Juhn, Young J.

Abstract Objective To assess clinical documentation variations across health care institutions using different electronic medical record systems and investigate how they affect natural language processing (NLP) system portability. Materials and Methods Birth cohorts from Mayo Clinic and Sanford Children’s Hospital (SCH) were used in this study (n = 298 for each). Documentation variations regarding asthma between the 2 cohorts were examined in various aspects: (1) overall corpus at the word level (ie, lexical variation), (2) topics and asthma-related concepts (ie, semantic variation), and (3) clinical note types (ie, process variation). We compared those statistics and explored NLP system portability for asthma ascertainment in 2 stages: prototype and refinement. Results There exist notable lexical variations (word-level similarity = 0.669) and process variations (differences in major note types containing asthma-related concepts). However, semantic-level corpora were relatively homogeneous (topic similarity = 0.944, asthma-related concept similarity = 0.971). The NLP system for asthma ascertainment had anF-score of 0.937 at Mayo, and produced 0.813 (prototype) and 0.908 (refinement) when applied at SCH. Discussion The criteria for asthma ascertainment are largely dependent on asthma-related concepts. Therefore, we believe that semantic similarity is important to estimate NLP system portability. As the Mayo Clinic and SCH corpora were relatively homogeneous at a semantic level, the NLP system, developed at Mayo Clinic, was imported to SCH successfully with proper adjustments to deal with the intrinsic corpus heterogeneity.

Click here to view the Original Article by Dr. J. Helby et al.

Abstract Rationale Difficulty of asthma ascertainment and its associated methodologic heterogeneity have created significant barriers to asthma care and research. Objectives We evaluated the validity of an existing natural language processing (NLP) algorithm for asthma criteria to enable an automated chart review using electronic medical records (EMRs). Methods The study was designed as a retrospective birth cohort study using a random sample of 500 subjects from the 1997–2007 Mayo Birth Cohort who were born at Mayo Clinic and enrolled in primary pediatric care at Mayo Clinic Rochester. Performance of NLP-based asthma ascertainment using predetermined asthma criteria was assessed by determining both criterion validity (chart review of EMRs by abstractor as a gold standard) and construct validity (association with known risk factors for asthma, such as allergic rhinitis). Measurements and Main Results After excluding three subjects whose respiratory symptoms could be attributed to other conditions (e.g., tracheomalacia), among the remaining eligible 497 subjects, 51% were male, 77% white persons, and the median age at last follow-up date was 11.5 years. The asthma prevalence was 31% in the study cohort. Sensitivity, specificity, positive predictive value, and negative predictive value for NLP algorithm in predicting asthma status were 97%, 95%, 90%, and 98%, respectively. The risk factors for asthma (e.g., allergic rhinitis) that were identified either by NLP or the abstractor were the same. Conclusions Asthma ascertainment through NLP should be considered in the era of EMRs because it can enable large-scale clinical studies in a more time-efficient manner and improve the recognition and care of childhood asthma in practice.

ABSTRACTObjectives:Celiac disease (CD) is a common immune‐mediated disorder that affects up to 1% of the general population. Recent reports suggest that the incidence of CD has reached a plateau in many countries. We aim to study the incidence and altered presentation of childhood CD in a well‐defined population.Methods:Using the Rochester Epidemiology Project, we retrospectively reviewed Mayo Clinic and Olmsted Medical Center medical records from January 1994 to December 2014. We identified all CD cases of patients ages 18 years or younger at the time of diagnosis. Incidence rates were calculated by adjusting for age, sex, and calendar year and standardizing to the 2010 US white population.Results:We identified 100 patients with CD. Incidence of CD has increased from 8.1 per 100,000 person‐years (2000–2002) to 21.5 per 100,000 person‐years (2011–2014). There was an increase in CD prevalence in children from 2010 (0.10%) to 2014 (0.17%). Thirty‐four patients (34%) presented with classical CD symptoms, 43 (43%) had nonclassical CD, and 23 (23%) were diagnosed by screening asymptomatic high‐risk patients. Thirty‐six patients (36%) had complete villous atrophy, 51 (51%) had partial atrophy, and 11 (11%) had increased intraepithelial lymphocytes. Two patients were diagnosed without biopsy. Most patients (67%) had a normal body mass index, 17% were overweight/obese, and only 9% were underweight.Conclusions:Both incidence and prevalence of CD have continued to increase in children during the past 15 years in Olmsted County, Minnesota. Clinical and pathologic presentations of CD are changing over time (more nonclassical and asymptomatic cases are emerging).

AbstractAsthma is independently associated with HLA‐DR3 and increased risks of pneumococcal diseases. We aimed to determine whether HLA‐DR polymorphism (HLA‐DRB1*03), sensitization to house dust mite (HDM), or their interaction affects humoral immune responses to pneumococcal polysaccharide and protein antigens of intact pneumococci. Induction of serum titers of anti‐pneumococcal polysaccharide and anti‐surface protein IgM and IgG in response to immunization with intact pneumococci (Pn) serotype 14 was determined using humanized HLA‐DR3 and DR2 transgenic mice. Transgenic mice were sensitized by injecting HDM and challenged with intranasal HDM. Mice were subsequently immunized with heat‐killed Pn14 at day 24. Serum titers of anti‐phosphorylcholine (PC) IgM and IgG, anti‐pneumococcal polysaccharide, capsular type 14 (PPS14) IgM and IgG, and anti‐pneumococcal surface protein A (PspA) IgG were measured. We included a total of 44 mice (22 DR3 and 22 DR2 mice) and half of mice in each group were sensitized with HDM (i.e. 22 HDM‐sensitized and 22 control mice). HDM‐sensitized mice, irrespective of HLA‐DR polymorphism, had significantly lower humoral immune responses. HLA‐DR3 mice, irrespective of HDM sensitization, elicited a significantly lower anti‐PC IgG response. In contrast, the anti‐PspA IgG response was higher in DR3 relative to DR2 mice. The effect of HDM sensitization on lowering humoral immune responses to Pn14 was observed in DR3 mice regardless of the nature of the antigen, whereas such decreases were observed only for the anti‐PPS14 IgG and anti‐PC IgM responses in DR2 mice. HDM sensitization lowered humoral immune responses to intact pneumococcus and this effect was significantly modified by the HLA‐DR polymorphism.

Objectives Socioeconomic status (SES) is a well-established risk factor for many health outcomes. Recently, we developed an SES measure based on 4 housing-related characteristics (termed HOUSES) and demonstrated its ability to assess health disparities. In this study, we aimed to evaluate whether fewer housing-related characteristics could be used to provide a similar representation of SES. Study setting and participants We performed a cross-sectional study using parents/guardians of children aged 1–17 years from 2 US Midwestern counties (n=728 in Olmsted County, Minnesota, and n=701 in Jackson County, Missouri). Primary and secondary outcome measures For each participant, housing-related characteristics used in the formulation of HOUSES (assessed housing value, square footage, number of bedrooms and number of bathrooms) were obtained from the local government assessor's offices, and additional SES measures and health outcomes with known associations to SES (obesity, low birth weight and smoking exposure) were collected from a telephone survey. Housing characteristics with the greatest contribution for predicting the health outcomes were added to formulate a modified HOUSES index. Results Among the 4 housing characteristics used in the original HOUSES, the strongest contributions for predicting health outcomes were observed from assessed housing value and square footage (combined contribution ranged between 89% and 96%). Based on this observation, these 2 were used to calculate a modified HOUSES index. Correlation between modified HOUSES and other SES measures was comparable to the original HOUSES for both locations. Consistent with the original HOUSES formula, the strongest association with modified HOUSES was observed with smoking exposure (OR=0.24 with 95% CI 0.11 to 0.49 for comparing participants in highest HOUSES vs lowest group; overall p<0.001). Conclusions The modified HOUSES requires only 2 readily available housing characteristics thereby improving the feasibility of using this index as a proxy for SES in multiple communities, especially in the US Midwestern region.

Background: Subclinical hypothyroidism (SCH) has been associated with increased risk of adverse pregnancy outcomes in some, but not all, studies. Uncertainty remains regarding the impact of levothyroxine (LT4) therapy on improving health outcomes in pregnant women with SCH. The objective of this study was to assess the potential benefits of LT4 therapy in pregnant women with SCH. Methods: The medical records were reviewed of pregnant women with SCH, defined as an elevated serum thyrotropin (TSH) of >2.5 mIU/L for the 1st trimester or >3 mIU/L for the 2nd and 3rd trimesters, but ≤10 mIU/L. Pregnant women were divided into two groups depending on whether they received LT4 (group A) or not (group B). Pregnancy loss and other pre-specified adverse outcomes were evaluated during follow-up. Results: There were 82 women in group A and 284 in group B. Group A had a higher body mass index ( p = 0.04) and a higher serum TSH level ( p < 0.0001) compared with group B. Group A had fewer pregnancies lost ( n = 5 [6.1%] vs. n = 25 [8.8%]; p = 0.12), low birth weight (LBW) offspring (1.3% vs. 10%; p < 0.001), and no neonates with a five-minute Apgar score ≤7 (0% vs. 7%; p < 0.001) compared with group B. Other pregnancy-related adverse outcomes were similar between the two groups. Inferences remained unchanged after considering different models to adjust for potential predictors of outcome. Conclusions: LT4 therapy is associated with a decreased risk of LBW and a low Apgar score among women with SCH. This association awaits confirmation in randomized trials before the widespread use of LT4 therapy in pregnant women with SCH.

Background Socioeconomic status (SES) is an important predictor for outcomes of chronic diseases. However, it is often unavailable in clinical data. We sought to determine whether an individual housing-based SES index termed HOUSES can influence the likelihood of multiple chronic conditions (MCC) and hospitalisation in a community population. Methods Participants were residents of Olmsted County, Minnesota, aged >18 years, who were enrolled in Mayo Clinic Biobank on 31 December 2010, with follow-up until 31 December 2011. Primary outcome was all-cause hospitalisation over 1 calendar-year. Secondary outcome was MCC determined through a Minnesota Medical Tiering score. A logistic regression model was used to assess the association of HOUSES with the Minnesota tiering score. With adjustment for age, sex and MCC, the association of HOUSES with hospitalisation risk was tested using the Cox proportional hazards model. Results Eligible patients totalled 6402 persons (median age, 57 years; 25th–75th quartiles, 45–68 years). The lowest quartile of HOUSES was associated with a higher Minnesota tiering score after adjustment for age and sex (OR (95% CI) 2.4 (2.0 to 3.1)) when compared with the highest HOUSES quartile. Patients in the lowest HOUSES quartile had higher risk of all-cause hospitalisation (age, sex, MCC-adjusted HR (95% CI) 1.53 (1.18 to 1.98)) compared with those in the highest quartile. Conclusions Low SES, as assessed by HOUSES, was associated with increased risk of hospitalisation and greater MCC health burden. HOUSES may be a clinically useful surrogate for SES to assess risk stratification for patient care and clinical research.