Dr. Answer AI for Prostate Cancer: Predicting Biochemical Recurrence Following Radical Prostatectomy.
Ontology highlight
ABSTRACT: Objectives
To develop a model to predict biochemical recurrence (BCR) after radical prostatectomy (RP), using artificial intelligence (AI) techniques.Patients and methods
This study collected data from 7,128 patients with prostate cancer (PCa) who received RP at 3 tertiary hospitals. After preprocessing, we used the data of 6,755 cases to generate the BCR prediction model. There were 16 input variables with BCR as the outcome variable. We used a random forest to develop the model. Several sampling techniques were used to address class imbalances.Results
We achieved good performance using a random forest with synthetic minority oversampling technique (SMOTE) using Tomek links, edited nearest neighbors (ENN), and random oversampling: accuracy = 96.59%, recall = 95.49%, precision = 97.66%, F1 score = 96.59%, and ROC AUC = 98.83%.Conclusion
We developed a BCR prediction model for RP. The Dr. Answer AI project, which was developed based on our BCR prediction model, helps physicians and patients to make treatment decisions in the clinical follow-up process as a clinical decision support system.
SUBMITTER: Park J
PROVIDER: S-EPMC8243093 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Accurate estimation of recurrence risk is needed for optimal treatment of clinically localized prostate cancer (PCa) patients. We combined classical clinicopathological predictors of biochemical recurrence (BCR) and molecular markers into a new risk score for predicting BCR after radical prostatectomy (RP). A retrospective study which included 122 PCa patients who attended our department between 2000 and 2007 was conducted. Total RNA was isolated from formalin-fixed paraffin embedded PCa tissue. Gene expression patterns were analyzed in 21 selected samples from 7 localized, 6 locally advanced, and 8 metastatic PCa patients using Illumina microarrays. Expression levels of 41 genes were validated by quantitative PCR in an independent retrospective series of 101 patients with ≥ 10 years follow-up who underwent RP for clinically localized PCa. Univariate and multivariate logistic regression analysis were used to identify individual predictors of BCR. A risk score (RS) for predicting BCR including clinicopathological and gene expression data was developed and Kaplan-Meier curves were generated. Interaction networks between the genes of the model were built by GeneMANIA Cytoscape plugin. In a median follow-up of 120 months (range 3-190), 37 patients developed BCR (36.6%). Expression levels of 7,930 transcripts differed between clinically localized and locally advanced-metastatic PCa groups (FDR<0.1). A set of 41 genes were validated by quantitative PCR. Regression analysis showed that expression of ASF1B and MCL1 as well as Gleason score, extracapsular extension, seminal vesicle invasion and positive margins were independent prognostic factors of BCR. A RS generated using these gene expression and clinicopathological variables was able to discriminate between two groups of patients with a significantly different probability of BCR (HR 6.24; CI 3.23-12.4, p<0.01), improving the individual discriminative performance of each of these variables on their own. Direct interactions between the two genes of the model were not found. In conclusion, identification of new gene expression patterns associated with a high probability of BCR in clinically localized PCa patients treated with RP, and their combination with clinicopathological variables in a robust, easy-to-use and reliable classifier may contribute to improve PCa risk stratification and, consequently, to tailor treatment and surveillance strategies in these patients.
2024-04-23 | GSE149226 | GEO
Project description:The natural history of prostate-specific antigen (PSA)-defined biochemical recurrence (BCR) of prostate cancer (PCa) after definitive local therapy is highly variable. Validated prediction models for PCa-specific mortality (PCSM) in this population are needed for treatment decision-making and clinical trial design.To develop and validate a nomogram to predict the probability of PCSM from the time of BCR among men with rising PSA levels after radical prostatectomy.Between 1987 and 2011, 2254 men treated by radical prostatectomy at one of five high-volume hospitals experienced BCR, defined as three successive PSA rises (final value >0.2 ng/ml), single PSA >0.4 ng/ml, or use of secondary therapy administered for detectable PSA >0.1 ng/ml. Clinical information and follow-up data were modeled using competing-risk regression analysis to predict PCSM from the time of BCR.Radical prostatectomy for localized prostate cancer and subsequent PCa BCR.PCSM.The 10-yr PCSM and mortality from competing causes was 19% (95% confidence interval [CI] 16-21%) and 17% (95% CI 14-19%), respectively. A nomogram predicting PCSM for all patients had an internally validated concordance index of 0.774. Inclusion of PSA doubling time (PSADT) in a nomogram based on standard parameters modestly improved predictive accuracy (concordance index 0.763 vs 0.754). Significant parameters in the models were preoperative PSA, pathological Gleason score, extraprostatic extension, seminal vesicle invasion, time to PCa BCR, PSA level at PCa BCR, and PSADT (all p<0.05).We constructed and validated a nomogram to predict the risk of PCSM at 10 yr among men with PCa BCR after radical prostatectomy. The nomogram may be used for patient counseling and the design of clinical trials for PCa.For men with biochemical recurrence of prostate cancer after radical prostatectomy, we have developed a model to predict the long-term risk of death from prostate cancer.
| S-EPMC4779062 | biostudies-literature
Project description:Background: D'Amico high-risk prostate cancer (Pca) patients experience poor and heterogeneous oncological outcomes. This heterogeneity highlights a need to extensively explore factors associated with poor outcomes to guide decision-making. Objective: To assess predictors of biochemical recurrence (BCR)-free survival in high-risk patients following radical prostatectomy (RP), and subsequently establish a model predicting outcomes. Methods: We retrospectively identified D'Amico high-risk non-metastatic Pca patients who underwent RP between 2013 and 2019 in our hospital. We collected data including PSA level, clinical stage, biopsy Gleason score (GS), number of D'Amico high-risk factors (RF), the inflammatory status (Neutrophil-to-lymphocyte ratio [NLR], derived NLR [dNLR], platelet-to-lymphocyte ratio [PLR] and LDH). Kaplan–Meier methods were used to analyze BCR-free survival. Univariate and multivariate analyses were performed using Cox proportional hazards model to evaluate the association between clinicopathological parameters and BCR-free survival. Results: The median follow-up time for the 101 patients' cohort was 26 months (range: 3–81 months). The number of RF (1RF vs. ?2RF), biopsy GS (<8 vs. ?8), clinical stage (?cT2c vs. >cT2c), pathological stage, and the presence of adverse pathological features were significant predictors of BCR (P < 0.05). Other parameters including inflammatory status (dNLR, NLR, PLR, and LDH) were not of predictive value. On multivariable analysis, biopsy GS (<8 vs. ?8; HR 2.439) and clinical stage (?cT2c vs. >cT2c; HR 3.271) were the independent predictors of BCR. Based on these two independent predictors, patients were stratified into three risk subgroups: favorable (0 risk factor; 47% of patients), intermediate (1 risk factor; 42 %), unfavorable (2 risk factors; 11%). The intermediate and unfavorable subgroups have a significantly shorter median BCR-free survival compared to the favorable subgroup (P < 0.001). Conclusion: Several factors are associated with BCR. Clinical stage (?cT2c vs. >cT2c) and biopsy GS (<8 vs. ?8) are the independent predictors of BCR. The stratification of high-risk patients into risk subgroups based on these two predictors shows that the intermediate and unfavorable subgroups have a significantly shorter median BCR-free survival compared to the favorable subgroup. The preoperative stratification model may help urologists and patients during decision-making. In non-metastatic high-risk patients, preoperative inflammatory markers (NLR, dNLR, PLR, and LDH) are not of prognostic value.
| S-EPMC7511762 | biostudies-literature
Project description:BackgroundThe Cancer/Testis Antigens (CTAs) are an important group of proteins that are typically restricted to the testis in the normal adult but are aberrantly expressed in several types of cancers. As a result of their restricted expression patterns, the CTAs could serve as unique biomarkers for cancer diagnosis/prognosis. The aim of this study was to identify promising CTAs that are associated with prostate cancer (PCa) recurrence following radical prostatectomy (RP).MethodsThe expression of 5 CTAs was measured by quantitative multiplex real-time PCR using prostate tissue samples obtained from 72 patients with apparently clinically localized PCa with a median of two years follow-up (range, 1 to 14 years).ResultsThe expression of CTAs namely, CEP55, NUF2, PBK and TTK were significantly higher while PAGE4 was significantly lower in patients with recurrent disease. All CTAs with the exception of TTK were significantly correlated with the prostatectomy Gleason score, but none were correlated with age, stage, or preoperative PSA levels. In univariate proportional hazards models, CEP55 (HR = 3.59, 95% CI: 1.50-8.60), p = 0.004; NUF2 (HR = 2.28, 95% CI: 1.11-4.67), p = 0.024; and PAGE4 (HR = 0.44, 95% CI: 0.21-0.93), p = 0.031 were significantly associated with the risk of PCa recurrence. However, the results were no longer significant after adjustment for prostatectomy Gleason score.ConclusionsTo our knowledge, this is the first study to identify CTAs as biomarkers that can differentiate patients with recurrent and non-recurrent disease following RP and underscores its potential impact on PCa prognosis and treatment.
| S-EPMC3184272 | biostudies-literature
Project description:The metabolic syndrome (MetS) comprises a constellation of risk factors associated with an increased risk for cardiovascular disease. Components of MetS have emerged as putative risk factors for prostate carcinoma. In this study, we examine the association between three features of the MetS (obesity, hypertension and diabetes) and the risk of biochemical recurrence (BCR) after radical prostatectomy (RP).We examined data from 1428 men in the University of Michigan Prostate Cancer Data Bank who elected to have RP as their primary treatment. We calculated body mass index from patients' weight and height measured at the time of prostate cancer diagnosis. We used the University of Michigan's Electronic Medical Record Search Engine to identify subjects with hypertension and/or diabetes before their prostate cancer diagnosis.Of 1428 men who underwent RP, 107 (8%) subsequently developed BCR with a median length of follow-up post-surgery of 3.6 years. Obesity and hypertension were each associated with an increased risk of BCR (adjusted hazard ratio (aHR) = 1.37; 95% CI 0.92-2.09 and aHR = 1.51, 95% CI 1.01-2.26), whereas no association was observed between diabetes and BCR (aHR = 0.73; 95% CI 0.40-1.33).Obesity and hypertension were each associated with an increased risk for BCR of prostate cancer after RP, independent of age at diagnosis and tumor pathological features. Given the increasing rates of obesity, hypertension and prostate cancer, a better understanding of the relationship between these entities is of significant public health importance. Elucidation of the involved pathogenic mechanisms will be needed to establish causality.
| S-EPMC3860174 | biostudies-literature
Project description:BACKGROUND:The qualitative transcriptional characteristics, the within-sample relative expression orderings (REOs) of genes, are highly robust against batch effects and sample quality variations. Hence, we develop a qualitative transcriptional signature based on REOs to predict the biochemical recurrence risk of prostate cancer (PCa) patients after radical prostatectomy. METHODS:Gene pairs with REOs significantly correlated with the biochemical recurrence-free survival (BFS) were identified from 131 PCa samples in the training data set. From these gene pairs, we selected a qualitative transcriptional signature based on the within-sample REOs of gene pairs which could predict the recurrence risk of PCa patients after radical prostatectomy. RESULTS:A signature consisting of 74 gene pairs, named 74-GPS, was developed for predicting the recurrence risk of PCa patients after radical prostatectomy based on the majority voting rule that a sample was assigned as high risk when at least 37 gene pairs of the 74-GPS voted for high risk; otherwise, low risk. The signature was validated in six independent datasets produced by different platforms. In each of the validation datasets, the Kaplan-Meier survival analysis showed that the average BFS of the low-risk group was significantly better than that of the high-risk group. Analyses of multiomics data of PCa samples from TCGA suggested that both the epigenomic and genomic alternations could cause the reproducible transcriptional differences between the two different prognostic groups. CONCLUSIONS:The proposed qualitative transcriptional signature can robustly stratify PCa patients after radical prostatectomy into two groups with different recurrence risk and distinct multiomics characteristics. Hence, 74-GPS may serve as a helpful tool for guiding the management of PCa patients with radical prostatectomy at the individual level.
| S-EPMC7065139 | biostudies-literature
Project description:PurposeThis study proposed the optimal definition of biochemical recurrence (BCR) after salvage radiotherapy (SRT) following radical prostatectomy for prostate cancer.Materials and methodsAmong 1,117 patients who had received SRT, data from 205 hormone-naïve patients who experienced post-SRT prostate-specific antigen (PSA) elevation were included in a multi-institutional database. The primary endpoint was to determine the PSA parameters predictive of distant metastasis (DM). Absolute serum PSA levels and the prostate-specific antigen doubling time (PSA-DT) were adopted as PSA parameters.ResultsWhen BCR was defined based on serum PSA levels ranging from 0.4 ng/mL to nadir+2.0 ng/mL, the 5-year probability of DM was 27.6%-33.7%. The difference in the 5-year probability of DM became significant when BCR was defined as a serum PSA level of 0.8 ng/ml or higher (1.0-2.0 ng/mL). Application of a serum PSA level of ≥ 0.8 ng/mL yielded a c-index value of 0.589. When BCR was defined based on the PSA-DT, the 5-year probability was 22.7%-39.4%. The difference was significant when BCR was defined as a PSA-DT ≤ 3 months and ≤ 6 months. Application of a PSA-DT ≤ 6 months yielded the highest c-index (0.660). These two parameters complemented each other; for patients meeting both PSA parameters, the probability of DM was 39.5%-44.5%; for those not meeting either parameter, the probability was 0.0%-3.1%.ConclusionA serum PSA level > 0.8 ng/mL was a reasonable threshold for the definition of BCR after SRT. In addition, a PSA-DT ≤ 6 months was significantly predictive of subsequent DM, and combined application of both parameters enhanced predictability.
| S-EPMC9582474 | biostudies-literature
Project description:The hypersensitive prostate specific antigen (PSA) test can measure in 0.01 ng/mL units, and its efficacy for screening after radical prostatectomy (RP) has been reported. In this study, we assessed patients who underwent RP to evaluate whether the nadir value affects biochemical recurrence (BCR). From 1995 to 2014, patients classified as N0 who had negative resection margins and a nadir PSA of less than 0.2 ng/mL were evaluated. The characteristics, pathological outcomes, PSA after RP, and BCR were assessed. A total of 1483 patients were enrolled. Among them, 323 (21.78%) patients showed BCR after RP. The mean age of the BCR group was 63.86±7.31 years, and while that of the no-recurrence group was 64.06±6.82 years (P = 0.645). The mean preoperative PSA of the BCR group was 9.75±6.92 ng/mL and that of the no-recurrence group was 6.71±5.19 ng/mL (P < 0.001). The mean time to nadir (TTN) in the BCR group was 4.64±7.65 months, while that in the no-recurrence group was 7.43±12.46 months (P < 0.001). The mean PSA nadir value was 0.035±0.034 ng/mL in the BCR group and 0.014±0.009 ng/mL in the no-recurrence group (P < 0.001). In multivariable Cox regression analyses, Gleason score, positive biopsy core percentages, minimal invasive surgery, nadir PSA value, and TTN were independently associated with BCR. The mean BCR occurred at 48.23±2.01 months after RP, and there was a significant difference in BCR occurrence according to the nadir PSA value (P < 0.001). A high PSA nadir value and short TTN may predict the risk of BCR after successful RP, aiding the identification of candidates for adjuvant or salvage therapies after RP.
| S-EPMC8092790 | biostudies-literature
Project description:This study undertook to predict biochemical recurrence (BCR) in prostate cancer patients after radical prostatectomy using serum biomarkers and clinical features. Three radical prostatectomy cohorts were used to build and validate a model of clinical variables and serum biomarkers to predict BCR. The Cox proportional hazard model with stepwise selection technique was used to develop the model. Model evaluation was quantified by the AUC, calibration, and decision curve analysis. Cross-validation techniques were used to prevent overfitting in the Irish training cohort, and the Austrian and Norwegian independent cohorts were used as validation cohorts. The integration of serum biomarkers with the clinical variables (AUC = 0.695) improved significantly the predictive ability of BCR compared to the clinical variables (AUC = 0.604) or biomarkers alone (AUC = 0.573). This model was well calibrated and demonstrated a significant improvement in the predictive ability in the Austrian and Norwegian validation cohorts (AUC of 0.724 and 0.606), compared to the clinical model (AUC of 0.665 and 0.511). This study shows that the pre-operative biomarker PEDF can improve the accuracy of the clinical factors to predict BCR. This model can be employed prior to treatment and could improve clinical decision making, impacting on patients' outcomes and quality of life.
| S-EPMC8391749 | biostudies-literature
Project description:MicroRNA profiling was performed using multiplex qPCR on laser micro dissected material from 36 PC patients to identify microRNAs associated with recurrence after radical prostatectomy
2014-10-23 | GSE62610 | GEO