RationalePre-eclampsia, a severe hypertensive disorder of pregnancy, poses significant maternal and perinatal risks. Artificial intelligence (AI) offers the potential for improved prediction, risk stratification, and personalized management. This umbrella review aims to synthesize existing systematic reviews to evaluate AI’s current applications, benefits, limitations, and ethical considerations in pre-eclampsia care. MethodsThis umbrella review will follow the Joanna Briggs Institute (JBI) methodology and the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We will systematically search major databases for relevant systematic reviews that examine the application of AI in pre-eclampsia. Data extraction will include information on AI algorithm performance, clinical applications, predictive variables, population diversity, ethical considerations, and limitations. Quantitative and qualitative synthesis of the extracted data will be performed to address the specific aims. Discussion This review’s findings will critically examine AI’s translational potential in pre-eclampsia care. We will discuss the balance between the promise of enhanced predictive accuracy and the practical challenges of clinical implementation, including data quality, model interpretability, and the need for rigorous validation across diverse populations. Ultimately, this review will contribute to a nuanced understanding of how AI can be responsibly leveraged to improve maternal and perinatal outcomes in pre-eclampsia.

NSCLC is a highly prevalent cancer and accounts for 85% of cases of lung cancer. Conventional cancer treatments, such as chemotherapy and radiation, frequently exhibit limited efficacy and notable adverse reactions. Therefore, a drug repurposing method is proposed for effective NSCLC treatment. This study aims to evaluate candidate drugs that are effective for NSCLC at the clinical level using systems biology and network analysis approach. Differentially expressed genes of transcriptomics data were identified using the systems biology and network analysis approach. A network of gene co-expression was developed with the aim of detecting two modules of gene co-expression. Subsequently, the Drug-Gene interaction database was employed to pinpoint potential pharmaceutical agents that target crucial genes within two gene co-expression modules associated with non-small cell lung cancer (NSCLC). The construction of a drug-gene interaction network was facilitated with the utilisation of Cytoscape. Finally, the gene set enrichment analysis was done to validate candidate drugs. Unlike previous research on repositioning drugs for NSCLC, which uses a gene co-expression network, this project is the first to research both gene co-expression and co-occurrence networks. And the co-occurrence network also accounts for differentially expressed genes in cancer cells and their adjacent normal cells. Drugs exhibiting elevated gene regulation and gene affinity within the drug-gene interaction network are deemed noteworthy for the efficacious management of non-small cell lung cancer (NSCLC). According to this discourse, NSCLC genes exert a high degree of regulation over medications such as vincristine, fluorouracil, methotrexate, clotrimazole, etoposide, tamoxifen, sorafenib, doxorubicin, and pazopanib. Hence, there is a possibility of repurposing these drugs for the treatment of non-small cell lung cancer. Key words: Non-small cell lung cancer (NSCLC), drug repurposing, network analysis, drug-gene interaction, therapeutics