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 May 7;16(1):3660.
doi: 10.1038/s41467-025-57990-5.

Development and external validation of prediction algorithms to improve early diagnosis of cancer

J Hippisley-Cox  1 , C A Coupland  2
Affiliations

Development and external validation of prediction algorithms to improve early diagnosis of cancer

J Hippisley-Cox et al. Nat Commun. .

Abstract

Cancer prediction algorithms are used in the UK to identify individuals at high probability of having a current, as yet undiagnosed cancer with the intention of improving early diagnosis and treatment. Here we develop and externally validate two diagnostic prediction algorithms to estimate the probability of having cancer for 15 cancer types. The first incorporates multiple predictors including age, sex, deprivation, smoking, alcohol, family history, medical diagnoses and symptoms (both general and cancer-specific symptoms). The second additionally includes commonly used blood tests (full blood count and liver function tests). We use multinomial logistic regression to develop separate equations in men and women to predict the absolute probability of 15 cancer types using a population of 7.46 million adults aged 18 to 84 years in England. We evaluate performance in two separate validation cohorts (total 2.64 million patients in England and 2.74 million from Scotland, Wales and Northern Ireland). The models have improved performance compared with existing models with improved discrimination, calibration, sensitivity and net benefit. These algorithms provide superior prediction estimates in the UK compared with existing scores and could lead to better clinical decision-making and potentially earlier diagnosis of cancer.

PubMed Disclaimer

Conflict of interest statement

Competing interests: All authors have completed the ICMJE uniform disclosure form at www.icmje.org/coi_disclosure.pdf and declare: J.H.C. reports grants from National Institute for Health Research, John Fell Oxford University Press Research Fund, Cancer Research U.K. (C5255/A18085), and other research councils, during the conduct of the study. J.H.C. is an unpaid director of QResearch, a not-for-profit organisation which is a partnership between the University of Oxford and EMIS Health who supply the QResearch database used for this work. Until 9 Aug 2023, J.H.C. had a 50% shareholding in ClinRisk Ltd, co-owning it with her husband, who was an executive director. On 9 August 2023, 100% of the share capital was donated to Endeavour Health Care Charitable Trust and the company was renamed to Endeavour Predict Ltd. J.H.C. is a consultant to Endeavour Predict Ltd. and her husband is a non-executive director to cover the transition. The company licences software both to the private sector and to NHS bodies or bodies that provide services to the NHS (through GP electronic health record providers, pharmacies, hospital providers and other NHS providers). This software implements algorithms (including QRISK3) developed from access to the QResearch database during her time at the University of Nottingham. C.C. reports receiving personal fees from ClinRisk Ltd., outside this work.

Figures

Fig. 1
Fig. 1. Fractional Polynomial Terms (age, BMI, haemoglobin).
Fractional polynomial terms showing adjusted odds ratios in model B for probability of each cancer type for age, BMI and haemoglobin in men and women.
Fig. 2
Fig. 2. Fractional Polynomial terms (white cells and platelets).
Fractional polynomial terms showing adjusted odds ratios for probability of each cancer type for white cell counts (lymphocytes, neutrophils) and platelets in men and women in Model B.
Fig. 3
Fig. 3. Fractional Polynomial Terms (liver function tests).
Fractional polynomial terms showing adjusted odds ratios for probability of each cancer type for liver function tests (albumin, alkaline phosphatase and bilirubin) in men and women in model B.
Fig. 4
Fig. 4. Discrimination.
Discrimination using c statistic values for final model A (no blood test predictors) and model B (with blood tests) in men and women aged 18–84 in the QResearch validation cohort.
Fig. 5
Fig. 5. Decision Curve Analysis.
Decision curve analysis comparing probability of any cancer using model A and Model B in men and women aged 18–84 in the English validation cohort.
See this image and copyright information in PMC

References

    1. Cancer Research UK. Cancer in the UK (Cancer Research UK, 2024).
    1. Department of Health. Improving Outcomes: A Strategy for Cancer (Department of Health, 2011).
    1. Rubin, G. et al. The expanding role of primary care in cancer control. Lancet Oncol.16, 1231–1272 (2015). - DOI - PubMed
    1. Hippisley-Cox, J. & Coupland, C. Symptoms and risk factors to identify women with suspected cancer in primary care: derivation and validation of an algorithm. Br. J. Gen. Pract.63, 11–21 (2013). - DOI - PMC - PubMed
    1. Hippisley-Cox, J. & Coupland, C. Symptoms and risk factors to identify men with suspected cancer in primary care: derivation and validation of an algorithm. Br. J. Gen. Pract.63, 1–10 (2013). - DOI - PMC - PubMed

Publication types

LinkOut - more resources