Prostate cancer is the most common malignancy in men. Newly diagnosed men face complex treatment choices, each with different risks of acquired patient-centered outcomes (e.g. urinary and erectile dysfunction). Currently, patients and clinicians cannot easily compare the trade-offs among patient-centered outcomes across different treatments because the empirical evidence regarding these trade-offs does not exist, because patient centered outcomes are not routinely recorded in assessable formats. However, electronic healthcare records (EHR) free text is a rich, untapped source of patient centered outcomes. We propose to assemble a robust data-mining workflow to efficiently and accurately capture treatment and outcome quality metrics from structured data and free-text in EHRs. We will put this evidence in the hands of both clinicians and patients through a web-based risk assessment tool. Our proposal has three innovative aspects. First, we will develop an EHR prostate cancer database that will allow for clinical care data to be analyzed alongside diagnostic details. Second, we will create novel ontological representations of quality metrics that will be public and reliably calculable across EHR-systems. Third, we will assemble a robust data- mining workflow that expands on existing methods by focusing on ontology-based dictionaries to annotate free text. Combining this set of innovative components will uniquely allow us to use existing EHRs to efficiently study the trade-offs among patient-centered outcomes across different treatments. In Aim 1 we will create the building blocks needed to identify quality metric data in EHRs. We will develop an EHR-database, map quality metrics to medical vocabularies and ontologies, and create electronic quality metric phenotypes. In Aim 2, we will expand our data-mining workflow with quality metric vocabulary and use it to gather data relevant to quality metrics. In Aim 3 we will develop a web-based tool that integrates the empirical evidence assessed in our first two aims with patient and clinical characteristics to estimate patients' personalized risks of patient centered outcomes across treatments. Our web tool will display such personalized risk predictions, to help clinicians and patients choose a treatment option that offers the best predicted quality of life given the importance they assign toeach patient-centered outcome. This proposal will address a critical gap in evidence for prostate cancer treatment and research by providing clinicians and patients with empirical evidence needed to compare the trade-offs among patient centered outcomes across different treatments. Our work is consistent with our nation's focus on EHR `meaningful use' and the comprehensive assessment of healthcare delivery, and with NCI's focus on improving the quality of cancer care delivery.