SEARCH · Search PubMed

Results for “Cancer prediction”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 37 records · Page 2Linked to original sources

PubMed2026

Sensitivity to Endocrine Therapy Index Predicts Benefit from Weekly Adjuvant Paclitaxel for Hormone Receptor-Positive Breast Cancer in the GEICAM/9906 Trial.

PURPOSE: To independently validate that low endocrine transcriptional activity measured by the sensitivity to endocrine therapy (SETER/PR) index in hormone receptor-positive (HR+) breast cancer predicts benefit from dose-dense paclitaxel chemotherapy within a second prospective-retrospective biomarker study. EXPERIMENTAL DESIGN: We conducted a blinded, prospective-retrospective biomarker analysis within the GEICAM/9906 trial (NCT00129922), which compared adjuvant 5-fluorouracil, epirubicin, and cyclophosphamide (FEC) followed by weekly paclitaxel (P) versus six cycles of FEC in lymph node-positive breast cancer. The SETER/PR index was measured in all available HR+/HER2- tumor RNA samples using a prespecified cut point (<0.75). The primary endpoint was the distant recurrence-free interval (DRFI); secondary endpoints were overall survival (OS) and breast cancer-specific survival (BCSS). RESULTS: Of 647 HR+/HER2- tumors, 567 (87.6%) passed assay quality control (279 FEC + P; 288 FEC). A low SETER/PR index was identified in 92 tumors (16.2%). There was a significant interaction between SETER/PR status and treatment on DRFI (P = 0.046). Among patients with a low SETER/PR index, FEC + P significantly improved DRFI [hazard ratio (HR), 0.46; 95% confidence interval (CI), 0.22-0.95; P = 0.035], with similar results after adjustment (HR, 0.48; 95% CI, 0.24-1; P = 0.049). No treatment benefit was observed for SETER/PR ≥0.75 (HR, 1.02; 95% CI, 0.70-1.47; P = 0.931). Differences in OS and BCSS did not reach significance. CONCLUSIONS: Low endocrine transcriptional activity predicts benefit from adding weekly paclitaxel to anthracycline-based adjuvant chemotherapy in HR+/HER2- breast cancer. These findings independently validate the SETER/PR index as a predictive biomarker for paclitaxel-based chemotherapy and support its potential role in guiding regimen selection.

Humans↗

PubMed2026

NMR metabolomics and glycomics for cancer detection in patients with non-specific symptoms: a prospective observational cohort study.

BACKGROUND: Early cancer diagnosis in patients with non-specific symptoms is limited by the lack of discriminatory tests. Within the Oxfordshire Suspected CANcer (SCAN) pathway, exploratory biomarker work showed that serum 1H NMR-based metabolomics can identify cancer with high accuracy. SCAN2 evaluated whether integrating metabolomics with glycomics provides complementary molecular information and improves discrimination in a clinically complex, real-world population. METHODS: Serum from 369 SCAN patients (59 cancers) was analysed using AXINON® System-derived NMR metabolomics and HPLC-MS glycomics. Machine-learning models were trained to predict cancer status, with performance assessed by receiver operating characteristic (ROC) analysis of pooled cross-validated predictions. To place cancer risk in a broader clinical context, a second classifier modelling alternative non-cancer diagnosis was incorporated, and mean predicted probabilities from both models were jointly projected into a two-dimensional space, maintaining strict separation of training and test data. FINDINGS: In the full cohort, integration of glycomics with metabolomics achieved an AUC of 0.814 (95% CI 0.808-0.820). In a refined sub-cohort excluding major comorbidities and selected cancer types (32 cancers, 277 non-cancers), performance improved to an AUC of 0.884 (95% CI 0.879-0.890). Discriminatory features included cancer-associated biantennary fucosylated glycans alongside amino acid metabolites (glutamate, histidine) and lipoprotein-related measures. A classifier distinguishing metastatic from non-metastatic disease (n = 29 vs. 30) achieved an AUC of 0.80. Joint probability analysis in the full cohort preserved cancer-associated signatures across comorbidity burden, with projection-based classification achieving an accuracy of 89.2% (95% CI 85.7-92.6). INTERPRETATION: These findings validate the SCAN1 metabolomic signature in a more clinically complex cohort and indicate that integrating glycomics with metabolomics provides complementary biological information for cancer discrimination. Joint probability analysis provides an interpretable framework for cancer risk stratification within multimorbid diagnostic pathways, supporting the clinical potential of scalable multi-omics blood testing. FUNDING: EPSRC, EU Horizon 2020, Wellcome/MLSTF, Novo Nordisk Foundation.

Humans↗

PubMed2025

Impact of personalised risk predictions on breast cancer risk perceptions: insights from the BREATHE study.

OBJECTIVE: Biennial mammography screening is well-established for women aged 50 and above, but guidelines for younger women are less clear. Risk-based screening may provide women with key information to make informed decisions about their breast cancer risk and screening. This study examines how predicted breast cancer (BC) risk shapes women's perception and confidence in risk prediction. METHODS: Women aged 35 to 59 years were recruited for a prospective multi-centre cohort and stratified into above-average, average, or below-average BC risk categories based on genetic and non-genetic risk factors. Perceived risk was assessed at enrolment and after participants were informed of their predicted risk. We used ordinal models to identify predictors of perceived risk and logistic regression to examine the relationship between changes in perceived risk and confidence in the risk prediction. RESULTS: At enrolment, 43% and 47% of 4112 participants perceived their BC risk pre-result as low or average, respectively. Thirty-five percent adjusted their perceived risk to align more closely with their predicted risk. Predictors of perceived risk post-result: perceived risk pre-result, predicted risk, ethnicity and having regular menstruation. Participants who underestimated their BC risk were nearly eight times more likely to have low confidence in the accuracy of their predicted risk (OR for underestimation vs. accurate perception: 7.94 [95% CI 5.60-11.28]). Predictors of perceived risk post-result: perceived risk pre-result, predicted risk, ethnicity and having regular menstruation. Confidence in risk prediction was lowest when women's perceived risk pre-result was lower than their predicted risk (OR-2 vs 0 [95%CI] 5.06 [3.67 to 6.97]). CONCLUSION: Many women underestimated their BC risk, and their initial perceptions were influenced by the knowledge of their predicted risk. Women who underestimated their risk had less confidence in their predicted risk scores.

Humans↗

PubMed2026

GBFN: A gated bimodal fusion network leveraging foundation model embeddings for cancer drug sensitivity prediction.

Despite recent progress in deep learning for cancer drug sensitivity prediction, many existing models still rely on task-specific representation learning or relatively simple multimodal fusion, which may limit their ability to capture complex drug-cell interactions. To address this issue, we developed GBFN, a gated bimodal fusion network for continuous IC50 prediction that integrates pretrained drug and cell-line representations. Specifically, drug embeddings were obtained from SMI-TED, whereas cell-line embeddings were derived from transcriptomic profiles using BulkFormer. These two modalities were then combined through a dimension-wise gated fusion module and used to predict IC50 values in matched drug-cell line pairs. On the CCLE-based benchmark, GBFN outperformed representative neural baselines, including GraphDRP, TGSA, and TransEDRP, and achieved the best overall performance, with an R² of 0.8714 and an RMSE of 0.8938. Moreover, ablation analysis showed that the model using drug features and cell-line expression data with gated fusion performed better than the corresponding model using direct concatenation, indicating that the improvement was associated with the fusion strategy rather than with the input modalities alone. In addition, cell-line expression data were more informative than mutation data in the present setting, and adding mutation data to the model using drug features and expression data did not further improve performance. Across major cancer types, GBFN maintained generally high cell-line-level predictive performance, and perturbation-based attribution identified biologically relevant transcriptomic programs in selected drug-cell line settings. Together, these findings support GBFN as a compact and effective framework for continuous drug response prediction.

Humans↗

PubMed2026

Using cancer profiles to identify synthetic lethal therapeutic targets and predictive biomarkers in cancer gene dependency data.

MOTIVATION: Large scale loss-of-function screens utilising CRISPR or siRNA can provide profound insights into the importance of individual genes for the survival of a cancer cell and can drive the identification of therapeutic targets and biomarkers, and the development of targeted drugs. However, the analysis of these data and the substantial bodies of metadata that relate to them, is technically challenging and typically requires substantial expertise in data science and computer coding. RESULTS: To facilitate the analysis of cancer gene dependency data by cancer biologists and clinical scientists, we have developed DepMine-a computational toolkit providing a powerful system for framing complex queries relating cancer gene dependency to the underlying genetic changes that occur in cancer cells. DepMine identifies synthetic lethal relationships between putative target genes and complex 'cancer profiles' built from user-specified combinations of mutations, copy-number variation, and expression levels, and can refine these to optimal biomarker definitions for target dependency. AVAILABILITY: The Python implementation of DepMine and associated data files can be obtained at https://github.com/UOSbioinformaticslab/depmine and is free to academics and Not-For-Profit organisations. The DepMine release referenced in this paper is archived as DOI: 10.5281/zenodo.19570601.

Humans↗

PubMed2026

Targeting cancer stem cells predicts response and reverses chemoresistance in ascites-derived ovarian cancer organoids.

BACKGROUND: Ovarian cancer (OC) is frequently diagnosed at an advanced stage, where tumor heterogeneity and rapid development of chemoresistance contribute to a poor prognosis. The lack of reliable predictive biomarkers further hinders the development of effective treatment strategies. Patient-derived organoids (PDOs) have recently emerged as promising preclinical models with the potential to predict therapeutic responses. METHODS: OC PDOs were generated from ascites samples representing diverse histological subtypes. Histological and genomic fidelity to parental tumors was confirmed through histopathological analysis and whole-exome sequencing. Drug sensitivity to cisplatin and poly (ADP-ribose) polymerase (PARP) inhibitors was evaluated and correlated with 1-year clinical outcomes. We also investigated the therapeutic efficacy of oncolytic herpes simplex virus 2 (OH2) both as a single agent and in combination with cisplatin. The expression of cancer stem cell (CSC) markers CD44 and ALDH1A1 under treatment conditions was analyzed using immunohistochemistry and flow cytometry. RESULTS: PDOs were successfully established with an 86.2% success rate. These PDOs faithfully recapitulated the histopathological and genomic features of their corresponding tumors, maintaining intratumoral heterogeneity, and were amenable to xenotransplantation. Drug sensitivity assays demonstrated that PDOs accurately predicted patient-specific responses to cisplatin and PARP inhibitors. OH2 exhibited direct cytotoxicity in both cisplatin-sensitive and cisplatin-resistant PDOs, reducing cell viability by 20-60%. Notably, the combination treatment with OH2 and cisplatin enhanced antitumor efficacy, resulting in a significant reduction of the CD44+CSC subpopulation. CONCLUSIONS: Ascites-derived OC PDOs represent a robust platform for individualized drug testing. The combination of OH2 and cisplatin offers a novel and effective strategy for circumventing chemoresistance in OC.

Female↗

PubMed2026

Beyond predictive performance: A systematic review and critical methodological appraisal of AI/ML and conventional modelling strategies in breast, colorectal, and pancreatic Cancer.

BACKGROUND: Predictive modelling for cancer risk, treatment-related complications, and survival is central to precision oncology. Conventional logistic regression (LR) and Cox proportional hazards (CoxPH) regression remain widely used but are limited when modelling nonlinear interactions, high-dimensional imaging features, and multimodal clinical-metabolic predictors. Artificial intelligence (AI) and machine learning (ML) methods offer expanded capability through automated feature extraction, ensemble learning, and flexible survival modelling, but the evidence on when AI/ML adds value over conventional models across cancer sites and predictive tasks remains fragmented. OBJECTIVE: To systematically evaluate the methodological performance, validation strategies, and translational limitations of AI/ML models compared with conventional statistical models in published predictive-modelling studies for breast, colorectal, or pancreatic cancer. METHODS: PubMed, Scopus, and Web of Science were searched for studies published between January 2019 and March 2025. Two reviewers independently conducted title-and-abstract screening, full-text eligibility assessment, and PROBAST risk-of-bias assessment. Sixty-five studies (n = 907,567 participants) were narratively synthesised by cancer site, predictive task, model family, comparator, validation strategy, predictor modality, and calibration or explainability reporting. RESULTS: The 65 studies comprised breast cancer (n = 35), colorectal cancer (n = 21), and pancreatic cancer (n = 9). AI/ML superiority over LR and CoxPH was task- and data-dependent. CNN- and U-Net-based models predominated in imaging and body-composition tasks, tree-based ensembles consistently outperformed LR for tabular perioperative complication prediction, and CoxPH remained competitive, and in the largest pancreatic risk study, superior to XGBoost (C-index 0.802 vs 0.723) in well-structured datasets. PROBAST analysis-domain risk was moderate in 54 of 65 studies (83%), driven by limited external validation, sparse calibration reporting (11/65), and few decision-curve analyses (7/65). CONCLUSION: AI/ML adds the most methodological value in imaging-derived feature extraction and nonlinear perioperative prediction, while conventional regression remains preferable in large, structured datasets with linear predictors. Clinical translation requires standardised body-composition definitions, external validation, calibration assessment, decision-curve analysis, and explainability, in line with TRIPOD+AI and CLAIM standards.

Humans↗

PubMed2026

An overview of the DNA damage response in female reproductive system and breast cancers: A narrative review.

The DNA damage response (DDR) is a fundamental cellular network that preserves genomic integrity, and its dysregulation drives initiation, progression, and therapeutic response in female reproductive system and breast cancers. This narrative review provides a comparative analysis of DDR alterations across ovarian, endometrial, cervical, and breast cancers, synthesizing molecular studies, clinical trials, and international guidelines from PubMed/MEDLINE, Scopus, and Web of Science. DDR alterations vary substantially among these cancers, reflecting differences in tissue origin, hormonal regulation, and viral oncogenesis. Homologous recombination repair defects, particularly in breast cancer susceptibility 1/2, partner and localizer of BRCA2, ataxia telangiectasia mutated, and checkpoint kinase 2), are prevalent in ovarian, endometrial, and breast cancers, predicting sensitivity to platinum-based chemotherapy and poly (ADP-ribose) polymerase inhibitors. In endometrial cancer, homologous recombination deficiency predominates in high-grade tumor protein p53-mutated subtypes, while Fanconi anemia pathway alterations characterize aggressive serous carcinomas. Cervical cancer exhibits virus-induced DDR disruption and replication stress. Quantitative biomarkers, including tumor mutational burden, microsatellite instability, Radiation sensitive 51, Fanconi anemia complementation group D2, excision repair cross-complementation group 1, and DDR-related microRNAs enable patient stratification. Emerging ataxia telangiectasia and Rad3-related and WEE1 inhibitors show promise in combination regimens. Understanding of tumor-specific DDR enables rational therapeutic stratification, providing a framework for precision oncology.

DNA damage response, Ovarian neoplasms, Endometria↗

PubMed2025

Computational Pathology for Accurate Prediction of Breast Cancer Recurrence: Development and Validation of a Deep Learning-Based Tool.

Accurate recurrence risk stratification is crucial for optimizing treatment plans for breast cancer patients. Current prognostic tools like Oncotype DX offer valuable genomic insights into hormone receptor-positive and human epidermal growth factor receptor-negative patients but are limited by cost and accessibility, particularly in underserved populations. In this study, we present Deep-Breast-Cancer-Recurrence (BCR)-Auto, a deep learning-based computational pathology approach that predicts breast cancer recurrence risk from routine hematoxylin and eosin-stained whole slide images. Our methodology was validated on 2 independent cohorts: The Cancer Genome Atlas Program breast cancer data set and an in-house data set from The Ohio State University. Deep-BCR-Auto demonstrated robust performance in stratifying patients into low- and high-recurrence risk categories. On The Cancer Genome Atlas Program breast cancer data set, the model achieved an area under the receiver operating characteristic curve of 0.827, significantly outperforming the existing weakly supervised models (P = .041). In the independent The Ohio State University data set, Deep-BCR-Auto maintained strong generalizability, achieving an area under the receiver operating characteristic curve of 0.832, along with 82.0% accuracy, 85.0% specificity, and 67.7% sensitivity. These findings highlight the potential of computational pathology as a cost-effective alternative for recurrence risk assessment, broadening access to personalized treatment strategies. This study underscores the clinical utility of integrating deep learning-based computational pathology into routine pathological assessment for breast cancer prognosis across diverse clinical settings.

Humans↗

PubMed2026

Predictive biomarkers in cancer immunotherapy for genitourinary malignancies.

Immunotherapy has transformed the management of genitourinary cancers, offering durable responses in selected patient groups. However, the clinical benefit of immune checkpoint inhibitors varies significantly across renal cell carcinoma, urothelial carcinoma, and prostate cancer, underscoring the need for reliable predictive biomarkers. This review summarizes current knowledge on established and emerging biomarkers, including PD L1 expression, tumor mutational burden, molecular subtypes, genomic alterations, tumor microenvironment characteristics, circulating biomarkers, microbiome influences, and multi omic integrative approaches. We discuss their potential clinical relevance, limitations, and applicability across different tumor types. Future directions emphasize the development of composite biomarkers, standardization of testing platforms, real time monitoring strategies, and the integration of advanced technologies such as artificial intelligence and spatial profiling. Understanding and validating these biomarkers will be essential for optimizing personalized immunotherapy in genitourinary cancers.

Circulating tumor DNA↗

PubMed1975

[Toluidine blue staining in laryngeal diseases (author's transl)].

The authors present the results of 83 consecutive in vivo stainings with toluidine blue in various laryngeal diseases. Thirty one (86%) of the 36 malignant tumors showed positive staining. (95% confidence limits: 70-95.) It is concluded that malignant tumors will nearly always fix the dye, and that a negative staining test seems to be evidence against cancer. (Predictive value of negative test: 0.89, 95% confidence limits: 76-96.

Carcinoma in Situ↗

PubMed1978

Recent results of in vitro drug prediction in human tumour chemotherapy.

To assess the clinical value of the organ culture drug prediction assay in the present study we summarize the results of two randomized trials in lung carcinoma (61 patients) and ovarian carcinoma (74 patients) comparing predicted and non-predicted or no surgical adjuvant chemotherapy. No real progress could be achieved by predicted cancer chemotherapy. The reasons of the negative results of our studies are discussed.

Antineoplastic Agents↗

PubMedDate not supplied

Predictive value of cancer statistics.

The value of routinely collected cancer statistics for hypothesis generation and for risk prediction is examined in relation to age, place, migration, time, anatomical sub-site, morphology, and occupation. Current descriptive epidemiological data of this nature reflect the carcinogenic exposures of the past 40 years, and are thus useful for generating hypotheses. While they do not permit prediction of risk associated with a new substance entering the environment, once etiology for a given cancer is known, the likely course of events unless preventive action is taken can be forecast on the basis of existing statistics.

Age Factors↗

PubMed2026

Longitudinal genome-wide aneuploidy measurements in circulating cell-free DNA to predict lack of benefit from pembrolizumab in patients with metastatic urothelial cancer.

Accurate prediction of lack of benefit from pembrolizumab in patients with metastatic urothelial cancer (mUC) is an unmet need. We investigated the dynamics of circulating tumor DNA (ctDNA) load, estimated using the modified fast aneuploidy screening test-sequencing system (mFast-SeqS), as a potential biomarker for early on-treatment identification of treatment response. A total of 104 patients with mUC treated with pembrolizumab from two prospective biomarker discovery trials were included and mFast-SeqS was performed on paired blood samples collected at baseline and on-treatment. Patients with a high on-treatment aneuploidy score (≥ 5, n = 26) had a shorter median OS than patients with a low (< 5) score (n = 76) (3 vs 17 months: P-value< 0.001). Patients with an increased (n = 10), stable (n = 66), or decreased (n = 28) on-treatment score relative to their baseline score had a median PFS of 1.5, 4.0, and 8.3 months, respectively. Median OS was 3.0, 11.1, and 18.7 months, respectively. In patients with mUC treated with pembrolizumab, the on-treatment mFast-SeqS-based ctDNA level and its dynamics relative to baseline are independent prognostic markers that can be used to identify patients that are unlikely to benefit from pembrolizumab.

Humans↗

PubMed1979

Predictive value of serial carcinoembryonic antigen levels in long-term follow-up of ovarian cancer.

The predictive value of serial levels of carcinoembryonic antigen (CEA) in tumor monitoring was examined in 213 patients with ovarian cancer; each patient had been followed-up at monthly intervals for at least 12 months. CEA was not detectable throughout the period of observation in 35% of the patients. In general. patterns showing a disappearance of CEA or persistently low levels were associated with a good prognosis, whereas those showing a reappearance or highly elevated and rising levels were associated with a poor prognosis. A transient reappearance of CEA was observed in 10 patients; this did not appear to be associated with tumor recurrence or progression. "False positive" results were obtained in 6 patients in whom no tumor has been clinically detectable to date. "False negative" results were obtained in 4 patients with obvious tumor progression. In terms of a good or poor prognosis, the use of CEA levels was highly accurate in patients with minimal or no residual disease (97% and 89%, respectively); the rate fell to 62% in patients with extensive disease. As the clinical significance and limitations become better known, serial CEA levels should contribute substantially to the monitoring of patients with ovarian cancer.

Carcinoembryonic Antigen↗

PubMed2026

EPIC: Event Prototyping via Information Constrained graph learning for personalized cancer driver gene prediction.

MOTIVATION: Precision oncology relies on accurately distinguishing patient-specific driver mutations from the vast background of passenger alterations. While graph-based computational methods have emerged as powerful tools for this task, they often struggle to preserve the distinct genomic context of individual mutations within complex biological networks. Consequently, subtle patient-specific driver signals are frequently obscured by dominant topological patterns, critically impeding the identification of individualized oncogenic events essential for personalized cancer therapy. RESULTS: To address this, we propose EPIC, a novel framework for Event Prototyping via Information Constrained Graph Learning. Unlike traditional node-centric approaches, EPIC redefines driver prediction as a metric learning task in an event embedding space. We introduce an information-constrained learning strategy that imposes explicit geometric constraints on feature variance, effectively preventing feature collapse and ensuring that low-frequency driver signals are distinctively preserved. Experiments on large-scale cancer cohorts demonstrate that EPIC significantly outperforms established baselines. Notably, the model prioritizes low-frequency driver variants typically overlooked by population-based methods, mapping them to critical oncogenic mechanisms associated with drug resistance and metastasis. Furthermore, clinical actionability analysis confirms that EPIC substantially expands the patient population eligible for targeted therapies. EPIC provides a robust and context-aware solution for personalized cancer driver discovery, bridging the gap between genomic data and actionable therapeutic insights. AVAILABILITY AND IMPLEMENTATION: The source code and datasets are available at https://github.com/spcho-dev/EPIC.

Humans↗

PubMed2024

Pan-cancer analysis of biallelic inactivation in tumor suppressor genes identifies KEAP1 zygosity as a predictive biomarker in lung cancer.

The canonical model of tumor suppressor gene (TSG)-mediated oncogenesis posits that loss of both alleles is necessary for inactivation. Here, through allele-specific analysis of sequencing data from 48,179 cancer patients, we define the prevalence, selective pressure for, and functional consequences of biallelic inactivation across TSGs. TSGs largely assort into distinct classes associated with either pan-cancer (Class 1) or lineage-specific (Class 2) patterns of selection for biallelic loss, although some TSGs are predominantly monoallelically inactivated (Class 3/4). We demonstrate that selection for biallelic inactivation can be utilized to identify driver genes in non-canonical contexts, including among variants of unknown significance (VUSs) of several TSGs such as KEAP1. Genomic, functional, and clinical data collectively indicate that KEAP1 VUSs phenocopy established KEAP1 oncogenic alleles and that zygosity, rather than variant classification, is predictive of therapeutic response. TSG zygosity is therefore a fundamental determinant of disease etiology and therapeutic sensitivity.

Kelch-Like ECH-Associated Protein 1↗

PubMed1978

Predictive tests for cancer chemotherapy.

Explore the source record for details and available documents.

Animals↗