Home Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection
Article
Licensed
Unlicensed Requires Authentication

Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection

  • Mingkuan Su EMAIL logo , Jianfeng Guo EMAIL logo , Hongbin Chen and Jiancheng Huang
Published/Copyright: November 17, 2022
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Clinical Chemistry and Laboratory Medicine (CCLM)
From the journal Clinical Chemistry and Laboratory Medicine (CCLM) Volume 61 Issue 3

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.

Keywords: artificial neural network; machine learning; procalcitonin; urosepsis
Corresponding authors: Jianfeng Guo and Mingkuan Su, Department of Laboratory Medicine, Mindong Hospital Affiliated to Fujian Medical University, No. 89, He’shan Road, Fuan City, Fujian Province 355000, P.R. China, E-mail: and

Funding source: Natural Science Foundation of Fujian Province

Award Identifier / Grant number: 2021J011447

  1. Research funding: This study was funded by the Natural Science Foundation of Fujian Province (grant number 2021J011447).

  2. 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.

  3. Competing interests: Authors state no conflicts of interest.

  4. Informed Consent: The requirement for informed consent was waived for all individuals included in this study.

  5. 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).

Received: 2022-10-06
Accepted: 2022-11-06
Published Online: 2022-11-17
Published in Print: 2023-02-23

© 2022 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Editorial
  3. Cell population data: much more to explore
  4. Reviews
  5. Differences between high-sensitivity cardiac troponin T and I in stable populations: underlying causes and clinical implications
  6. Choosing which in-hospital laboratory tests to target for intervention: a scoping review
  7. Opinion Papers
  8. Definitions and major prerequisites of direct and indirect approaches for estimating reference limits
  9. An algorithm for PCT-guided antimicrobial therapy: a consensus statement by Japanese experts
  10. General Clinical Chemistry and Laboratory Medicine
  11. The usefulness of implementing minimum retest intervals in reducing inappropriate laboratory test requests in a Dutch hospital
  12. Using three external quality assurance schemes to achieve equivalent international normalized ratio results in primary and secondary healthcare
  13. Optimizing the screening of alpha-1 antitrypsin deficiency using serum protein electrophoresis
  14. Anti-Ki/anti-PA28γ autoantibodies contribute to the HEp-2 indirect immunofluorescence nuclear speckled pattern
  15. Simultaneous quantification of tryptophan metabolites by liquid chromatography tandem mass spectrometry during early human pregnancy
  16. Reference Values and Biological Variations
  17. Verification of sex- and age-specific reference intervals for 13 serum steroids determined by mass spectrometry: evaluation of an indirect statistical approach
  18. Cancer Diagnostics
  19. Mucin 13 (MUC13) as a candidate biomarker for ovarian cancer detection: potential to complement CA125 in detecting non-serous subtypes
  20. Increased levels of N6-methyladenosine in peripheral blood RNA: a perspective diagnostic biomarker and therapeutic target for non-small cell lung cancer
  21. Cardiovascular Diseases
  22. Diagnostic utility of total NT-proBNP testing by immunoassay based on antibodies targeting glycosylation-free regions of NT-proBNP
  23. Infectious Diseases
  24. Serial measurement of circulating calprotectin as a prognostic biomarker in COVID-19 patients in intensive care setting
  25. Evaluation of ichroma™ COVID-19 interferon gamma release assay for detection of vaccine-induced immunity in healthcare workers
  26. Application of ultrasensitive assay for SARS-CoV-2 antigen in nasopharynx in the management of COVID-19 patients with comorbidities during the peak of 2022 Shanghai epidemics in a tertiary hospital
  27. Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection
  28. Letters to the Editor
  29. A panhaemocytometric approach to COVID-19: the importance of cell population data on Sysmex XN-series analysers in severe disease
  30. Critical appraisal of “choosing which in-hospital laboratory tests to target for intervention: a scoping review”
  31. What is the best external quality control sample for your laboratory?
  32. Pre-analytical variability of the Lumipulse immunoassay for plasma biomarkers of Alzheimer’s disease
  33. Biological variation of serum iron from the European biological variation study (EuBIVAS)
  34. Tube shaking and pneumatic transportation: impact on presepsin concentrations measured by both fully automated and POCT analyzers
  35. Endogenous isobaric interference on serum 17 hydroxyprogesterone by liquid chromatography-tandem mass spectrometry methods
  36. A simulation model for organization and management skills assessment that meets ISO 15189
  37. Congress Abstracts
  38. Annual meeting of the Royal Belgian Society of Laboratory Medicine: “Men’s health”
https://doi.org/10.1515/cclm-2022-1006
Keywords for this article
artificial neural network; machine learning; procalcitonin; urosepsis

Articles in the same Issue

  1. Frontmatter
  2. Editorial
  3. Cell population data: much more to explore
  4. Reviews
  5. Differences between high-sensitivity cardiac troponin T and I in stable populations: underlying causes and clinical implications
  6. Choosing which in-hospital laboratory tests to target for intervention: a scoping review
  7. Opinion Papers
  8. Definitions and major prerequisites of direct and indirect approaches for estimating reference limits
  9. An algorithm for PCT-guided antimicrobial therapy: a consensus statement by Japanese experts
  10. General Clinical Chemistry and Laboratory Medicine
  11. The usefulness of implementing minimum retest intervals in reducing inappropriate laboratory test requests in a Dutch hospital
  12. Using three external quality assurance schemes to achieve equivalent international normalized ratio results in primary and secondary healthcare
  13. Optimizing the screening of alpha-1 antitrypsin deficiency using serum protein electrophoresis
  14. Anti-Ki/anti-PA28γ autoantibodies contribute to the HEp-2 indirect immunofluorescence nuclear speckled pattern
  15. Simultaneous quantification of tryptophan metabolites by liquid chromatography tandem mass spectrometry during early human pregnancy
  16. Reference Values and Biological Variations
  17. Verification of sex- and age-specific reference intervals for 13 serum steroids determined by mass spectrometry: evaluation of an indirect statistical approach
  18. Cancer Diagnostics
  19. Mucin 13 (MUC13) as a candidate biomarker for ovarian cancer detection: potential to complement CA125 in detecting non-serous subtypes
  20. Increased levels of N6-methyladenosine in peripheral blood RNA: a perspective diagnostic biomarker and therapeutic target for non-small cell lung cancer
  21. Cardiovascular Diseases
  22. Diagnostic utility of total NT-proBNP testing by immunoassay based on antibodies targeting glycosylation-free regions of NT-proBNP
  23. Infectious Diseases
  24. Serial measurement of circulating calprotectin as a prognostic biomarker in COVID-19 patients in intensive care setting
  25. Evaluation of ichroma™ COVID-19 interferon gamma release assay for detection of vaccine-induced immunity in healthcare workers
  26. Application of ultrasensitive assay for SARS-CoV-2 antigen in nasopharynx in the management of COVID-19 patients with comorbidities during the peak of 2022 Shanghai epidemics in a tertiary hospital
  27. Developing a machine learning prediction algorithm for early differentiation of urosepsis from urinary tract infection
  28. Letters to the Editor
  29. A panhaemocytometric approach to COVID-19: the importance of cell population data on Sysmex XN-series analysers in severe disease
  30. Critical appraisal of “choosing which in-hospital laboratory tests to target for intervention: a scoping review”
  31. What is the best external quality control sample for your laboratory?
  32. Pre-analytical variability of the Lumipulse immunoassay for plasma biomarkers of Alzheimer’s disease
  33. Biological variation of serum iron from the European biological variation study (EuBIVAS)
  34. Tube shaking and pneumatic transportation: impact on presepsin concentrations measured by both fully automated and POCT analyzers
  35. Endogenous isobaric interference on serum 17 hydroxyprogesterone by liquid chromatography-tandem mass spectrometry methods
  36. A simulation model for organization and management skills assessment that meets ISO 15189
  37. Congress Abstracts
  38. Annual meeting of the Royal Belgian Society of Laboratory Medicine: “Men’s health”
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 15.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/cclm-2022-1006/html
Scroll to top button