Comparing Kaplan‐Meier curves with the probability of agreement

Stevens, Nathaniel T.; Lu, Lu

doi:10.1002/sim.8744

Cited by 9 publications

(10 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 we compare performance scores, (Eq. ( 8 )) for different models, indicating the probability of agreement [ 13 ] between hold-out data and predictions. Predicting based on Eq.…”

Section: Resultsmentioning

confidence: 99%

“…Classification performance on synthetic data of varying data density . Model performance is given as the probability of agreement [ 13 ] score ( from ( 8 )) with CI. Higher signifies better model fit.…”

Section: Resultsmentioning

confidence: 99%

“…To illustrate the potential for developing risk prediction models for more personalized screening recommendations, we validated the framework on the NCCSP registry data using Kaplan-Meier (K-M) estimates from model predictions and a hold-out set. The K-M curves showed a strong correlation and a corresponding high probability of agreement (PoA) [ 13 ] using an equivalence margin based the time-varying standard deviation of the ground truth K-M curve.…”

Section: Discussionmentioning

confidence: 99%

“…We present a regulariser for the temporal dependencies between the results in histories and propose a discrepancy term for utilizing correlations between different histories. We evaluate our method on both synthetic data and registry data by measuring the probability of agreement [ 13 ] between Kaplan-Meier estimates from model predictions and a hold-out set.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

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

et al. 2022

View full text Add to dashboard Cite

Background 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. Results 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. Conclusions 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.

show abstract

“…4 we compare performance scores, (Eq. ( 8 )) for different models, indicating the probability of agreement [ 13 ] between hold-out data and predictions. Predicting based on Eq.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The MF has become a popular approach to dealing with scarce and irregular data. The proposed framework was compared to a geometric deep learning (GDL) model based on 16 , and validated by the probability of agreement 17 between Kaplan-Meier estimates derived from model predictions and a hold-out set. Despite highlighting a heavy class imbalance in their data sample, the authors did not evaluate model calibration or state drift – factors that may explain and affect model performance.…”

Section: Introductionmentioning

confidence: 99%

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

Langberg

Nygård

Gogineni

et al. 2022

Sci Rep

View full text Add to dashboard Cite

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.

show abstract

Comparative Probability Metrics: Using Posterior Probabilities to Account for Practical Equivalence in A/B tests

Stevens

Hagar

2022

The American Statistician

View full text Add to dashboard Cite

Comparing Kaplan‐Meier curves with the probability of agreement

Cited by 9 publications

References 25 publications

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

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

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

Comparative Probability Metrics: Using Posterior Probabilities to Account for Practical Equivalence in A/B tests

Contact Info

Product

Resources

About