Artificial Intelligence‐Based Urine Volatomic Assay for Multi‐Cancer Detection: A Multicentric Case–Control Discovery and Internal Validation Study
Künstliche-Intelligenz-basierter Urin-Volatomik-Test zur Multi-Krebs-Erkennung: multizentrische Fall-Kontroll-Entdeckungs- und interne Validierungsstudie
Cancer Reports · 2026-11 · 9 (11)
DOI: 10.1002/cnr2.70735 ↗Auf einen Blick
Urinale VOC-Profile wurden per GC-MS und KI auf Krebsnachweis geprüft. Der Test trennte bekannte Krebsfälle von krebsfreien Kontrollen mit hoher AUC.
Fragestellung
Unterscheiden urinale Volatomik-Profile mit GC-MS und KI Personen mit bekanntem Krebs von krebsfreien Kontrollen und unterstützen sie eine explorative Zuordnung von Tumorursprung und Stadium?
Methode
Multizentrische retrospektive Fall-Kontroll-Studie; Urin von 491 therapienaiven Teilnehmenden mit 10 Krebsarten und 200 gesunden Kontrollen; interne Kreuzvalidierung mit wiederholter geschichteter Auswertung.
Ergebnisse
AUC 0,990 (95 %-KI 0,984–0,996). Bei 98 % Spezifität betrug die Sensitivität 91,9 % (451/491), der PPV 99,1 %. TOO-Genauigkeit 91,6 % (450/491; 95 %-KI 89,2 %–94,1 %).
Einschränkungen
Prospektive, verblindete Validierung in der Zielpopulation ist weiterhin erforderlich.
Schlussfolgerung der Autor:innen
Urinäre VOC-Profile enthielten ein zusammengesetztes Signal, das bekannte Krebsfälle unter interner Kreuzvalidierung von krebsfreien Kontrollen trennte und einen plausiblen Tumorursprung zuordnen konnte.
Kernaussagen
- AUC 0,990 für den Krebs-Signal-Klassifikator
- Sensitivität 91,9 % bei 98 % Spezifität
- TOO-Genauigkeit 91,6 %
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Multizentrische Studie in der Zeitschrift Cancer Reports, online erschienen am 10.11.2026. Verfasst von Scott Campit und 3 weiteren Autor:innen. Beteiligte Einrichtung: TOBY Inc., Austin, Texas, USA. Hauptthemen laut MEDLINE: Artificial Intelligence, Early Detection of Cancer, Neoplasms, Volatile Organic Compounds. Die Arbeit nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Toby Inc..
Abstract (Originalsprache)
Background
Multi‐cancer detection assays may extend early‐detection efforts beyond organ‐specific screening programs and support emerging models of oncologic primary care, including age‐ and risk‐stratified multi‐cancer screening. We evaluated urine volatile organic compound profiles (volatome), an emerging biomarker source, for its association with cancer detection.
Objective
To determine whether urinary volatome profiles measured by gas chromatography–mass spectrometry (GC–MS) and interpreted with artificial intelligence (AI) distinguish participants with known cancer from cancer‐free controls and support exploratory tissue‐of‐origin (TOO) and stage classification.
Methods
This multicenter retrospective case–control discovery study included urine from 491 treatment‐naive participants with one of 10 cancers each and 200 cancer‐free healthy controls. Three participating sites contributed de‐identified specimens. Volatome profiles were measured by GC–MS. A proprietary ensemble tree‐based AI pipeline underwent repeated stratified fivefold internal cross‐validation. Preprocessing was fitted within each training partition. Each participant contributed one sample and was assigned only once within a given fold partition. The reported cancer‐signal operating point targeted 98% specificity. TOO analysis identified the most likely cancer type and its presumed tissue of origin.
Results
The cancer‐signal classifier produced an out‐of‐fold area under the receiver operating characteristic curve (AUC) of 0.990 (95% confidence interval [CI], 0.984–0.996). At the reported 98% specificity‐optimized cutoff, sensitivity was 91.9% (451/491). The positive predictive value (PPV) was 99.1% with the cohort's 71% (491/691) cancer prevalence. Grouped TOO accuracy was 91.6% (450/491; 95% CI, 89.2%–94.1%). Among 374 cancers with a recorded stage, the early‐versus‐late detection classifier had an AUC of 0.866, and it correctly assigned 98.1% (252/257) of early‐stage cancers to the early class while recovering 25.6% (30/117) of the late‐stage cancers. Recursive removal with high feature importance values produced a small, gradual decline rather than an abrupt loss of performance across the evaluated classification tasks.
Conclusions
Urinary VOC profiles contained a composite signal that discriminated known cancer cases from cancer‐free controls under internal cross‐validation with signals that were able to identify TOO with reasonable certainty. The feature‐removal analysis was consistent with distributed predictive information rather than reliance on one dominant VOC or a small feature panel. Prospective blinded validation in the intended‐use population remains necessary to establish population‐screening accuracy, comparative superiority, or clinical utility.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- TOBY Inc., Austin, Texas, USA.
- Department of Urology, Wake Forest University, Winston-Salem, North Carolina, USA.
ORCID-Profile: Scott Campit, Sudharshanan Balaji, Matthew Laskowski, Thomas J Polascik
Förderung
- Toby Inc.
Zitieren
APA
Campit, S., Balaji, S., Laskowski, M., & Polascik, T. J. (2026). Artificial Intelligence‐Based Urine Volatomic Assay for Multi‐Cancer Detection: A Multicentric Case–Control Discovery and Internal Validation Study. Cancer Reports, 9(11). https://doi.org/10.1002/cnr2.70735
Vancouver
Campit S, Balaji S, Laskowski M, Polascik TJ. Artificial Intelligence‐Based Urine Volatomic Assay for Multi‐Cancer Detection: A Multicentric Case–Control Discovery and Internal Validation Study. Cancer Reports. 2026;9(11). doi:10.1002/cnr2.70735
BibTeX
@article{Campit2026,
author = {Campit, Scott and Balaji, Sudharshanan and Laskowski, Matthew and Polascik, Thomas J},
title = {Artificial Intelligence‐Based Urine Volatomic Assay for Multi‐Cancer Detection: A Multicentric Case–Control Discovery and Internal Validation Study},
journal = {Cancer Reports},
year = {2026},
volume = {9},
number = {11},
doi = {10.1002/cnr2.70735}
}
EUVIMED