Dataset Information

A clinician's guide for developing a prediction model: a case study using real-world data of patients with castration-resistant prostate cancer.

ABSTRACT: PURPOSE:With the increasing interest in treatment decision-making based on risk prediction models, it is essential for clinicians to understand the steps in developing and interpreting such models. METHODS:A retrospective registry of 20 Dutch hospitals with data on patients treated for castration-resistant prostate cancer was used to guide clinicians through the steps of developing a prediction model. The model of choice was the Cox proportional hazard model. RESULTS:Using the exemplary dataset several essential steps in prediction modelling are discussed including: coding of predictors, missing values, interaction, model specification and performance. An advanced method for appropriate selection of main effects, e.g. Least Absolute Shrinkage and Selection Operator (LASSO) regression, is described. Furthermore, the assumptions of Cox proportional hazard model are discussed, and how to handle violations of the proportional hazard assumption using time-varying coefficients. CONCLUSION:This study provides a comprehensive detailed guide to bridge the gap between the statistician and clinician, based on a large dataset of real-world patients treated for castration-resistant prostate cancer.

SUBMITTER: Veen KM

PROVIDER: S-EPMC7324416 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A clinician's guide for developing a prediction model: a case study using real-world data of patients with castration-resistant prostate cancer.

Veen Kevin M KM de Angst Isabel B IB Mokhles Mostafa M MM Westgeest Hans M HM Kuppen Malou M Groot Carin A Uyl-de CAU Gerritsen Winald R WR Kil Paul J M PJM Takkenberg Johanna J M JJM

Journal of cancer research and clinical oncology 20200617 8

<h4>Purpose</h4>With the increasing interest in treatment decision-making based on risk prediction models, it is essential for clinicians to understand the steps in developing and interpreting such models.<h4>Methods</h4>A retrospective registry of 20 Dutch hospitals with data on patients treated for castration-resistant prostate cancer was used to guide clinicians through the steps of developing a prediction model. The model of choice was the Cox proportional hazard model.<h4>Results</h4>Using ...[more]

PMID: 32556680

Similar Datasets

Project description:BackgroundMetastatic prostate cancer has a 30% 5-year survival rate despite recent therapeutic advances. There is a need to improve the clinical understanding and treatment of this disease, particularly in the real-world setting and among patients who are under-represented in clinical trials.ObjectiveWe aimed to evaluate the characteristics and clinical outcomes of patients who received their first treatment for metastatic castration-resistant prostate cancer (mCRPC) in routine clinical practice, independent of treatment used, including subgroups with baseline cardiac disease, diabetes mellitus, or visceral metastases.Patients and methodsProspective, noninterventional analysis of patient record data in the multicenter Prostate Cancer Registry (PCR) of men with mCRPC. The data were collected in 16 countries with the aim of recruiting more than 3000 patients between 2013 and 2016. The study end date was 9 July 2018. Data evaluated included baseline characteristics, treatment exposure, and efficacy outcomes [overall survival (OS) and time to progression (TTP)] of patients treated with abiraterone acetate plus prednisone or prednisolone (collectively, "abiraterone"), enzalutamide, or docetaxel. Descriptive outcomes are reported from the overall patient population and subgroups of patients with baseline cardiovascular disease, diabetes mellitus, or visceral metastases. The treatment effects for time to progression were compared for the overall patient population.ResultsThe study enrollment period lasted 2.5 years, and each patient was followed for a maximum of 3 years. A total of 1874 patients in the PCR had not received previous mCRPC treatment at baseline, although they had received androgen-deprivation therapy. Prevalent co-morbidities included cardiovascular disease in 65.4% and diabetes mellitus in 17.4% of patients. Baseline characteristics suggested that patients with more advanced disease received docetaxel treatment. In the overall patient population, the median time to progression with abiraterone, enzalutamide, and docetaxel as first-line mCRPC therapy was 9.6, 10.3, and 7.6 months, respectively, and median OS was 27.1, 27.1, and 27.9 months, respectively. Outcomes in the subgroups of patients with cardiovascular disease or diabetes mellitus were similar to those of the whole population in the analysis. As expected, patients with visceral metastases had shorter TTP and OS than patients in the overall population.ConclusionsThis analysis shows, for the first time, the effectiveness in parallel of first-line abiraterone, enzalutamide, and docetaxel in mCRPC, including in patients with co-morbidities such as cardiovascular disease or diabetes mellitus or in patients with visceral metastases. These real-world findings from the PCR provide meaningful information to help manage mCRPC, particularly in patients under-represented in clinical studies.Trial registrationClinicalTrials.gov identifier NCT02236637; registered September 2014.

Dataset Information

A clinician's guide for developing a prediction model: a case study using real-world data of patients with castration-resistant prostate cancer.

Publications

A clinician's guide for developing a prediction model: a case study using real-world data of patients with castration-resistant prostate cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets