Application of a Natural Language Processing Algorithm to Asthma Ascertainment. An Automated Chart Review

Epidemiology of Asthma in Children and Adults

Asthma is a globally significant non-communicable disease with major public health consequences for both children and adults, including high morbidity, and mortality in severe cases. We have summarized the evidence on asthma trends, environmental determinants, and long-term impacts while comparing these epidemiological features across childhood asthma and adult asthma. While asthma incidence and prevalence are higher in children, morbidity, and mortality are higher in adults. Childhood asthma is more common in boys while adult asthma is more common in women, and the reversal of this sex difference in prevalence occurs around puberty suggesting sex hormones may play a role in the etiology of asthma. The global epidemic of asthma that has been observed in both children and adults is still continuing, especially in low to middle income countries, although it has subsided in some developed countries. As a heterogeneous disease, distinct asthma phenotypes, and endotypes need to be adequately characterized to develop more accurate and meaningful definitions for use in research and clinical settings. This may be facilitated by new clustering techniques such as latent class analysis, and computational phenotyping methods are being developed to retrieve information from electronic health records using natural language processing (NLP) algorithms to assist in the early diagnosis of asthma. While some important environmental determinants that trigger asthma are well-established, more work is needed to define the role of environmental exposures in the development of asthma in both children and adults. There is increasing evidence that investigation into possible gene-by-environment and environment-by-environment interactions may help to better uncover the determinants of asthma. Therefore, there is an urgent need to further investigate the interrelationship between environmental and genetic determinants to identify high risk groups and key modifiable exposures. For children, asthma may impair airway development and reduce maximally attained lung function, and these lung function deficits may persist into adulthood without additional progressive loss. Adult asthma may accelerate lung function decline and increase the risk of fixed airflow obstruction, with the effect of early onset asthma being greater than late onset asthma. Therefore, in managing asthma, our focus going forward should be firmly on improving not only short-term symptoms, but also the long-term respiratory and other health outcomes.

Association between an individual housing-based socioeconomic index and inconsistent self-reporting of health conditions: a prospective cohort study in the Mayo Clinic Biobank

OBJECTIVE

Using surveys to collect self-reported information on health and disease is commonly used in clinical practice and epidemiological research. However, the inconsistency of self-reported information collected longitudinally in repeated surveys is not well investigated. We aimed to investigate whether a socioeconomic status based on current housing characteristics, HOUsing-based SocioEconomic Status (HOUSES) index linking current address information to real estate property data, is associated with inconsistent self-reporting.

STUDY SETTING AND PARTICIPANTS

We performed a prospective cohort study using the Mayo Clinic Biobank (MCB) participants who resided in Olmsted County, Minnesota, USA, at the time of enrolment between 2009 and 2013, and were invited for a 4-year follow-up survey (n=11 717).

PRIMARY AND SECONDARY OUTCOME MEASURES

Using repeated survey data collected at the baseline and 4 years later, the primary outcome was the inconsistency in survey results when reporting prevalent diseases, defined by reporting to have 'ever' been diagnosed with a given disease in the baseline survey but reported 'never' in the follow-up survey. Secondary outcome was the response rate for the 4-year follow-up survey.

RESULTS

Among the MCB participants invited for the 4-year follow-up survey, 8508/11 717 (73%) responded to the survey. Forty-three per cent had at least one inconsistent self-reported disease. Lower HOUSES was associated with higher inconsistency rates, and the association remained significant after pertinent characteristics such as age and perceived general health (OR=1.46; 95% CI 1.17 to 1.84 for the lowest compared with the highest HOUSES decile). HOUSES was also associated with lower response rate for the follow-up survey (56% vs 77% for the lowest vs the highest HOUSES decile).

CONCLUSION

This study demonstrates the importance of using the HOUSES index that reflects current SES when using self-reporting through repeated surveys, as the HOUSES index at baseline survey was inversely associated with inconsistent self-report and the response rate for the follow-up survey.

Automated chart review utilizing natural language processing algorithm for asthma predictive index

BACKGROUND

Thus far, no algorithms have been developed to automatically extract patients who meet Asthma Predictive Index (API) criteria from the Electronic health records (EHR) yet. Our objective is to develop and validate a natural language processing (NLP) algorithm to identify patients that meet API criteria.

METHODS

This is a cross-sectional study nested in a birth cohort study in Olmsted County, MN. Asthma status ascertained by manual chart review based on API criteria served as gold standard. NLP-API was developed on a training cohort (n = 87) and validated on a test cohort (n = 427). Criterion validity was measured by sensitivity, specificity, positive predictive value and negative predictive value of the NLP algorithm against manual chart review for asthma status. Construct validity was determined by associations of asthma status defined by NLP-API with known risk factors for asthma.

RESULTS

Among the eligible 427 subjects of the test cohort, 48% were males and 74% were White. Median age was 5.3 years (interquartile range 3.6-6.8). 35 (8%) had a history of asthma by NLP-API vs. 36 (8%) by abstractor with 31 by both approaches. NLP-API predicted asthma status with sensitivity 86%, specificity 98%, positive predictive value 88%, negative predictive value 98%. Asthma status by both NLP and manual chart review were significantly associated with the known asthma risk factors, such as history of allergic rhinitis, eczema, family history of asthma, and maternal history of smoking during pregnancy (p value < 0.05). Maternal smoking [odds ratio: 4.4, 95% confidence interval 1.8-10.7] was associated with asthma status determined by NLP-API and abstractor, and the effect sizes were similar between the reviews with 4.4 vs 4.2 respectively.

CONCLUSION

NLP-API was able to ascertain asthma status in children mining from EHR and has a potential to enhance asthma care and research through population management and large-scale studies when identifying children who meet API criteria.

Classification of Pediatric Asthma: From Phenotype Discovery to Clinical Practice

Advances in big data analytics have created an opportunity for a step change in unraveling mechanisms underlying the development of complex diseases such as asthma, providing valuable insights that drive better diagnostic decision-making in clinical practice, and opening up paths to individualized treatment plans. However, translating findings from data-driven analyses into meaningful insights and actionable solutions requires approaches and tools which move beyond mining and patterning longitudinal data. The purpose of this review is to summarize recent advances in phenotyping of asthma, to discuss key hurdles currently hampering the translation of phenotypic variation into mechanistic insights and clinical setting, and to suggest potential solutions that may address these limitations and accelerate moving discoveries into practice. In order to advance the field of phenotypic discovery, greater focus should be placed on investigating the extent of within-phenotype variation. We advocate a more cautious modeling approach by "supervising" the findings to delineate more precisely the characteristics of the individual trajectories assigned to each phenotype. Furthermore, it is important to employ different methods within a study to compare the stability of derived phenotypes, and to assess the immutability of individual assignments to phenotypes. If we are to make a step change toward precision (stratified or personalized) medicine and capitalize on the available big data assets, we have to develop genuine cross-disciplinary collaborations, wherein data scientists who turn data into information using algorithms and machine learning, team up with medical professionals who provide deep insights on specific subjects from a clinical perspective.

Clinical information extraction applications: A literature review

BACKGROUND

With the rapid adoption of electronic health records (EHRs), it is desirable to harvest information and knowledge from EHRs to support automated systems at the point of care and to enable secondary use of EHRs for clinical and translational research. One critical component used to facilitate the secondary use of EHR data is the information extraction (IE) task, which automatically extracts and encodes clinical information from text.

OBJECTIVES

In this literature review, we present a review of recent published research on clinical information extraction (IE) applications.

METHODS

A literature search was conducted for articles published from January 2009 to September 2016 based on Ovid MEDLINE In-Process & Other Non-Indexed Citations, Ovid MEDLINE, Ovid EMBASE, Scopus, Web of Science, and ACM Digital Library.

RESULTS

A total of 1917 publications were identified for title and abstract screening. Of these publications, 263 articles were selected and discussed in this review in terms of publication venues and data sources, clinical IE tools, methods, and applications in the areas of disease- and drug-related studies, and clinical workflow optimizations.

CONCLUSIONS

Clinical IE has been used for a wide range of applications, however, there is a considerable gap between clinical studies using EHR data and studies using clinical IE. This study enabled us to gain a more concrete understanding of the gap and to provide potential solutions to bridge this gap.

Clinical documentation variations and NLP system portability: a case study in asthma birth cohorts across institutions

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.

Comparing effectiveness and outcomes in asthma and cystic fibrosis

As technology yields new treatments, pediatric pulmonologists need determine how best to use them and how to decide which ones are best for any specific group or individual patient. Physicians have always customized therapies based upon patient response, but the new concept of "Personalized (or precision) medicine" focuses attention to a greater degree on the individual needs of patients based on their genetic, biomarker, phenotypic, or psychosocial characteristics. The newly developed biologics for treatment of asthma and CFTR modulators for treatment of cystic fibrosis (CF) highlight this newer approach. As we have more treatments available, new approaches to testing efficacy and effectiveness of these new therapies is necessary in order to efficiently bring them to market and compare their benefits in real world practice. While comparative effectiveness can be tested in pragmatic clinic trials, the most common approaches make use of observational data such as administrative databases and patient registries but their use for this is fraught with pitfalls that may or may not be methodologically surmountable. Once new therapies have been shown to be efficacious and effective, it is important to be cognizant of methods for ensuring that all patients actually receive the treatments that will be best for them. Comparisons of the effectiveness of clinical practice in the form of benchmarking is helpful for this, and consideration of costs and cost-effectiveness is essential to judging the best treatment for patients in a real-world setting.