scholarly journals Genomic Classifier Augments the Role of Pathological Features in Identifying Optimal Candidates for Adjuvant Radiation Therapy in Patients With Prostate Cancer: Development and Internal Validation of a Multivariable Prognostic Model

2017 ◽  
Vol 35 (18) ◽  
pp. 1982-1990 ◽  
Author(s):  
Deepansh Dalela ◽  
María Santiago-Jiménez ◽  
Kasra Yousefi ◽  
R. Jeffrey Karnes ◽  
Ashley E. Ross ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Risk Factors ◽  
Lymph Node ◽  
Risk Stratification ◽  
The United States ◽  
Cumulative Number ◽  
Clinical Recurrence ◽  
Cox Regression Analysis ◽  
Initial Observation ◽  
Risk Stratification Tool

Purpose Despite documented oncologic benefit, use of postoperative adjuvant radiotherapy (aRT) in patients with prostate cancer is still limited in the United States. We aimed to develop and internally validate a risk-stratification tool incorporating the Decipher score, along with routinely available clinicopathologic features, to identify patients who would benefit the most from aRT. Patient and Methods Our cohort included 512 patients with prostate cancer treated with radical prostatectomy at one of four US academic centers between 1990 and 2010. All patients had ≥ pT3a disease, positive surgical margins, and/or pathologic lymph node invasion. Multivariable Cox regression analysis tested the relationship between available predictors (including Decipher score) and clinical recurrence (CR), which were then used to develop a novel risk-stratification tool. Our study adhered to the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis guidelines for development of prognostic models. Results Overall, 21.9% of patients received aRT. Median follow-up in censored patients was 8.3 years. The 10-year CR rate was 4.9% vs. 17.4% in patients treated with aRT versus initial observation ( P < .001). Pathologic T3b/T4 stage, Gleason score 8-10, lymph node invasion, and Decipher score > 0.6 were independent predictors of CR (all P < .01). The cumulative number of risk factors was 0, 1, 2, and 3 to 4 in 46.5%, 28.9%, 17.2%, and 7.4% of patients, respectively. aRT was associated with decreased CR rate in patients with two or more risk factors (10-year CR rate 10.1% in aRT v 42.1% in initial observation; P = .012), but not in those with fewer than two risk factors ( P = .18). Conclusion Using the new model to indicate aRT might reduce overtreatment, decrease unnecessary adverse effects, and reduce risk of CR in the subset of patients (approximately 25% of all patients with aggressive pathologic disease in our cohort) who benefit from this therapy.

Genomic classifier to augment the role of pathological features in identifying optimal candidates for adjuvant radiation therapy in patients with prostate cancer: Development and internal validation of a multivariable prognostic model.

2017 ◽  
Vol 35 (6_suppl) ◽  
pp. 142-142
Author(s):  
Firas Abdollah ◽  
Deepansh Dalela ◽  
Maria Santiago-Jimenez ◽  
Kasra Yousefi ◽  
Jeffrey Karnes ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Risk Factors ◽  
Risk Stratification ◽  
Cox Regression ◽  
Adjuvant Radiation ◽  
Cumulative Number ◽  
Clinical Recurrence ◽  
Cox Regression Analysis ◽  
Initial Observation ◽  
Risk Stratification Tool

142 Background: Despite documented oncological benefit, postoperative adjuvant radiotherapy (aRT) utilization in prostate cancer (PCa) patients is still limited in the US. We aimed to develop and internally validate a risk stratification tool incorporating the Decipher score, along with routinely available clinicopathologic features, to identify patients who would benefit the most from aRT. Methods: Our cohort included a total of 512 PCa patients treated with RP at one of four US academic centers between 1990-2010. All patients had ≥ pT3a disease, positive margins, and/or pathologic lymph node invasion (LNI). Multivariable Cox regression analysis (MVA) tested the relationship between available predictors (including Decipher score) and clinical recurrence (CR), which were then used to develop a novel risk stratification tool. Our study adhered to the TRIPOD guidelines for development of prognostic models. Results: Overall, 21.9% patients received aRT. Median follow-up in censored patients was 8.3 years. The 10-year CR rate was 4.9% vs. 17.4% in patients treated with aRT vs. initial observation (p < 0.001). Pathological T3b/T4 stage, Gleason score 8-10, LNI and Decipher score > 0.6 were independent predictors of CR (all p < 0.01) Cumulative number of risk factors was 0, 1, 2, and 3-4 in respectively 46.5, 28.9, 17.2, and 7.4% of patients. Adjuvant RT was associated with decreased CR rate in patients with ≥ 2 risk factors (10-year CR rate 10.1% in aRT vs. 42.1% in initial observation, p = 0.008), but not in those with < 2 risk factors (p = 0.23). Conclusions: Utilizing the novel model to indicate aRT might reduce overtreatment, decrease unnecessary side effects, and reduce risk of CR in the subset of patients (~25% of all patients with aggressive pathological disease) who really benefit from this therapy.

scholarly journals A data-driven approach to predict daily risk of Clostridium difficile infection at two large academic health centers

2017 ◽  
Vol 4 (suppl_1) ◽  
pp. S403-S404
Author(s):  
Maggie Makar ◽  
Jeeheh Oh ◽  
Christopher Fusco ◽  
Joseph Marchesani ◽  
Robert McCaffrey ◽  
...  
Keyword(s):  
Risk Factors ◽  
Clostridium Difficile ◽  
Risk Stratification ◽  
Clostridium Difficile Infection ◽  
Prediction Models ◽  
The United States ◽  
Data Driven ◽  
Discriminative Performance ◽  
Adult Inpatient ◽  
Data Driven Approach

Abstract Background An estimated 293,300 healthcare-associated cases of Clostridium difficile infection (CDI) occur annually in the United States. Prior research on risk-prediction models for CDI have focused on a small number of risk factors with the goal of developing a model that works well across hospitals. We hypothesize that risk factors are, in part, hospital-specific. We applied a generalizable machine learning approach to discovering, or “learning”, hospital-specific risk-stratification models using electronic health record (EHR) data collected during the course of patient care from the Massachusetts General Hospital (MGH) and the University of Michigan Health System (UM). Methods We utilized EHR data from 115,958 adult inpatient admissions from 2012–2014 (MGH) and 258,050 adult inpatient admissions from 2010–2016 (UM) (Fig 1). We extracted patient demographics, admission details, patient history, and daily hospitalization details, resulting in 2,964 and 4,739 features in the MGH and UM models, respectively. We used L2 regularized logistic regression to learn the models and measured the discriminative performance of the models on a year of held-out data from each hospital. Results The MGH and UM models achieved AUROCs of 0.74 (CI: 0.73–0.75) and 0.77 (CI: 0.75–0.80), respectively. The relative importance of risk factors varied significantly across hospitals. In particular, in-hospital locations appeared in the set of top risk factors at one hospital and in the set of protective factors at the other. On average, both models were able to predict CDI five days in advance of clinical diagnosis (Fig 2). Conclusion We used EHR data to generate a daily estimate of the risk of CDI for each inpatient hospitalization. We applied a generalizable data-driven approach to existing data from two large institutions with different patient populations and different data formats and content. In contrast to approaches that focus on learning models that apply generally across hospitals, our proposed approach yields risk stratification models tailored to an institution’s EHR system and patient population. In turn, these hospital-specific models could allow for earlier and more accurate identification of high-risk patients. Disclosures All authors: No reported disclosures.

Mo1163 A Multicenter Study Evaluating Risk Factors of Lymph Node Metastasis in Early Gastric Cancer in the United States

2017 ◽  
Vol 85 (5) ◽  
pp. AB444
Author(s):  
Olaya Isabella Brewer Gutierrez ◽  
Alyssa Y. Choi ◽  
Peter V. Draganov ◽  
Lauren Khanna ◽  
Amrita Sethi ◽  
...  
Keyword(s):  
United States ◽  
Risk Factors ◽  
Gastric Cancer ◽  
Lymph Node ◽  
Lymph Node Metastasis ◽  
Early Gastric Cancer ◽  
Multicenter Study ◽  
The United States ◽  
Node Metastasis

Current landscape of prostate cancer quality measures in the United States.

2016 ◽  
Vol 34 (7_suppl) ◽  
pp. 273-273
Author(s):  
Scott C Flanders ◽  
Eleanor Fitall ◽  
Dayo Jagun ◽  
Kristi Mitchell ◽  
Peter St. John Francis ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
United States ◽  
Risk Stratification ◽  
Late Stage ◽  
Symptom Assessment ◽  
Quality Measures ◽  
The United States ◽  
Additional Treatment ◽  
Urological Surgery ◽  
The Us

273 Background: Prostate cancer (PCa) is the leading cancer for men in the United States (US) and identified by the Centers for Medicare & Medicaid Services (CMS) as one of the top 20 high-impact Medicare conditions experienced by beneficiaries. Thus, there is increasing focus by stakeholders to measure and achieve high-value, quality care in PCa. However, quality measurement is particularly difficult in oncology. Our aim was to assess the current landscape of PCa quality measures (QMs) in the US. Methods: Published literature and online resources from the past 5 years were reviewed to identify PCa QMs and general oncology QMs relevant to PCa. PCa QMs were categorized using a “continuum of care” framework across 5 stages: 1) symptom assessment and screening; 2) diagnosis and risk stratification; 3) initial treatment; 4) monitoring and additional treatment; and 5) advanced- or late-stage care. Finally, PCa QMs were evaluated for their type (eg. process, outcomes), and use by CMS. Results: We identified 16 PCa-specific QMs and 20 general oncology QMs relevant to PCa. The majority of PCa QMs were developed by the American Medical Association–Physician Consortium for Performance Improvements (6 measures) and the Michigan Urological Surgery Improvement Collaborative (6 measures). There are 3 QMs for symptom assessment and screening, 5 QMs for diagnosis and risk stratification, 6 QMs for initial treatment, 2 QMs for monitoring and additional treatment, and 0 QMs for advanced- or late-stage care. Fourteen PCa QMs focus on process of care, but only 2 PCa QMs address outcomes. Nine PCa QMs are part of CMS quality improvement programs, 6 of which are reportable through the Michigan Urological Surgery Improvement Collaborative. Three new PCa QMs are under consideration by CMS. Conclusions: We found few PCa QMs that capture outcomes of patient experience or care, and no PCa-specific QMs available for advanced disease and late-stage care, demonstrating a need to better define quality in this setting. Opportunities to increase the focus on innovative, real-world data-generation strategies, such as PCa disease registries that collect clinical outcomes, patient preferences, and comorbidities, may inform stakeholder development and adoption of new QMs in the US.

Coronary Calcium Score May Replace Cardiovascular Risk Factors as Primary Risk Stratification Tool Before Kidney Transplantation

2016 ◽  
Vol 100 (10) ◽  
pp. 2177-2187 ◽  
Author(s):  
Simon Winther ◽  
Morten Bøttcher ◽  
Hanne S. Jørgensen ◽  
Kirsten Bouchelouche ◽  
Lars C. Gormsen ◽  
...  
Keyword(s):  
Risk Factors ◽  
Kidney Transplantation ◽  
Cardiovascular Risk ◽  
Risk Stratification ◽  
Cardiovascular Risk Factors ◽  
Calcium Score ◽  
Coronary Calcium ◽  
Coronary Calcium Score ◽  
Risk Stratification Tool

303 WHEN TO PERFORM BONE SCAN IN PATIENTS WITH NEWLY DIAGNOSED PROSTATE CANCER: EXTERNAL VALIDATION OF A NOVEL RISK STRATIFICATION TOOL

2011 ◽  
Vol 185 (4S) ◽  
Author(s):  
Cosimo De Nunzio ◽  
Costantino Leonardo ◽  
Andrea Cantiani ◽  
Alfonso Carluccini ◽  
Carlo De Dominicis ◽  
...  
Keyword(s):  
Prostate Cancer ◽  
Risk Stratification ◽  
Bone Scan ◽  
External Validation ◽  
Newly Diagnosed ◽  
Risk Stratification Tool
Sign in / Sign up

Export Citation Format

Share Document