المؤلفون: Kwong, Jethro C. C.^1,2, Khondker, Adree³, Tran, Christopher³, Evans, Emily³, Cozma, Adrian I.⁴, Javidan, Ashkan³, Ali, Amna⁵, Jamal, Munir¹, Short, Thomas¹, Papanikolaou, Frank¹, Srigley, John R.⁶, Fine, Benjamin^5,7,8, Feifer, Andrew^1,5

المصدر: Canadian Urological Association Journal. Jun2022, Vol. 16 Issue 6, p213-221. 9p.

مصطلحات موضوعية: *ARTIFICIAL intelligence, *TRAFFIC safety, *DECISION making, *PROSTATECTOMY, *RADICAL prostatectomy, *WEB-based user interfaces

مستخلص: Introduction: We aimed to develop an explainable machine learning (ML) model to predict side-specific extraprostatic extension (ssEPE) to identify patients who can safely undergo nerve-sparing radical prostatectomy using preoperative clinicopathological variables. Methods: A retrospective sample of clinicopathological data from 900 prostatic lobes at our institution was used as the training cohort. Primary outcome was the presence of ssEPE. The baseline model for comparison had the highest performance out of current biopsyderived predictive models for ssEPE. A separate logistic regression (LR) model was built using the same variables as the ML model. All models were externally validated using a testing cohort of 122 lobes from another institution. Models were assessed by area under receiver-operating-characteristic curve (AUROC), precision-recall curve (AUPRC), calibration, and decision curve analysis. Model predictions were explained using SHapley Additive exPlanations. This tool was deployed as a publicly available web application. Results: Incidence of ssEPE in the training and testing cohorts were 30.7 and 41.8%, respectively. The ML model achieved AUROC 0.81 (LR 0.78, baseline 0.74) and AUPRC 0.69 (LR 0.64, baseline 0.59) on the training cohort. On the testing cohort, the ML model achieved AUROC 0.81 (LR 0.76, baseline 0.75) and AUPRC 0.78 (LR 0.75, baseline 0.70). The ML model was explainable, wellcalibrated, and achieved the highest net benefit for clinically relevant cutoffs of 10-30%. Conclusions: We developed a user-friendly application that enables physicians without prior ML experience to assess ssEPE risk and understand factors driving these predictions to aid surgical planning and patient counselling (https://share.streamlit.io/jcckwong/ssepe/main/ssEPE_V2.pyTest). [ABSTRACT FROM AUTHOR]

المؤلفون: Gotto, Geoffrey¹ drgotto@gmail.com, Drachenberg, Darrel E.², Chin, Joseph³, Casey, Richard⁴, Fradet, Vincent⁵, Sabbagh, Robert⁶, Shayegan, Bobby⁷, Rendon, Ricardo A.⁸, Danielson, Brita⁹, Camacho, Fernandes¹⁰, Zardan, Anousheh¹¹, Plante, Richard¹¹, Hew, Huong¹¹, Chan, Katherine¹¹, Feifer, Andrew¹²

المصدر: Canadian Urological Association Journal. Dec2020, Vol. 14 Issue 12, pE616-E620. 5p.

مصطلحات موضوعية: *ABIRATERONE acetate, *PROSTATE cancer, *METASTASIS, *MONTREAL Cognitive Assessment

مصطلحات جغرافية: CANADA

مستخلص: Introduction: Abiraterone acetate plus prednisone (AA+P) has shown to significantly improve survival. COSMiC, a Canadian Observational Study in Metastatic Cancer of the Prostate, set out to prospectively amass real-world data on metastatic castrationresistant prostate cancer (mCRPC) patients managed with AA+P in Canada. Herein, we report their patient-reported outcomes (PROs). Methods: After a median followup of 67.1 weeks, 254 patients were enrolled across 39 sites. Functional Assessment of Cancer Therapy- Prostate (FACT-P), Montreal Cognitive Assessment (MoCA), Brief Pain Inventory-Short Form (BPI-SF), Brief Fatigue Inventory (BFI), and Current Health Satisfaction in Prostate Cancer (CHS-PCa) were evaluated at baseline, as well as at weeks 12, 24, 48, and 72 after AA+P initiation. Descriptive analysis was used with continuous variables. Changes from baseline were summarized using mean (standard deviation [SD]). Results: At a median age of 76.6 (8.94), baseline FACT-P total score was 111.3 (19.56) with no significant change in their functional status observed from baseline over time. The median baseline MoCA score was 25.2 (4.52), yet subsequent assessments showed an absence of cognitive decline while under treatment. Similarly, no meaningful changes were detected in BPI, BFI, and CHS-PCa during the 72-week study period, thus suggesting that patients' PROs were well-maintained throughout AA+P treatment. Prostatespecific antigen (PSA) response with >50% decline was 66.4%. Safety profile was consistent with the known side effect of AA+P. Conclusions: COSMiC represents the largest Canadian mCRPC cohort treated with AA+P with real-world, prospective evaluation of PROs. This data demonstrated the maintenance in quality of life and cognitive status over the course of the study and underscores the importance of PRO use in this complex patient population. [ABSTRACT FROM AUTHOR]