Revolutionizing Antibiotic Resistance Surveillance in India: Insights from AI Innovator on AMRSense
Table of Contents
A team of researchers from IIIT-Delhi has developed groundbreaking AI-powered tools to combat the growing threat of antibiotic resistance in India. Their innovative approach uses readily available hospital data to provide real-time insights, enabling faster and more effective interventions. This collaboration between indraprastha Institute of Information Technology-Delhi, CHRI-PATH, Tata 1mg, and the Indian Council of Medical Research resulted in the creation of AMRSense, an AI-driven tool designed to analyze routine hospital data. This allows for the generation of accurate and timely insights into antimicrobial resistance (AMR) at the global,national,and hospital levels.
A recent paper, “Emerging trends in antimicrobial resistance in bloodstream infections: multicentric longitudinal study in India,” published in The Lancet Regional Health – Southeast asia, details the results of a six-year study. Authors Jasmine Kaur, Harpreet singh, and Tavpritesh Sethi analyzed data from 21 tertiary care centers within the Indian Council of Medical Research’s AMR surveillance network.This retrospective analysis revealed crucial relationships between antibiotic pairs and the directional influence of resistance in both community- and hospital-acquired infections.
“There is a shared mechanism of resistance between antibiotics, we already no. Usually to do that, people use genomics, but that’s an expensive proposition,” explains Dr. Sethi. “We have proposed a way, which is inexpensive, as it uses these routine data sets from hospitals. We show that by using routine data effectively, we can discern relationships between different antibiotics pairs and the direction AMR is taking – whether it is rising or not.Say, for instance, if resistance to one specific antibiotic is going up, some months down the line, it is quite likely that resistance to an antibiotic pair might also shoot up. With these connections, we generated actionable pieces of evidence.”
Dr. Sethi further emphasizes the innovative approach: We have tried to go beyond the customary way of looking at AI – asking how can it enable better decision-making for a given patient in a clinical setting or a public health setting. We think AI can also be used to understand AMR stewardship and surveillance aspects, from the hospital level, upwards.
The team highlights that hospitals already collect data through culture sensitivity testing, and AMRSense leverages this existing information to create AI-based pipelines for enhanced antimicrobial stewardship.
The team’s AMROrbit Scorecard, which won an award at the 2024 AMR surveillance Data Challenge, provides a visual depiction of resistance trends.it plots the orbit of resistance, say of every hospital or department, alongside a global median of resistance and a global rate of change. So around those global values, how well does a department, a hospital, or a certain country fare? That is what the scorecard will be able to provide real-time data for,
explains Dr. sethi.
Jasmine Kaur, lead author of the paper and researcher at IIIT-D, explains the ideal scenario: The ideal quadrant for any hospital or country to be in is where there is low baseline resistance and low rate of change as well. Orbits spiral in or out, but the AI tool can offer information facilitating timely interventions that can bring it to a desirable range of resistance.
Addressing the accuracy and reliability of the AI models,Kaur notes: In our paper,we have shown that our models did capture the trends as observed in the period we collected data for. Though, unless we have future data, we can’t really say, like, for example COVID-19 upended things, right? The only evidence we have currently is that globally it truly seems that our models are capturing the increasing rate of resistance in various studies.
The AMROrbit Scorecard offers clinicians a visual tool for informed decision-making based on hospital-generated data. Kaur emphasizes its ability to augment existing surveillance efforts at various levels, enabling comparisons between departments, cities, and centers across the country.However, she acknowledges a limitation: The only possible limitation would be in circumstances and settings that do not have consistent, granular surveillance data. Then the AI model will not make sense. This could occur in countries where surveillance data is not digitally accessible.
Looking ahead, Dr. Sethi envisions a broader request: We know there are other environmental factors such as antibiotics being used as growth factors in the poultry industry or leachates in the soil, that can also lead to AMR. The ideal would be, if at the public health level, we should be able to use the data we have from the hospitals, matching it with antibiotic sales, and community-level data, and study the environmental factors too. We hope to do that soon.
Revolutionizing Antibiotic resistance in India: AI Innovations That Could Save Lives
Opening Statement:
Imagine a world where the spread of antibiotic resistance is not just monitored,but predicted and controlled through the intelligent use of data. This is not a distant dream—India is already taking concrete steps towards this future. IIIT-Delhi’s groundbreaking AI-powered tool, AMRSense, is changing the game by providing real-time insights into antimicrobial resistance (AMR), harnessing data already available in hospitals for faster, more effective interventions. Could this be the silver bullet against the growing global health crisis of antibiotic resistance?
Interview with Dr. Tavpritesh Sethi, AI Innovator and Key Developer of AMRSense
Editor: Dr. Sethi, the development of AMRSense is a remarkable leap forward in the fight against antibiotic resistance in India.Can you help us understand how this tool works and it’s significance in a global context?
Dr.Sethi: Absolutely, and thank you for this chance.AMRSense is designed to analyze routine hospital data, something that hospitals are already collecting through processes like culture sensitivity testing. By leveraging this data, the AI tool can generate precise and timely insights into antimicrobial resistance at several levels—hospital, national, and even global. What makes AMRSense especially meaningful is its ability to discern relationships between different antibiotic pairs and the direction AMR is taking. This kind of foresight can inform strategies to slow down or reverse resistance trends, which is crucial not just for India, but for combating AMR worldwide.
Editor: Your recent paper highlighted trends in antimicrobial resistance, particularly in bloodstream infections. What were some of the key findings and unexpected insights from your study?
Dr.Sethi: Our study, conducted across 21 tertiary care centers, revealed critical connections between antibiotic pairs and the directional influence of resistance in both community- and hospital-acquired infections. one unexpected insight was the shared mechanism of resistance between certain antibiotics. Traditionally, understanding these mechanisms required expensive genomic analyses. With AMRSense,we’ve shown that you can achieve similar insights by using routine data sets—making it far more accessible and practical for widespread use.
Editor: Could you explain how AI is being utilized here to go beyond the conventional patient-focused applications, particularly in AMR stewardship?
Dr. sethi: Certainly. While AI is commonly associated with enhancing decision-making in clinical settings, we’re taking it a step further by applying it to AMR surveillance and stewardship. This involves looking at the bigger picture—identifying patterns and trends in resistance that can inform public health strategies. Our approach allows healthcare providers and policymakers to make informed decisions based on real-time data, optimizing the use of antibiotics and mitigating the risk of resistance.
The AMROrbit Scorecard: Visualizing Resistance Trends
Editor: The AMROrbit Scorecard seems like an intriguing tool. How does this visual depiction of resistance trends aid clinicians and public health officials?
Dr.Sethi: The AMROrbit Scorecard is quite effective in visualizing resistance trends, providing a comparative perspective of a hospital’s or department’s resistance levels against global medians and rates of change. This visualization helps clinicians and policymakers see how well their current practices fare against global standards, encouraging timely and actionable interventions.The ultimate goal is to get into the ideal quadrant—low baseline resistance and low rate of change.By observing how orbits spiral in or out,we can pinpoint areas needing attention,facilitating better resource allocation and targeted strategies.
Looking Beyond: Broader Applications of Hospital Data
editor: There’s mention of exploring environmental factors contributing to AMR.How might hospital data be integrated with other sources like antibiotic sales or community data to deepen this understanding?
Dr. Sethi: This is an exciting frontier! By correlating hospital data with information about antibiotic sales and environmental factors such as the use of antibiotics in agriculture, we can develop a more holistic understanding of AMR. This integration can provide insights into how antibiotics used outside clinical settings influence resistance patterns, enabling the design of more thorough intervention strategies that address the root causes rather than just the symptoms.
Editor: Dr. Sethi, what would you say is the potential impact of AI tools like AMRSense on the global fight against antibiotic resistance?
Dr. Sethi: The potential is enormous. AI tools like AMRSense not only enhance our ability to track and predict resistance trends but also empower us to take quicker, more informed actions. By democratizing access to robust surveillance tools,we can enable even resource-limited settings to participate actively in the fight against AMR. The goal is to create a global network of data-driven, responsive health systems that can act in unison to curb the spread of resistance.
Conclusion: A Call to Action
Join us in this crucial fight against antibiotic resistance. The innovations spearheaded by dr. Tavpritesh Sethi and his team at IIIT-Delhi are not just promising—they are imperative for the future of global health. By integrating AI with existing hospital data, we are opening new avenues for intervention and awareness. Your thoughts and engagement are vital. share your insights in the comments below or on social media to keep this significant conversation going.
Together, we can turn the tide against AMR and secure a healthier future for all.