{ "abstract": "Background: Gastric cancer (GC) is often diagnosed at an advanced stage, while endoscopy is invasive and conventional serum tumour markers have limited sensitivity. A low-cost, widely available tool that can identify patients at higher risk and prioritise them for endoscopic evaluation could therefore strengthen early-detection pathways. The complete blood count (CBC) is routinely available and well suited to such first-contact risk stratification; however, existing CBC-based machine-learning models are often developed in cohorts that mix prevalent, postoperative, on-treatment and surveillance records, potentially confounding the haematological signal. We therefore developed and temporally validated an explainable CBC-based model to stratify the risk of newly diagnosed GC versus benign gastric disease in a rigorously verified, treatment-naïve cohort.\n\nMethods: In this retrospective single-centre study, 2,044 patients (477 pathologically confirmed, newly diagnosed, treatment-naïve GC and 1,567 benign gastric-disease controls) were assembled through case-by-case chart review, patient-level identity de-duplication and application of the same prespecified comorbidity-screening criteria. The baseline CBC was obtained at admission before treatment. A parsimonious model incorporated six routinely available variables: age, sex, and neutrophil, lymphocyte, monocyte and platelet counts. Eight algorithms were trained using five-fold cross-validation in the training cohort (n = 1,309) and evaluated in a temporally separated validation cohort (n = 735). Random forest was designated as the reference explainable model and interpreted using SHAP. Model behaviour in tumour-marker-negative GC and robustness in sensitivity analyses were also assessed.\n\nResults: Discrimination was similar across algorithms. In temporal validation, random forest achieved an AUC of 0.831 (95% CI 0.798–0.864), which was numerically similar to that of the highest-AUC model, XGBoost (AUC 0.832), with substantially overlapping 95% confidence intervals. Random forest had a low Brier score (0.133) and showed positive net benefit across the evaluated threshold-probability range. SHAP identified lymphocyte count, male sex and age as the leading predictors, with an identical feature ranking under XGBoost (Spearman ρ = 1.00). Adding derived inflammatory ratios did not improve discrimination (ΔAUC −0.010, p = 0.139). Among temporal-validation patients with triple-negative GC, defined as CEA-, CA19-9- and CA72-4-negative disease, the model classified 62.7% (95% CI 50.0–73.9) as high risk.\n\nConclusions: A six-variable model combining pretreatment CBC parameters with age and sex discriminated newly diagnosed GC from benign gastric disease in a temporally separated validation cohort and showed broadly acceptable graphical calibration and a low Brier score. The model classified a substantial proportion of tumour-marker-negative GC cases as high risk, supporting further evaluation as a low-cost pre-endoscopic triage aid. External multicentre validation is required.", "abstract_shown": true, "affiliations": [ "Department of Clinical Laboratory, Hanzhong Central Hospital, Hanzhong, Shaanxi, China.", "Department of Pathology, Hanzhong Central Hospital, Hanzhong, Shaanxi, China.", "Department of Surgical Oncology, Hanzhong Central Hospital, Hanzhong, Shaanxi, China." ], "article_type": "research article", "arxiv": null, "author_total": 5, "authors": [ { "affs": [ 0 ], "name": "Yongfeng Qiao", "orcid": "0000-0003-4820-8591" }, { "affs": [ 1 ], "name": "Qian Long" }, { "affs": [ 0 ], "name": "Jin Tang" }, { "affs": [ 0 ], "name": "Xin Wang" }, { "affs": [ 2 ], "name": "Shouli Wang" } ], "bibtex": "https://research.draconitic.com/paper/eg17by5nt7gjh.bib", "cited_by": 0, "doi": "10.3389/fimmu.2026.1892111", "fulltext_url": "https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13716773/?tool=EBI", "id": "eg17by5nt7gjh", "issns": [ "1664-3224" ], "landing_url": "https://www.frontiersin.org/articles/10.3389/fimmu.2026.1892111/full", "language": "eng", "licence": "CC-BY-4.0", "licence_label": "CC BY 4.0", "licence_source": "article", "licence_url": "https://creativecommons.org/licenses/by/4.0/", "metadata_licence": null, "native_subjects": [ [ "heading", "Original Research" ], [ "openalex", "2730|Inflammatory Biomarkers in Disease Prognosis" ] ], "openalex": "W7222059103", "pdf_url": "https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2026.1892111/pdf", "pmcid": "PMC13716773", "pmid": "42959316", "published": "2026-10-15", "publisher": "Frontiers Media SA", "ris": "https://research.draconitic.com/paper/eg17by5nt7gjh.ris", "sources": [ { "first_seen": "2026-10-30T12:19:17Z", "native_id": "10.3389/fimmu.2026.1892111", "source": "crossref", "url": "https://www.frontiersin.org/articles/10.3389/fimmu.2026.1892111/full" }, { "first_seen": "2026-10-31T00:20:37Z", "native_id": "PMC:PMC13716773", "source": "europepmc", "url": "https://europepmc.org/article/PMC/PMC13716773" }, { "first_seen": "2026-11-01T00:20:52Z", "native_id": "MED:42959316", "source": "europepmc", "url": "https://europepmc.org/article/MED/42959316" }, { "first_seen": "2026-11-01T12:23:59Z", "native_id": "PMC13716773", "source": "pmc", "url": "https://doi.org/10.3389/fimmu.2026.1892111" } ], "subjects": [ { "field": "medicine", "origin": "openalex:2730|Inflammatory Biomarkers in Disease Prognosis", "subfield": "oncology" } ], "title": "Explainable machine learning using pretreatment complete blood count parameters and demographic characteristics for gastric cancer risk stratification: a temporal validation study", "title_text": "Explainable machine learning using pretreatment complete blood count parameters and demographic characteristics for gastric cancer risk stratification: a temporal validation study", "type": "peer-reviewed", "updated_at": "2026-11-02T12:21:13Z", "url": "https://research.draconitic.com/paper/eg17by5nt7gjh", "venue": "Frontiers in Immunology", "versions": [] }