Hereditary pancreatic cancers are caused by several inherited genes. Familial pancreatic cancer is defined as pancreatic cancer arising in a patient with at least two first-degree relatives with pancreatic cancer in the absence of an identified genetic cause. Hereditary pancreatic cancer syndromes and familial pancreatic cancers account for about 10% of pancreatic cancer cases. Germline mutations in BRCA1, BRCA2, ATM, PALB2, CDKN2A, STK11, and TP53 and mismatch repair genes (MLH1, MSH2, MSH6, PMS2, and EPCAM) are among the well-known inherited susceptibility genes. Currently available targeted medications include poly (ADP-ribose) polymerase inhibitors (PARP) for cases with mutant BRCA and immune checkpoint inhibitors for cases with mismatch repair deficiency. Loss of heterozygosity of hereditary pancreatic cancer susceptibility genes such as BRCA1/2 plays a key role in carcinogenesis and sensitivity to PARP inhibitors. Signature 3 identified by whole genome sequencing is also associated with homologous recombination deficiency and sensitivity to targeted therapies. In this review, we summarize molecular features and treatments of hereditary pancreatic cancer syndromes and surveillance procedures for unaffected high-risk cases. We also review transgenic murine models to gain a better understanding of carcinogenesis in hereditary pancreatic cancer.

Genotyping of tumor tissues to assess RAS and BRAF V600E mutations enables us to select optimal molecularly targeted therapies when considering treatment strategies for patients with metastatic colorectal cancer. Tissue-based genetic testing is limited by the difficulty of performing repeated tests, due to the invasive nature of tissue biopsy, and by tumor heterogeneity, which can limit the usefulness of the information it yields. Liquid biopsy, represented by circulating tumor DNA (ctDNA), has attracted attention as a novel method for detecting genetic alterations. Liquid biopsies are more convenient and much less invasive than tissue biopsies and are useful for obtaining comprehensive genomic information on primary and metastatic tumors. Assessing ctDNA can help track genomic evolution and the status of alterations in genes such as RAS, which are sometimes altered following chemotherapy. In this review, we discuss the potential clinical applications of ctDNA, summarize clinical trials focusing on RAS, and present the future prospects of ctDNA analysis that could change daily clinical practice.

Modern clinical oncology faces an unprecedented data complexity that exceeds human analytical capacity, making artificial intelligence (AI) integration essential rather than optional. This review examines the dual impact of AI on productivity enhancement and creative discovery in cancer care. We trace the evolution from traditional machine learning to deep learning and transformer-based foundation models, analyzing their clinical applications. AI enhances productivity by automating diagnostic tasks, streamlining documentation, and accelerating research workflows across imaging modalities and clinical data processing. More importantly, AI enables creative discovery by integrating multimodal data to identify computational biomarkers, performing unsupervised phenotyping to reveal hidden patient subgroups, and accelerating drug development. Finally, we introduce the FUTURE-AI framework, outlining the essential requirements for translating AI models into clinical practice. This ensures the responsible deployment of AI, which augments rather than replaces clinical judgment, while maintaining patient-centered care.

Background The C-reactive protein to albumin ratio (CAR) reflects systemic inflammation and nutritional status, but its prognostic value in esophageal squamous cell carcinoma (ESCC) treated with immune checkpoint inhibitor (ICI)-based therapy remains unclear. Methods We retrospectively analyzed 199 patients with unresectable advanced or recurrent ESCC who received ICI-based therapy across three cohorts: second- or later-line nivolumab monotherapy (n = 107), first-line chemotherapy plus ICI (n = 60), and first-line nivolumab plus ipilimumab (n = 32). The CAR cutoff values were determined using time-dependent receiver operating characteristic curve analysis. Progression-free survival (PFS) and overall survival (OS) were analyzed using Kaplan-Meier methods and Cox proportional hazards models. Results In the nivolumab monotherapy cohort, patients with a low CAR (< 0.072) had significantly better PFS (median 5.6 vs. 1.9 months; p = 0.001) and OS (median 20.0 vs. 5.5 months; p < 0.01) than those with a high CAR. In the first-line chemotherapy plus ICI cohort, patients with a low CAR (< 0.090) were associated with longer OS (median, 21.2 vs. 8.8 months; P = 0.03). A similar association was observed in the nivolumab plus ipilimumab cohort (median OS, 22.3 vs. 13.1 months; P = 0.003). In multivariable analyses, CAR remained an independent prognostic factor for OS in both the nivolumab monotherapy cohort (hazard ratio (HR) 2.36; 95% confidence interval (CI) 1.35–4.12; p = 0.002) and the first-line cohort (HR 2.38; 95% CI 1.24–4.56; p = 0.009). Patients with a high CAR were more likely to transition directly to best supportive care after discontinuing ICI-based therapy. Conclusions CAR is a simple, reliable, and independent prognostic biomarker in patients with unresectable advanced or recurrent ESCC receiving ICI-based therapy.