e13591 Background: Electronic Health Records (EHR) provide the possibility of leveraging modern machine learning algorithms for disease detection prediction. Since a patient’s medical journey contains a complex pattern and it is difficult to identify interactive feature impacts, we propose to reconstruct patients’ attributes at different time points into dynamic graphs. Then we can use graph-based learning algorithms to enhance the predictive precision and identify leading feature interactions that reveal key services transitions. Methods: Sequential EHR like diagnosis (Dx), procedure (Px) and prescription (Rx) can be transformed into dynamic temporal graphs with nodes representing attributes, services, and medical status and edges representing patient-object interactions. Also, graph based sequential recommendation can use structured historical behavior trajectories as input, aiming to predict patient’s next behavior. Then, the model can investigate patients’ time-sensitive features interactively identifying a potential disease and then output a probability of getting that disease. Dynamic graphs can also help to track patient’s medical treatment/drug use service transitions. Results: We applied our method on a Newly Diagnosed Multiple Myeloma (NDMM) dataset consisting of 1.5 million candidates’ longitudinal medical claims from 2017 to 2020 with diagnosis rate around 0.6%. In this data set, patients’159 aggregated Dx, Rx and Px features, together with 30 demographic attributes are updated monthly. The model was trained on 4 monthly data cohorts from the 12/2017 to 03/2019 period and its performance was tested on 9 monthly cohorts from year 2020. The 1000 patients scored as having highest risk were evaluated for the predictive precision which was around 6.5% This precision compares most favorably relative to the reported 0.76% lifetime risk of getting multiple myeloma in US. We also captured the top, service transitions in NDMM patients having 30% more frequency than those in overall populations. Conclusions: The novel dynamic graph-based learning approach on a large-scale EHR dataset demonstrates the advancement of the disease detection methodology. While the outcome of this model significantly improves the accuracy of predictive precision, it also helps identify more meaningful key drivers attributing to disease. The incremental new patients identified through this novel model will provide a better basis for the evolving identification solution within Biopharma industry.

e18588 Background: A growing body of evidence has shown that a Whole Person Integrative Oncology approach, adding the use of complementary and lifestyle therapies to cancer treatments, benefits patients by improving patient-reported outcomes and potentially extending overall survival. This study aims to investigate the relationship between the survival outcomes of breast cancer patients and the level of involvement in Integrative Oncology at the institutions treating those patients. Methods: Between January 2013 and December 2014, 4,815 breast cancer patients were available for survival analysis using an established claims-based method. These patients were filtered to include those with clear mapping to treating oncologists and treating institutions. To measure each institution’s level of Integrative involvement, a scoring system was developed with the Samueli Foundation and oncologists from each institution were surveyed on the education, availability, and financing of 12 complementary and lifestyle approaches during the treatment timeframe. Statistical analysis using multivariate modeling with logistic regression and a lasso approach were employed. 19 variables across region, patient demographics, and institutional profile were included. Model coefficients are exponentiated and presented as odds-ratios, with less than one having a negative impact on survival and greater than one improved survival. Results: We identified 173 patients mapping to 103 institutions and 103 oncologists who responded to our survey. Median age of breast cancer patients was 51 (range: 32-76). 14 of the patients (8%) were identified as metastatic. The 5-year overall survival among the Low scoring institutions was 89%, Low-Mid 96%, Mid-High 96%, High 95%. Chi square testing across these cohorts showed no statistically significant difference between them. On multivariate modeling, age, geography, metastatic status, academic setting, and Integrative score were predictors of 5-year survival. The most significant 9 variables are shown in Table. Having metastatic disease, treatment at a non NCCN designated facility, treatment at Midwest or Western Region predicts for lower 5-year survival. Older age, treatment at an academic setting, and having a High or Low-Mid Integrative score are predictors of improved survival. Conclusions: This study suggests that in addition to traditional predictors of survival such as metastatic disease and younger age, patients receiving treatment at an institution that supports Integrative Oncology programs may be associated with improved survival. More work is needed to evaluate the relationship between Integrative Oncology and cancer treatment outcomes.[Table: see text]

e24123 Background: The use of Complementary and Lifestyle (C&L) approaches in conjunction with medical treatments is known as Integrative Oncology. While Integrative Oncology practices have been steadily rising in the past few decades, there are still awareness and education gaps that medical professionals can help address for their patients. Methods: Survey-based data collection and analysis was used to assess awareness, perceptions, and usage of Integrative Oncology. Patients were randomly sampled among breast cancer patients diagnosed within 2 years and included all stages (0-IV) and all US regions (NE, South, Midwest, West). Physicians were sampled from a panel of community and academic practices across the US, with the requirement they treat at least 10 breast cancer patients in a typical 3-month period and have been in practice for at least 6 years since residency or fellowship. Results: Survey invitations were sent to 1,901 patients and 2,758 Oncologists; 164 breast cancer patients and 115 Oncologists completed the surveys. Approximately two-thirds of Oncologists and patients agree that C&L approaches contribute to improved quality of life and well-being for patients (table row 1, 2). However, significantly more patients than Oncologists believe that Integrative Oncology also leads to better treatment outcome and survival (row 3). In addition, Oncologists are significantly more aware of C&L practices than are patients (row 4). When asked what percent of breast cancer patients they discuss C&L methods with, Oncologists report 55% average (CI: 50-60%). However, when asked how they became aware of C&L, only 28% of patients (CI: 21-35%) mention their Oncologist/cancer care team or the institution where they were treated (not in table). Ideally, patients desire information about C&L to come directly from Oncologists, but that is not the predominant model (row 5). Conclusions: Many breast cancer patients believe an Integrative approach will improve their treatment outcomes and prefer their providers to discuss this with them.[Table: see text]

No abstract

e20002 Background: Identifying optimal therapy options can help maximize treatment outcomes. Finding ways to help improve treatment decision is of great value to achieve better patient care. With the availability of robust patient real world data and the application of state of the art Artificial Intelligence and Machine Learning (AIML) technology, new opportunities have emerged for a broad spectrum of research needs from oncology R&D to commercialization. To illustrate the above advancements, this study identified patients diagnosed with CLL who may progress to next line of treatment in the near future (e.g. future 3 months). More importantly, we can identify treatment patterns which are more effective in treating different types of CLL patients. Methods: This study includes multiple steps which have already been analyzed for feasibility: 1. Collect CLL patients. IQVIA's real world data contains ~60,000 active CLL treated patients. ~2,000 patients have progressed line of treatment in 3 month. 2. Define patients into positive and negative cohorts based on those who have/have not advanced to line L2+. 3. Determine patient profiles based on treatment regimens, symptoms, lab tests, doctor visits, hospital visits, and co-morbidity, etc. 4. Select patient and treatment features to fit an AIML predictive model. 5. Test different algorithms to achieve best model results and validate model performance. 6. Score and classify CLL patients into high and low probability based on the predictive model. 7. Match patients based on feature importance and compare regimens between positive and negative cohort. Results: Model accuracy is above 90%. Top clinical features are calculated for each patient. Optimum treatment patterns between high and low probability patients are identified, with controlling patient key features. Conclusions: Conclusions from this study is expected to yield deeper insight into more tailored treatments by patient type. CLL patients started with oral therapy(targeting) have better response than other treatments.