Using AI for COPD Diagnosis, Equity, Guideline Gaps: Alvar Agusti, MD, PhD
AI in COPD Diagnosis and the Challenge of Underdiagnosis
Roughly 70% of people with chronic obstructive pulmonary disease (COPD) worldwide remain undiagnosed, and spirometry, the test required to confirm the disease, is often unavailable or misinterpreted where it is performed.
The GOLD Science Committee has identified underdiagnosis, misdiagnosis, and late diagnosis as the 3 key bottlenecks limiting timely COPD care.
Deep learning applied to low-dose CT scans obtained for lung cancer screening identified COPD with an area under the curve of 0.87, compared with 0.68 for traditional quantitative measures of emphysema in the same dataset.
AI models mining electronic health records for smoking history, repeated infections, and symptom descriptions can similarly flag patients who warrant spirometry.
GOLD 2026, Clinical Control and the RADAR Score
GOLD 2026 also introduced disease activity, disease stability, and clinical control as new conceptual frameworks for primary care, alongside tools such as the RADAR score, derived from the COPD Clinical Control Questionnaire, still in early validation.
The GOLD 2026 report, for the first time, talks about disease activity, which refers to biological activity, and also disease stability and clinical control, which refer to the clinical manifestation of the disease.
This is an area that needs more research, discussion, and consensus, but probably the RADAR score might be a very good tool to address this.
Equity and Representative AI Models in COPD
Non-representative training data is a separate, named risk in the GOLD Perspective’s list of AI implementation challenges, since models built on skewed cohorts can reinforce existing disparities in COPD care.
As in any other aspect of research, medicine in general, before you recommend the use of any intervention or tool, you need to validate it in cohorts that are large enough and representative enough.
This is what we are doing now, and I hope that in the very near future, we will have the data, the evidence, to support that.
Why Clinical Guidelines Remain Essential in the AI Era
Now that we have AI, guidelines are more important than ever before, because guidelines are the quality, evidence-proven input data for AI.
We will still need guidelines that are the result of human consensus on available evidence to inform AI.
But once we have this, AI can be a great tool to help physicians around the world treat their patients better.
Conclusions:
Authors
Alvar Agusti, MD, PhD
Read more details at
Fecha de publicación
September 22, 2026
Categorías asociadas al artículo
Noticias relacionadas
Academia Europaea’s guidelines for the visualization of clinical outcomes
Academia Europaea proposes ring diagrams to improve clinical outcome visualization and support evidence-based healthcare decision-making.
Video del evento: Transformando la EPOC, claves para un manejo proactivo
Conferencia sobre el manejo proactivo de la EPOC centrada en el infradiagnóstico, el control clínico y el seguimiento estructurado del paciente.
Vídeo de la Presentación de las Novedades GOLD 2026
Video de la presentación «Novedades GOLD 2026», en el que se trataron, entre otros aspectos: cambios en diagnóstico de la EPOC, tratamiento, comparativa con GESEPOC, etc.
Artificial Intelligence in COPD
Artificial Intelligence in COPD is transforming disease management, from underdiagnosis to treatment guidance. Discover how machine learning clusters patients, predicts outcomes, and optimizes healthcare resources.
Imagen desarrollada con ChatGPT