AI, AMR and Behavioral Economics: Transforming antibiotic prescribing practices to curb AMR

 

Antimicrobial resistance (AMR) is one of the most pressing public health issues today, with the potential to cause 10 million deaths annually by 2050, according to the World Health Organization. One of the key drivers of AMR is the inappropriate use of antibiotics, especially within primary care settings. While healthcare professionals are aware of the dangers of overprescribing, systemic pressures such as patient expectations and diagnostic uncertainty often result in unnecessary antibiotic use. Combining artificial intelligence (AI) with behavioral economics may offer a novel solution to address this, helping clinicians make more informed decisions and reduce antibiotic misuse.

AI’s role in reducing antibiotic prescriptions

AI has already begun transforming healthcare, from diagnostics to personalized treatment plans. When applied to AMR, AI systems can analyze patient data in real-time to guide antibiotic prescriptions. For instance, machine learning algorithms can predict whether an infection is bacterial or viral, thus helping clinicians avoid prescribing antibiotics for viral infections, where they are ineffective. One study found that combining physician and algorithmic decisions can achieve a reduction in inefficient overprescribing of antibiotics by 20.3 percent.

Beyond diagnostics, AI can also identify patterns in clinician prescribing behaviors. By integrating AI into electronic health records, hospitals can flag instances where prescriptions deviate from guidelines and provide clinicians with real-time feedback. This allows physicians to adjust their treatment plans before finalizing decisions, thereby reducing inappropriate antibiotic use without compromising patient care.

Nudging clinicians toward better choices

Behavioral economics offers another effective approach to improving antibiotic prescribing practices. Cognitive biases, for instance the availability heuristic (i.e. where recent cases come to mind more easily) and patient pressure, can lead to antibiotic overprescribing. By applying behavioral insights, healthcare systems may be able to “nudge” clinicians toward better decisions without restricting their autonomy.

Studies have shown that peer comparison, wherein clinicians receive feedback to their performance compared to top performing peers, led to a decrease in absolute inappropriate antibiotic prescribing rates from 20% to 4%, a decrease that persisted 12 months after the end of the intervention.

A synergistic approach

By combining AI’s predictive capabilities with behavioral nudges, we can create a powerful system to reduce antibiotic misuse. AI tools can track a clinician’s prescribing patterns, and when the system detects an inappropriate prescription, a behavioral nudge—such as a pop-up reminder about local resistance rates—can prompt the clinician to reconsider their decision.

A systematic review of prescribing practices in primary healthcare settings found that 78.3% of nudge interventions resulted in a reduction in overall antibiotic prescribing. Social norm feedback was the most frequently applied nudge, with 76.5% of these studies reporting a reduction.

Overcoming challenges and ethical considerations

Despite the promise of AI and behavioral economics, challenges remain. AI systems must be carefully designed to avoid reinforcing existing biases in prescribing patterns, especially in underserved populations. Additionally, the widespread adoption of AI raises concerns about data privacy and security, which can and must be addressed via robust regulatory frameworks.

Ethical considerations also apply to behavioral nudges. While nudges can be effective, they must be designed to respect clinician autonomy and authority. Transparency in how AI systems and nudges operate is key to ensuring that healthcare professionals trust and adopt these interventions.

Combining AI and behavioral economics offers an important approach to curb the inappropriate use of antibiotics and addressing AMR. By providing real-time decision support and leveraging behavioral insights, healthcare systems can significantly reduce unnecessary antibiotic prescriptions, helping preserve the efficacy of the life-saving drugs. As AMR continues to pose a global threat, adopting innovative, evidence-based solutions is essential to safeguarding public health.

About the author: Mallika Auplish is a global health professional with over a decade of experience in policy, financing, and innovation. She has worked with the World Bank, the WHO, CIHR, the UN Secretariat, Vital Strategies and Bloomberg Philanthropies to mobilize investments, shape health policies, and drive innovative solutions to improve healthcare access and outcomes.

Competing interest: None

Handling Editor: Neha Faruqui

(Visited 113 times, 1 visits today)