Search

During the COVID-19 pandemic, artificial intelligence (AI) models were created to address health-care resource constraints. Previous research shows that health-care datasets often have limitations, leading to biased AI technologies. This systematic review assessed datasets used for AI development during the pandemic, identifying several deficiencies. Datasets were identified by screening articles from MEDLINE and using Google Dataset Search. 192 datasets were analysed for metadata completeness, composition, data accessibility, and ethical considerations. Findings revealed substantial gaps: only 48% of datasets documented individuals’ country of origin, 43% reported age, and under 25% included sex, gender, race, or ethnicity. Information on data labelling, ethical review, or consent was frequently missing. Many datasets reused data with inadequate traceability. Notably, historical paediatric chest x-rays appeared in some datasets without acknowledgment. These deficiencies highlight the need for better data quality and transparent documentation to lessen the risk that biased AI models are developed in future health emergencies.

The seventh leading cause of cancer-related death globally, pancreatic ductal adenocarcinoma (PDAC) involves the exocrine pancreas and constitutes greater than 90% of all pancreatic cancers. Surgical resection in combination with systemic chemotherapy with or without radiation remains the mainstay of treatment and the only potentially curative treatment option. While there has been improvement in systemic chemotherapy, long-term survival among patients with PDAC remains poor. Improvement in the understanding of tumorigenesis, genetic mutations, the tumor microenvironment (TME), immunotherapies, as well as targeted therapies continued to drive advances in PDAC treatment. We herein review the TME, genetic landscape, as well as various metabolic pathways associated with PDAC tumorigenesis relative to emerging therapies.