Leveraging Digital Data to Inform and Improve Quality Cancer Care

Abstract

Background: Efficient capture of routine clinical care and patient outcomes are needed at a population-level, as is evidence on important treatment-related side effects and their effect on well-being and clinical outcomes. The increasing availability of electronic health records (EHRs) offers new opportunities to generate population-level patient-centered evidence on oncological care that can better guide treatment decisions and patient-valued care.Methods: This study includes patients seeking care at an academic medical center, 2008-2018. Digital data sources are combined to address missingness, inaccuracy, and noise common to EHR data. Clinical concepts were identified and extracted from EHR unstructured data using natural language processing (NLP) and machine/deep learning techniques. All models are trained, tested, and validated on independent data samples using standard metrics. Results:We provide use cases for using EHR data to assess guideline adherence and quality measurements among cancer patients. Pretreatment assessment was evaluated by guideline adherence and quality metrics for cancer staging metrics. Our studies in perioperative quality focused on medications administered and guideline adherence.Patient outcomes included treatment-related side-effects and patient-reported outcomes.Conclusions: Advanced technologies applied to EHRs present opportunities to advance population-level quality assessment, to learn from routinely collected clinical data for personalized treatment guidelines, and to augment epidemiological and

Assessment of a Clinical Trial–Derived Survival Model in Patients With Metastatic Castration-Resistant Prostate Cancer

“…Furthermore, RCT data may better capture patient-reported outcomes and survival, whereas advanced technologies are needed to identify and extract this information in EHRs. 23 , 24 , 25 Hence, the accuracy of the EHR model improved as feature reduction strategies were applied; the optimal model included only 25 of the 101 features included in the RCT-derived model. These feature reduction strategies are important when using real-world data because data collection is expensive for the health care system, requiring time as well as computational and financial resources, particularly if many of the identified features do not have substantial implications for model performance.…”

Holding out the promise of Lasswell's dream: Big data analytics in public policy research and teaching

“…Meanwhile, the most exclusive terms in the theme on Healthcare include 'health care ', 'clinic', 'comorbidity', 'diagnosis', 'disease', 'child', and 'COVID'. Other commonly occurring terms in this theme are: 'health', 'patient', 'population', and 'intervention'. Scholars in this area show an interest in big data analytics broadly to study its strengths and weaknesses (Howie et al, 2014), to examine a large volume of information (Aznar-Lou et al, 2018;Zenk et al, 2018), to analyze unstructured data such as text or video (Bayen et al, 2017;Hernandez-Boussard et al, 2020), to combine multiple types of data, such as geographic information and medical records (Pandey et al, 2020), and to apply machine learning for impact assessment (Rikin et al, 2015).…”

Developing clinical indicators for oncology: the inaugural cancer care indicator set for the Australian Council on Healthcare Standards

“…This was either because the information would likely need to be aggregated from multiple and disparate sources or may not have been recorded at all. Despite the recognition that the burgeoning amount of digital data should be easy to harness to inform patient‐valued care, quality initiatives, and policy guidelines, the systems of electronic recording of health processes remain basic in many Australian settings 24 . Preference was therefore given to indicators sourced from data that are widely collected as routine for health facility systems (bookings, rudimentary electronic medical records, financial systems etc).…”