PURPOSE The implementation and utilization of electronic health records is generating a large volume and variety of data, which are difficult to process using traditional techniques. However, these data could help answer important questions in cancer surveillance and epidemiology research. Artificial intelligence (AI) data processing methods are capable of evaluating large volumes of data, yet current literature on their use in this context of pharmacy informatics is not well characterized. METHODS A systematic literature review was conducted to evaluate relevant publications within four domains (cancer, pharmacy, AI methods, population science) across PubMed, EMBASE, Scopus, and the Cochrane Library and included all publications indexed between July 17, 2008, and December 31, 2018. The search returned 3,271 publications, which were evaluated for inclusion. RESULTS There were 36 studies that met criteria for full-text abstraction. Of those, only 45% specifically identified the pharmacy data source, and 55% specified drug agents or drug classes. Multiple AI methods were used; 25% used machine learning (ML), 67% used natural language processing (NLP), and 8% combined ML and NLP. CONCLUSION This review demonstrates that the application of AI data methods for pharmacy informatics and cancer epidemiology research is expanding. However, the data sources and representations are often missing, challenging study replicability. In addition, there is no consistent format for reporting results, and one of the preferred metrics, F-score, is often missing. There is a resultant need for greater transparency of original data sources and performance of AI methods with pharmacy data to improve the translation of these results into meaningful outcomes.

Background The population of 17 million cancer survivors in the US is projected to steadily increase by 29% in 2029. With advancing age, cancer incidence increases; therefore, the increase of cancer survivors aged 65 and older is expected to place undue burden on the healthcare system. Older cancer patients have higher prevalence of comorbid conditions, which contributes to a higher overall illness burden compared to younger cancer patients and may require complex medication management during cancer treatment. Cancer patients with multiple comorbid conditions report lower health-related quality of life (HRQOL). Women with breast cancer (BC) experience noticeable comorbidity prevalence rates (30%) that can negatively influence HRQOL and increase breast cancer mortality by 20-50%. The causes of HRQOL deficits are likely multifactorial, including demographic and clinical factors which require further investigation. Furthermore, research examining the relationship between medication management, comorbidities, and HRQOL in cancer patients, including stratifying the potential role of obesity that contributes to changes in HRQOL, is limited. Further research addressing the medication management of comorbid conditions can improve understanding of HRQOL in BC patients. Objectives To investigate the association of the medication management of hypertension, diabetes, and respiratory conditions on BC survivor's HRQOL. The secondary objective is to evaluate the role of obesity in medication management for these conditions and resultant changes in HRQOL. Methods Patients diagnosed with Stage I-IV BC between 2007-2016 were identified from the Surveillance Epidemiology and End Results (SEER) and Medicare Health Outcomes Survey (MHOS; SEER-MHOS) data resource. Descriptive statistics and multivariate models, including demographics, clinical characteristics, and Medicare Part D claims, was used to evaluate medication management and potential underlying associations. HRQOL was assessed using the VR-12. Obesity was calculated from self-reported height and weight at the time of survey. Results The study population for this analysis includes 1,016 breast cancer patients diagnosed between 2007-2016 in the SEER-MHOS dataset with continuous Part D coverage one year before and after diagnosis. Among these patients, 85% reported at least one comorbid condition. Further analysis is in progress. Conclusions Understanding the potential aspects of treatment that influence HRQOL can provide further insights into patient-reported experiences and may improve standards of care to support older BC survivors with chronic comorbid conditions. Citation Format: Melissa A. Bruno, Roxanne Jensen, Catherine Wang, Dannielle Kelley, Erin Kent, Donna R. Rivera. Examining the relationship between medication utilization and health-related quality of life (HRQOL) among breast cancer patients with comorbidities: A Surveillance Epidemiology and End Results and Medicare Health Outcomes Survey (SEER-MHOS) analysis [abstract]. In: Proceedings of the Annual Meeting of the American Association for Cancer Research 2020; 2020 Apr 27-28 and Jun 22-24. Philadelphia (PA): AACR; Cancer Res 2020;80(16 Suppl):Abstract nr 5756.