AI and Cancer Research ── 2026-10-05

8 papers in this issue. Lead: Improving clinical data standardization in surgical notes through biomedical entity linking with contextual evidence from large language models

New papers on cancer and AI, collected from journal feeds, PubMed (searched across all journals) and OpenAlex (a public index used instead of Google Scholar), judged by Jev (an AI that makes language judgements): original research, AI central, which of 13 themes, treatment or trials, and then ranked by importance up to a daily limit. Journals are not filtered by impact factor; each paper shows its journal's IF-equivalent (OpenAlex two-year mean citedness) and the date of that value. Each entry shows the full original abstract.

Read by cancer type: Cancer biology（2） · Breast（2） · Lung（1） · Pancreatic（0） · Prostate（0） · ACC（0） · Brain（2） · Ovarian（0） · Endometrial（0） · Gastric（0） · Liver（1） · Kidney（0） · Bladder（0）

Cancer molecular biology and AI

Improving clinical data standardization in surgical notes through biomedical entity linking with contextual evidence from large language models
BMC Medical Informatics and Decision Making · 2026-10-03 · Evidence: Retrospective, single-center method development study using existing surgical notes
Abstract
Surgical notes contain essential clinical information for postoperative care, yet free-text format and institutional variability limit their use for standardized data representation and secondary analysis. Biomedical entity linking enables mapping of heterogeneous clinical expressions to standardized ontologies such as SNOMED-CT, supporting semantic interoperability. However, existing approaches often rely on predefined mention spans through named entity recognition (NER), which is labor-intensive and may introduce errors. We analyzed 9,051 gastric cancer surgical notes from Seoul National University Hospital. We developed a framework that leverages an open-source large language model (LLM; LLaMA-3.1-8B) to identify contextually relevant text segments, termed evidence spans, which provide cues for ontology-based entity linking. These spans were explicitly marked and used to fine-tune SapBERT, a pretrained embedding-based biomedical encoder. We compared multiple input variants against conventional pipelines and LLM-based approaches, including in-context learning and re-ranking. Incorporating evidence spans improved entity linking performance across metrics, with gains of +2.7 in Recall@1 and +2.2 in mean Average Precision at 3 (mAP@3) compared to raw text inputs. Evidence-guided models outperformed other LLM-based approaches, with additional gains when using the evidence marker token as the pooled representation. Attention analysis indicated that explicit evidence span marking reinforced the model’s focus on ontology-relevant context while reducing attention to irrelevant text. Leveraging LLM-derived contextual evidence improves ontology-based representation of clinical text by enhancing biomedical entity linking. This approach provides a practical strategy for standardizing unstructured surgical notes and supports more reliable secondary use of clinical data in real-world healthcare settings. More broadly, the framework supports mapping of unstructured clinical text to standardized ontologies, contributing to semantic interoperability and enabling downstream secondary use of clinical data.
Journal IF-equivalent: 6.6 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Shin C, Eom D, You H, Kim K, Kim S, Yoon HJ. Improving clinical data standardization in surgical notes through biomedical entity linking with contextual evidence from large language models. BMC Med Inform Decis Mak. 2026 Oct 3 [Epub ahead of print]. doi:10.1186/s12911-026-03877-4.
Checked: Abstract only
An explainable vision transformer approach for automated neurological disorder classification from brain MRI scans
Scientific Reports · 2026-10-02 · Evidence: Retrospective model development on a public imaging dataset
Abstract
Diagnosing Alzheimer’s Disease (AD), Multiple Sclerosis (MS), and brain tumors early enough to matter still depends heavily on brain MRI, and brain MRI still depends on radiologists who are in short supply almost everywhere. Convolutional neural networks have made real progress on this problem, but a single convolution only sees a small patch of the image, which limits how well a purely convolutional model can tie together pathology that is spread across the brain. This study addresses that limitation from two directions at once: a controlled, same-protocol comparison of established CNN backbones, and a lightweight attention mechanism grafted onto one of them. We classify the full eight-class Multi-Class Neurological Disorder (MCND) dataset (AD MildDemented, AD ModerateDemented, AD VeryMildDemented, Multiple Sclerosis, Normal, and three brain-tumor subtypes: glioma, meningioma, and pituitary), comprising 9,564 MRI images split 80:20 into 7,651 training and 1,913 test images. Four established CNNs, VGG-16, ResNet-50, DenseNet121, and EfficientNet-B0, were fine-tuned under one shared protocol to serve as controlled baselines. We then built VGG-16 + CBAM: a VGG16 backbone fitted with a Convolutional Block Attention Module and a much smaller classification head in place of VGG-16’s original fully connected layers, trained for 15 epochs under the same optimizer and augmentation settings used for the baselines. It reached 98.90% accuracy, a weighted F1-score of 0.9890, a macro F1 of 0.9893, a macro AUC-ROC of 0.9997, and an MCC of 0.9874 on the held-out test set, beating all four baselines (98.12%–98.85% accuracy) while using just 14.88 million parameters, roughly 9% of VGG-16’s 134.29 million, for a 56.8 MB model. We also report parameter counts, model size, FLOPs, GPU inference latency, and training time for every baseline, so the accuracy gain can be weighed against actual computational cost rather than accuracy alone. Grad-CAM maps for all eight classes show the model focusing on plausible anatomical regions: periventricular and hippocampal areas for the AD stages, white matter for MS, and the tumor core for each tumor subtype. A t-SNE projection of the learned features shows the eight classes forming distinct, mostly non-overlapping clusters. Taken together, the results suggest a small, attention-augmented CNN can match or beat larger backbones on this task at a fraction of the cost, without losing the interpretability a clinician would need to trust it.
Journal IF-equivalent: 5.2 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Alahmadi A, Asim N, Khan MZ, Sirshar M, Aljubayri I. An explainable vision transformer approach for automated neurological disorder classification from brain MRI scans. Sci Rep. 2026 Oct 2 [Epub ahead of print]. doi:10.1038/s41598-026-71565-4.
Checked: Abstract only

See all 2 Cancer biology papers →

Breast cancer: treatment, trials and AI

A dual-tower multimodal framework with feature quality enhancement for predicting pathological complete response after neoadjuvant chemotherapy in breast cancer: a multicenter study
Translational Oncology · 2026-10-02 · Evidence: Retrospective multicenter observational study with external validation
Abstract
BACKGROUND: Pathological complete response (pCR) is a key endpoint following neoadjuvant chemotherapy (NAC) in breast cancer, with potential to guide treatment adaptation and surgical de-escalation. However, limited generalizability across institutions remains a major challenge due to heterogeneous imaging protocols (scanner vendors, field strengths, and acquisition parameters) and diverse patient populations, which can cause significant domain shifts in model performance. This study develops and externally validates a multimodal framework for post-neoadjuvant, preoperative prediction of pCR using multiparametric MRI (mpMRI) and routinely available clinical data. METHODS: In a multicenter retrospective setting, 1291 patients from five institutions were enrolled and institutionally divided into a development cohort pooled from two centers (n=683) and three independent, single-center external validation cohorts (n=608). Model inputs comprised post-treatment mpMRI (dynamic contrast-enhanced and diffusion-weighted imaging) for deep feature extraction, clinicopathological variables, radiomics features from both pre- and post-treatment scans, and delta-radiomics features capturing longitudinal within-sequence changes (Δ = post - pre). A dual-tower attention network incorporating a Feature Quality Enhancer (FQE) module-which regularizes the latent space by promoting intra-class compactness, inter-class separability, and feature consistency-was designed to learn discriminative imaging representations. Deep, radiomic, and clinical features were then integrated through a hierarchical feature selection strategy, with robustness assessed via repeated experiments.. Predictive performance was evaluated using the area under the receiver operating characteristic curve (AUC) in both development and external validation cohorts. RESULTS: The proposed AIFPS achieved an AUC of 0.882 (95% CI: 0.855-0.905) in the development cohort. In external validation, AIFPS achieved the highest numerical AUCs (0.853, 0.888, and 0.895) and demonstrated statistically significant improvements over all single-modality models in all cohorts. While its superiority over certain dual-modality models did not reach statistical significance after correction for multiple comparisons, the full multimodal approach consistently yielded the numerically highest discrimination. CONCLUSION: AIFPS integrates quality-enhanced deep imaging features with radiomics, including delta-radiomics, and clinicopathological variables to enable accurate and generalizable preoperative prediction of pathological complete response, particularly in HER2-positive disease, while further validation is required for triple-negative and luminal subtypes. Its application in luminal breast cancer requires further dedicated subtype-specific modeling. With prospective validation, this approach may support individualized treatment stratification following neoadjuvant chemotherapy.
Journal IF-equivalent: 4.3 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Ke Y, Yang W, Yang Z, Yue J, Li C, Yuan P, et al. A dual-tower multimodal framework with feature quality enhancement for predicting pathological complete response after neoadjuvant chemotherapy in breast cancer: a multicenter study. Transl Oncol. 2026 Nov;73:103060. doi:10.1016/j.tranon.2026.103060. PMID: 42822322.
Checked: Abstract only
Explainable machine learning and hybrid transformer-based proteochemometric modelling for breast cancer molecular subtyping and multi-target natural product discovery
Scientific Reports · 2026-10-02 · Evidence: Preclinical, in silico computational study without experimental validation
Abstract
Breast cancer comprises five intrinsic molecular subtypes with distinct transcriptomic programs, prognoses, and therapeutic vulnerabilities. Yet, accurate subtype discrimination remains limited by boundary-overlap and poor cross-cohort generalisability, while single-target agents often fail against pathway redundancy and acquired resistance. We developed an integrated computational framework linking transcriptomic-classification, explainable target prioritisation, and multi-target natural-product discovery. Three transcriptomic cohorts (METABRIC-BRCA-2016, TCGA-BRCA-2012, and TCGA-BRCA-2018; n = 2512 after quality-control and ComBat-correction) were integrated. Differential-expression analysis and PCA-based feature selection yielded a 50-gene signature that retained more than 90% of the subtype-associated variance. Among the six evaluated classifiers, XGBoost achieved the best performance and generalised to an independent cohort of 3,409 samples (accuracy: 85.70%; ROC-AUC: 0.95–0.99). SHAP-analysis identified 30-candidate genes associated with Basal-like and HER2-enriched subtypes, which were cross-referenced against ChEMBL to retain 11 targets for proteochemometric (PCM) modelling. A hybrid PCM multilayer-perceptron integrating ProtBERT and ChemBERTa embeddings with molecular fingerprints and chemical descriptors achieved a balanced-accuracy of 0.9140 and mean ROC-AUC of 0.9696. Screening of 30,898 NPASS natural products identified 292 pan-active compounds. Independent binding- and safety-prioritisation strategies converged on three leads: NPC139056, NPC196231, and NPC471997. This reproducible pipeline provides computationally prioritised leads for experimental validation in clinically challenging breast cancer subtypes.
Journal IF-equivalent: 5.2 (OpenAlex 2-year mean citedness, value as of 2026-10-04, retrieved 2026-10-05; not the official Clarivate IF)
Reference: Jakkula BK, Perugu S. Explainable machine learning and hybrid transformer-based proteochemometric modelling for breast cancer molecular subtyping and multi-target natural product discovery. Sci Rep. 2026 Oct 2 [Epub ahead of print]. doi:10.1038/s41598-026-71603-1.
Checked: Abstract only

See all 2 Breast papers →