Dataset Information

Fusion Gene Detection in Prostate Cancer Samples Enhances the Prediction of Prostate Cancer Clinical Outcomes from Radical Prostatectomy through Machine Learning in a Multi-Institutional Analysis.

ABSTRACT: Prostate cancer remains one of the most fatal malignancies in men in the United States. Predicting the course of prostate cancer is challenging given that only a fraction of prostate cancer patients experience cancer recurrence after radical prostatectomy or radiation therapy. This study examined the expressions of 14 fusion genes in 607 prostate cancer samples from the University of Pittsburgh, Stanford University, and the University of Wisconsin-Madison. The profiling of 14 fusion genes was integrated with Gleason score of the primary prostate cancer and serum prostate-specific antigen level to develop machine-learning models to predict the recurrence of prostate cancer after radical prostatectomy. Machine-learning algorithms were developed by analysis of the data from the University of Pittsburgh cohort as a training set using the leave-one-out cross-validation method. These algorithms were then applied to the data set from the combined Stanford/Wisconsin cohort (testing set). The results showed that the addition of fusion gene profiling consistently improved the prediction accuracy rate of prostate cancer recurrence by Gleason score, serum prostate-specific antigen level, or a combination of both. These improvements occurred in both the training and testing cohorts and were corroborated by multiple models.

SUBMITTER: Yu YP

PROVIDER: S-EPMC10123524 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Fusion Gene Detection in Prostate Cancer Samples Enhances the Prediction of Prostate Cancer Clinical Outcomes from Radical Prostatectomy through Machine Learning in a Multi-Institutional Analysis.

Yu Yan-Ping YP Liu Silvia S Ren Bao-Guo BG Nelson Joel J Jarrard David D Brooks James D JD Michalopoulos George G Tseng George G Luo Jian-Hua JH

The American journal of pathology 20230118 4

Prostate cancer remains one of the most fatal malignancies in men in the United States. Predicting the course of prostate cancer is challenging given that only a fraction of prostate cancer patients experience cancer recurrence after radical prostatectomy or radiation therapy. This study examined the expressions of 14 fusion genes in 607 prostate cancer samples from the University of Pittsburgh, Stanford University, and the University of Wisconsin-Madison. The profiling of 14 fusion genes was in ...[more]

PMID: 36681188

Similar Datasets

Project description:BackgroundThe effectiveness of surgery versus observation for men with localized prostate cancer detected by means of prostate-specific antigen (PSA) testing is not known.MethodsFrom November 1994 through January 2002, we randomly assigned 731 men with localized prostate cancer (mean age, 67 years; median PSA value, 7.8 ng per milliliter) to radical prostatectomy or observation and followed them through January 2010. The primary outcome was all-cause mortality; the secondary outcome was prostate-cancer mortality.ResultsDuring the median follow-up of 10.0 years, 171 of 364 men (47.0%) assigned to radical prostatectomy died, as compared with 183 of 367 (49.9%) assigned to observation (hazard ratio, 0.88; 95% confidence interval [CI], 0.71 to 1.08; P=0.22; absolute risk reduction, 2.9 percentage points). Among men assigned to radical prostatectomy, 21 (5.8%) died from prostate cancer or treatment, as compared with 31 men (8.4%) assigned to observation (hazard ratio, 0.63; 95% CI, 0.36 to 1.09; P=0.09; absolute risk reduction, 2.6 percentage points). The effect of treatment on all-cause and prostate-cancer mortality did not differ according to age, race, coexisting conditions, self-reported performance status, or histologic features of the tumor. Radical prostatectomy was associated with reduced all-cause mortality among men with a PSA value greater than 10 ng per milliliter (P=0.04 for interaction) and possibly among those with intermediate-risk or high-risk tumors (P=0.07 for interaction). Adverse events within 30 days after surgery occurred in 21.4% of men, including one death.ConclusionsAmong men with localized prostate cancer detected during the early era of PSA testing, radical prostatectomy did not significantly reduce all-cause or prostate-cancer mortality, as compared with observation, through at least 12 years of follow-up. Absolute differences were less than 3 percentage points. (Funded by the Department of Veterans Affairs Cooperative Studies Program and others; PIVOT ClinicalTrials.gov number, NCT00007644.).

Project description:BackgroundBone metastasis is a serious complication following radical prostatectomy in prostate cancer patients, significantly affecting their long-term survival. This study aims to develop a clinical predictive model utilizing Magnetic Resonance Imaging (MRI) and advanced machine learning algorithms to identify key factors that increase the risk of bone metastasis (BM).Patients and methodsThe study analyzed a cohort of 1161 prostate cancer patients, including 38 who developed bone metastasis. Preoperative T2-weighted images (T2WI) were obtained, and tumor lesions were manually delineated to extract relevant features from the imaging data. Spearman correlation analysis, the least absolute shrinkage and selection operator (LASSO) algorithm, and logistic regression were used to select and construct the model. Four machine learning algorithms-extreme gradient boosting (XGBoost), random forest (RF), support vector machine (SVM), and k-nearest neighbor (KNN)-were employed to predict BM occurrence, integrating these with clinical information.ResultsAmong the four prognostic models evaluated, the XGBoost algorithm performed the best. In the training dataset, the XGBoost model achieved an AUC of 0.926 (0.870-0.982), an accuracy of 0.847 (0.773-0.921), a sensitivity of 0.880 (0.835-0.926), and a specificity of 0.829 (0.755-0.904). In the validation dataset, the XGBoost model attained an AUC of 0.706 (0.586-0.826), an accuracy of 0.687 (0.661-0.713), a sensitivity of 0.693 (0.557-0.829), and a specificity of 0.664 (0.505-0.822). The external validation dataset yielded an AUC of 0.91, demonstrating the robust predictive capabilities of the XGBoost model.ConclusionThe predictive model for bone metastasis in prostate cancer, developed using the XGBoost machine learning algorithm, shows high accuracy and significant clinical relevance. This model provides a valuable tool for identifying high-risk patients, potentially informing better management and treatment strategies.

Project description:BackgroundRadical prostatectomy reduces mortality among men with localized prostate cancer; however, important questions regarding long-term benefit remain.MethodsBetween 1989 and 1999, we randomly assigned 695 men with early prostate cancer to watchful waiting or radical prostatectomy and followed them through the end of 2012. The primary end points in the Scandinavian Prostate Cancer Group Study Number 4 (SPCG-4) were death from any cause, death from prostate cancer, and the risk of metastases. Secondary end points included the initiation of androgen-deprivation therapy.ResultsDuring 23.2 years of follow-up, 200 of 347 men in the surgery group and 247 of the 348 men in the watchful-waiting group died. Of the deaths, 63 in the surgery group and 99 in the watchful-waiting group were due to prostate cancer; the relative risk was 0.56 (95% confidence interval [CI], 0.41 to 0.77; P=0.001), and the absolute difference was 11.0 percentage points (95% CI, 4.5 to 17.5). The number needed to treat to prevent one death was 8. One man died after surgery in the radical-prostatectomy group. Androgen-deprivation therapy was used in fewer patients who underwent prostatectomy (a difference of 25.0 percentage points; 95% CI, 17.7 to 32.3). The benefit of surgery with respect to death from prostate cancer was largest in men younger than 65 years of age (relative risk, 0.45) and in those with intermediate-risk prostate cancer (relative risk, 0.38). However, radical prostatectomy was associated with a reduced risk of metastases among older men (relative risk, 0.68; P=0.04).ConclusionsExtended follow-up confirmed a substantial reduction in mortality after radical prostatectomy; the number needed to treat to prevent one death continued to decrease when the treatment was modified according to age at diagnosis and tumor risk. A large proportion of long-term survivors in the watchful-waiting group have not required any palliative treatment. (Funded by the Swedish Cancer Society and others.).

Project description:ImportanceWhether the conventional 1.5-month to 2.0-month time interval following radical prostatectomy (RP) for prostate cancer (PC) is sufficient to accurately document a persistent prostate-specific antigen (PSA) remains unanswered.ObjectiveTo evaluate the time necessary to accurately document a persistent PSA level after RP.Design, setting, and participantsThis cohort study evaluated whether a significant interaction existed between (1) a pre-RP PSA level greater than 20 ng/mL vs 20 ng/mL or less and (2) persistent PSA vs undetectable PSA after RP on PC-specific mortality (PCSM) risk and all-cause mortality (ACM) risk, adjusting for known PC prognostic factors, age at RP, year of RP, and the time-dependent use of post-RP radiation therapy (RT) and androgen deprivation therapy (ADT). Whether an increasing persistent PSA level was associated with a worse prognosis was also investigated. Patients with T1N0M0 to T3N0M0 PC treated with RP between 1992 and 2020 at 2 academic centers were included. Follow-up data were collected until November 2023. Data were analyzed from July 2024 to January 2025.ExposureRP.Main outcomes and measuresAdjusted hazard ratio (aHR) of ACM and PCSM risk.ResultsOf 30 461 patients included in the discovery cohort, the median (IQR) age was 64 (59-68) years; of 12 837 patients included in the validation cohort, the median (IQR) age was 59 (54-64) years. Compared with patients with undetectable PSA, among patients with persistent PSA, a pre-RP PSA level greater than 20 ng/mL vs 20 ng/mL or less was significantly associated with reduced ACM risk (aHR, 0.69; 95% CI, 0.51-0.91; P = .01; P for interaction < .001) and PCSM risk (aHR, 0.41; 95% CI, 0.25-0.66; P < .001; P for interaction = .02). This result remained after adjustment for prostate volume and was confirmed in the validation cohort for PCSM risk and may represent a higher proportion of patients with a pre-RP PSA greater than 20 ng/mL vs 20 ng/mL or less who could have reached an undetectable PSA level if additional time for PSA assessment occurred before initiating post-RP therapy for presumed persistent PSA. Notably, there was more frequent and a shorter median time to post-RP RT plus ADT or ADT use in patients with a pre-RP PSA greater than 20 ng/mL (244 of 446 [54.7%] at a median [IQR] of 2.68 [1.51-4.40] months) vs 20 ng/mL or less (338 of 972 [34.8%] at a median [IQR] of 3.30 [2.00-5.39] months). These treatment times were shorter than the times to an undetectable PSA in observed patients (median [IQR] of 2.96 [1.84-3.29] months vs 3.37 [2.35-4.09] months, respectively). Increasing persistent PSA level was associated with an increased ACM risk (aHR, 1.14; 95% CI, 1.04-1.24; P = .004) and PCSM risk (aHR, 1.27; 95% CI, 1.12-1.45; P < .001).Conclusions and relevancePSA level assessed for at least 3 months after RP may minimize overtreatment, and in this study, a higher persistent PSA level was associated with a worse prognosis.

Dataset Information

Fusion Gene Detection in Prostate Cancer Samples Enhances the Prediction of Prostate Cancer Clinical Outcomes from Radical Prostatectomy through Machine Learning in a Multi-Institutional Analysis.

Publications

Fusion Gene Detection in Prostate Cancer Samples Enhances the Prediction of Prostate Cancer Clinical Outcomes from Radical Prostatectomy through Machine Learning in a Multi-Institutional Analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets