Improving Methods of Identifying Anaphylaxis for Medical Product Safety Surveillance Using Natural Language Processing and Machine Learning.

We sought to determine whether machine learning and natural language processing (NLP) applied to electronic medical records could improve performance of automated health-care claims-based algorithms to identify anaphylaxis events using data on 516 patients with outpatient, emergency department, or inpatient anaphylaxis diagnosis codes during 2015-2019 in 2 integrated health-care institutions in the Northwest United States. We used one site's manually reviewed gold-standard outcomes data for model development and the other's for external validation based on cross-validated area under the receiver operating characteristic curve (AUC), positive predictive value (PPV), and sensitivity. In the development site 154 (64%) of 239 potential events met adjudication criteria for anaphylaxis compared with 180 (65%) of 277 in the validation site. Logistic regression models using only structured claims data achieved a cross-validated AUC of 0.58 (95% CI: 0.54, 0.63). Machine learning improved cross-validated AUC to 0.62 (0.58, 0.66); incorporating NLP-derived covariates further increased cross-validated AUCs to 0.70 (0.66, 0.75) in development and 0.67 (0.63, 0.71) in external validation data. A classification threshold with cross-validated PPV of 79% and cross-validated sensitivity of 66% in development data had cross-validated PPV of 78% and cross-validated sensitivity of 56% in external data. Machine learning and NLP-derived data improved identification of validated anaphylaxis events.

Disparities in the Use of Internet and Telephone Medication Refills among Linguistically Diverse Patients.

BACKGROUND: Health systems are increasingly implementing remote telephone and Internet refill systems to enhance patient access to medication refills. Remote refill systems may provide an effective approach for improving medication non-adherence, but more research is needed among patients with limited English proficiency with poor access to remote refill systems. OBJECTIVE: To compare the use of remote medication refill systems among limited-English-proficiency (LEP) and English-proficient (EP) patients with chronic conditions. METHODS: Cross-sectional survey in six languages/dialects (English, Cantonese, Mandarin, Korean, Vietnamese, and Spanish) of 509 adults with diabetes, hypertension, or hyperlipidemia. Primary study outcomes were self-reported use of 1) Internet refills, 2) telephone refills, and 3) any remote refill system. LEP was measured by patient self-identification of a primary language other than English and a claims record of use of an interpreter. Other measures were age, gender, education, years in the U.S., insurance, health status, chronic conditions, and number of prescribed medications. Analyses included multivariable logistic regression weighted for survey non-response. RESULTS: Overall, 33.1 % of patients refilled their medications by telephone and 31.6 % by Internet. Among LEP patients (n = 328), 31.5 % refilled by telephone and 21.2 % by Internet, compared with 36.7 % by telephone and 52.7 % by Internet among EP patients (n = 181). Internet refill by language groups were as follows: English (52.7 %), Cantonese (34.9 %), Mandarin (17.4 %), Korean (16.7 %), Vietnamese (24.4 %), and Spanish (12.6 %). Compared to EP patients, LEP patients had lower use of any remote refill system (adjusted odds ratio [AOR] 0.18; p < 0.001), CONCLUSIONS: LEP patients are significantly less likely than EP patients to use any remote medication refill system. Increased reliance on current systems for remote medication refills may increase disparities in health outcomes affecting LEP patients with poor access to telephone and Internet medication refills.

Relationship between cardiovascular risk and lipid testing in one health care system: a retrospective cohort study.

BACKGROUND: The US Preventive Services Taskforce (USPSTF) recommends routine lipid screening beginning age 35 for men [1]. For women age 20 and older, as well as men age 20-34, screening is recommended if cardiovascular risk factors are present. Prior research has focused on underutilization but not overuse of lipid testing. The objective is to document over- and under-use of lipid testing in an insured population of persons at low, moderate and high cardiovascular disease (CVD) risk for persons not already on statins. METHODS: The study is a retrospective cohort study that included all adults without prior CVD who were continuously enrolled in a large integrated healthcare system from 2005 to 2010. Measures included lipid test frequency extracted from administrative data and Framingham cardiovascular risk equations applied using electronic medical record data. Five year lipid testing patterns were examined by age, sex and CVD risk. Generalized linear models were used to estimate the relative risk for over testing associated with patient characteristics. RESULTS: Among males and females for whom testing is not recommended, 35.8 % and 61.5 % received at least one lipid test in the prior 5 years and 8.4 % and 24.4 % had two or more. Over-testing was associated with age, race, comorbidity, primary care use and neighborhood income. Among individuals at moderate and high-risk (not already treated with statins) and for whom screening is recommended, between 21.4 % and 25.1 % of individuals received no screening in the prior 5 years. CONCLUSIONS: Based on USPSTF lipid screening recommendations, this study documents substantial over-testing among individuals with low CVD risk and under-testing among individuals with moderate to high-risk not already on statins. Opportunity exists to better focus lipid screening efforts appropriate to CVD risk.

Obstructive sleep apnea and risk of motor vehicle accident.

OBJECTIVE: To evaluate the association between obstructive sleep apnea (OSA) and risk of motor vehicle accident (MVA). METHODS: We conducted a cohort study at Kaiser Permanente Washington using electronic health plan data and linked Washington State Department of Transportation MVA records. We included persons 18-79 years of age during 2005-2014. OSA was ascertained via diagnosis codes. The primary outcome, first MVA during cohort follow-up, was ascertained from state MVA records. Risk factors for MVAs, including medical conditions and medication use, were ascertained from health plan data. Multivariable Cox proportional hazards models were used to estimate the adjusted hazard ratio (HR) and 95% confidence interval (CI) for the association between OSA and study outcomes. RESULTS: Among the 879,547 eligible persons, the unadjusted rate of MVA in those with and without OSA was 238 and 229 per 10,000 person-years, respectively. A diagnosis of OSA was associated with a 17% increased risk of MVA (adjusted HR = 1.17; 95% CI: 1.13 to 1.20). CONCLUSION: In this large population-based study, a diagnosis of OSA was associated with a modestly increased risk of MVA.

Medication Related Self- efficacy among Linguistically Diverse Patients with Chronic Illnesses.

This study examines medication-related self-efficacy in a linguistically diverse group of patients with diabetes, hypertension, and elevated cholesterol. A telephone survey of 509 adults conducted in six languages (English, Spanish, Korean, Vietnamese, Mandarin, and Cantonese) was analyzed. Self-efficacy was assessed with the overall Medication Understanding and Use Self-Efficacy (MUSE) score and its two subscale scores on taking medication and learning about medications. Compared with English proficient (EP) patients, patients with limited English proficiency (LEP) had a lower mean learning self-efficacy subscale score (LEP: 14.5, EP: 15.4; p<.001) and no difference in the mean taking self-efficacy subscale score (LEP: 14.4, EP: 14.6; p=.40). Receiving verbal medication information (VMI) from providers modified the relationship between LEP status and learning self-efficacy. In conclusion, among patients with chronic illnesses, LEP patients had lower medication-related self-efficacy scores than EP patients, which may put them at greater risk for medication taking errors and lower adherence.

Clinician identification of youth abusing over-the-counter products for weight control in a large U.S. integrated health system.

BACKGROUND: Abuse of over-the-counter (OTC) products, such as diet pills and laxatives, for weight control by adolescents is well-documented and can precipitate serious medical conditions. Yet only a small percentage of youth with disordered weight control behaviors receive treatment. The objective of this study was to examine how often clinicians communicate with youth with symptoms consistent with abuse of OTC products for weight control about possible use of these products. We used electronic medical records and administrative claims for services for 53,229 12 to 17 year old patients receiving care from an integrated health system in the U.S. Northwest from August 2007 to December 2010. We examined electronic text of clinical notes to identify encounters in which the clinician noted one of 10 metabolic conditions potentially associated with abuse of OTC products (diet pills, laxatives, diuretics, ipecac, orlistat, and alli®) for weight control and then assessed whether clinicians noted communication with adolescent patients about possible use of OTC products for weight control. RESULTS: We identified 130 (0.2% of sample) patients with clinical notes indicating one or more of the metabolic conditions. In clinical notes for only four (3.1%) of these patients did clinicians document suspicion or communication about possible abuse of the OTC products. All four had a previous eating disorder diagnosis. In the 12 months subsequent to the clinical encounter in which a metabolic disturbance was identified, medical notes for only three (2.3%) of the 130 patients indicated clinician suspicion or communication about possible abuse of these products or an eating disorder. CONCLUSIONS: Clinicians are missing a critical window of opportunity to query adolescents when presenting with suspicious metabolic disturbances about possible abuse of OTC products for weight control. Clinicians may need more training to detect OTC product abuse, and electronic medical records should prompt more thorough enquiry.