A review of 11 studies published from 2019-2025 found that AI tools in radiation oncology — most often the Radiation Planning Assistant — delivered comparable contouring quality and time-efficiency in low- and middle-income countries (LMICs) versus high-income settings, despite limited real-world adoption. The review, covering studies across Africa, Asia, and Latin America, suggests AI could help offset workforce shortages in radiotherapy, but the evidence base in LMIC-specific practice remains thin.

Why It Matters To Your Practice

• AI-assisted contouring, treatment planning, and quality checks may help centers manage shortages of radiation oncologists and medical physicists.

• For clinicians in resource-constrained settings, the main near-term value is workflow efficiency without clear evidence of worse planning performance.

• The literature still reflects a gap between where AI is most needed and where it has actually been validated.

Clinical Implications

• Radiation Planning Assistant was the most frequently reported platform, making automated planning support the most visible use case in LMIC-focused reports.

• Comparable performance to high-income country settings suggests some AI tools may transfer across practice environments, especially for target volume contouring.

• Before implementation, clinicians should assess local infrastructure, internet reliability, staffing, QA capacity, and compatibility with existing planning systems.

Insights

• The review included 11 studies: 5 original research papers, 4 reviews, 1 survey, and 1 study protocol.

• Most evidence centered on contouring and treatment-planning tools rather than broader end-to-end autonomous radiotherapy workflows.

• A key limitation is that several conclusions for LMIC use were extrapolated from high-income country data, reducing direct generalizability.

The Bottom Line

• AI in radiation oncology appears promising for improving efficiency and access in LMICs, particularly in planning and contouring workflows.

• For practice today, the opportunity is real but the evidence remains early, heterogeneous, and not yet sufficient to assume seamless deployment across lower-resource settings.

• Clinicians should view these tools as potential force multipliers that still require local validation, implementation planning, and quality oversight.

Reference: Role of Artificial Intelligence in Radiation Oncology: A Missed Opportunity for LMICs?