Dataset Information

An R package for an integrated evaluation of statistical approaches to cancer incidence projection.

ABSTRACT:

Background

Projection of future cancer incidence is an important task in cancer epidemiology. The results are of interest also for biomedical research and public health policy. Age-Period-Cohort (APC) models, usually based on long-term cancer registry data (>?20?yrs), are established for such projections. In many countries (including Germany), however, nationwide long-term data are not yet available. General guidance on statistical approaches for projections using rather short-term data is challenging and software to enable researchers to easily compare approaches is lacking.

Methods

To enable a comparative analysis of the performance of statistical approaches to cancer incidence projection, we developed an R package (incAnalysis), supporting in particular Bayesian models fitted by Integrated Nested Laplace Approximations (INLA). Its use is demonstrated by an extensive empirical evaluation of operating characteristics (bias, coverage and precision) of potentially applicable models differing by complexity. Observed long-term data from three cancer registries (SEER-9, NORDCAN, Saarland) was used for benchmarking.

Results

Overall, coverage was high (mostly >?90%) for Bayesian APC models (BAPC), whereas less complex models showed differences in coverage dependent on projection-period. Intercept-only models yielded values below 20% for coverage. Bias increased and precision decreased for longer projection periods (>?15?years) for all except intercept-only models. Precision was lowest for complex models such as BAPC models, generalized additive models with multivariate smoothers and generalized linear models with age x period interaction effects.

Conclusion

The incAnalysis R package allows a straightforward comparison of cancer incidence rate projection approaches. Further detailed and targeted investigations into model performance in addition to the presented empirical results are recommended to derive guidance on appropriate statistical projection methods in a given setting.

SUBMITTER: Knoll M

PROVIDER: S-EPMC7559591 | biostudies-literature | 2020 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An R package for an integrated evaluation of statistical approaches to cancer incidence projection.

Knoll Maximilian M Furkel Jennifer J Debus Jürgen J Abdollahi Amir A Karch André A Stock Christian C

BMC medical research methodology 20201015 1

<h4>Background</h4>Projection of future cancer incidence is an important task in cancer epidemiology. The results are of interest also for biomedical research and public health policy. Age-Period-Cohort (APC) models, usually based on long-term cancer registry data (> 20 yrs), are established for such projections. In many countries (including Germany), however, nationwide long-term data are not yet available. General guidance on statistical approaches for projections using rather short-term data ...[more]

PMID: 33059585

Similar Datasets

Project description:ObjectivesTo identify and summarise all studies using statistical methods to project lung cancer incidence or mortality rates more than 5 years into the future.Study typeSystematic review.MethodsWe performed a systematic literature search in multiple electronic databases to identify studies published from 1 January 1988 to 14 August 2018, which used statistical methods to project lung cancer incidence and/or mortality rates. Reference lists of relevant articles were checked for additional potentially relevant articles. We developed an organisational framework to classify methods into groups according to the type of data and the statistical models used. Included studies were critically appraised using prespecified criteria.ResultsOne hundred and one studies met the inclusion criteria; six studies used more than one statistical method. The number of studies reporting statistical projections for lung cancer increased substantially over time. Eighty-eight studies used projection methods, which did not incorporate data on smoking in the population, and 16 studies used a method which did incorporate data on smoking. Age-period-cohort models (44 studies) were the most commonly used methods, followed by other generalised linear models (35 studies). The majority of models were developed using observed rates for more than 10?years and used data that were considered to be good quality. A quarter of studies provided comparisons of fitted and observed rates. While validation by withholding the most recent observed data from the model and then comparing the projected and observed rates for the most recent period provides important information on the model's performance, only 12 studies reported doing this.ConclusionThis systematic review provides an up-to-date summary of the statistical methods used in published lung cancer incidence or mortality projections. The assessment of the strengths of existing methods will help researchers to better apply and develop statistical methods for projecting lung cancer rates. Some of the common methods described in this review can be applied to the projection of rates for other cancer types or other non-infectious diseases.

Project description:Integrated bioinformatics and statistical approaches are now playing the vital role in identifying potential molecular biomarkers more accurately in presence of huge number of alternatives for disease diagnosis, prognosis and therapies by reducing time and cost compared to the wet-lab based experimental procedures. Breast cancer (BC) is one of the leading causes of cancer related deaths for women worldwide. Several dry-lab and wet-lab based studies have identified different sets of molecular biomarkers for BC. But they did not compare their results to each other so much either computationally or experimentally. In this study, an attempt was made to propose a set of molecular biomarkers that might be more effective for BC diagnosis, prognosis and therapies, by using the integrated bioinformatics and statistical approaches. At first, we identified 190 differentially expressed genes (DEGs) between BC and control samples by using the statistical LIMMA approach. Then we identified 13 DEGs (AKR1C1, IRF9, OAS1, OAS3, SLCO2A1, NT5E, NQO1, ANGPT1, FN1, ATF6B, HPGD, BCL11A, and TP53INP1) as the key genes (KGs) by protein-protein interaction (PPI) network analysis. Then we investigated the pathogenetic processes of DEGs highlighting KGs by GO terms and KEGG pathway enrichment analysis. Moreover, we disclosed the transcriptional and post-transcriptional regulatory factors of KGs by their interaction network analysis with the transcription factors (TFs) and micro-RNAs. Both supervised and unsupervised learning's including multivariate survival analysis results confirmed the strong prognostic power of the proposed KGs. Finally, we suggested KGs-guided computationally more effective seven candidate drugs (NVP-BHG712, Nilotinib, GSK2126458, YM201636, TG-02, CX-5461, AP-24534) compared to other published drugs by cross-validation with the state-of-the-art alternatives top-ranked independent receptor proteins. Thus, our findings might be played a vital role in breast cancer diagnosis, prognosis and therapies.

Project description:ImportanceCoping with the current and future burden of cancer requires an in-depth understanding of trends in cancer incidences and deaths. Estimated projections of cancer incidences and deaths will be important to guide future research funding allocations, health care planning, and health policy efforts.ObjectiveTo estimate cancer incidences and deaths in the United States to the year 2040.Design and settingThis cross-sectional study's estimated projection analysis used population growth projections and current population-based cancer incidence and death rates to calculate the changes in incidences and deaths to the year 2040. Cancer-specific incidences and deaths in the US were estimated for the most common cancer types. Demographic cancer-specific delay-adjusted incidence rates from the Surveillance, Epidemiology, and End Results Program were combined with US Census Bureau population growth projections (2016) and average annual percentage changes in incidence and death rates. Statistical analyses were performed from July 2020 to February 2021.Main outcomes and measuresTotal cancer incidences and deaths to the year 2040.ResultsThis study estimated that the most common cancers in 2040 will be breast (364 000 cases) with melanoma (219 000 cases) becoming the second most common cancer; lung, third (208 000 cases); colorectal remaining fourth (147 000 cases); and prostate cancer dropping to the fourteenth most common cancer (66 000 cases). Lung cancer (63 000 deaths) was estimated to continue as the leading cause of cancer-related death in 2040, with pancreatic cancer (46 000 deaths) and liver and intrahepatic bile duct cancer (41 000 deaths) surpassing colorectal cancer (34 000 deaths) to become the second and third most common causes of cancer-related death, respectively. Breast cancer (30 000 deaths) was estimated to decrease to the fifth most common cause of cancer death.Conclusions and relevanceThese findings suggest that there will be marked changes in the landscape of cancer incidence and deaths by 2040.

Dataset Information

An R package for an integrated evaluation of statistical approaches to cancer incidence projection.

Background

Methods

Results

Conclusion

Publications

An R package for an integrated evaluation of statistical approaches to cancer incidence projection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets