PURPOSE: Treatment decisions about localized prostate cancer depend on accurate estimation of the patient's life expectancy. Current cancer and noncancer survival models use a limited number of predefined variables, which could restrict their predictive capability. We explored a technique to create more comprehensive survival prediction models using insurance claims data from a large administrative data set. These data contain substantial information about medical diagnoses and procedures, and thus may provide a broader reflection of each patient's health. METHODS: We identified 57,011 Medicare beneficiaries with localized prostate cancer diagnosed between 2004 and 2009. We constructed separate cancer survival and noncancer survival prediction models using a training data set and assessed performance on a test data set. Potential model inputs included clinical and demographic covariates, and 8,971 distinct insurance claim codes describing comorbid diseases, procedures, surgeries, and diagnostic tests. We used a least absolute shrinkage and selection operator technique to identify predictive variables in the final survival models. Each model's predictive capacity was compared with existing survival models with a metric of explained randomness (ρ2) ranging from 0 to 1, with 1 indicating an ideal prediction. RESULTS: Our noncancer survival model included 143 covariates and had improved survival prediction (ρ2 = 0.60) compared with the Charlson comorbidity index (ρ2 = 0.26) and Elixhauser comorbidity index (ρ2 = 0.26). Our cancer-specific survival model included nine covariates, and had similar survival predictions (ρ2 = 0.71) to the Memorial Sloan Kettering prediction model (ρ2 = 0.68). CONCLUSION: Survival prediction models using high-dimensional variable selection techniques applied to claims data show promise, particularly with noncancer survival prediction. After further validation, these analyses could inform clinical decisions for men with prostate cancer.
PURPOSE: Treatment decisions about localized prostate cancer depend on accurate estimation of the patient's life expectancy. Current cancer and noncancer survival models use a limited number of predefined variables, which could restrict their predictive capability. We explored a technique to create more comprehensive survival prediction models using insurance claims data from a large administrative data set. These data contain substantial information about medical diagnoses and procedures, and thus may provide a broader reflection of each patient's health. METHODS: We identified 57,011 Medicare beneficiaries with localized prostate cancer diagnosed between 2004 and 2009. We constructed separate cancer survival and noncancer survival prediction models using a training data set and assessed performance on a test data set. Potential model inputs included clinical and demographic covariates, and 8,971 distinct insurance claim codes describing comorbid diseases, procedures, surgeries, and diagnostic tests. We used a least absolute shrinkage and selection operator technique to identify predictive variables in the final survival models. Each model's predictive capacity was compared with existing survival models with a metric of explained randomness (ρ2) ranging from 0 to 1, with 1 indicating an ideal prediction. RESULTS: Our noncancer survival model included 143 covariates and had improved survival prediction (ρ2 = 0.60) compared with the Charlson comorbidity index (ρ2 = 0.26) and Elixhauser comorbidity index (ρ2 = 0.26). Our cancer-specific survival model included nine covariates, and had similar survival predictions (ρ2 = 0.71) to the Memorial Sloan Kettering prediction model (ρ2 = 0.68). CONCLUSION: Survival prediction models using high-dimensional variable selection techniques applied to claims data show promise, particularly with noncancer survival prediction. After further validation, these analyses could inform clinical decisions for men with prostate cancer.
Authors: Freddie C Hamdy; Jenny L Donovan; J Athene Lane; Malcolm Mason; Chris Metcalfe; Peter Holding; Michael Davis; Tim J Peters; Emma L Turner; Richard M Martin; Jon Oxley; Mary Robinson; John Staffurth; Eleanor Walsh; Prasad Bollina; James Catto; Andrew Doble; Alan Doherty; David Gillatt; Roger Kockelbergh; Howard Kynaston; Alan Paul; Philip Powell; Stephen Prescott; Derek J Rosario; Edward Rowe; David E Neal Journal: N Engl J Med Date: 2016-09-14 Impact factor: 91.245
Authors: Matthew Kent; David F Penson; Peter C Albertsen; Michael Goodman; Ann S Hamilton; Janet L Stanford; Antoinette M Stroup; Behfar Ehdaie; Peter T Scardino; Andrew J Vickers Journal: BMC Med Date: 2016-02-09 Impact factor: 8.775
Authors: Saira Khan; Sanah Vohra; Laura Farnan; Shekinah N C Elmore; Khadijah Toumbou; Madhav K C; Elizabeth T H Fontham; Edward S Peters; James L Mohler; Jeannette T Bensen Journal: Prostate Date: 2022-07-26 Impact factor: 4.012
Authors: Elizabeth C Chase; Alex K Bryant; Yilun Sun; William C Jackson; Daniel E Spratt; Robert T Dess; Matthew J Schipper Journal: BJU Int Date: 2022-04-24 Impact factor: 5.969
Authors: Abhishek Kumar; Zachary D Guss; Patrick T Courtney; Vinit Nalawade; Paige Sheridan; Reith R Sarkar; Matthew P Banegas; Brent S Rose; Ronghui Xu; James D Murphy Journal: JAMA Netw Open Date: 2020-07-01