, and C. krusei was four times more prevalent than the continental average. Conclusions: A four-variable model may provide calibrated resistance estimates during the critical gap before susceptibility results return, though performance reflects predominantly deterministic species\u2013drug patterns rather than complex learned biology. Overall performance was comparable to a rule-based lookup table, confirming that the majority of predictive signal derives from established species\u2013drug susceptibility patterns. Meaningful added value is limited to temporal trend tracking and improved prediction where resistance is acquired rather than intrinsic (C. albicans, C. tropicalis hard-subset AUC 0.929 vs. rule-based 0.899). The model complements a local antifungal testing; it does not replace one.<\/jats:p>","DOI":"10.3390\/medsci14020319","type":"journal-article","created":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T15:00:48Z","timestamp":1781535648000},"page":"319","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["From Species Identification to Empirical Therapy: A Machine Learning and Rule-Based Decision Support Framework for Antifungal Resistance Prediction in ICU Candida Infections"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5927-7069","authenticated-orcid":false,"given":"Madalina (Preda)","family":"Solomon","sequence":"first","affiliation":[{"name":"Department of Microbiology, Parasitology and Virology, Faculty of Nursing, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania"},{"name":"Clinical Laboratory of Medical Microbiology, Marius Nasta Institute of Pneumology, 050159 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9240-922X","authenticated-orcid":false,"given":"Beatrice","family":"Mahler","sequence":"additional","affiliation":[{"name":"Cardiothoracic Department, Faculty of Medicine, Carol Davila University of Medicine and Pharmacy, 020956 Bucharest, Romania"},{"name":"Pneumology Department, Marius Nasta Institute of Pneumology, 050159 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lia-Mara","family":"Ditu","sequence":"additional","affiliation":[{"name":"Department of Botany and Microbiology, Faculty of Biology, University of Bucharest, 060101 Bucharest, Romania"},{"name":"MICROGEN Research Centre, Faculty of Biology, University of Bucharest, 060101 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Oana","family":"Popescu","sequence":"additional","affiliation":[{"name":"National Reference Laboratory of Tuberculosis, Marius Nasta Institute of Pneumology, 050159 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3563-6987","authenticated-orcid":false,"given":"Corina-Aurelia","family":"Zugravu","sequence":"additional","affiliation":[{"name":"Department of Hygiene and Nutrition, Carol Davila University of Medicine and Pharmacy, 050463 Bucharest, Romania"},{"name":"National Institute of Public Health, 050463 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8694-6195","authenticated-orcid":false,"given":"Loredana Sabina Cornelia","family":"Manolescu","sequence":"additional","affiliation":[{"name":"Department of Microbiology, Parasitology and Virology, Faculty of Nursing, Carol Davila University of Medicine and Pharmacy, 020021 Bucharest, Romania"},{"name":"Clinical Laboratory of Medical Microbiology, Marius Nasta Institute of Pneumology, 050159 Bucharest, Romania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"18026","DOI":"10.1038\/nrdp.2018.26","article-title":"Invasive Candidiasis","volume":"4","author":"Pappas","year":"2018","journal-title":"Nat. Rev. Dis. Prim."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1445","DOI":"10.1056\/NEJMra1315399","article-title":"Invasive Candidiasis","volume":"373","author":"Kullberg","year":"2015","journal-title":"N. Engl. J. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1086\/421946","article-title":"Nosocomial Bloodstream Infections in US Hospitals: Analysis of 24,179 Cases from a Prospective Nationwide Surveillance Study","volume":"39","author":"Wisplinghoff","year":"2004","journal-title":"Clin. Infect. Dis."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Handra, C.-M., Chirila, M., Smarandescu, R.-A., and Ghita, I. (2022). Near Missed Case of Occupational Pleural Malignant Mesothelioma, a Case Report and Latest Therapeutic Options. Int. J. Environ. Res. Public Health, 19.","DOI":"10.3390\/ijerph192214763"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"S445","DOI":"10.1093\/infdis\/jix131","article-title":"Multidrug-Resistant Candida: Epidemiology, Molecular Mechanisms, and Treatment","volume":"216","author":"Arendrup","year":"2017","journal-title":"J. Infect. Dis."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Solomon, M., Mahler, B., Popescu, O., Ditu, L.-M., Gheorghe-Barbu, I., Chivu, L.I., and Manolescu, L.S.C. (2026). Shifting Epidemiology and Antifungal Susceptibility Patterns of Clinical Fungal Isolates in an Intensive Care Unit (ICU) from Bucharest, Romania: A Retrospective Observational Study. Antibiotics, 15.","DOI":"10.3390\/antibiotics15050440"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"792","DOI":"10.1016\/j.cmi.2019.03.028","article-title":"Resistance of Candida to Azoles and Echinocandins Worldwide","volume":"25","author":"Pristov","year":"2019","journal-title":"Clin. Microbiol. Infect."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Cernat, E.M., Dima, A., Popescu, C., Neagu, A., Betianu, C., Moga, M., Manolescu, L.S.C., and Barbilian, A. (2024). Anterior Intercondylar Notch Geometry in Relation to the Native Anterior Cruciate Ligament Size. J. Clin. Med., 13.","DOI":"10.3390\/jcm13020309"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1002\/ijgo.14482","article-title":"Women\u2019s Assessment of the Quality of Hospital-Based Perinatal Care by Mode of Birth in Romania during the COVID-19 Pandemic: Results from the IMAgiNE EURO Study","volume":"159","author":"Otelea","year":"2022","journal-title":"Int. J. Gynecol. Obstet."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Preda, M., Chivu, R.D., Ditu, L.M., Popescu, O., and Manolescu, L.S.C. (2024). Pathogenesis, Prophylaxis, and Treatment of Candida auris. Biomedicines, 12.","DOI":"10.3390\/biomedicines12030561"},{"key":"ref_11","unstructured":"World Health Organization (2026, May 09). WHO Fungal Priority Pathogens List to Guide Research, Development and Public Health Action. Available online: https:\/\/www.who.int\/publications\/i\/item\/9789240060241."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"De Gaetano, S., Midiri, A., Mancuso, G., Avola, M.G., and Biondo, C. (2024). Candida auris Outbreaks: Current Status and Future Perspectives. Microorganisms, 12.","DOI":"10.3390\/microorganisms12050927"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1007\/s12281-024-00489-1","article-title":"Empirical Therapy for Invasive Candidiasis in Critically Ill Patients","volume":"18","author":"Bartalucci","year":"2024","journal-title":"Curr. Fungal Infect. Rep."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sakagianni, A., Koufopoulou, C., Feretzakis, G., Kalles, D., Verykios, V.S., Myrianthefs, P., and Fildisis, G. (2023). Using Machine Learning to Predict Antimicrobial Resistance\u2015A Literature Review. Antibiotics, 12.","DOI":"10.3390\/antibiotics12030452"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Gurzu, I.L., Handra, C.M., Ghita, I., and Otelea, M.R. (2025). Unveiling the Threat of Crystalline Silica on the Cardiovascular System. A Comprehensive Review of the Current Knowledge. Front. Cardiovasc. Med., 12.","DOI":"10.3389\/fcvm.2025.1506846"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Ardila, C.M., Gonz\u00e1lez-Arroyave, D., and Tob\u00f3n, S. (2025). Machine Learning for Predicting Antimicrobial Resistance in Critical and High-Priority Pathogens: A Systematic Review Considering Antimicrobial Susceptibility Tests in Real-World Healthcare Settings. PLoS ONE, 20.","DOI":"10.1371\/journal.pone.0319460"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, Y., Hu, W., Chen, F., Zhao, J., Chen, X., and Han, L. (2021). Application of Machine Learning Classifier to Candida auris Drug Resistance Analysis. Front. Cell Infect. Microbiol., 11.","DOI":"10.3389\/fcimb.2021.742062"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"e280","DOI":"10.1016\/S1473-3099(24)00749-7","article-title":"Global Guideline for the Diagnosis and Management of Candidiasis: An Initiative of the ECMM in Cooperation with ISHAM and ASM","volume":"25","author":"Cornely","year":"2025","journal-title":"Lancet Infect. Dis."},{"key":"ref_19","unstructured":"The European Committee on Antimicrobial Susceptibility Testing (2026, January 13). Breakpoint Tables for Interpretation of MICs for Antifungal Agents, Version 12.1. Available online: http:\/\/www.eucast.org\/astoffungi\/clinicalbreakpointsforantifungals\/."},{"key":"ref_20","unstructured":"CLSI (2022). Epidemiological Cutoff Values for Antifungal Susceptibility Testing, CLSI."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3640","DOI":"10.1128\/AAC.49.9.3640-3645.2005","article-title":"Delaying the Empiric Treatment of Candida Bloodstream Infection until Positive Blood Culture Results Are Obtained: A Potential Risk Factor for Hospital Mortality","volume":"49","author":"Morrell","year":"2005","journal-title":"Antimicrob. Agents Chemother."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1086\/504810","article-title":"Time to Initiation of Fluconazole Therapy Impacts Mortality in Patients with Candidemia: A Multi-Institutional Study","volume":"43","author":"Garey","year":"2006","journal-title":"Clin. Infect. Dis."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.jinf.2023.08.001","article-title":"European Candidaemia Is Characterised by Notable Differential Epidemiology and Susceptibility Pattern: Results from the ECMM Candida III Study","volume":"87","author":"Arendrup","year":"2023","journal-title":"J. Infect."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/s13756-023-01297-x","article-title":"First Report of Candida auris in Romania: Clinical and Molecular Aspects","volume":"12","author":"Stanciu","year":"2023","journal-title":"Antimicrob. Resist. Infect. Control"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Popa, M.V., Gurzu, I.L., M\u00eendru, D.E., Gurzu, B., Handra, C.M., Eva-Maria, E., Olaru, I., Anton-P\u0103duraru, D.T., Warter, C., and Duceac, L.D. (2025). Dynamics of Absences Due to Respiratory Infections, Including COVID-19, Among Medical Staff in a Regional Pediatric Hospital. Healthcare, 13.","DOI":"10.3390\/healthcare13050563"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Melinte, V., Tudor, A.D., Bujoi, A.G., Radu, M.-A., V\u0103c\u0103riou, M.C., Cismaru, I.M., Holban, T.S., M\u00eerzan, C.L., Popescu, R., and Ciupan, R.C. (2024). Candida auris Outbreak in a Multidisciplinary Hospital in Romania during the Post-Pandemic Era: Potential Solutions and Challenges in Surveillance and Epidemiological Control. Antibiotics, 13.","DOI":"10.20944\/preprints202403.0911.v1"},{"key":"ref_27","unstructured":"European Centre for Disease Prevention and Control (2024). Survey on the Epidemiological Situation, Laboratory Capacity and Preparedness for Candidozyma (Candida) Auris, 2024, European Centre for Disease Prevention and Control."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1007\/s12281-014-0209-7","article-title":"Epidemiology of Echinocandin Resistance in Candida","volume":"8","author":"Grossman","year":"2014","journal-title":"Curr. Fungal Infect. Rep."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Lima, R., Ribeiro, F.C., Colombo, A.L., and de Almeida, J.N. (2022). The Emerging Threat Antifungal-Resistant Candida tropicalis in Humans, Animals, and Environment. Front. Fungal Biol., 3.","DOI":"10.3389\/ffunb.2022.957021"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e01926-17","DOI":"10.1128\/AAC.01926-17","article-title":"Development of Echinocandin Resistance in Candida tropicalis Following Short-Term Exposure to Caspofungin for Empiric Therapy","volume":"62","author":"Khan","year":"2018","journal-title":"Antimicrob. Agents Chemother."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Lai, Q., Tang, H., Luo, R., He, Z., Huang, W., Wang, L., Zhang, Z., Lin, S., and Qin, W. (2024). Identifying the Risk Factors of ICU-Acquired Fungal Infections: Clinical Evidence from Using Machine Learning. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1386161"}],"container-title":["Medical Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-3271\/14\/2\/319\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T04:12:39Z","timestamp":1781842359000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-3271\/14\/2\/319"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,15]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["medsci14020319"],"URL":"https:\/\/doi.org\/10.3390\/medsci14020319","relation":{},"ISSN":["2076-3271"],"issn-type":[{"value":"2076-3271","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,15]]}}}