Background Breast cancer (BC) remains the most diagnosed malignancy and leading cancer-related cause of mortality in women worldwide. Although blood-based untargeted metabolomics has emerged as a promising modality for detecting early-stage BC, the clinical translation of this approach has been bottlenecked by two unresolved issues: (i) the field has almost exclusively relied on serum or plasma, which require venipuncture and cold-chain logistics, and (ii) machine-learning models reported on such data are frequently validated with protocols that are blind to analytical batch structure, producing optimistically biased performance estimates.

Methods We present a breast cancer detection study based on dried blood spots (DBS), an analytical matrix that enables self-collection and ambient-temperature shipping. A cohort of 2,734 participants (114 biopsy-confirmed BC cases; 2,620 non-cancer controls) was profiled by untargeted LC-MS/MS on a Thermo Scientific Orbitrap IQ-X coupled to a Vanquish UHPLC. A 39-metabolite panel meeting MSI Level 1 identification criteria [1] was pre-specified a priori from the published breast-cancer metabolomics literature, frozen prior to LC-MS acquisition, and applied to the present cohort without any feature selection on the data. Six standard supervised-learning architectures (LASSO, Elastic Net, Linear SVM, PLS-DA, OPLS-DA, XGBoost) were evaluated on this pre-specified panel; OPLS-DA, whose pyopls implementation does not integrate cleanly into the repeated multi-seed batch-aware protocol, is reported only in the sex-matched subgroup analysis where a single-seed 5-fold stratified protocol permits a directly comparable fit. Per-batch control-median normalization is applied upstream, following the protocol of the companion same-lab study [2], which removes batch-specific intensity shifts at the data-preparation stage; kNN imputation, log transform, and robust scaling are then fit within each training fold. The evaluation battery comprises batch-aware StratifiedGroupKFold CV reported at single-seed (seed=42) with inter-seed SD quantified across 10 independent seeds, batch-aware nested CV, a 100-seed held-out 20%-batch validation with disjoint-batch isotonic probability calibration (30% calibration partition), PPV/NPV reporting at multiple operating points and three deployment prevalences, subgroup analyses by TNM stage and tumor grade, pathway-ablation sensitivity analysis, and a 1,000-iteration permutation test.

Results Under batch-aware evaluation (StratifiedGroupKFold, single-seed=42), AUC ranged from 0.914 to 0.949 across classifiers, with LASSO achieving 0.928 and XGBoost 0.949; inter-seed SD across 10 seeds was 0.002-0.006. At 95% specificity, LASSO reached 75.4% sensitivity and XGBoost 81.6%. Held-out batch validation (100 seeds) yielded mean AUC 0.912 for Elastic Net and 0.935 for XGBoost, confirming robust generalization. All 39 panel features showed high coefficient stability, and permutation testing on representative classifiers (LASSO, Linear SVM, PLS-DA) yielded p ≤ 0.001. Subgroup analyses showed weaker detection of stage IIA tumors (AUC 0.87, n=40) compared with stage IIB/IIIA (AUC 0.95), consistent with stronger metabolic signatures in more advanced disease. Bootstrap coefficient consistency of the Elastic Net classifier confirmed that all 39 panel features received a non-zero multivariate weight in >=80% of 100 stratified bootstraps. Permutation testing on the three representative classifiers subjected to this analysis (LASSO, Linear SVM, PLS-DA) confirmed significance at p ≤ 0.001 in all three cases.

Conclusions On this cohort of diagnosed, pre-treatment breast-cancer cases, DBS LC-MS metabolomic profiling delivers classification performance (AUC 0.928 for LASSO and 0.949 for XGBoost under batch-aware GroupKFold CV at single-seed=42; held-out AUC 0.912-0.935) that is robust across classifier families and biological pathways. The DBS matrix is non-radiating, self-collectable by finger-prick, and mailable at ambient temperature. The approach complements the established venous-blood workflow while addressing a clear infrastructural gap identified over nearly a decade of preliminary work [3, 4]. Performance is weaker on stage IIA than on more advanced disease, and prospective validation in an independent asymptomatic screening cohort is required before clinical positioning as a decentralized triage modality.

All authors are employees and shareholders of BioTwin Inc. N.A. serves as Chief Scientific Officer, P.H. serves as Chief Technology Officer, and L.-P.N. serves as Chief Executive Officer and Founder. BioTwin Inc. develops DBS-based metabolomic diagnostic solutions, and the breast-cancer detection panel described in this work is the subject of pending intellectual property protection. The authors declare that the scientific conclusions presented in this manuscript are not influenced by these financial and intellectual property interests.

This work was funded entirely by BioTwin Inc. (internal R&D budget). No external government grants or agency funding were received for this study.

I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained.

Yes

The details of the IRB/oversight body that provided approval or exemption for the research described are given below:

Ethics committee/IRB of Canadian SHIELD Ethics Review Board gave ethical approval for this work (REB Tracking Number: 2023-11-003; OHRP Registration IORG0003491; FDA Registration IRB00004157; initial approval granted December 15, 2020; continuing review approval granted April 30, 2025, valid through April 29, 2026). All participants provided written informed consent prior to enrollment.

I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals.

Yes

I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance).

Yes

I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable.

Yes