Development of a liver cancer risk prediction model for the general population in china: A potential tool for screening

Feng, Xiaoshuang; Li, N.; Wang, G.; Chen, S.; Lyu, Zhangyan; Wei, Luopei; Li, X.; Wen, Yan; Giovannucci, Edward; Wu, Shouling; Dai, Min; He, Jinsong

doi:10.1093/annonc/mdz422.008

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While early clinical trial results show promising outcomes 11 and large-scale trials are currently conducted 12 , risk adjusted targeting of the most susceptible individuals could further increase efficiency and enable broader implementation across age groups. Many bespoke risk models have been developed for specific cancer types including Colorectal [13][14][15] , Melanoma [16][17][18] , Lung 19-21 Prostate [22][23][24] , Breast [25][26][27][28] , Pancreatic 29,30 , Liver [31][32][33] , Stomach 34,35 , Kidney cancer 36 or AML 37 . The emergence of multi-cancer early detection tests warrant the development of pan-cancer risk models, which have recently been developed building on polygenic risk scores 38 or primary care data 39 .…”

Section: Introductionmentioning

confidence: 99%

Multi-cancer risk stratification based on national health data: A retrospective modelling and validation study

Jung

Holm

Gaurav

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Health care is experiencing a drive towards digitisation and many countries are implementing national health data resources. Digital medicine promises to identify individuals at elevated risk of disease who may benefit from screening or interventions. This is particularly needed for cancer where early detection improves outcomes. While a range of cancer risk models exists, the utility of population-wide electronic health databases for risk stratification across cancer types has not been fully explored. Methods We use time-dependent Bayesian Cox Hazard models built on modern machine learning frameworks to scale the statistical approach to 6.7 million Danish individuals covering 193 million life-years over a period from 1978-2015. A set of 1,392 covariates from available clinical disease trajectories, text-mined basic health factors and family histories are used to train predictive models of 20 major cancer types. The models are validated on cancer incidence between 2015-2018 across Denmark and on 0.35 million individuals in the UK Biobank. Findings The predictive performance of models was found to exceed age-sex-based predictions in all but one cancer type. Models trained on Danish data perform similarly on the UK Biobank in a direct transfer without any additional retraining. Cancer risks are associated, in addition to heritable components, with a broad range of preceding diagnoses and health factors. The best overall performance was seen for cancers of the digestive system but also Thyroid, Kidney and Uterine Cancers. Risk-adapted cohorts may on average include 25% individuals younger than age-sex-based cohorts with similar incidence. Interpretation Data available in national electronic health databases can be used to approximate cancer risk factors and enable risk predictions in most cancer types. Model predictions generalise between the Danish and UK health care systems and may help to enable cancer screening in younger age groups. Funding Novo Nordisk Foundation.

show abstract