Dataset Information

The Huashan risk calculators performed better in prediction of prostate cancer in Chinese population: a training study followed by a validation study.

ABSTRACT: The performances of the Prostate Cancer Prevention Trial (PCPT) risk calculator and other risk calculators for prostate cancer (PCa) prediction in Chinese populations were poorly understood. We performed this study to build risk calculators (Huashan risk calculators) based on Chinese population and validated the performance of prostate-specific antigen (PSA), PCPT risk calculator, and Huashan risk calculators in a validation cohort. We built Huashan risk calculators based on data from 1059 men who underwent initial prostate biopsy from January 2006 to December 2010 in a training cohort. Then, we validated the performance of PSA, PCPT risk calculator, and Huashan risk calculators in an observational validation study from January 2011 to December 2014. All necessary clinical information were collected before the biopsy. The results showed that Huashan risk calculators 1 and 2 outperformed the PCPT risk calculator for predicting PCa in both entire training cohort and stratified population (with PSA from 2.0 ng ml-1 to 20.0 ng m). In the validation study, Huashan risk calculator 1 still outperformed the PCPT risk calculator in the entire validation cohort (0.849 vs 0.779 in area under the receiver operating characteristic curve [AUC] and stratified population. A considerable reduction of unnecessary biopsies (approximately 30%) was also observed when the Huashan risk calculators were used. Thus, we believe that the Huashan risk calculators (especially Huashan risk calculator 1) may have added value for predicting PCa in Chinese population. However, these results still needed further evaluation in larger populations.

SUBMITTER: Wu YS

PROVIDER: S-EPMC5109890 | biostudies-literature | 2016 Nov-Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

The Huashan risk calculators performed better in prediction of prostate cancer in Chinese population: a training study followed by a validation study.

Wu Yi-Shuo YS Zhang Ning N Liu Sheng-Hua SH Xu Jian-Feng JF Tong Shi-Jun SJ Cai Ye-Hua YH Zhang Li-Min LM Bai Pei-De PD Hu Meng-Bo MB Jiang Hao-Wen HW Na Rong R Ding Qiang Q Sun Ying-Hao YH

Asian journal of andrology 20161101 6

The performances of the Prostate Cancer Prevention Trial (PCPT) risk calculator and other risk calculators for prostate cancer (PCa) prediction in Chinese populations were poorly understood. We performed this study to build risk calculators (Huashan risk calculators) based on Chinese population and validated the performance of prostate-specific antigen (PSA), PCPT risk calculator, and Huashan risk calculators in a validation cohort. We built Huashan risk calculators based on data from 1059 men w ...[more]

PMID: 27212127

Similar Datasets

Project description:ObjectivesElevated intracranial pressure (ICP) is a potentially devastating complication of neurologic injury. Developing an ICP prediction algorithm to help the clinician adjust treatments and potentially prevent elevated ICP episodes.DesignRetrospective study.SettingThree hundred thirty-five ICUs at 208 hospitals in the United States.SubjectsAdults patients from the electronic ICU (eICU) Collaborative Research Database was used to train an ensemble machine learning model to predict the ICP 30 minutes in the future. Predictive performance was evaluated using a left-out test dataset and externally evaluated on the Medical Information Mart for Intensive Care-III (MIMIC-III) Matched Waveform Database.InterventionsNone.Measurements and main resultsPredictors included age, assigned sex, laboratories, medications and infusions, input/output, Glasgow Coma Scale (GCS) components, and time-series vitals (heart rate, ICP, mean arterial pressure, respiratory rate, and temperature). Each patient ICU stay was divided into successive 95-minute timeblocks. For each timeblock, the model was trained on nontime-varying covariates as well as on 12 observations of time-varying covariates at 5-minute intervals and asked to predict the 5-minute median ICP 30 minutes after the last observed ICP value. Data from 931 patients with ICP monitoring in the eICU dataset were extracted (46,207 timeblocks). The root mean squared error was 4.51 mm Hg in the eICU test set and 3.56 mm Hg in the MIMIC-III dataset. The most important variables driving ICP prediction were previous ICP history, patients' temperature, weight, serum creatinine, age, GCS, and hemodynamic parameters.ConclusionsIntraCranial pressure prediction AlgoRithm using machinE learning, an ensemble machine learning model, trained to predict the ICP of a patient 30 minutes in the future based on baseline characteristics and vitals data from the past hour showed promising predictive performance including in an external validation dataset.

Project description:PurposeWe developed the Korean Prostate Cancer Risk Calculator for High-Grade Prostate Cancer (KPCRC-HG) that predicts the probability of prostate cancer (PC) of Gleason score 7 or higher at the initial prostate biopsy in a Korean cohort (http://acl.snu.ac.kr/PCRC/RISC/). In addition, KPCRC-HG was validated and compared with internet-based Western risk calculators in a validation cohort.Materials and methodsUsing a logistic regression model, KPCRC-HG was developed based on the data from 602 previously unscreened Korean men who underwent initial prostate biopsies. Using 2,313 cases in a validation cohort, KPCRC-HG was compared with the European Randomized Study of Screening for PC Risk Calculator for high-grade cancer (ERSPCRC-HG) and the Prostate Cancer Prevention Trial Risk Calculator 2.0 for high-grade cancer (PCPTRC-HG). The predictive accuracy was assessed using the area under the receiver operating characteristic curve (AUC) and calibration plots.ResultsPC was detected in 172 (28.6%) men, 120 (19.9%) of whom had PC of Gleason score 7 or higher. Independent predictors included prostate-specific antigen levels, digital rectal examination findings, transrectal ultrasound findings, and prostate volume. The AUC of the KPCRC-HG (0.84) was higher than that of the PCPTRC-HG (0.79, p<0.001) but not different from that of the ERSPCRC-HG (0.83) on external validation. Calibration plots also revealed better performance of KPCRC-HG and ERSPCRC-HG than that of PCPTRC-HG on external validation. At a cut-off of 5% for KPCRC-HG, 253 of the 2,313 men (11%) would not have been biopsied, and 14 of the 614 PC cases with Gleason score 7 or higher (2%) would not have been diagnosed.ConclusionsKPCRC-HG is the first web-based high-grade prostate cancer prediction model in Korea. It had higher predictive accuracy than PCPTRC-HG in a Korean population and showed similar performance with ERSPCRC-HG in a Korean population. This prediction model could help avoid unnecessary biopsy and reduce overdiagnosis and overtreatment in clinical settings.

Dataset Information

The Huashan risk calculators performed better in prediction of prostate cancer in Chinese population: a training study followed by a validation study.

Publications

The Huashan risk calculators performed better in prediction of prostate cancer in Chinese population: a training study followed by a validation study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets