Comprehensive distress screening and referral at a tertiary cancer center

134

Background: Addressing distress in cancer patients is now broadly recognized as critical to well-being and associated with increased survival. Cancer centers are developing innovative distress screening methods; we describe our novel process and results. Methods: New patients from 9/2015 to 3/2017 received an email requesting completion of a 44-item web-based survey assessing depression (2-item Patient Health Questionnaire), anxiety (2-item Generalized Anxiety Disorder), quality of life (QOL, 28-item Functional Assessment of Cancer Treatment-General), malnutrition (3-item Malnutrition Screening Tool), and 9 items addressing existential crisis, physical function, symptoms, tangible needs and concerns for dependent children. Results were computer scored, with positive screens resulting in direct, automated referrals to supportive care services (SCR). Analysis includes descriptive statistics and logistic regression using SAS 9.4. Results: 71% (n = 2629 of 3724) of those approached provided an email and completed the survey; 73% reporting no survey burden. Non-responders were more likely to be minority, non-English speaking, with non-commercial insurance (all p < 0.001). 59% (n = 1543) of responders screened positive for one or more SCR, including 6% to palliative care for poor QOL or symptoms. Receipt of SCR was more likely with Medicaid insurance (1.36 odds ratio [OR], 95% confidence interval [CI] 1.06-1.76, p = .0061); plan to receive care (1.27 OR, CI 1.07-1.50, p = .0061); and any report of survey burden (2.26 OR, CI 1.83-2.80, p < .0001). Conclusions: Web-based distress screening is feasible, efficient and not burdensome for the majority of cancer patients. Those who find this screening burdensome are two-fold more likely to have distress. Future efforts should address screening of vulnerable populations.

Measuring adherence to a Choosing Wisely recommendation in a regional oncology clinic

196

Background: Natural language processing (NLP) has the potential to significantly ease the burden of manual abstraction of unstructured electronic text when measuring adherence to national guidelines. We incorporated NLP into standard data processing techniques such as manual abstraction and database queries in order to more efficiently evaluate a regional oncology clinic’s adherence to ASCO’s Choosing Wisely colony stimulating factor (CSF) recommendation using clinical, billing, and cancer registry data. Methods: Database queries on the clinic’s cancer registry yielded the study population of patients with stage II-IV breast, non-small cell lung (NSCL), and colorectal cancer. We manually abstracted chemotherapy regimens from paper prescription records. CSF orders were collected through queries on the clinic’s facility billing data, when available; otherwise through a custom NLP program and manual abstraction of the electronic medical record. The NLP program was designed to identify clinical note text containing CSF information, which was then manually abstracted. Results: Out of 31,725 clinical notes for the eligible population, the NLP program identified 1,487 clinical notes with CSF-related language, effectively reducing the number of notes requiring abstraction by up to 95%. Between 1/1/2012-12/31/2014, adherence to the ASCO CW CSF recommendation at the regional oncology clinic was 89% for a population of 322 patients. Conclusions: NLP significantly reduced the burden of manual abstraction by singling out relevant clinical text for abstractors. Abstraction is often necessary due to the complexity of data collection tasks or the use of paper records. However, NLP is a valuable addition to the suite of data processing techniques traditionally used to measure adherence to national guidelines.