Zhonghua Jie He He Hu Xi Za Zhi. 2026 Jan 12;49(1):78-83. doi: 10.3760/cma.j.cn112147-20250728-00445.

ABSTRACT

Rare lung diseases are a group of diseases characterized by significant clinical heterogeneity, challenging diagnosis and treatment processes, and diverse underlying causes. Due to their uncommon symptoms and limited awareness among healthcare providers, these diseases are frequently misdiagnosed or diagnosed too late, resulting in poor patient outcomes and placing a significant healthcare burden on the healthcare system. However, in recent years, the rapid advancements in artificial intelligence (AI) technology within the medical field have created new opportunities for early identification, accurate diagnosis, and personalized management of these diseases. A variety of AI techniques, ranging from traditional machine learning to more recent methods such as deep learning, reinforcement learning, and transfer learning, have been employed in areas such as clinical decision support, radiomics, omics data analysis, and the prediction of treatment responses for rare lung diseases. This article systematically reviews the latest research progress of AI applications in idiopathic pulmonary fibrosis, cystic fibrosis, idiopathic pulmonary arterial hypertension, and other rare lung diseases. It also emphasizes AI's potential benefits in disease classification, treatment evaluation, and prognosis prediction through illustrative research examples.

PMID:41483922 | DOI:10.3760/cma.j.cn112147-20250728-00445

World J Gastroenterol. 2025 Dec 14;31(46):111176. doi: 10.3748/wjg.v31.i46.111176.

ABSTRACT

Artificial intelligence (AI) is rapidly transforming the landscape of hepatology by enabling automated data interpretation, early disease detection, and individualized treatment strategies. Chronic liver diseases, including non-alcoholic fatty liver disease, cirrhosis, and hepatocellular carcinoma, often progress silently and pose diagnostic challenges due to reliance on invasive biopsies and operator-dependent imaging. This review explores the integration of AI across key domains such as big data analytics, deep learning-based image analysis, histopathological interpretation, biomarker discovery, and clinical prediction modeling. AI algorithms have demonstrated high accuracy in liver fibrosis staging, hepatocellular carcinoma detection, and non-alcoholic fatty liver disease risk stratification, while also enhancing survival prediction and treatment response assessment. For instance, convolutional neural networks trained on portal venous-phase computed tomography have achieved area under the curves up to 0.92 for significant fibrosis (F2-F4) and 0.89 for advanced fibrosis, with magnetic resonance imaging-based models reporting comparable performance. Advanced methodologies such as federated learning preserve patient privacy during cross-center model training, and explainable AI techniques promote transparency and clinician trust. Despite these advancements, clinical adoption remains limited by challenges including data heterogeneity, algorithmic bias, regulatory uncertainty, and lack of real-time integration into electronic health records. Looking forward, the convergence of multi-omics, imaging, and clinical data through interpretable and validated AI frameworks holds great promise for precision liver care. Continued efforts in model standardization, ethical oversight, and clinician-centered deployment will be essential to realize the full potential of AI in hepatopathy diagnosis and treatment.

PMID:41479639 | PMC:PMC12754151 | DOI:10.3748/wjg.v31.i46.111176