.png){kind=logo}
AI for COPD early detection and identify high-risk patients.
Globally, Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of death, causing 3.23 million deaths in 2019 (3). The prevalence of COPD in Latin America is significant, with estimates indicating around 8.9% of the population affected.
COPD is often underdiagnosed or misdiagnosed in Latin America due to limited access to spirometry and other diagnostic tools. Many patients are diagnosed only when the disease has progressed to advanced stages, making treatment less effective. Studies indicate that the prevalence ranges from 6% to 20% among adults over 40 years old, with higher rates observed in urban areas due to increased exposure to air pollution and smoking.
AI algorithms have been developed to assist in the interpretation of spirometry results These algorithms can analyze complex patterns in lung function data more accurately and consistently than traditional methods, reducing the rate of misdiagnosis.
On the other hand, AI can be used to develop predictive models that identify individuals at high risk of developing COPD based on factors such as smoking history, environmental exposures, and genetic predispositions. This allows for earlier intervention and management.
The demo shown is a predictive model that has been crafted utilizing varied data inputs from electronic medical records to accurately discern COPD symptoms and distinguish the condition from other respiratory ailments, leveraging information on patient health conditions, medication history, and exposure risks.
The model is enhanced by a synthetic data set, built on the basis of careful analysis of real-world data. Social determinants of health (SDoH) provide contextual information about environmental and social factors that may influence health outcomes. These data are complemented by the clinical experience on COPD symptomatology from the Mayo Clinic (1), the findings on the predictive role of AI in COPD by Zafari et al. (2), and the WHO's comprehensive overview of the prevalence and global impact of COPD (3), ensuring that the model is aligned with current medical knowledge and practices.
Globally, Chronic Obstructive Pulmonary Disease (COPD) is the third leading cause of death, causing 3.23 million deaths in 2019 (3). The prevalence of COPD in Latin America is significant, with estimates indicating around 8.9% of the population affected.
COPD is often underdiagnosed or misdiagnosed in Latin America due to limited access to spirometry and other diagnostic tools. Many patients are diagnosed only when the disease has progressed to advanced stages, making treatment less effective. Studies indicate that the prevalence ranges from 6% to 20% among adults over 40 years old, with higher rates observed in urban areas due to increased exposure to air pollution and smoking.
AI algorithms have been developed to assist in the interpretation of spirometry results These algorithms can analyze complex patterns in lung function data more accurately and consistently than traditional methods, reducing the rate of misdiagnosis.
On the other hand, AI can be used to develop predictive models that identify individuals at high risk of developing COPD based on factors such as smoking history, environmental exposures, and genetic predispositions. This allows for earlier intervention and management.
The demo shown is a predictive model that has been crafted utilizing varied data inputs from electronic medical records to accurately discern COPD symptoms and distinguish the condition from other respiratory ailments, leveraging information on patient health conditions, medication history, and exposure risks.
AI can streamline the diagnostic process by quickly and accurately interpreting spirometry and imaging results, reducing the need for repeat tests and specialist consultations.
Early diagnosis and treatment reduce COPD-related healthcare costs by 20–40%.
Predictive analytics can identify patients at risk of exacerbations by monitoring symptoms, vital signs, and environmental factors in real time.In Colombia, the cost per episode of COPD exacerbation was estimated at $270 for moderate exacerbations, $990 for severe exacerbations in moderate COPD, and $1,400 for severe exacerbations in severe COPD [7].
AI into COPD management is cost-effective by enhancing diagnostic accuracy, preventing costly exacerbations, and optimizing treatment plans. These improvements lead to better patient outcomes and significant cost savings for healthcare systems, despite the initial investment required for implementation.
The model is enhanced by a synthetic data set, built on the basis of careful analysis of real-world data. Social determinants of health (SDoH) provide contextual information about environmental and social factors that may influence health outcomes. These data are complemented by the clinical experience on COPD symptomatology from the Mayo Clinic (1), the findings on the predictive role of AI in COPD by Zafari et al. (2), and the WHO's comprehensive overview of the prevalence and global impact of COPD (3), ensuring that the model is aligned with current medical knowledge and practices.
