Towards a data-driven system for personalized cervical cancer risk stratification

Abstract

Mass-screening programs for cervical cancer prevention in the Nordic countries have been effective in reducing cancer incidence and mortality at the population level. Women who have been regularly diagnosed with normal screening exams represent a sub-population with a low risk of disease and distinctive screening strategies which avoid over-screening while identifying those with high-grade lesions are needed to improve the existing one-size-fits-all approach. Machine learning methods for more personalized cervical cancer risk estimation may be of great utility to screening programs shifting to more targeted screening. However, deriving personalized risk prediction models is challenging as effective screening has made cervical cancer rare and the exam results are strongly skewed towards normal. Moreover, changes in female lifestyle and screening habits over time can cause a non-stationary data distribution. In this paper, we treat cervical cancer risk prediction as a longitudinal forecasting problem. We define risk estimators by extending existing frameworks developed on cervical cancer screening data to incremental learning for longitudinal risk predictions and compare these estimators to machine learning methods popular in biomedical applications. As input to the prediction models, we utilize all the available data from the individual screening histories.Using data from the Cancer Registry of Norway, we find in numerical experiments that the models are strongly biased towards normal results due to imbalanced data. To identify females at risk of cancer development, we adapt an imbalanced classification strategy to non-stationary data. Using this strategy, we estimate the absolute risk from longitudinal model predictions and a hold-out set of screening data. Comparing absolute risk curves demonstrate that prediction models can closely reflect the absolute risk observed in the hold-out set. Such models have great potential for improving cervical cancer risk stratification for more personalized screening recommendations.

The future of cervical cancer prevention: advances in research and technology

“…For instance, the My CancerIQ tool for cervical cancer risk assessment prompts users to inquire about factors influencing their cervical cancer risk, such as age, smoking habits, and family cancer history. Subsequently, the tool computes the user's risk by referencing studies involving individuals aged ≥ 40 years with no prior cancer history [50]. Apart from online tools, precision medicine strategies utilizing genomic applications and digital health interventions can also offer individualized risk evaluations for cervical cancer.…”

Cervical cancer risk stratification based on nationwide electronic health data: a retrospective modelling and validation study from Estonia

“…We opted to create new models instead of validating or updating existing ones due to variations in target populations, measurement procedures, changes over time and access to the nationwide health data. Although the models promise potentially e cient estimation of outcomes, cervical cancer prediction model development and validation remains in its infancy, grappling with the challenges of re ning its algorithms and data sources 24 . Following internal validation, external validation, and randomized controlled trials are essential steps to further validate the model's performance across diverse populations and settings, ensuring robustness and generalizability in clinical practice.…”

Acceptability of risk-based triage in cervical cancer screening: A focus group study

“…In an optimized risk-based scenario, the individual risk of developing CIN2+ would determine the intensity of the follow-up trajectory, improving the population benefit-harm ratio. A recent study has indeed shown that accurate risk classification can be improved to develop a personalized cervical cancer screening program [ 19 ].…”