Artificial intelligence in NSCLC management for revolutionizing diagnosis, prognosis, and treatment optimization: A...

Non-small cell lung cancer (NSCLC) accounts for approximately 85 % of all lung cancer cases and remains a leading cause of cancer-related mortality. The integration of artificial intelligence (AI), artificial neural networks (ANNs), and machine learning (ML) into NSCLC management has shown potential in improving diagnostic accuracy, treatment personalization, and patient outcomes. However, the impact of these technologies on patient-reported outcome measures (PROM), overall survival (OS), and cost-effectiveness remains underexplored. This systematic review aims to evaluate the impact of AI, ANNs, and ML models on PROM, OS, and cost-effectiveness in adult patients with histologically confirmed NSCLC compared to conventional research methodologies and standard-of-care approaches.

A systematic review was conducted following the PRISMA guidelines, with data synthesized using the Synthesis Without Meta-analysis (SWiM) approach. Data extraction focused on study design, patient characteristics, AI methodology, and outcomes of interest. Given the heterogeneity in study designs and statistical methods, a meta-analysis was deemed inappropriate.

Ten studies were included after screening 509 articles. AI-based models demonstrated improvements in diagnostic precision, treatment optimization, and predictive accuracy for survival outcomes. AI-enhanced approaches outperformed conventional statistical models in prognosis prediction and resource allocation. However, data heterogeneity, model generalizability, and algorithmic transparency remain significant challenges.

Current evidence supports exploratory associations between AI models and prognostic stratification for OS; there is no evaluable evidence on PROM or cost‑effectiveness in NSCLC. Future prospective studies should incorporate validated PROM and formal economic evaluation alongside clinical endpoints. AI, ANNs, and ML have the potential to revolutionize NSCLC care by improving diagnostic accuracy and treatment outcomes. However, further research is needed to validate their real-world clinical applicability and address potential biases, ethical implications, and concerns regarding healthcare disparities.