SEARCH · Search PubMed

Results for “Cancer detection”

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 19 recordsLinked to original sources

PubMed2026

Large-scale simulation of coverage and error rate tradeoffs for cancer detection in cell-free DNA whole-genome sequencing.

MOTIVATION: Cell-free DNA (cfDNA) whole-genome sequencing (WGS) is a promising approach for detecting cancer recurrence. It enables cancer detection by identifying all tumor-derived cfDNA (ctDNA) molecules carrying somatic single nucleotide variants (sSNVs). While ideally, a sequencing platform should be highly accurate for reliable ctDNA detection, in reality, all sequencing platforms introduce sequencing errors that generate false positives indistinguishable from true SNVs. Understanding how sequencing parameters influence ctDNA detection sensitivity at low tumor fractions (TFs) in cfDNA samples is essential for guiding sequencing strategies in clinical contexts. To model cfDNA sequencing for tumor detection, which contains asymmetric noise and multiple interacting parameters, analytical modeling is intractable, motivating large-scale parallelized simulation. RESULTS: We developed a simulation framework to generate in silico cfDNA data across 10 cancer types. In total, 480 million cfDNA samples were simulated from tumor WGS profiles. Overall, the lowest detectable TF differs substantially between cancer types under identical sequencing conditions due to variations in mutational load. For cancers with high mutational load, 3× coverage with low-error techniques reliably detects TFs below 0.1%. In contrast, cancers with low mutational load require at least six-fold higher coverage to achieve comparable detection thresholds. Increasing sequencing quality scores from Q30 to Q55 at 30× coverage further enhances sensitivity, enabling detection of TFs as low as 1 × 10-5. This study provides a comprehensive framework for optimizing sequencing parameters, offering valuable guidance for tailoring future technology development for specific cancer types and clinical applications. AVAILABILITY AND IMPLEMENTATION: The code is publicly available at https://github.com/UMCUGenetics/cfdetect/tree/main.

Whole Genome Sequencing↗

PubMed2025

Circulating microRNA panels for multi-cancer detection and gastric cancer screening: leveraging a network biology approach.

BACKGROUND: Screening tests, particularly liquid biopsy with circulating miRNAs, hold significant potential for non-invasive cancer detection before symptoms manifest. METHODS: This study aimed to identify biomarkers with high sensitivity and specificity for multiple and specific cancer screening. 972 Serum miRNA profiles were compared across thirteen cancer types and healthy individuals using weighted miRNA co-expression network analysis. To prioritize miRNAs, module membership measure and miRNA trait significance were employed. Subsequently, for specific cancer screening, gastric cancer was focused on, using a similar strategy and a further step of preservation analysis. Machine learning techniques were then applied to evaluate two distinct miRNA panels: one for multi-cancer screening and another for gastric cancer classification. RESULTS: The first panel (hsa-miR-8073, hsa-miR-614, hsa-miR-548ah-5p, hsa-miR-1258) achieved 96.1% accuracy, 96% specificity, and 98.6% sensitivity in multi-cancer screening. The second panel (hsa-miR-1228-5p, hsa-miR-1343-3p, hsa-miR-6765-5p, hsa-miR-6787-5p) showed promise in detecting gastric cancer with 87% accuracy, 90% specificity, and 89% sensitivity. CONCLUSIONS: Both panels exhibit potential for patient classification in diagnostic and prognostic applications, highlighting the significance of liquid biopsy in advancing cancer screening methodologies.

Neoplasms↗

PubMed2026

Novel serum small extracellular vesicle miRNAs with multi-target RCA-CRISPR sensor for liver cancer detection.

BACKGROUND: Detecting liver cancer (LC) remains a significant challenge in clinical practice. Small extracellular vesicle (sEV) miRNAs show promise as non-invasive biomarkers for LC detection, yet their diagnostic potential remains largely unexplored. This study aimed to identify specific sEV miRNA signatures for LC detection and develop a novel synchronized multi-miRNA detection platform to enhance diagnostic efficiency and sensitivity. METHODS: High-throughput sequencing was conducted across four distinct cohorts: normal controls (NC), hepatitis B virus (HBV) patients, liver cirrhosis patients, and LC patients. This sequencing process identified miRNAs with differential expression, followed by RT-qPCR validation in serum sEV miRNAs from LC patients and NC. An innovative detection method, RCA-CRISPR, was introduced, combining rolling circle amplification (RCA) with CRISPR/Cas12a (RCA-CRISPR) for quick and sensitive miRNAs detection. RESULTS: Sequencing results showed a consistent elevation of hsa-miR-203b-5p, hsa-miR-4661-5p, and hsa-miR-219a-2-3p across all cohorts. RT-qPCR validations confirmed significant upregulation of these miRNAs in serum sEVs from LC patients, and the combined three-miRNA panel exhibited high diagnostic accuracy (p = 0.0003; AUC = 0.81). The RCA-CRISPR method demonstrated a detection limit of 3.12 pM for simultaneous multi-target miRNA detection, highlighting its exceptional sensitivity. CONCLUSIONS: Our study identifies hsa-miR-203b-5p, hsa-miR-4661-5p, and hsa-miR-219a-2-3p as promising sEV miRNA biomarkers for LC detection. The developed RCA-CRISPR sensor provides a robust tool for multi-miRNA analysis, potentially advancing non-invasive LC diagnostics. Future validation in larger, prospectively collected cohorts is essential to establish the clinical utility and performance of this biomarker panel and RCA-CRISPR sensor.

MicroRNAs↗

PubMed2026

Development and preliminary validation of plasma cell-free DNA methylation-based diagnostic prediction model for colorectal cancer detection.

BACKGROUND: Colorectal cancer (CRC) is a common malignancy associated with genetic and epigenetic alterations. Several methylation biomarkers have been investigated for non-invasive CRC detection; however, their reported performance varies across clinical settings, and the detection of early-stage or precancerous disease and discrimination from non-malignant colorectal conditions remain challenging. This exploratory study aimed to identify reproducible CRC-associated plasma cell-free DNA (cfDNA) methylation regions and to develop and preliminarily evaluate diagnostic prediction model for distinguishing CRC from healthy controls and benign samples. METHODS: Public CRC tissue methylation datasets from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) were analyzed to identify reproducible CRC-associated methylation alterations. Plasma cfDNA methylation was profiled using methyl-CpG-binding-domain enrichment followed by paired-end sequencing in patients with CRC, patients with colorectal polyps, and healthy controls. After quality-control filtering, 30 CRC and healthy-control samples were randomly allocated at the participant level in a 7:3 ratio to a development set comprising 10 patients with CRC and 11 healthy controls and a held-out test set comprising 4 patients with CRC and 5 healthy controls. Hypermethylated regions were selected using least absolute shrinkage and selection operator (LASSO) logistic regression. The 12-region model was evaluated in the held-out test set and subsequently applied to 10 colorectal polyp samples without refitting or recalibration. RESULTS: Tissue methylation analysis identified reproducible CRC-associated alterations across independent datasets. In the plasma development set, 707 differentially methylated regions (DMRs) were identified between CRC and healthy-control samples, including 324 hypermethylated and 383 hypomethylated regions. LASSO regression selected a 12-region hypermethylation signature. In the held-out test set, the model achieved an area under the curve (AUC) of 0.85 [95% confidence interval (CI): 0.579-1.000]. At the development-set-derived threshold, sensitivity was 75.0% (3/4), specificity was 60.0% (3/5), and accuracy was 66.7% (6/9). When the original model was applied to colorectal polyp samples, model scores were significantly higher in both CRC and polyp samples than in healthy controls, while CRC samples showed a tendency toward higher scores than polyp samples. CONCLUSIONS: This exploratory study identified a 12-region plasma cfDNA hypermethylation signature associated with CRC and developed a LASSO-based diagnostic prediction model that showed preliminary discrimination between CRC and healthy controls in a small held-out test set. By integrating tissue methylation evidence with plasma cfDNA profiling, this study expands the repertoire of candidate region-level methylation markers for blood-based CRC detection.

Colorectal cancer (CRC)↗

PubMed2025

Discovery and performance of DNA methylation panels for cancer detection and classification in blood.

Examining DNA in a liquid biopsy for non-invasive cancer detection relies on identifying dilute signal in a high background. This study aims to identify DNA methylation biomarkers for multi-cancer detection. Utilizing large tissue datasets, we apply novel search algorithms to discover confined biomarker panels capable of distinguishing tumor from normal and determining the tissue of origin. We explore the applicability to blood-based testing using targeted methylation sequencing followed by machine learning classification. We present an 8-marker panel, which successfully predicts tumors across 14 types with a 91% average sensitivity, maintaining a low false positive rate (< 0.04%). Additionally, a panel of 39 CpG sites exhibits accuracies ranging from 69% to 98% for identifying tissue of origin. When tested on 114 patient plasma samples (colon, liver, pancreatic, prostate, and stomach cancer), the 8-marker panel obtains an AUC of 0.78 with a 78% sensitivity among 32 early-stage patients (stage I-II), and 60% overall. Using the 39-marker panel in a multi-class classification model selecting only the best match, 54% of tumor samples were on average correctly assigned to the tissue of origin, and up to 80% when allowing more inclusive criteria. Using a limited set of biomarkers, our work contributes to advancing non-invasive cancer diagnostics.

DNA methylation↗

PubMed2026

Non-invasive strategy for gastric cancer detection: Integration of cell-free DNA fragmentomics and protein biomarkers.

Gastric cancer (GC) ranks as the fifth most common cancer worldwide, however, accurate and non-invasive diagnostic modalities for GC remain limited. Cell-free DNA (cfDNA) fragmentomics has emerged as a promising tool for cancer cell detection. Here we develop a gastric cancer detection model, named GaFraD model. The GaFraD model uses four cfDNA fragmentomics features, including fragment size ratio (FSR), copy number variation (CNV), 9-bp end motif (Motif), and fragment size at transcription start sites (TF). This model achieves an area under the receiver-operating characteristic curve (AUC) of 0.970 (95% CI: 0.944 - 0.990), a sensitivity of 95.0% and a specificity of 80.9%. By combining the GaFraD model and conventional protein biomarkers CA19-9 and PG-I/PG-II, the CONFIRM model was generated. The CONFIRM model attained an AUC of 0.986 (95% CI: 0.966 - 1.000), a sensitivity of 95.0% and a specificity of 95.6% in detecting GC. Moreover, the CONFIRM model achieved remarkable performance (AUC = 0.983, sensitivity 95.6%, specificity 94.2%) in distinguishing patients with early-stage GC from controls. Our work showed the high discriminatory power in distinguishing GC patients from controls, indicating the clinical potential of using cfDNA fragmentomics combined with protein biomarkers for non-invasive GC detection. The results of the study provide a new avenue for early, accurate, and non-invasive clinical diagnosis of GC.

Cell-free DNA↗

PubMed2025

Enhancing the sensitivity of non-invasive cervical cancer detection using CpG methylation haplotype profiling.

DNA methylation is a critical epigenetic modification that regulates gene expression and plays a significant role in cancer development. This methylation signature can be detected in cancer-derived DNA from non-invasive samples, such as plasma, urine or Pap smears. However, in early-stage cancers-when detection is most critical-the concentration of cancer DNA is often low, limiting the sensitivity of current detection methods. Traditional DNA methylation detection techniques, which rely on methylation ratio-based measurements, may obscure subtle variations in methylation patterns, further reducing detection sensitivity. In this study, we analyzed cervical scraping specimens and examined whether detecting cancer-specific methylation patterns in cervical cancer could be enhanced using a Highly Methylated Haplotype (HMH) approach. This novel approach captures highly methylated haplotypes at single-molecule resolution using next-generation sequencing, providing greater detail than conventional methods. HMHs in specific DNA regions are a hallmark of cancer and stand out in contrast to sporadic methylation commonly observed in non-cancerous tissues. We applied HMH profiling to a gene panel of four biomarkers (CA10, DPP10, FMN2, and HAS1) previously validated in cervical cancer studies. At pre-specified cutoffs (99th percentile of normals), haplotype-based scoring achieved 89.9% sensitivity for invasive cancer at high specificity (~ 94-98%), outperforming median (78.0%) and single-CpG (71.6%) methods. For clinically relevant endpoints, the combined panel detected 51-52% of CIN2 + and 66-67% of CIN3 + cases, again exceeding the performance of median- and single-CpG-based scoring methods.These findings demonstrate the potential of HMH to substantially enhance sensitivity in cervical cancer detection, offering a promising approach for non-invasive diagnostics.

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↗

PubMed2026

Advancing cancer detection and treatment using longitudinal routine clinical data.

Cancer management remains fragmented across its continuum, from late-stage diagnosis and salvage therapies to non-personalized surveillance. Here, we present Oncoformer, a unified multimodal transformer model trained on the China Oncology Multimodal Prediction and Surveillance Study (COMPASS) cohort (3.67 million individuals, 17.7 million clinical visits) and validated on independent external cohorts, including the UK Biobank. Oncoformer integrates longitudinal electronic health records with chest X-ray imaging to address multiple clinical tasks: pan-cancer diagnosis (area under the receiver operating characteristic curve [AUROC] = 0.956), future cancer prediction up to 1 year before diagnosis (AUROC = 0.869), tumor stage inference (mean AUROC > 0.90), patient-specific treatment-response forecasting, and recurrence-free survival stratification across ten cancer types (all p < 0.01). Staging predictions were independently validated against postoperative pathological endpoints and shown to converge on core cancer genomic pathways. By translating routine clinical data into a dynamic view of cancer evolution, Oncoformer provides a framework for risk-informed cancer prediction and treatment stratification using routine clinical data.

Humans↗

PubMed2026

Multicancer Detection Tests for Population-Wide Screening of Asymptomatic Individuals: A Systematic Review.

PURPOSE: Multicancer detection (MCD) tests aim to detect different cancer types using a single test. However, evidence on their potential for screening asymptomatic populations remains limited. We consolidated evidence from prospective cohort studies evaluating blood-based MCD tests in primarily asymptomatic adults to contextualize upcoming randomized controlled trial results. MATERIALS AND METHODS: We updated and extended a prior review (to September 2023), conducting comprehensive Medline/Embase searches to February 1, 2026. Key outcomes included cancers detected and not detected by MCD tests, false-positive MCD tests, and diagnostic investigation pathways. Risk of bias (RoB) was assessed using a modified Quality Assessment of Diagnostic Accuracy Studies-2 tool. RESULTS: From 2,723 screened records (244 previously shortlisted to 2023, 2,479 records for 2023-2026), we included 18 articles (12 studies, nine MCD tests); of these, 11 articles had not appeared in prior reviews. Cancer detection rates varied widely between studies, for example, new MCD-test-detected invasive cancers diagnosed ≤12 months post-test ranging from 18.8 (95% CI, 11.0 to 30.1) to 43.8 (95% CI, 29.4 to 62.8) per 10,000 tested, with MCD-test-detected invasive stage I to II cancers ranging from 9.0 (95% CI, 4.2 to 17.2) to 21.0 (95% CI, 11.6 to 35.5) per 10,000 tested. False-positives exceeded MCD-test-detected cancers (eg, approximately 1.6-fold in PATHFINDER, 1.5-fold K-DETEK, 4.2-fold DETECT-A, 8.1-fold SeekInCare studies). Diagnostic investigation pathways were prespecified/suggested in four of eight interventional studies. Where reported, the median time to diagnostic resolution varied from <0.1 months to 4 months for MCD-test-detected cancers, with substantially higher 75th percentiles (3.1-7 months), and similar patterns were observed for false-positive MCD tests. No study was judged to have overall low RoB. CONCLUSION: Substantial heterogeneity in cancer yield metrics likely reflects differences in MCD technologies, diagnostic pathways, follow-up duration, and background standard-of-care screening. Long-term follow-up, randomized trials, fully-paired test comparisons, and implementation research are essential to determine the potential of MCD tests for population screening.

Journal Article↗

PubMed2026

Uncovering the diagnostic potential of seminal fluid beyond fertility: cfDNA methylation analysis for the detection of clinically significant prostate cancer.

Research on the potential use of seminal fluid as a liquid biopsy for prostate cancer detection has been limited due to challenges associated with acquisition of this bodily fluid in clinical studies. Here we sought to expand on our previous analysis, which demonstrated high levels of prostate-derived cell free DNA (cfDNA) in seminal fluid in presumed healthy individuals, to a much larger cohort that included participants with prostate cancer. A total of 279 men scheduled for prostate biopsy were enrolled over 4 months across 12 sites. Prior to their biopsy, participants mailed a seminal fluid sample collected at home to the laboratory, from which cfDNA was extracted and underwent methylation analysis. Consistent with our earlier study in healthy individuals, we observed an abundance of high molecular weight (HMW) cfDNA in all samples. Tissue-of-origin deconvolution revealed that granulocytes and sperm were the principal contributors to seminal fluid cfDNA, while prostate-derived cfDNA was present at abundances readily detectable with current technologies. The nucleosomal fraction was very pronounced in some but not all samples and was determined to be correlated with the relative sperm signal. The sperm signal was also observed to be associated with an increase in small insert sizes (< 125 bp) in the sequenced libraries. Unsupervised clustering revealed two distinct populations driven by the abundance of sperm and granulocytes. Since summarizing at the genomic region level confounded tissues of different origins, fragment-level DNA methylation features were used to characterize and quantify the prostate cancer related signal, and features associated with clinically significant prostate cancer were identified. This study expands on our previous work to further characterize seminal fluid and highlights its potential as a promising liquid biopsy medium for the detection and monitoring of clinically significant prostate cancer.

Humans↗

PubMed2026

Liquid Biopsy of HPV Cell-Free DNA Enables Blood-Based Early Detection and Molecular Stratification of HPV-Associated Cancer and Precancer Stages.

Liquid biopsies targeting circulating tumor DNA enable noninvasive cancer detection but lack sensitivity in pre- and early- cancer stages, where clinical benefits would be greatest. Human papillomavirus (HPV) causes six cancer types, accounting for 5% of all cancers worldwide. Targeting HPV cell-free (cf)DNA offers a compelling opportunity to overcome current liquid biopsy constraints due to its unique tumor-specific origin, lack of sequence homology to the human genome, and the high viral-to-human copy ratio per cell. Utilizing HPV-associated anal cancer and precancer as a model, here we applied a custom, multi-feature HPV whole-genome liquid biopsy to biobanked and prospective screening cohorts spanning the HPV infection-precancer-cancer continuum. HPV cfDNA was detected years before cancer diagnosis and as early as the infection stage, with increasing detection as stages advanced. Genomic hallmarks of HPV malignancy, including HPV integration, PIK3CA mutations, and 3q amplification, were detected exclusively in cancer, while precancers exhibited distinct HPV genotypes. Fragmentomics analysis of HPV cfDNA revealed stage-informative signatures reflecting viral epigenetic changes during carcinogenesis. A unified classifier incorporating genomic and fragmentomics features achieved a mean AUC of 0.77 for identifying cancer and high-grade precancer, stages requiring clinical intervention. Together, these findings demonstrate the feasibility of blood-based screening and molecular risk stratification for HPV-associated cancer and precancer.

Journal Article↗

PubMed2025

Modeling Early-Onset Cancer Kinetics Reveals Changes in Underlying Risk and the Impact of Population Screening.

UNLABELLED: Recent studies have reported increases in early-onset cancer cases (diagnosed less than 50 years of age) and raised questions about whether the increase is related to earlier diagnosis from nonspecific medical tests as reflected by decreasing tumor-size-at-diagnosis (apparent effects) or actual increases in underlying cancer risk (true effects), or both. The classic Multistage Clonal Expansion (MSCE) model assumes cancer detection at the first malignant cell's emergence, although later modifications have included lag-times or stochasticity in detection to represent the delay in tumor detection. In this study, we introduced an approach to explicitly incorporate tumor-size-at-diagnosis in the MSCE framework accounting for improvements in cancer detection over time to distinguish between apparent and true increases in early-onset cancer incidence. The model was structurally identifiable and provided better parameter estimation than the classic model. The model was applied to colorectal, breast, and thyroid cancers to examine changes in cancer risk while accounting for detection improvements over time in three representative birth cohorts (1950-1954, 1965-1969, and 1980-1984). The analyses suggested accelerated carcinogenic events and shorter mean sojourn times (the average time from the first malignant cell emergence to cancer detection) in more recent cohorts. Furthermore, using this model to examine the screening impact on the incidence of breast and colorectal cancers, for which both have established screening protocols, provided results that align with well-documented differences in screening effects between these cancers. These findings underscore the importance of incorporating tumor-size-at-diagnosis in cancer modeling and support true increases in early-onset cancer risk in recent years for breast, colorectal, and thyroid cancers. SIGNIFICANCE: A model of early-onset cancer trends that distinguishes true risk from detection effects accurately captures cancer kinetics, trends in cancer progression, and the impact of screening, which could inform cancer prevention strategies. This article is part of a special series: Driving Cancer Discoveries with Computational Research, Data Science, and Machine Learning/AI .

Humans↗

PubMed2026

Circulating tumor human papillomavirus DNA whole genome sequencing enables human papillomavirus-associated oropharynx cancer early detection.

BACKGROUND: Early detection of HPV-associated oropharyngeal squamous cell carcinoma, the most common HPV cancer in the United States, could reduce disease-related morbidity and mortality, yet currently, there are no early detection tests. HPV circulating tumor DNA (ctDNA) is a sensitive and specific biomarker for HPV-associated oropharyngeal squamous cell carcinoma at diagnosis. It is unknown if ctDNA HPV is detectable prior to diagnosis, and thus its potential as an early detection test is also unknown. METHODS: Plasma samples from the Mass General Brigham Biobank collected 1.3-10.8 years prior to diagnosis from HPV-associated oropharyngeal squamous cell carcinoma patients (n = 28) and age- and sex-matched controls (n = 28) were blinded and run on a newly developed and validated multifeature HPV whole genome sequencing liquid biopsy assay and a validated HPV antibody assay. RESULTS: HPV ctDNA results were positive in 22 of 28 prediagnostic samples from HPV-associated oropharyngeal squamous cell carcinoma cases (sensitivity 79%) with a maximum lead time of 7.8 years. HPV ctDNA results were negative in all controls (0 of 28, 100% specificity). Diagnostic accuracy was highest within 4 years of cancer diagnosis and was higher than HPV Ab detection within the same timeframe (P = .004). Application of a machine-learning model trained and tested on an independent cohort of 306 cases and controls increased the sensitivity of detection to 27 of 28 cases (overall sensitivity 96%) and the maximum lead time to 10.3 years. CONCLUSIONS: HPV ctDNA can be detected in the blood years prior to diagnosis with HPV-associated oropharyngeal squamous cell carcinoma, with high specificity, in a case-control cohort of 56 participants. HPV ctDNA detection alone, or in combination with previously identified serological biomarkers, may be a feasible approach to early detection of HPV-associated oropharyngeal squamous cell carcinoma.

Humans↗

PubMed2026

Machine learning approaches for cancer prognosis and diagnosis via non-coding RNA: a comprehensive review.

Non-coding RNAs (ncRNAs), once considered genomic dark matter, are now established as key regulators of gene expression with widespread roles in cellular homeostasis and disease. In cancer, ncRNA expression is frequently and systematically dysregulated, and many of these molecules circulate in stable, protected form within biofluids, offering a compelling basis for non-invasive or minimally invasive diagnostic strategies. However, their clinical translation remains substantially hindered to date due to biological complexity, technical noise, and high dimensionality inherent to ncRNA expression datasets. In this context, machine learning (ML) has emerged as a powerful analytical tool to address these challenges, enabling the identification of subtle, reproducible ncRNA signatures predictive of diverse malignancies. This review critically evaluates ML-driven frameworks for cancer diagnosis and prognosis across four ncRNA subclasses, namely miRNAs, lncRNAs, circRNAs, and piRNAs, while also acknowledging the biophysical and thermodynamic models that reinforce ncRNA bioinformatics. Despite substantial methodological progress in ML-based cancer diagnosis and prognosis, key challenges persist, including tumor biological heterogeneity, limited multicenter validation, and the lack of widely adopted standardized protocols for preprocessing, normalization, and reporting workflows. Furthermore, many current ML models lack interpretability in biological or clinical context, constraining their translational utility. By synthesizing recent advances and identifying unresolved barriers, this review charts a roadmap for developing a robust, clinically actionable ncRNA biomarker platform for cancer detection. With global cancer incidence projected to exceed 35 million annual cases by 2050, validated ncRNA-ML-driven frameworks hold potential to revolutionize early-stage detection and personalized therapeutic strategies, thereby reducing the escalating socio-economic burden of cancer worldwide.

Humans↗

PubMed2026

Artificial intelligence-supported double reading in European population breast cancer screening: A systematic review and meta-analysis of prospective programs.

BACKGROUND: Most European population mammography screening programs rely on double reading with arbitration, a model that delivers mortality benefit but is increasingly challenged by radiologist workload, variable specificity, and interval cancers. Artificial intelligence (AI) is being evaluated to support or optimize these established European screening pathways. PURPOSE: To synthesize prospective or program-embedded evaluations of AI conducted within European-style population screening programs and to estimate exploratory program-level absolute risk differences (RDs) per 1000 examinations for cancer detection rate (CDR) and recall. MATERIALS AND METHODS: We performed a prespecified, focused evidence synthesis of three large studies embedded within routine population screening programs operating under European-relevant workflows: MASAI (randomized AI-supported risk triage within a national program), ScreenTrustCAD (prospective paired-reader evaluation with AI as an independent reader in a double-reading framework), and PRAIM (nationwide decision-referral implementation). Outcomes were harmonized as AI-control RDs per 1000 examinations. Random-effects pooling used Hartung-Knapp-Sidik-Jonkman models. For the paired-reader design, sensitivity analyses applied a Kish effective sample-size approach across plausible within-examination correlations (ρ = 0.3-0.8). Positive predictive value (PPV) and workflow/time outcomes were summarized descriptively. RESULTS: Across 597,419 examinations, the pooled CDR RD was +0.9 per 1000 (95% CI -0.0 to +1.8; I2 ≈ 12%), consistent with a modest directional increase with borderline statistical uncertainty. The pooled recall RD was -0.6 per 1000 (95% CI -3.1 to +2.1; I2 ≈ 41-43%), indicating no consistent recall increase across screening programs. Where reported, PPV was higher with AI-supported screening. Efficiency signals included 44.3% fewer total readings in MASAI and shorter reading times for AI-normal examinations in PRAIM; in PRAIM, a program-level safety-net mechanism recovered 204 cancers that would otherwise have been missed. CONCLUSION: In European population screening programs characterized by double reading and arbitration, prospective program-embedded evidence suggests that AI integration may yield a small absolute increase in cancer detection (≈1/1000) without a consistent increase in recall, alongside improved PPV and efficiency signals. These findings suggestAI primarily as a complementary reader within European screening workflows, with implementation requiring explicit quality assurance and monitoring of interval cancers and stage distribution.

Humans↗

PubMed2025

Real-world deployment of a fine-tuned pathology foundation model for lung cancer biomarker detection.

Artificial intelligence models using digital histopathology slides stained with hematoxylin and eosin offer promising, tissue-preserving diagnostic tools for patients with cancer. Despite their advantages, their clinical utility in real-world settings remains unproven. Assessing EGFR mutations in lung adenocarcinoma demands rapid, accurate and cost-effective tests that preserve tissue for genomic sequencing. PCR-based assays provide rapid results but with reduced accuracy compared with next-generation sequencing and require additional tissue. Computational biomarkers leveraging modern foundation models can address these limitations. Here we assembled a large international clinical dataset of digital lung adenocarcinoma slides (N = 8,461) to develop a computational EGFR biomarker. Our model fine-tunes an open-source foundation model, improving task-specific performance with out-of-center generalization and clinical-grade accuracy on primary and metastatic specimens (mean area under the curve: internal 0.847, external 0.870). To evaluate real-world clinical translation, we conducted a prospective silent trial of the biomarker on primary samples, achieving an area under the curve of 0.890. The artificial-intelligence-assisted workflow reduced the number of rapid molecular tests needed by up to 43% while maintaining the current clinical standard performance. Our retrospective and prospective analyses demonstrate the real-world clinical utility of a computational pathology biomarker.

Humans↗

PubMed2025

Detecting known neoepitopes, gene fusions, transposable elements, and circular RNAs in cell-free RNA.

MOTIVATION: Cancer is the second leading cause of death worldwide, and although there have been advances in treatments, including immunotherapies, these often require biopsies which can be costly and invasive to obtain. Due to lack of pre-emptive cancer detection methods, many cases of cancer are detected at a late stage when the definitive symptoms appear. Plasma samples are relatively easy to obtain, and they can be used to monitor the molecular signatures of ongoing processes in the body. Profiling cell-free DNA is a popular method for monitoring cancer, but only a few studies have explored the use of cell-free RNA (cfRNA), which shows the recent footprint of systemic transcription. RESULTS: Here, we developed FastNeo, a computational method for detecting known neoepitopes in human cfRNA. We show that neoepitopes and other biomarkers detected in cfRNA can discern Hepatocellular carcinoma patients from the healthy patients with a sensitivity of 0.84 and a specificity of 0.79. For colorectal cancer we achieve a sensitivity of 0.87 and a specificity of 0.8. An important advantage of our cfRNA based approach is that it also reports putative neoepitopes which are important for therapeutic purposes. AVAILABILITY AND IMPLEMENTATION: The FastNeo package is available at https://github.com/yashumayank/FastNeo and https://zenodo.org/records/11521368. The benchmark pipelines to detect Immune Epitope database and Tumor-Specific Neoantigen database neoepitopes using HaplotypeCaller, bcftools, and Lofreq, and to run FastNeo with STAR instead of Bowtie2 are also available in the above github repository.

Humans↗