Search

Objective To develop novel, scalable, and valid literacy profiles for identifying limited health literacy patients by harnessing natural language processing. Data Source With respect to the linguistic content, we analyzed 283 216 secure messages sent by 6941 diabetes patients to physicians within an integrated system's electronic portal. Sociodemographic, clinical, and utilization data were obtained via questionnaire and electronic health records. Study Design Retrospective study used natural language processing and machine learning to generate five unique “Literacy Profiles” by employing various sets of linguistic indices: Flesch‐Kincaid (LP_FK); basic indices of writing complexity, including lexical diversity (LP_LD) and writing quality (LP_WQ); and advanced indices related to syntactic complexity, lexical sophistication, and diversity, modeled from self‐reported (LP_SR), and expert‐rated (LP_Exp) health literacy. We first determined the performance of each literacy profile relative to self‐reported and expert‐rated health literacy to discriminate between high and low health literacy and then assessed Literacy Profiles’ relationships with known correlates of health literacy, such as patient sociodemographics and a range of health‐related outcomes, including ratings of physician communication, medication adherence, diabetes control, comorbidities, and utilization. Principal Findings LP_SR and LP_Exp performed best in discriminating between high and low self‐reported (C‐statistics: 0.86 and 0.58, respectively) and expert‐rated health literacy (C‐statistics: 0.71 and 0.87, respectively) and were significantly associated with educational attainment, race/ethnicity, Consumer Assessment of Provider and Systems (CAHPS) scores, adherence, glycemia, comorbidities, and emergency department visits. Conclusions Since health literacy is a potentially remediable explanatory factor in health care disparities, the development of automated health literacy indicators represents a significant accomplishment with broad clinical and population health applications. Health systems could apply literacy profiles to efficiently determine whether quality of care and outcomes vary by patient health literacy; identify at‐risk populations for targeting tailored health communications and self‐management support interventions; and inform clinicians to promote improvements in individual‐level care.

Objectives: To explore racial and ethnic (ethnic hereafter) differences in health-related quality of life (HRQL) in older adults with diabetes mellitus in an integrated delivery system. Design: Observational cross-sectional study. Setting: Kaiser Permanente Northern California. Participants: Ethnic-stratified, random sample of 6,096 adults with diabetes mellitus aged 60 to 75 who completed a HRQL questionnaire. Measurements: Physical and mental HRQL were measured based on the Medical Outcomes Study 8-item Short Form Survey (range 0�100, mean 50). Age- and sex-adjusted weighted linear regression models estimated associations between ethnicity and HRQL and evaluated potential mediators (socioeconomic status, acculturation, health behaviors, diabetes mellitus�related conditions). Differences in ethnic-specific, adjusted mean HRQL scores were tested (reference whites). Results: Physical HRQL was better for Filipinos (48.3, 95% confidence interval (CI) = 47.0�49.6, P < .001), Asians (48.1, 95% CI = 46.8�49.3, P < .001), Hispanics (45.1, 95% CI = 44.2�46.0, P < .001), and blacks (44.2, 95% CI = 43.3�45.1, P = .04) than whites (42.9, 95% CI = 42.6�43.2). Adjusting for potential mediators did not change these relationships. Mental HRQL was better only for Asians (52.7, 95% CI = 51.6�53.7, P = .01) than for whites (51.0, 95% CI = 50.7�51.3), but this difference was small and became nonsignificant after adjustment for socioeconomic status, acculturation, health behaviors, and diabetes mellitus�related conditions. Conclusion: In older adults with diabetes mellitus in a well-established integrated healthcare delivery system, ethnic minorities had better physical HRQL than whites. Equal access to care in an integrated delivery system may hold promise for reducing health disparities in diabetes mellitus-related patient-reported outcomes.

Aims Our aim was to examine the associations of alcohol consumption with six diabetes self-care behaviours. Methods We determined levels of alcohol consumption and examined associations between alcohol consumption and six self-care behaviours in 65 996 adults with diabetes who received care through Kaiser Permanente Northern California and who responded to a 1994–1997 survey. Adherence with recommendations for self monitoring of blood glucose, HbA1c testing, and diabetes medications were determined from electronic records; smoking and use of diet and exercise to treat diabetes were self reported. Multiple logistic regression models were used to determine the associations between alcohol consumption (average number of drinks/day in the past year) and the probability of adherence to each self-care behaviour. Results Current alcohol consumption was reported by 50.8% of adults with diabetes. In adjusted models, we observed a gradient of increasing risk for poor adherence to diabetes self-care behaviours with increasing alcohol consumption, starting with those who consume even one drink a day. Former drinkers had the greatest compliance with each self-care behaviour, except for current smoking. Conclusions Alcohol consumption is a marker for poorer adherence to diabetes self-care behaviours. These findings highlight the importance of routine assessment of alcohol intake in people with diabetes, particularly as half of adults with diabetes consume alcohol. Given extant evidence that moderate alcohol intake may have cardiovascular benefits for patients with diabetes, examination of the trade-offs between cardiovascular benefits vs. potential risk of lower adherence with self-care behaviours deserves study.