Automatically Identifying Financial Stress Information from Clinical Notes for Patients with Prostate Cancer.

Background: Financial stress, one of the social determinants, is common among cancer patients because of high out-ofpocket costs for treatment, as well as indirect costs. The National Academy of Medicine (NAM) has advised providers to recognize and discuss cost concerns with patients in order to enhance shared decision-making for treatment and exploration of financial assistant programs. However, financial stress is rarely assessed in clinical practice or research, thus, under-coded and under-documented in clinical practice. Natural language processing (NLP) offers great potential that can automatically extract and process data on financial stress from clinical free text existing in the patient electronic health record (EHR). Methods: We developed and evaluated an NLP approach to identify financial stress from clinical narratives for patients with prostate cancer. Of 4,195 eligible prostate cancer patients, we randomly sampled 3,138 patients (75%) as a training dataset (150,990 documents) to develop a financial stress lexicon and NLP algorithms iteratively. The remaining 1,057 patients (25%) were used as a test dataset (55,516 documents) to evaluate the NLP algorithm performance. The common terms representing financial stress were "financial concerns," "unable to afford," "insurance issue," "unemployed," and "financial assistance." Negations were used to exclude false mentions of financial stress. Results: Applying both pre- and post-negation, the NLP algorithm identified 209 patients (6.0%) from the training sample and 66 patients (6.2%) with 161 notes from the test sample as having documented financial stress. Two independent domain experts manually reviewed all 161 notes with NLP identified positives and randomly selected 161 notes with NLP-identified negatives, the NLP algorithm yielded 0.86 for precision, 1 for recall, and 0.9.2 for F-score. Conclusions: Financial stress information is not commonly documented in the EHR, neither in structured format nor in clinical narratives. However, natural language processing can accurately extract financial stress information from clinical notes when such narrative information is available.

Social Networks Across Common Cancer Types: The Evidence, Gaps, and Areas of Potential Impact.

Although the association between social context and health has been demonstrated previously, much less is known about network interactions by gender, race/ethnicity, and sociodemographic characteristics. Given the variability in cancer outcomes among groups, research on these relationships may have important implications for addressing cancer health disparities. We examined the literature on social networks and cancer across the cancer continuum among adults. Relevant studies (N=16) were identified using two common databases: PubMed and Google Scholar. Most studies used a prospective cohort study design (n=9), included women only (n=11), and were located in the United States (n=14). Seventy-five percent of the studies reviewed used a validated scale or validated items to measure social networks (n=12). Only one study examined social network differences by race, 57.1% (n=8) focused on breast cancer alone, 14.3% (n=2) explored colorectal cancer or multiple cancers simultaneously, and 7.1% (n=1) only prostate cancer. More than half of the studies included multiple ethnicities in the sample, while one study included only low-income subjects. Despite findings of associations between social networks and cancer survival, risk, and screening, none of the studies utilized social networks as a mechanism for reducing health disparities; however, such an approach has been utilized for infectious disease control. Social networks and the support provided within these networks have important implications for health behaviors and ultimately cancer disparities. This review serves as the first step toward dialog on social networks as a missing component in the social determinants of cancer disparities literature that could move the needle upstream to target adverse cancer outcomes among vulnerable populations.

Effect of genetic counseling and testing for BRCA1 and BRCA2 mutations in African American women: a randomized trial.

BACKGROUND: Limited empirical data are available on the effects of genetic counseling and testing among African American women. OBJECTIVE: To evaluate the effects of genetic counseling and testing in African American women based on different levels of exposure: (a) women who were randomized to culturally tailored (CTGC) and standard genetic counseling (SGC) to women who declined randomization (non-randomized group), (b) participants and non-participants in genetic counseling, and (c) BRCA1 and BRCA2 (BRCA1/2) test result acceptors and decliners. DESIGN: Randomized trial of genetic counseling conducted from February 2003 to November 2006. MEASURES: We evaluated changes in perceived risk of developing breast cancer and cancer worry. RESULTS: Women randomized to CTGC and SGC did not differ in terms of changes in risk perception and cancer worry compared to decliners. However, counseling participants had a significantly greater likelihood of reporting reductions in perceived risk compared to non-participants (p = 0.03). Test result acceptors also had a significantly greater likelihood of reporting decreases in cancer worry (p = 0.03). However, having a cancer history (p = 0.03) and a BRCA1/2 prior probability (p = 0.04) were associated with increases in cancer worry. CONCLUSIONS: Although CTGC did not lead to significant improvements in perceived risk or psychological functioning, African American women may benefit from genetic counseling and testing. Continued efforts should be made to increase access to genetic counseling and testing among African American women at increased risk for hereditary disease. But, follow-up support may be needed for women who have a personal history of cancer and those with a greater prior probability of having a BRCA1/2 mutation.

Decisions and outcomes of genetic testing for inherited breast cancer risk.

Since the discovery of breast cancer susceptibility genes and the availability of genetic testing, a substantial amount of research has been conducted to evaluate rates of genetic test acceptance and to understand the psychological and behavioral impact of BRCA1 and BRCA2 (BRCA1/2) genetic test results. This article explores findings related to genetic test acceptance for inherited breast cancer risk and the impact of genetic test results on psychological functioning, cancer prevention and control behaviors, and family communication about genetic testing. Overall, rates of genetic test acceptance were lower than anticipated based on interest in genetic testing reported in early research. While there is limited evidence that genetic testing generates adverse psychological effects, receiving positive BRCA1/2 test results may cause emotional reactions and concerns that are specific to such results. Although early reports suggested that receiving positive BRCA1/2 test results may have a limited impact on cancer screening or prevention behaviors, recent studies have shown that genetic testing for inherited breast cancer risk may increase screening behaviors among mutation carriers. However, utilization of some screening tests remains low among mutation carriers. Additional studies are needed to identify subgroups of participants in genetic testing who may be vulnerable to experiencing testing-specific concerns, and to evaluate the effects of interventions designed to promote behavioral change and address other concerns that may be generated by receiving positive BRCA1/2 test results.