Abstract
Objectives
Early recognition and timely intervention for urosepsis are key to reducing morbidity and mortality. Blood culture has low sensitivity, and a long turnaround time makes meeting the needs of clinical diagnosis difficult. This study aimed to use biomarkers to build a machine learning model for early prediction of urosepsis.
Methods
Through retrospective analysis, we screened 157 patients with urosepsis and 417 patients with urinary tract infection. Laboratory data of the study participants were collected, including data on biomarkers, such as procalcitonin, D-dimer, and C-reactive protein. We split the data into training (80%) and validation datasets (20%) and determined the average model prediction accuracy through cross-validation.
Results
In total, 26 variables were initially screened and 18 were statistically significant. The influence of the 18 variables was sorted using three ranking methods to further determine the best combination of variables. The Gini importance ranking method was found to be suitable for variable filtering. The accuracy rates of the six machine learning models in predicting urosepsis were all higher than 80%, and the performance of the artificial neural network (ANN) was the best among all. When the ANN included the eight biomarkers with the highest influence ranking, its model had the best prediction performance, with an accuracy rate of 92.9% and an area under the receiver operating characteristic curve of 0.946.
Conclusions
Urosepsis can be predicted using only the top eight biomarkers determined by the ranking method. This data-driven predictive model will enable clinicians to make quick and accurate diagnoses.
Funding source: Natural Science Foundation of Fujian Province
Award Identifier / Grant number: 2021J011447
-
Research funding: This study was funded by the Natural Science Foundation of Fujian Province (grant number 2021J011447).
-
Author’s contributions: JG wrote the manuscript. JH and HC collected the clinical data and performed data analysis. MS contributed to the conception, design, and code writing of this study. All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: Authors state no conflicts of interest.
-
Informed Consent: The requirement for informed consent was waived for all individuals included in this study.
-
Ethical Approval: Research involving human subjects complied with all relevant national regulations and institutional policies and is in accordance with the tenets of the Helsinki Declaration (as revised in 2013) and has been approved by the Ethics Committee of Mindong Hospital affiliated with Fujian Medical University (0325-17).
References
1. Jiang, L, Lin, SH, Wang, J, Chu, CK. Prognostic values of procalcitonin and platelet in the patient with urosepsis. Medicine 2021;100:e26555. https://doi.org/10.1097/md.0000000000026555.Search in Google Scholar PubMed PubMed Central
2. Evans, L, Rhodes, A, Alhazzani, W, Antonelli, M, Coopersmith, CM, French, C, et al.. Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021. Crit Care Med 2021;49:e1063–143.10.1097/CCM.0000000000005337Search in Google Scholar PubMed
3. Goh, KH, Wang, L, Yeow, AYK, Poh, H, Li, K, Yeow, JJL, et al.. Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare. Nat Commun 2021;12:711. https://doi.org/10.1038/s41467-021-20910-4.Search in Google Scholar PubMed PubMed Central
4. Giacobbe, DR, Mikulska, M, Tumbarello, M, Furfaro, E, Spadaro, M, Losito, AR, et al.. Combined use of serum (1,3)-β-D-glucan and procalcitonin for the early differential diagnosis between candidaemia and bacteraemia in intensive care units. Crit Care 2017;21:176. https://doi.org/10.1186/s13054-017-1763-5.Search in Google Scholar PubMed PubMed Central
5. Pierrakos, C, Velissaris, D, Bisdorff, M, Marshall, JC, Vincent, JL. Biomarkers of sepsis: time for a reappraisal. Crit Care 2020;24:287. https://doi.org/10.1186/s13054-020-02993-5.Search in Google Scholar PubMed PubMed Central
6. Masajtis-Zagajewska, A, Nowicki, M. New markers of urinary tract infection. Clin Chim Acta 2017;471:286–91. https://doi.org/10.1016/j.cca.2017.06.003.Search in Google Scholar PubMed
7. Heffernan, AJ, Denny, KJ. Host diagnostic biomarkers of infection in the ICU: where are we and where are we going? Curr Infect Dis Rep 2021;23:4. https://doi.org/10.1007/s11908-021-00747-0.Search in Google Scholar PubMed PubMed Central
8. Brodska, H, Valenta, J, Pelinkova, K, Stach, Z, Sachl, R, Balik, M, et al.. Diagnostic and prognostic value of presepsin vs. established biomarkers in critically ill patients with sepsis or systemic inflammatory response syndrome. Clin Chem Lab Med 2018;56:658–68. https://doi.org/10.1515/cclm-2017-0839.Search in Google Scholar PubMed
9. Song, Y, Chen, Y, Dong, X, Jiang, X. Diagnostic value of neutrophil CD64 combined with CRP for neonatal sepsis: a meta-analysis. Am J Emerg Med 2019;37:1571–6. https://doi.org/10.1016/j.ajem.2019.05.001.Search in Google Scholar PubMed
10. Tran, BX, Vu, GT, Ha, GH, Vuong, QH, Ho, MT, Vuong, TT, et al.. Global evolution of research in artificial intelligence in health and medicine: a bibliometric study. J Clin Med 2019;8:360. https://doi.org/10.3390/jcm8030360.Search in Google Scholar PubMed PubMed Central
11. Bi, WL, Hosny, A, Schabath, MB, Giger, ML, Birkbak, NJ, Mehrtash, A, et al.. Artificial intelligence in cancer imaging: clinical challenges and applications. CA A Cancer J Clin 2019;69:127–57.10.3322/caac.21552Search in Google Scholar PubMed PubMed Central
12. Singer, M, Deutschman, CS, Seymour, CW, Shankar-Hari, M, Annane, D, Bauer, M, et al.. The third international consensus definitions for sepsis and septic shock (sepsis-3). JAMA 2016;315:801–10. https://doi.org/10.1001/jama.2016.0287.Search in Google Scholar PubMed PubMed Central
13. Choi, JJ, McCarthy, MW, Meltzer, KK, Cornelius-Schecter, A, Jabri, A, Reshetnyak, E, et al.. The diagnostic accuracy of procalcitonin for urinary tract infection in hospitalized older adults: a prospective study. J Gen Intern Med 2022;8:1–7. https://doi.org/10.1007/s11606-021-07265-8.Search in Google Scholar PubMed PubMed Central
14. Ratzinger, F, Haslacher, H, Perkmann, T, Pinzan, M, Anner, P, Makristathis, A, et al.. Machine learning for fast identification of bacteraemia in SIRS patients treated on standard care wards: a cohort study. Sci Rep 2018;8:12233. https://doi.org/10.1038/s41598-018-30236-9.Search in Google Scholar PubMed PubMed Central
15. Lee, KH, Dong, JJ, Jeong, SJ, Chae, MH, Lee, BS, Kim, HJ, et al.. Early detection of bacteraemia using ten clinical variables with an artificial neural network approach. J Clin Med 2019;8:1592. https://doi.org/10.3390/jcm8101592.Search in Google Scholar PubMed PubMed Central
16. Mahmoud, E, Al Dhoayan, M, Bosaeed, M, Al Johani, S, Arabi, YM. Developing machine-learning prediction algorithm for bacteremia in admitted patients. Infect Drug Resist 2021;14:757–65. https://doi.org/10.2147/idr.s293496.Search in Google Scholar PubMed PubMed Central
17. Harbarth, S, Holeckova, K, Froidevaux, C, Pittet, D, Ricou, B, Grau, GE, et al.. Diagnostic value of procalcitonin, interleukin-6, and interleukin-8 in critically ill patients admitted with suspected sepsis. Am J Respir Crit Care Med 2001;164:396–402. https://doi.org/10.1164/ajrccm.164.3.2009052.Search in Google Scholar PubMed
18. Jekarl, DW, Kim, JY, Lee, S, Kim, M, Kim, Y, Han, K, et al.. Diagnosis and evaluation of severity of sepsis via the use of biomarkers and profiles of 13 cytokines: a multiplex analysis. Clin Chem Lab Med 2015;53:575–81. https://doi.org/10.1515/cclm-2014-0607.Search in Google Scholar PubMed
19. Mitaka, C, Ishibashi, C, Kawagoe, I, Hashimoto, T, Takahashi, M, Satoh, D, et al.. Correlation between urinary biomarker and organ failure in patients with sepsis and patients after esophagectomy: a prospective observational study. J Intensive Care 2020;8:11. https://doi.org/10.1186/s40560-020-0428-7.Search in Google Scholar PubMed PubMed Central
20. Clerico, A, Plebani, M. Biomarkers for sepsis: an unfinished journey. Clin Chem Lab Med 2013;51:1135–8. https://doi.org/10.1515/cclm-2013-0003.Search in Google Scholar PubMed
21. Macdonald, SP, Stone, SF, Neil, CL, van Eeden, PE, Fatovich, DM, Arendts, G, et al.. Sustained elevation of resistin, NGAL and IL-8 are associated with severe sepsis/septic shock in the emergency department. PLoS One 2014;9:e110678. https://doi.org/10.1371/journal.pone.0110678.Search in Google Scholar PubMed PubMed Central
22. Zhang, A, Cai, Y, Wang, PF, Qu, JN, Luo, ZC, Chen, XD, et al.. Diagnosis and prognosis of neutrophil gelatinase-associated lipocalin for acute kidney injury with sepsis: a systematic review and meta-analysis. Crit Care 2016;20:41. https://doi.org/10.1186/s13054-016-1212-x.Search in Google Scholar PubMed PubMed Central
23. Rehman, FU, Khan, A, Aziz, A, Iqbal, M, Mahmood, SBZ, Ali, N. Neutrophils to lymphocyte ratio: earliest and efficacious markers of sepsis. Cureus 2020;12:e10851. https://doi.org/10.7759/cureus.10851.Search in Google Scholar PubMed PubMed Central
24. Frydrych, LM, Bian, G, O’Lone, DE, Ward, PA, Delano, MJ. Obesity and type 2 diabetes mellitus drive immune dysfunction, infection development, and sepsis mortality. J Leukoc Biol 2018;104:525–34. https://doi.org/10.1002/jlb.5vmr0118-021rr.Search in Google Scholar
25. Sato, J, Kanazawa, A, Watada, H. Type 2 diabetes and bacteremia. Ann Nutr Metab 2017;71(1 Suppl):17–22. https://doi.org/10.1159/000479919.Search in Google Scholar PubMed
26. Gardiner, BJ, Stewardson, AJ, Abbott, IJ, Peleg, AY. Nitrofurantoin and fosfomycin for resistant urinary tract infections: old drugs for emerging problems. Aust Prescr 2019;42:14–9. https://doi.org/10.18773/austprescr.2019.002.Search in Google Scholar PubMed PubMed Central
27. Huttner, A, Verhaegh, EM, Harbarth, S, Muller, AE, Theuretzbacher, U, Mouton, JW. Nitrofurantoin revisited: a systematic review and meta-analysis of controlled trials. J Antimicrob Chemother 2015;70:2456–64. https://doi.org/10.1093/jac/dkv147.Search in Google Scholar PubMed
28. Bientinesi, R, Murri, R, Sacco, E. Efficacy and safety of levofloxacin as a treatment for complicated urinary tract infections and pyelonephritis. Expet Opin Pharmacother 2020;21:637–44. https://doi.org/10.1080/14656566.2020.1720647.Search in Google Scholar PubMed
29. Bonkat, G, Cai, T, Veeratterapillay, R, Bruyère, F, Bartoletti, R, Pilatz, A, et al.. Management of urosepsis in 2018. Eur Urol Focus 2019;5:5–9. https://doi.org/10.1016/j.euf.2018.11.003.Search in Google Scholar PubMed
Supplementary Material
The online version of this article offers supplementary material (https://doi.org/10.1515/cclm-2022-1006).
© 2022 Walter de Gruyter GmbH, Berlin/Boston