Multidisciplinary tumor boards (MDTs) coordinate complex oncology decisions across imaging, pathology, genomics, and patient factors. Here we synthesize how artificial intelligence (AI)—including machine learning, natural language processing, deep learning, and large language models—supports MDT preparation and deliberation. Across cancers, reported agreement between AI recommendations and MDT decisions commonly ranges from 70% to 90%, and task-focused tools achieve high diagnostic performance in screening and staging. Benefits include faster information synthesis, more consistent guideline alignment, and clearer documentation of options, while human review remains central. Key limitations—data bias, uneven generalizability, privacy and governance concerns, and limited prospective validation—temper adoption. We outline implementation priorities: prospective multicenter evaluation, integration with electronic records, clinician training, and transparent oversight. Overall, AI can augment MDT decision-making and help personalize care and workflow efficiency when deployed with rigorous evaluation and safeguards.
23 January 2026 in Biochimica et Biophysica Acta (BBA) - Reviews on Cancer
Immune checkpoint inhibitors (ICIs) can elicit durable remissions, yet most solid tumors show primary non-response or acquired resistance because the tumor microenvironment (TME) limits T-cell priming, trafficking and effector fitness. Cytokines orchestrate these barriers by shaping spatial immune architecture, regulating suppressive myeloid programmes and inducing inhibitory ligands such as PD-L1. In this Review, we synthesize mechanistic and clinical evidence and propose a push-pull framework for cytokine modulation during checkpoint blockade: locally amplifying Th1/CTL-supporting signals (IL-2/IL-12/IL-15 and type I/II interferons) while selectively attenuating dominant suppressive circuits (TGF-β, IL-6/STAT3, IL-8-CXCR1/2, IL-10 and TNF-driven exhaustion). We critically contrast successful and failed cytokine-ICI combinations, highlighting how systemic exposure, network redundancy and counter-regulatory feedback have constrained several engineered agonists and explain why certain blockade strategies can improve efficacy while reducing immune-related toxicity. We discuss next-generation solutions-tumor-activated pro-cytokines, intratumoral gene delivery and immunocytokines-that concentrate activity within resistant niches and widen the therapeutic window. Finally, we outline actionable biomarkers, including transcriptomic signatures, plasma cytokine kinetics, myeloid/neutrophil metrics and spatial TME profiling, to stratify patients and guide dosing, sequencing and adaptive add-on strategies. Rational, biomarker-guided cytokine modulation offers a path to convert immune-excluded tumors into durable ICI responders.
Introduction: The purpose of this study was to assess the landscape of thyroid nodules research during the last 22 years using machine learning and text analysis.Methods: In November 2021, we obtained from PubMed all works indexed under the Medical Subject Headings (MeSH) subject line “thyroid nodules.” The entire set of search results was retrieved in XML format, and metadata such as title, abstract, keywords, MeSH words, and year of publication were extracted for bibliometric evaluation from the original XML files. To increase the specificity of the investigation, the Latent Dirichlet allocation (LDA) topic modeling method was applied.Results: Our study included 5,770 research papers. By using frequency analysis of MeSH terms, research on thyroid nodules was divided into two categories: clinical and basic. The proportion of clinical research is nearing 89% and is dominated by the differential diagnosis of thyroid nodules. In contrast, the proportion of MeSH terms relating to basic research was just 11%, with DNA mutation analysis being the most common topic. Following this, LDA analysis revealed the thyroid nodule study had three clusters: Imaging Studies, Biopsy and Diagnosis, and Epidemiology and Screening of Thyroid Cancer. The result suggests that current thyroid nodule research appears to have focused on ultrasonography and histological diagnosis, which are tightly correlated. Molecular biomarker research has increased, therefore enhancing the diagnostic precision of thyroid nodules. However, inflammation, anxiety, and mental health disorders related to thyroid nodules have received little attention.Conclusion: Basic research on thyroid nodules has unmet research requirements. Future research could focus on developing strategies to more efficiently identify malignant nodules, exploring the mechanism of thyroid nodule development, and enhancing the quality of life of thyroid patients.
Background: Inflammatory bowel disease (IBD) is a continuously increasing and worldwide disease, and the number of publications of IBD has been expanding in the past 10 years. The purpose of this study is to analyze the published articles of IBD in the past decade via machine learning and text analysis and get a more comprehensive understanding of the research trends and changes in IBD in the past 10 years. Method: In November 2021, we downloaded the published articles related to IBD in PubMed for the past 10 years (2012–2021). We utilized Python to extract the title, publication date, MeSH terms, and abstract from the metadata of each publication for bibliometric assessment. Latent Dirichlet allocation (LDA) was used to the abstracts to identify publications' research topics with greater specificity. Result: We finally identified and analyzed 34,458 publications in total. We found that publications in the last 10 years were mainly focused on treatment and mechanism. Among them, publications on biological agents and Gastrointestinal Microbiome have a significant advantage in terms of volume and rate of publications. In addition, publications related to IBD and coronavirus disease 2019 (COVID-19) have increased sharply since the outbreak of the worldwide pandemic caused by novel β-coronavirus in 2019. However, researchers seem to pay less attention to the nutritional and psychological status of patients with IBD. Conclusion: IBD is still a worldwide disease of concern with the publication of IBD-related research has expanded continuously over the past decade. More research related nutritional and psychological status of patients with IBD is needed in the future. Besides, it is worth noting that the management of chronic diseases such as IBD required additional attention during an infectious disease epidemic.
Hepatocellular carcinoma (HCC) recurrence postresection represents a thorny problem in clinical practice, of which impaired natural killer (NK) cell cytotoxicity represents one of crucial causes. Apart from recurrence, hepatectomy-induced abdominal adhesion also poses huge clinical challenges such as abdominal pain, intestinal obstruction, and perforation. Evidence demonstrates that radiotherapy can upregulate NK group 2D ligand expression on tumor cells to enhance NK cell cytotoxicity, indicating its great potential of curbing HCC recurrence. Nevertheless, radiotherapy has also been disclosed to incur suppression on NK antitumor cell immunity. Herein, we reveal that glycocholic acid (GCA)/tRNA-derived fragment 5 (tRF5)-GlyGCC signaling axis is activated in mouse HCC model after radiotherapy, which dampens NK cell antitumor immunity to limit therapeutic efficacy. Mechanistically, tRF5-GlyGCC can interact with KDM6B to epigenetically upregulate Runx2 and then transcriptionally activate ITGBL1 and S100A9 expression in HCC cells, which further reduces NK cell cytotoxicity directly and attracts myeloid-derived suppressor cell (MDSC) to inhibit NK cell function indirectly, respectively. Therefore, radiotherapy plus targeting tRF5-GlyGCC may be an optimized postoperative adjuvant therapy against HCC recurrence. Then, a nanocomposite powder is designed for liver-localized delivery of tRF5-GlyGCC inhibitor. After sprayed to liver resection margin of mouse HCC model, this powder can rapidly form an in-situ Janus-adhesive hydrogel, which allows for sustained delivery of tRF5-GlyGCC inhibitor. Importantly, it can synergize with radiotherapy to potentiate NK cell antitumor immunity and prevent HCC recurrence postresection. Moreover, its application to surgical bed also effectively mitigates abdominal adhesion in a rat hepatectomy model. Altogether, our work develops a tRF5-GlyGCC-targeting nanocomposite power for sensitizing radiotherapy to thwart HCC recurrence and preventing abdominal adhesion. Graphical Abstract
Cervical cancer is a highly prevalent female malignancy. Presently, cisplatin (DDP) is a first-line agent for cervical cancer chemotherapy. However, its curative effect is limited because of chemo-resistance. It has been previously reported that SOX9 targeted and activated oncogenic genes, enhancing cervical cancer cell resistance to DDP. The effects of the SOX9/lncRNA ANXA2P2/miR-361-3p/SOX9 regulatory loop on cervical cancer cell growth and resistance to DDP have been demonstrated. miR-361-3p expression was decreased in DDP-resistant cervical cancer cells and tissues. Moreover, miR-361-3p overexpression inhibited the growth of resistant cervical cancer cells and the resistance to DDP, whereas miR-361-3p inhibition exerted opposite effects. miR-361-3p inhibited SOX9 expression through binding; the effects of miR-361-3p inhibition were partially reversed by SOX9 knockdown. LncRNA ANXA2P2 expression was elevated in DDP-resistant cervical cancer cells and tissues. LncRNA ANXA2P2 inhibited miR-361-3p expression by binding, thereby upregulating SOX9. LncRNA ANXA2P2 knockdown inhibited DDP-resistant cervical cancer cell growth and resistance to DDP, whereas the effects of lncRNA ANXA2P2 knockdown were partially reversed by miR-361-3p inhibition. SOX9 expression was elevated in DDP-resistant cervical cancer cells and tissues, and SOX9 activated lncRNA ANXA2P2 transcription by binding. Collectively, SOX9, lncRNA ANXA2P2, and miR-361-3p form a regulatory loop, modulating DDP-resistant cervical cancer cell growth and response to DDP treatment.