Matrix factorization for the reconstruction of cervical cancer screening histories and prediction of future screening results

• Published in: BMC bioinformatics 2022-11, Vol.23 (Suppl 12), p.1-484, Article 484
• Main Authors: Langberg, Geir Severin R. E, Stapnes, Mikal, Nygård, Jan F, Nygård, Mari, Grasmair, Markus, Naumova, Valeriya
• Format: Article
• Language: English
• Subjects: Algorithms; Cancer; Cancer screening; Cellular biology; Cervical cancer; Cervix; Customization; Deep learning; Diagnosis; Experiments; Factorization; Females; Health risks; Histology; Human papillomavirus; Mathematical analysis; Mathematical models; Matrix completion; Matrix factorization; Medical history taking; Medical informatics; Medical screening; Methodology; Methods; Numerical models; Performance evaluation; Population-level cancer prevention; Prediction models; Reconstruction; Regularization; Risk; Technology application; Time series
• ISSN: 1471-2105; 1471-2105
• DOI: 10.1186/s12859-022-04949-8

Mass screening programs for cervical cancer prevention in the Nordic countries have strongly reduced cancer incidence and mortality at the population level. An alternative to the current mass screening is a more personalised screening strategy adapting the recommendations to each individual. However, this necessitates reliable risk prediction models accounting for disease dynamics and individual data. Herein we propose a novel matrix factorisation framework to classify females by the time-varying risk of being diagnosed with cervical cancer. We cast the problem as a time-series prediction model where the data from females in the Norwegian screening population are represented as sparse vectors in time and then combined into a single matrix. Using novel temporal regularisation and discrepancy terms for the cervical cancer screening context, we reconstruct complete screening profiles from this scarce matrix and use these to predict the next exam results indicating the risk of cervical cancer. The algorithm is validated on both synthetic and registry screening data by measuring the probability of agreement (PoA) between Kaplan-Meier estimates. In numerical experiments on synthetic data, we demonstrate that the novel regularisation and discrepancy term can improve the data reconstruction ability as well as prediction performance over varying data scarcity. Using a hold-out set of screening data, we compare several numerical models and find that the proposed framework attains the strongest PoA. We observe strong correlations between the empirical survival curves from our method and the hold-out data, and evaluate the ability of our framework to predict the females' next results for up to five years ahead in time using only their current screening histories as input. We have proposed a matrix factorization model for predicting future screening results and evaluated its performance in a female cohort to demonstrate the potential for developing prediction models for more personalized cervical cancer screening.