Routine laboratory trajectories predict organ-level complications in cancer
Routine laboratory panels drawn during cancer treatment constitute longitudinal physiological recordings of organ function, yet their temporal structure is discarded by single-timepoint prognostic tools. A transformer trained on 2,777,595 laboratory measurements from 3905 patients with multiple myeloma or ovarian cancer predicted which of 162 treatment-associated complications would be newly recorded within two years, spanning eight clinical categories, achieving 1.5- to 6.1-fold enrichment above prevalence. Across individual endpoints it exceeded non-sequential baselines, including engineered-trajectory models, by +0.024 to +0.070 in mean AUROC. Predictions generalised across both cancers, divergence concentrating in disease-specific complications, and biomarker masking recovered signatures consistent with established pathophysiology. External validation on MIMIC-IV and MMRF CoMMpass showed transferability, strongest for renal and metabolic endpoints, attenuated for infection endpoints. On CoMMpass it added prognostic value to ISS staging. Routine oncological laboratory data carry complication-specific physiological signal months before a complication is recorded, and require no testing beyond standard oncological care.
Authors
- Marion Högner
- Keno K. Bressem (ORCID: https://orcid.org/0000-0001-9249-8624)
- Krischan Braitsch (ORCID: https://orcid.org/0000-0003-4028-5357)
- Tristan Lemke (ORCID: https://orcid.org/0009-0006-4269-142X)
- Sebastian Ziegelmayer (ORCID: https://orcid.org/0000-0001-8724-4718)
- Jacqueline Lammert (ORCID: https://orcid.org/0000-0002-0380-574X)
- Florian Gabriel (ORCID: https://orcid.org/0000-0002-2528-6506)
- Christian Wachinger (ORCID: https://orcid.org/0000-0002-3652-1874)
- Anirudh Narayanan
- Jannik Lübberstedt
- Christof Winter (ORCID: https://orcid.org/0000-0002-0253-9056)
- Friedrich Puttkammer
- Hartmut Häntze (ORCID: https://orcid.org/0000-0002-6204-571X)
- Florian Bassermann
- Marcus Makowski
- Johannes Moll (ORCID: https://orcid.org/0009-0001-5237-0850)
- Fabian Drexel (ORCID: https://orcid.org/0009-0000-6735-5154)
- Andrei Zhukov
- Christopher Zirn
- Zeineb Ben Chaaben
- Jan Kirschke
- Su Hwan Kim (ORCID: https://orcid.org/0000-0002-5383-2041)
- Lisa Adams (ORCID: https://orcid.org/0000-0001-5836-4542)
- Markus Graf (ORCID: https://orcid.org/0000-0002-8468-2349)
Institutions
- TUM Klinikum (DE)
- National Center for Tumor Diseases (DE)
- Essen University Hospital (DE)
- Deutsches Herzzentrum München (DE)
- Deutsches Konsortium für Translationale Krebsforschung (DE)
- Technical University of Munich (DE)
- Charité - Universitätsmedizin Berlin (DE)
Publication Details
- Journal
- npj Digital Medicine
- Published
- 2026-11-17
- DOI
- https://doi.org/10.1038/s41746-026-03405-8
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Amgen
- Bristol-Myers Squibb
- Pfizer
- Sanofi
- Bayerisches Staatsministerium für Gesundheit, Pflege und Prävention