Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Feb 7;15(2):271-285.
doi: 10.1158/2159-8290.CD-24-0760.

The Hallmarks of Predictive Oncology

Akshat Singhal  1 , Xiaoyu Zhao  2 , Patrick Wall  3 , Emily So  4 , Guido Calderini  5   6 , Alexander Partin  7 , Natasha Koussa  8 , Priyanka Vasanthakumari  7 , Oleksandr Narykov  7 , Yitan Zhu  7 , Sara E Jones  8 , Farnoosh Abbas-Aghababazadeh  4 , Sisira Kadambat Nair  4 , Jean-Christophe Bélisle-Pipon  5 , Athmeya Jayaram  9 , Barbara A Parker  10 , Kay T Yeung  10 , Jason I Griffiths  11 , Ryan Weil  8 , Aritro Nath  11 , Benjamin Haibe-Kains  4   12   13   14 , Trey Ideker  1   2   3   10
Affiliations

The Hallmarks of Predictive Oncology

Akshat Singhal et al. Cancer Discov. .

Abstract

As the field of artificial intelligence evolves rapidly, these hallmarks are intended to capture fundamental, complementary concepts necessary for the progress and timely adoption of predictive modeling in precision oncology. Through these hallmarks, we hope to establish standards and guidelines that enable the symbiotic development of artificial intelligence and precision oncology.

PubMed Disclaimer

Conflict of interest statement

TI is a co-founder, member of the advisory board, and has an equity interest in Data4Cure and Serinus Biosciences. TI is a consultant for and has an equity interest in Ideaya Biosciences. The terms of these arrangements have been reviewed and approved by the University of California San Diego in accordance with its conflict-of-interest policies. B.A.P. has received research support to the institution from Pfizer, Genentech/Roche, Novartis, GlaxoSmithKline and Oncternal Therapeutics and had received consulting income from Daré Bioscience. K.T.Y received research support to the institution from Dantari, Gilead, Jazz Pharmaceuticals, Pfizer, Treadwell Therapeutics, and Zymeworks.

Figures

Figure 1.
Figure 1.. Predictive modeling workflow and development timeline.
A, High-level schematic of the standard pipeline for formulating a modern predictive oncology model. B, Approximate number of predictive oncology models published per year over the time period 2000 – 2023. PubMed query using search string ‘predictive oncology AND (“machine learning” OR “artificial intelligence”)’ with filter: ‘from 2000 – 2023’.
Figure 2.
Figure 2.. The seven hallmarks of predictive oncology.
Starting from the top left, in clockwise order the proposed hallmarks are: Data Relevance and Actionability (yellow), Expressive Architecture (blue), Standardized Benchmarking (black), Demonstrated Generalizability (green), Mechanistic Interpretability (orange), Accessibility and Reproducibility (purple) and Fairness (pink), with Ethics underlying each of these hallmarks (yellow ring).
Figure 3.
Figure 3.. Framework for ensuring fairness of a predictive oncology model.
From left to right are depicted four key aspects of fairness, related to A, training, B, testing, C, interpretation, and D, communication. SDH, Social Determinants of Health; ICD, International Classification of Diseases. Created in BioRender.
Figure 4.
Figure 4.. Sample model rating and comparison, with self-critique of authors’ own model.
A, Overview of the TCRP model (Transfer of Cellular Response Prediction) approach. Adapted with permission from Ma et al. (134). B, Scorecard for the TCRP model based on the criteria defined for scoring each hallmark.
See this image and copyright information in PMC

Similar articles

See all similar articles

References

    1. National Research Council, Division on Earth and Life Studies, Board on Life Sciences, Committee on A Framework for Developing a New Taxonomy of Disease. Toward Precision Medicine: Building a Knowledge Network for Biomedical Research and a New Taxonomy of Disease. National Academies Press; 2012.
    1. Ashley EA. Towards precision medicine. Nat Rev Genet. 2016;17:507–22. - PubMed
    1. Nelson MR, Tipney H, Painter JL, Shen J, Nicoletti P, Shen Y, et al. The support of human genetic evidence for approved drug indications. Nat Genet. 2015;47:856–60. - PubMed
    1. Faderl S, Talpaz M, Estrov Z, O’Brien S, Kurzrock R, Kantarjian HM. The biology of chronic myeloid leukemia. N Engl J Med. 1999;341:164–72. - PubMed
    1. Druker BJ, Sawyers CL, Kantarjian H, Resta DJ, Reese SF, Ford JM, et al. Activity of a specific inhibitor of the BCR-ABL tyrosine kinase in the blast crisis of chronic myeloid leukemia and acute lymphoblastic leukemia with the Philadelphia chromosome. N Engl J Med. 2001;344:1038–42. - PubMed