Idiopathic pulmonary fibrosis (IPF) is a progressive lung disease characterised by the accumulation of scar tissue in the lungs, leading to respiratory failure and significantly impacting patients’ quality of life. Recent advancements in AI have emerged as a promising tool that can contribute to the management of IPF.
AI algorithms that employ machine learning and deep learning techniques have been increasingly integrated into the analysis of computed tomography (CT) scans, which may be useful in IPF care. These technologies can identify patterns and features in lung imaging that might not be identified by radiologists. By analysing large data sets of CT images, AI models can assist in the early detection of IPF, allowing for early intervention, which can result in improved outcomes such as slowing down the progression of IPF. IMVARIA’s Fibresolve, which received US Food and Drug Administration marketing authorisation in January 2024, provides an example of a diagnostic tool within the IPF landscape that has been trained in thousands of cases with tissue pathology and lung fibrosis follow-up, allowing for maximising noninvasive performance in differentiating IPF from other forms of interstitial lung disease, thereby assisting with assessment consistent with American Thoracic Society Guidelines (Bradley Drummond et al, 2024).
Go deeper with GlobalData
AI can contribute to the development of prognostic models that predict disease outcomes based on imaging findings and clinical data such as CT scans. Tao Chen and colleagues (2024) highlighted that AI prognostic tools can segment patients according to their risk of disease progression, allowing for personalised treatment plans. In addition to imaging, AI applications can be implemented in the analysis of clinical data, including the identification of biomarkers and patient characteristics that may allow for the identification of treatable traits, providing better accuracy. By integrating different data sources, AI can improve our understanding of IPF and support clinical decision-making. For instance, AI can analyse and potentially predict trends in patient responses to various treatments, helping clinicians choose the most effective therapies based on real-world evidence. A study from Cheng-Chun Yang and colleagues (2022) focused on radiomics in IPF, which is a process of extracting a large number of quantitative features from medical images, combined with AI algorithms, that has further enhanced our ability to derive prognostic signatures from high-resolution CT (HRCT) scans (Asma Khalid et al, 2025). Yang and colleagues evaluated particular lung features to predict therapeutic responses, including sum entropy, difference entropy, kurtosis, skewness, inverse difference, and maximum probability as a way to predict therapeutic response to antifibrotics. The study presented a model that assessed radiomic features of patients, based on pretreatment HRCT that could potentially predict the response of patients with IPF to antifibrotic treatment (Yang et al, 2022). Through continuous disease monitoring using AI tools, insights into patient health can be obtained, allowing for early adjustments in treatment plans and better control of the disease.
The integration of AI into the management of IPF represents a significant advancement in the field. As research continues to evolve, AI has the potential to transform IPF care, improving early detection and eventually patient outcomes. By employing such technologies in the field of IPF, a new era in the management of this disease may arise, offering hope for a better quality of life for patients with IPF.
US Tariffs are shifting - will you react or anticipate?
Don’t let policy changes catch you off guard. Stay proactive with real-time data and expert analysis.
By GlobalData
