Clinical Utility of AI-Integrated Metabolomic and Proteomic Signatures for Guiding Early Antibiotic Therapy in Sepsis

Article Sidebar

Full Text PDF
Published: 2026-01-30
DOI: https://doi.org/10.61919/1czvx127
Keywords:
Artificial Intelligence, Antimicrobial Therapy, Metabolomics, Precision Medicine, Proteomics, Sepsis

Main Article Content

Rizma Tariq
MBBS, Fazaia Medical College, Islamabad, Pakistan
Muhammad Shahzaib
MBBS, Fazaia Medical College, Islamabad, Pakistan
Fazeela Abbas
Nursing Intern, PNNC, BUHSC, Karachi, Pakistan
Muhammad Hasnat
MBBS, University College of Medicine and Dentistry (UCMD), Lahore, Pakistan
Eisha Tur Raazia
Government College University, Lahore, Pakistan
Iqra Walayat
Lecturer, Khwaja Fareed University of Engineering and Information Technology, Rahim Yar Khan, Pakistan

Abstract

Background: Rapid selection of appropriate antimicrobial therapy in sepsis is limited by diagnostic uncertainty during the early hours of critical illness. Artificial intelligence-assisted integration of metabolomic and proteomic data may provide earlier biologically informed decision support. Objective: To evaluate whether AI-guided multi-omic diagnostics improve the timeliness of appropriate antimicrobial therapy compared with standard care in sepsis. Methods: This single-center parallel-group randomized controlled trial enrolled 96 adults with sepsis and allocated 48 participants per group. Ninety participants had evaluable outcome data. The intervention combined rapid metabolomic and proteomic profiling with AI-assisted clinical decision support. The primary outcomes were appropriate targeted therapy within 12 hours and time to appropriate treatment. Results: Appropriate therapy within 12 hours was achieved in 37/45 (82.2%) intervention participants versus 20/45 (44.4%) controls (RR 1.85, 95% CI 1.30–2.64; p<0.001). Mean time to appropriate therapy was 5.8 versus 14.2 hours. SOFA scores decreased from 8.3 ± 2.0 to 3.1 ± 1.4 versus 8.5 ± 2.2 to 5.4 ± 1.8, with a significant group-by-time interaction (p<0.001). ICU stay was 7.2 versus 10.5 days, while 28-day mortality was 13.3% versus 31.1%. Conclusion: AI-guided multi-omic decision support improved early appropriate antimicrobial treatment and was associated with more favorable clinical trajectories

Article Details

Issue

Vol. 4 No. 2 (2026)

Section

Articles
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Rizma Tariq et al. 2026. Clinical Utility of AI-Integrated Metabolomic and Proteomic Signatures for Guiding Early Antibiotic Therapy in Sepsis. Journal of Health, Wellness and Community Research. 4, 2 (Jan. 2026), 1–12. DOI:https://doi.org/10.61919/1czvx127.

References

1. 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(8):801–810. doi:10.1001/jama.2016.0287.

2. Rudd KE, Johnson SC, Agesa KM, Shackelford KA, Tsoi D, Kievlan DR, et al. Global, regional, and national sepsis incidence and mortality, 1990–2017: analysis for the Global Burden of Disease Study. Lancet. 2020;395(10219):200–211.

3. Cajander S, Kox M, Scicluna BP, Weigand MA, Mora RA, Flohé SB, et al. Profiling the dysregulated immune response in sepsis: overcoming challenges to achieve the goal of precision medicine. Lancet Respir Med. 2024. doi:10.1016/S2213-2600(23)00330-2.

4. Giamarellos-Bourboulis EJ, Aschenbrenner AC, Bauer M, Bock C, Calandra T, Gat-Viks I, et al. The pathophysiology of sepsis and precision-medicine-based immunotherapy. Nat Immunol. 2024. doi:10.1038/s41590-023-01660-5.

5. 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(11):e1063–e1143.

6. Kollef MH, Shorr AF, Bassetti M, Timsit JF, Micek ST, Michelson AP, Garnacho-Montero J. Timing of antibiotic therapy in the ICU. Crit Care. 2021;25. doi:10.1186/s13054-021-03787-z.

7. Leung LY, Huang HL, Hung KKC, Leung CY, Lam C, Lo R, et al. Door-to-antibiotic time and mortality in patients with sepsis: systematic review and meta-analysis. Eur J Intern Med. 2024. doi:10.1016/j.ejim.2024.06.015.

8. Van Heuverswyn J, Valik JK, van der Werff SD, Hedberg P, Giske CG, Nauclér P. Association between time to appropriate antimicrobial treatment and 30-day mortality in patients with bloodstream infections: a retrospective cohort study. Clin Infect Dis. 2023;76(3):469–478. doi:10.1093/cid/ciac727.

9. Ohnuma T, Chihara S, Costin B, Treggiari MM, Bartz RR, Raghunathan K, Krishnamoorthy V. Association of appropriate empirical antimicrobial therapy with in-hospital mortality in patients with bloodstream infections in the US. JAMA Netw Open. 2023. doi:10.1001/jamanetworkopen.2022.49353.

10. Barichello T, Generoso JS, Singer M, Dal-Pizzol F. Biomarkers for sepsis: more than just fever and leukocytosis—a narrative review. Crit Care. 2022. doi:10.1186/s13054-021-03862-5.

11. He RR, Yue GL, Dong ML, Wang JQ, Cheng C. Sepsis biomarkers: advancements and clinical applications—a narrative review. Int J Mol Sci. 2024;25(16):9010. doi:10.3390/ijms25169010.

12. Libório MP, Harris PNA, Ravi C, Irwin AD. Getting up to speed: rapid pathogen and antimicrobial resistance diagnostics in sepsis. Microorganisms. 2024;12(9):1824. doi:10.3390/microorganisms12091824.

13. Banerjee R, Humphries R. Rapid antimicrobial susceptibility testing methods for blood cultures and their clinical impact. Front Med (Lausanne). 2021;8:635831. doi:10.3389/fmed.2021.635831.

14. Peri AM, Chatfield MD, Ling W, Furuya-Kanamori L, Harris PNA, Paterson DL. 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. Clin Infect Dis. 2024. doi:10.1093/cid/ciae234.

15. Sinha P, Meyer NJ, Calfee CS. Biological phenotyping in sepsis and ARDS. Annu Rev Med. 2023;74. doi:10.1146/annurev-med-043021-014005.

16. Chen Q, Liang X, Wu T, Jiang J, Jiang Y, Zhang S, et al. Integrative analysis of metabolomics and proteomics reveals amino acid metabolism disorder in sepsis. J Transl Med. 2022. doi:10.1186/s12967-022-03320-y.

17. She H, Du Y, Du Y, Tan L, Yang S, Luo X, et al. Metabolomics and machine learning approaches for diagnostic and prognostic biomarkers screening in sepsis. BMC Anesthesiol. 2023. doi:10.1186/s12871-023-02317-4.

18. Xu LL, Zhou Z, Schäuble S, Vivas W, Dlubatz K, Bauer M, et al. Multi-omics and multi-organ insights into energy metabolic adaptations in early sepsis onset. Adv Sci (Weinh). 2025. doi:10.1002/advs.202504418.

19. Yuan M, Huang P, Liu Y, Shen L, Nan C, Song Y, et al. SAA1 as a potential early diagnostic biomarker for sepsis through integrated proteomics and metabolomics. Immunology. 2025. doi:10.1111/imm.13925.

20. Komorowski M, Green A, Tatham KC, Seymour CW, Antcliffe D. Sepsis biomarkers and diagnostic tools with a focus on machine learning. EBioMedicine. 2022;86:104394. doi:10.1016/j.ebiom.2022.104394.

21. Bignami E, Berdini M, Panizzi M, Domenichetti T, Bezzi F, Allai S, et al. Artificial intelligence in sepsis management: an overview for clinicians. J Clin Med. 2025;14(1):286. doi:10.3390/jcm14010286.

22. Adams R, Henry KE, Sridharan A, Soleimani H, Zhan A, Rawat N, et al. Prospective, multi-site study of patient outcomes after implementation of the TREWS machine learning-based early warning system for sepsis. Nat Med. 2022. doi:10.1038/s41591-022-01894-0.

23. Póvoa P, Bos LDJ, Coelho L. The role of proteomics and metabolomics in severe infections. Curr Opin Crit Care. 2022. doi:10.1097/MCC.0000000000000966.

24. Mi Y, Burnham KL, Charles PD, Heilig R, Vendrell I, Whalley JP, et al. High-throughput mass spectrometry maps the sepsis plasma proteome and differences in patient response. Sci Transl Med. 2024. doi:10.1126/scitranslmed.adh0185.

25. Antcliffe D, Burrell AJC, Boyle AJ, Gordon AC, McAuley DF, Silversides JA. Sepsis subphenotypes, theragnostics and personalized sepsis care. Intensive Care Med. 2025. doi:10.1007/s00134-025-07873-6.

26. Zhang Z, Chen L, Shen H, Wang J, Yang J, Yang S, et al. Deriving consensus sepsis clusters via goal-directed subgroup identification in multi-omics study. Nat Commun. 2025. doi:10.1038/s41467-025-65271-4.

27. Papareddy P, Lobo TJ, Holub M, Bouma HR, Máca J, Strodthoff N, et al. Transforming sepsis management: AI-driven innovations in early detection and tailored therapies. Crit Care. 2025. doi:10.1186/s13054-025-05588-0.

28. Jin X, Shen H, Zhou P, Yang J, Yang S, Ni H, et al. Research progress on sepsis diagnosis and monitoring based on omics technologies: a review. Diagnostics (Basel). 2025;15(22):2887. doi:10.3390/diagnostics15222887.

29. Bracht T, Kappler K, Bayer M, Grell F, Schork K, Palmowski L, et al. Plasma proteomics identifies molecular subtypes in sepsis. Crit Care. 2025. doi:10.1186/s13054-025-05639-6.

30. Kox M, Bauer M, Bos LDJ, Bouma HR, Calandra T, Calfee CS, et al. The immunology of sepsis: translating new insights into clinical practice. Nat Rev Nephrol. 2025. doi:10.1038/s41581-025-01004-6.