Qinyu Chen

PURPOSE: Pancreatic cancer is an aggressive malignancy with patients often experiencing nonspecific symptoms before diagnosis. This study evaluates a machine learning approach to help identify patients with early-stage pancreatic cancer from clinical data within electronic health records (EHRs). MATERIALS AND METHODS: From the Optum deidentified EHR data set, we identified early-stage (n = 3,322) and late-stage (n = 25,908) pancreatic cancer cases over 40 years of age diagnosed between 2009 and 2017. Patients with early-stage pancreatic cancer were matched to noncancer controls (1:16 match). We constructed a prediction model using eXtreme Gradient Boosting (XGBoost) to identify early-stage patients on the basis of 18,220 features within the EHR including diagnoses, procedures, information within clinical notes, and medications. Model accuracy was assessed with sensitivity, specificity, positive predictive value, and the area under the curve. RESULTS: The final predictive model included 582 predictive features from the EHR, including 248 (42.5%) physician note elements, 146 (25.0%) procedure codes, 91 (15.6%) diagnosis codes, 89 (15.3%) medications, and 9 (1.5%) demographic features. The final model area under the curve was 0.84. Choosing a model cut point with a sensitivity of 60% and specificity of 90% would enable early detection of 58% late-stage patients with a median of 24 months before their actual diagnosis. CONCLUSION: Prediction models using EHR data show promise in the early detection of pancreatic cancer. Although widespread use of this approach on an unselected population would produce high rates of false-positive tests, this technique may be rapidly impactful if deployed among high-risk patients or paired with other imaging or biomarker screening tools.

E16801 Background: Pancreatic cancer has an insidious presentation with four-in-five patients presenting with disease not amenable to potentially curative surgery. Efforts to screen patients for pancreatic cancer using population-wide strategies have proven ineffective. We applied a machine learning approach to create an early prediction model drawing on the content of patients’ electronic health records (EHRs). Methods: We used patient data from OptumLabs which included de-identified data extracted from patient EHRs collected between 2009 and 2017. We identified patients diagnosed with pancreatic cancer at age 40 or later, which we categorized into early-stage pancreatic cancer (ESPC; n = 3,322) and late-stage pancreatic cancer (LSPC; n = 25,908) groups. ESPC cases were matched to non-pancreatic cancer controls in a ratio of 1:16 based on diagnosis year and geographic division, and the cohort was divided into training (70%) and test (30%) sets. The prediction model was built using an eXtreme Gradient Boosting machine learning algorithm of ESPC patients’ EHRs in the year preceding diagnosis, with features including patient demographics, procedure and clinical diagnosis codes, clinical notes and medications. Model discrimination was assessed with sensitivity, specificity, positive predictive value (PPV) and area under the curve (AUC) with a score of 1.0 indicating perfect prediction. Results: The final AUC in the test set was 0.841, and the model included 583 features, of which 248 (42.5%) were physician note elements, 146 (25.0%) were procedure codes, 91 (15.6%) were diagnosis codes, 89 (15.3%) were medications and 9 (1.54%) were demographic features. The most important features were history of pancreatic disorders (not diabetes or cancer), age, income, biliary tract disease, education level, obstructive jaundice and abdominal pain. We evaluated model performance at varying classification thresholds. When applied to patients over 40 choosing a threshold with a sensitivity of 20% produced a specificity of 99.9% and a PPV of 2.5%. The model PPV increased with age; for patients over 80, PPV was 8.0%. LSPC patients identified by the model would have been detected a median of 4 months before their actual diagnosis, with a quarter of these patients identified at least 14 months earlier. Conclusions: Using EHR data to identify early-stage pancreatic cancer patients shows promise. While widespread use of this approach on an unselected population would produce high rates of false positives, this technique could be employed among high risk patients, or paired with other screening tools.

Background/Objectives: The practice of palliative radiation therapy (RT) is based on extrapolation from adult literature. We evaluated patterns of pediatric palliative RT to describe regimens used to identify opportunity for future pediatric‐specific clinical trials.Design/Methods: Six international institutions with pediatric expertise completed a 122‐item survey evaluating patterns of palliative RT for patients ≤21 years old from 2010 to 2015. Two institutions use proton RT. Palliative RT was defined as treatment with the goal of symptom control or prevention of immediate life‐threatening progression.Results: Of 3,225 pediatric patients, 365 (11%) were treated with palliative intent to a total of 427 disease sites. Anesthesia was required in 10% of patients. Treatment was delivered to metastatic disease in 54% of patients. Histologies included neuroblastoma (30%), osteosarcoma (18%), leukemia/lymphoma (12%), rhabdomyosarcoma (12%), medulloblastoma/ependymoma (12%), Ewing sarcoma (8%), and other (8%). Indications included pain (43%), intracranial symptoms (23%), respiratory compromise (14%), cord compression (8%), and abdominal distention (6%). Sites included nonspine bone (35%), brain (16% primary tumors, 6% metastases), abdomen/pelvis (15%), spine (12%), head/neck (9%), and lung/mediastinum (5%). Re‐irradiation comprised 16% of cases. Techniques employed three‐dimensional conformal RT (41%), intensity‐modulated RT (23%), conventional RT (26%), stereotactic body RT (6%), protons (1%), electrons (1%), and other (2%). The most common physician‐reported barrier to consideration of palliative RT was the concern about treatment toxicity (83%).Conclusion: There is significant diversity of practice in pediatric palliative RT. Combined with ongoing research characterizing treatment response and toxicity, these data will inform the design of forthcoming clinical trials to establish effective regimens and minimize treatment toxicity for this patient population.