Introduction

Humanity often views itself as the top species, capable of building cities, splitting atoms, taming wild beasts, and bending nature to its will. However, the continued survival of modern civilisation rests on an increasingly fragile foundation: our ability to control pathogenic microorganisms. That foundation is now under threat. Antimicrobial Resistance (AMR) is accelerating globally, eroding decades of medical progress and threatening health systems, especially in low- and middle-income countries (LMICs), with a possibility of a post-antibiotic era.

The implications of this crisis are not abstract. Last year, I witnessed a patient in a General Hospital succumb to complications from an infected wound despite receiving multiple courses of antibiotics. His case exemplifies a global trend: bacteria are evolving resistance at a faster rate than new treatments emerge. The above phenomenon is no isolated incident; AMR caused an estimated 1.27 million deaths in 2019, exceeding the mortality from HIV/AIDS or malaria in the same year. If current trends continue, projections suggest that AMR could contribute to 10 million deaths annually by 2050. This would lead to a world where routine surgeries and even minor injuries become risky.

The urgency of the situation is heightened by the operational delays inherent in LMICs healthcare systems. In cases of sepsis, each hour of delay in administering the correct antimicrobial increases mortality risk by approximately 9%. Many facilities must even wait up to 72 hours for culture results to be available. This is a fatal gap. It is within this context that artificial intelligence (AI) must be understood as a critical survival tool.

AI in the One Health Framework Surveillance.

AMR does not respect disciplinary boundaries. Microbial resistance emerges and spreads through interconnected ecosystems spanning humans, animals, plants, and the environment. The One Health framework, therefore, represents the most comprehensive approach to surveillance and fighting of AMR.

However, LMICs’ surveillance systems remain poor and fragmented. Veterinary, environmental, and clinical data streams often operate in isolation from one another. AI offers transformative potential by integrating these heterogeneous datasets. Machine-learning algorithms can harmonise genomic sequences, electronic medical records, wastewater surveillance data, and even digital media chatter to produce unified AMR intelligence systems. These systems can detect resistance trends early, predict outbreak hotspots, and link resistance profiles across sectors.

AI-driven One Health surveillance can function as an early warning system, providing predictive insights before clinical outbreaks escalate.

AI and Antibiotic Discovery Bottleneck

Antibiotic development has stagnated for decades. No new primary class of antibiotics has been discovered since 1987. Pharmaceutical companies often avoid antibiotic research due to low profitability. Also, short-course curative drugs generate less revenue than chronic-use medications. This market failure disproportionately affects LMICs, which lack the capacity to fund large-scale drug discovery pipelines independently.

AI can significantly reshape this. Generative AI models, such as SyntheMol, can computationally explore chemical spaces that exceed 30 billion molecules, identifying novel antimicrobial compounds with significantly reduced cost and time investment. These in-silico screening tools can evaluate molecular stability, pharmacokinetics, physicochemical properties, toxicity, and antimicrobial activity before laboratory testing, “modifying” drug discovery and enabling LMICs researchers to participate in innovation. With this, AI provides a realistic pathway to overcome the capitalist deadlock that has stalled antibiotic development for nearly four decades.

AI and Rapid Diagnostic Transformation.

While new antibiotics are essential, reducing AMR mortality requires immediate improvements in diagnostic speed and accuracy. Traditional microbial culture methods require 24–72 hours to determine antimicrobial susceptibility, a delay unacceptable for severe infections. In contrast, AI-powered diagnostic systems can analyse genomic and proteomic data in near real-time.

Models such as DeepARG and DeepAMR utilise deep-learning architectures to identify antibiotic-resistance genes from metagenomic sequences with accuracies exceeding 97%. Similarly, AI-enhanced MALDI-TOF mass spectrometry pipelines can predict resistance profiles within hours, substantially reducing diagnostic turnaround times.

For LMICs, such technologies enable clinicians to shift from empirical broad-spectrum prescribing, often referred to as therapeutic carpet bombing, to targeted antimicrobial therapy. This transition is crucial for preserving antibiotic efficacy while reducing mortality associated with delayed or inappropriate treatment.

Conclusion

The AMR crisis is not a future hypothetical; it is an unfolding reality with catastrophic implications for global health. LMICs, in particular, face a disproportionate burden due to resource limitations, infrastructure gaps, poor monitoring and surveillance, and delayed diagnostics. Integrating AI across One Health surveillance, antimicrobial discovery, and rapid diagnostic systems represents a pragmatic, evidence-based strategy to slow the progression toward a post-antibiotic world.

To prevent avoidable deaths and safeguard public health, health systems must embrace AI not as a novelty but as an essential component of contemporary medical practice. As bacteria continue to evolve at an extraordinary speed, our technological response must evolve even faster. We must, as a necessity, ACT NOW.

 References

1.  Murray, C. J. L., et al. (2022). Global burden of bacterial antimicrobial resistance in 2019: A systematic analysis. The Lancet, 399(10325), 629–655. https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(21)02724-0/fulltext 
2.  O’Neill, J. (2016). Tackling drug-resistant infections globally: Final report and recommendations. https://amr-review.org/sites/default/files/160525_Final%20paper_with%20cover.pdf
3.  Kumar, Anand MD; Roberts, Daniel MD; Wood, Kenneth E. DO; Light, Bruce MD; Parrillo, Joseph E. MD; Sharma, Satendra MD; Suppes, Robert BSc; Feinstein, Daniel MD; Zanotti, Sergio MD; Taiberg, Leo MD; Gurka, David MD; Kumar, Aseem PhD; Cheang, Mary MSc. Duration of hypotension before initiation of effective antimicrobial therapy is the critical determinant of survival in human septic shock*. Critical Care Medicine 34(6):p 1589-1596, June 2006. | DOI: 10.1097/01.CCM.0000217961.75225.E9 https://journals.lww.com/ccmjournal/Abstract/2006/06000/Duration_of_hypotension_before_initiation_of.1.aspx
4.  Kasse, G. E., Cosh, S. M., Humphries, J., & Islam, M. S. (2025). Leveraging artificial intelligence for One Health: opportunities and challenges in tackling antimicrobial resistance-scoping review. One Health Outlook, 7(1), 51. https://link.springer.com/article/10.1186/s42522-025-00170-8
5. Lewis K. (2020). The Science of Antibiotic Discovery. Cell, 181(1), 29–45. https://doi.org/10.1016/j.cell.2020.02.056
6.  Skinnider, M. A., Stacey, R. G., Wishart, D. S., & Foster, L. J. (2021). Chemical language models enable navigation in sparsely populated chemical space. Nature Machine Intelligence, 3(9), 759-770. https://doi.org/10.1038/s42256-021-00368-1
7.  Arango-Argoty, G., Garner, E., Pruden, A. et al. DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Microbiome 6, 23 (2018). https://doi.org/10.1186/s40168-018-0401-z
8.  Li, Y., Cui, X., Yang, X., Liu, G., & Zhang, J. (2024). Artificial intelligence in predicting pathogenic microorganisms’ antimicrobial resistance: challenges, progress, and prospects. Frontiers in Cellular and Infection Microbiology, 14, 1482186. https://doi.org/10.3389/fcimb.2024.1482186
9.  Florio, W., Baldeschi, L., Rizzato, C., Tavanti, A., Ghelardi, E., & Lupetti, A. (2020). Detection of Antibiotic-Resistance by MALDI-TOF Mass Spectrometry: an expanding area. Frontiers in Cellular and Infection Microbiology, 10, 572909. https://doi.org/10.3389/fcimb.2020.57290

SECOND POSITION: WAAW Essay Competition

Name: Torsen Saameer Kasmir

University: University Of Jos

Program: Pharmacy