Search

7057 Background: Cancer patients (pts) are at high risk of unplanned hospital readmissions. Predicting which cancer patients are at higher risk of readmission would improve post-discharge follow-up/navigation, decrease cost, and improve pt outcomes. Methods: We conducted a retrospective cohort study of non-surgical cancer pts hospitalized at our center between 12/2014 to 7/2018. A machine learning algorithm was trained on 348 medical, sociodemographic and cancer-specific variables with a total of 1,801,944 data points. The cohort was randomly divided into training (80%) and validation (20%) subsets. Prediction performance was measured by area under the receiver operator characteristic curve (AUC). Results: A total of 5,178 hospitalizations were included, of which 45.1% were women, and 27.6% experienced an unplanned readmission within 30 days. The most frequently represented cancers were hematologic malignancies (30.5%), followed by GI (18.1%), lung (13.7%), and GU (10.9%). Significant variables that impacted the algorithm decision are ranked from the most to the least important, including: days from last admission; planned index chemotherapy admission; number of vascular access lines, drains, and airways in use; length of stay; cancer diagnosis; total ED visits in past 6 months; age; discharge lab values (sodium, albumin, alkaline phosphatase, bilirubin, platelets); number of prior admissions; and discharge disposition. The AUC for the validation subset was 0.80. To ease the translation of this model into the clinic, we developed a web application whereby users can supply the aforementioned variables to the model and receive a personalized prediction that highlights those variables most affecting a subject’s readmission risk status: www.Cancer-Readmission.com. Conclusions: A cancer-specific readmission risk model with high AUC for 30-days unplanned readmission has been developed. The model is embedded in a freely available web application that provides personalized, patient-specific predictions. Programs that integrate this model can identify cancer patients with a greater risk for unplanned hospital readmission, thus providing a personalized approach to prevent future unplanned readmissions.

7534 Background: Conventional cytogenetics remain one of the most important prognostic factors in acute myeloid leukemia (AML), though 50-60% of patients (pts) have normal karyotype (NK), conventionally classified as intermediate-risk, and have very heterogeneous outcomes. A fraction of mutations such as NPM1, FLT3-ITD, and CEBPa can improve risk stratification for some pts but underestimate the molecular complexity and interactions between these genes and others. Methods: Genomic and clinical data of 2,793 primary AML (pAML) pts were analyzed. A panel of 35 genes that are commonly mutated in AML and myeloid malignancies and have shown to impact OS was included. Correlation of each mutation with others and their impact on OS were evaluated. OS was calculated from the date of diagnosis to date of death or last follow-up. Results: Of 2,793 pts with pAML, 1,352 (48%) had NK and were included in the final analysis. The median age was 55 years (range, 18-93). The median number of mutations/sample was 3 (range, 0-7). The most commonly mutated genes were: NPM1 (49%), DNMT3A (37%), FLT3-ITD (24%), CEBPa (19%), TET2 (17%), IDH2 (17%), and RUNX1 (15%). In univariate Cox regression analysis, mutations in NPM1 (HR 0.81, p =0.008), and CEBPa (single mutant, HR 0.8, double mutant, HR 0.69, p< 0.001, respectively) were associated with longer OS, while mutations in DNMT3a (HR 1.26, p =0.003), FLT3-ITD (HR 1.49, p< 0.001), TET2 (HR 1.26, p =0.02), RUNX1 (HR 1.36, p =0.003), SRSF2 (HR 1.58, p Mut/ DNMT3AWT/FLT3-ITDWT was 99.1 months(m), NMP1Mut/DNMT3AMut /FLT3-ITDWT 54.8m, NMP1Mu t/DNMT3AWT/FLT3-ITDMut 42.3m, NMP1Mut/DNMT3AMut/FLT3-ITDMut 13.4m, NMP1WT/DNMT3AMut/FLT3-ITDMut 13.1m, and NMP1WT/DNMT3AWT/FLT3-ITDWT (triple negative) 32.7m. The median OS for pts with 0-2 mutations/sample was 59.3m, compared to 34.1m for pts with 3-4 mutations, and 16.1m for pts with > 5 mutations ( p< 0.001). Conclusions: We propose a simplified and robust approach to risk stratify AML pts with NK based on the mutational status of NPM1, DNMT3A, FLT3-ITD (alone or in combination with each other), CEBPa, and the number of mutations/sample.