Validation Study of the Accuracy of a Postoperative Nomogram for Recurrence After Radical Prostatectomy for Localized Prostate Cancer

2002 ◽  
Vol 20 (4) ◽  
pp. 951-956 ◽  
Author(s):  
Markus Graefen ◽  
Pierre I. Karakiewicz ◽  
Ilias Cagiannos ◽  
Eric Klein ◽  
Patrick A. Kupelian ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radical Prostatectomy ◽  
Operating Characteristic ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Extracapsular Extension ◽  
Validation Data ◽  
Data Set ◽  
Time Period

PURPOSE: A postoperative nomogram for prostate cancer was developed at Baylor College of Medicine. This nomogram uses readily available clinical and pathologic variables to predict 7-year freedom from recurrence after radical prostatectomy. We evaluated the predictive accuracy of the nomogram when applied to patients of four international institutions. PATIENTS AND METHODS: Clinical and pathologic data of 2,908 patients were supplied for validation, and 2,465 complete records were used. Nomogram-predicted probabilities of 7-year freedom from recurrence were compared with actual follow-up in two ways. First, the area under the receiver operating characteristic curve (AUC) was calculated for all patients and stratified by the time period of surgery. Second, calibration of the nomogram was achieved by comparing the predicted freedom from recurrence with that of an ideal nomogram. For patients in whom the pathologic report does not distinguish between focal and established extracapsular extension (an input variable of the nomogram), two separate calculations were performed assuming one or the other. RESULTS: The overall AUC was 0.80 when applied to the validation data set, with individual institution AUCs ranging from 0.77 to 0.82. The predictive accuracy of the nomogram was apparently higher in patients who were operated on between 1997 and 2000 (AUC, 0.83) compared with those treated between 1987 and 1996 (AUC, 0.78). Nomogram predictions of 7-year freedom from recurrence were within 10% of an ideal nomogram. CONCLUSION: The postoperative Baylor nomogram was accurate when applied at international treatment institutions. Our results suggest that accurate predictions may be expected when using this nomogram across different patient populations.

scholarly journals The Application of Machine Learning to a General Risk–Need Assessment Instrument in the Prediction of Criminal Recidivism

2020 ◽  
pp. 009385482096975
Author(s):  
Mehdi Ghasemi ◽  
Daniel Anvari ◽  
Mahshid Atapour ◽  
J. Stephen wormith ◽  
Keira C. Stockdale ◽  
...  
Keyword(s):  
Machine Learning ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Assessment Instrument ◽  
Support Vector ◽  
Data Set ◽  
Applied Machine Learning ◽  
Vector Machines ◽  
Individual Scores

The Level of Service/Case Management Inventory (LS/CMI) is one of the most frequently used tools to assess criminogenic risk–need in justice-involved individuals. Meta-analytic research demonstrates strong predictive accuracy for various recidivism outcomes. In this exploratory study, we applied machine learning (ML) algorithms (decision trees, random forests, and support vector machines) to a data set with nearly 100,000 LS/CMI administrations to provincial corrections clientele in Ontario, Canada, and approximately 3 years follow-up. The overall accuracies and areas under the receiver operating characteristic curve (AUCs) were comparable, although ML outperformed LS/CMI in terms of predictive accuracy for the middle scores where it is hardest to predict the recidivism outcome. Moreover, ML improved the AUCs for individual scores to near 0.60, from 0.50 for the LS/CMI, indicating that ML also improves the ability to rank individuals according to their probability of recidivating. Potential considerations, applications, and future directions are discussed.

Detecting lower in addition to the highest Gleason score prostate cancer on core biopsy and the odds of upgrading at radical prostatectomy.

2013 ◽  
Vol 31 (15_suppl) ◽  
pp. e16026-e16026
Author(s):  
John G Phillips ◽  
Ayal A. Aizer ◽  
Ming-Hui Chen ◽  
Michelle S. Hirsch ◽  
Jerome P. Richie ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radical Prostatectomy ◽  
Gleason Score ◽  
Multivariable Analysis ◽  
High Rate ◽  
Study Cohort ◽  
Clinical Factors ◽  
Validation Data ◽  
Data Set ◽  
The Impact

e16026 Background: We evaluated the odds of upgrading at radical prostatectomy when a biopsy core with a lower Gleason score (GS) compared to the core with the highest GS was present (ComboGS) versus not at diagnosis and in a concurrent submission, test ComboGS in a validation data set on the endpoint of prostate cancer-specific mortality. Methods: The study cohort consisted of 134 men with clinically localized PC diagnosed between 4/08 and 9/11 using a 12-core prostate needle biopsy. GS at biopsy and RP were assigned by an expert genitourinary pathologist. Logistic regression multivariable analysis (Table) was performed to assess the impact that ComboGShad on the odds of upgrading at RP adjusting for known predictors of upgrading. Results: Of 134 patients, 46 (34%) were upgraded. Both increasing percent positive biopsies (ppb) (p < 0.001) and PSA level (p=0.001) were associated with an increased odds of upgrading, whereas ComboGSwas associated with a decreased odds of upgrading (0.18 [95% CI: 0.04-0.76); p = 0.02). Men whose ppb was ≥ 33% (median) were upgraded in 47% (28 of 60) versus 14% (3 of 21) of cases (p = 0.009) when ComboGSwas absent versus present. These respective estimates in men with a PSA ≥ 5.2 ng/ml (median) were 43% and 12% (p = 0.019). Conclusions: In men with clinical factors associated with upgrading namely, increasing ppb and PSA, ComboGSis a favorable prognostic factor associated with a high rate of downgrading (> 40%) and a low rate (< 15%) of upgrading. Adjusted odds ratios and associated 95% confidence intervals and p values representing the impact of clinical factors at diagnosis on upgrading at radical prostatectomy. [Table: see text]

Defining the optimal PSA range for the maximal predictive efficacy of PSA density to detect prostate cancer on biopsy: Results from a multi-institutional and prospective contemporary cohort.

2016 ◽  
Vol 34 (2_suppl) ◽  
pp. 70-70
Author(s):  
Samarpit Rai ◽  
Nicola Pavan ◽  
Nachiketh Soodana-Prakash ◽  
Bruno Nahar ◽  
Yan Dong ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Prostate Biopsy ◽  
Operating Characteristic ◽  
Predictive Accuracy ◽  
Characteristic Curve ◽  
Psa Density ◽  
Detect Prostate Cancer ◽  
Operating Characteristic Curve ◽  
The Difference ◽  
Negative Prostate Biopsy

70 Background: PSA density (PSAD) is an important predictor of prostate cancer (PCa). We assessed whether the predictive accuracy of PSAD varied based on the range of PSA or whether the patient had a previous negative prostate biopsy (PB). Methods: We assessed a prospective cohort of men who were referred for a PB due to suspicion of PCa at 26 different sites across USA. The area under the receiver operating characteristic curve (AUC) was used to assess the added predictive accuracy of PSAD versus PSA across 3 different PSA ranges ( < 4, 4 – 10, > 10 ng/mL) and in men with or without a prior negative PB for the detection of any and significant (Gleason ≥ 7) PCa. Results: Of the 1,290 men, 585 (45%) and 284 (22%) had any and significant PCa, respectively. PSAD was significantly more predictive than PSA for detecting any PCa in the PSA ranges of 4 – 10 (AUC 0.70 vs 0.53, P < 0.00001) and > 10 (AUC 0.84 vs 0.65, P < 0.00001) ng/mL. Similarly, for significant PCa, PSAD was more predictive than PSA in the PSA ranges of 4 – 10 (AUC 0.72 vs 0.57, P < 0.00001) and > 10 (AUC 0.82 vs 0.68, P = 0.0001) ng/mL. Furthermore, PSAD was significantly more predictive than PSA in detecting PCa in men that had a prior negative PB (AUC 0.69 vs 0.56, P = 0.0001 for any PCa and AUC 0.81 vs 0.70, P = 0.0042 for significant PCa), and those that didn’t (AUC 0.72 vs 0.67, P = 0.0001 for any PCa and AUC 0.77 vs 0.73, P = 0.0026 for significant PCa). However the difference between the AUC of PSAD and PSA (ΔAUC) was a lot more pronounced in men that had a prior negative PB (ΔAUC = 0.13 for any PCa and ΔAUC = 0.11 for significant PCa) as opposed to those that didn’t (ΔAUC = 0.05 for any PCa and ΔAUC = 0.04 for significant PCa), suggesting that PSAD is a much better predictor than PSA alone in men who have undergone a previous PB. Conclusions: As PSA increases, the predictive accuracy of PSAD over PSA appears to improve for the detection of any PCa and significant PCa. Additionally, PSAD has a more pronounced predictive value over PSA in detecting any and significant PCa in men who have undergone a prior negativePB. We support the use of PSAD testing to avoid unnecessary biopsies in men who have elevated PSA secondary to an enlarged prostate.

729: A Risk Adjusted Follow Up Scheme after Radical Prostatectomy for Prostate Cancer

2007 ◽  
Vol 177 (4S) ◽  
pp. 245-245
Author(s):  
Jochen Walz ◽  
Andrea Gallina ◽  
Felix K.-H. Chun ◽  
Luigi F. Da Pozzo ◽  
Alwyn M. Reuther ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radical Prostatectomy

scholarly journals Dr. Answer AI for Prostate Cancer: Predicting Biochemical Recurrence Following Radical Prostatectomy

2021 ◽  
Vol 20 ◽  
pp. 153303382110246
Author(s):  
Jihwan Park ◽  
Mi Jung Rho ◽  
Hyong Woo Moon ◽  
Jaewon Kim ◽  
Chanjung Lee ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Random Forest ◽  
Radical Prostatectomy ◽  
Prediction Model ◽  
Biochemical Recurrence ◽  
Clinical Decision ◽  
Outcome Variable ◽  
Tertiary Hospitals ◽  
Input Variables

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.

Role of ultrasensitive prostate-specific antigen in the follow-up of prostate cancer after radical prostatectomy

2015 ◽  
Vol 33 (1) ◽  
pp. 16.e1-16.e7 ◽  
Author(s):  
Heikki Seikkula ◽  
Kari T. Syvänen ◽  
Samu Kurki ◽  
Tuomas Mirtti ◽  
Pekka Taimen ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Radical Prostatectomy ◽  
Prostate Specific Antigen ◽  
Specific Antigen
Sign in / Sign up

Export Citation Format

Share Document