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

Juan Carlos Ivancevich Wednesday, 14 February 2018 11:49
Harsheen KaurSunghwan SohnChung-Il WiEuijung RyuMiguel A. ParkKay BachmanHirohito KitaIvana CroghanJose A. Castro-RodriguezGretchen A. VogeHongfang Liu, Young J. Juhn

Abstract

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.

Download PDF

Predictors of inappropriate and excessive use of reliever medications in asthma: a 16-year population-based study

Juan Carlos Ivancevich Tuesday, 13 February 2018 14:29
Hamid Tavakoli, J. Mark FitzGeraldLarry D. Lynd and Mohsen Sadatsafavi

Abstract

Background

Understanding factors associated with the inappropriate or excessive use of short-acting beta agonists (SABA) can help develop better policies.

Methods

We used British Columbian (BC)‘s administrative health data (1997–2014) to create a retrospective cohort of asthma patients aged between 14 and 55 years. The primary and secondary outcomes were, respectively, inappropriate and excessive use of SABA based on a previously validated definition. Exposures were categorised into groups comprising socio-demographic variables, indicators of type and quality of asthma care, and burden of comorbid conditions.

Results

343,520 individuals (56.3% female, average age 30.5) satisfied the asthma case definition, contributing 2.6 million person-years. 7.3% of person-years were categorised as inappropriate SABA use and 0.9% as excessive use. Several factors were associated with lower likelihood of inappropriate use, including female sex, higher socio-economic status, higher continuity of care, having received pulmonary function test in the previous year, visited a specialist in the previous year, and the use of inhaled corticosteroids in the previous year. An asthma-related outpatient visit to a general practitioner in the previous year was associated with a higher likelihood of inappropriate SABA use. Similar associations were found for excessive SABA use with the exception that visit to respirologist and the use of systemic corticosteroids were associated with increased likelihood of excessive use.

Conclusions

Despite proven safety issues, inappropriate SABA use is still prevalent. Several factors belonging to patients’ characteristics and type/quality of care were associated with inappropriate use of SABAs and can be used to risk-stratify patients for targeted attempts to reduce this preventable cause of adverse asthma outcomes.

Download PDF

Nerve ablation after bronchial thermoplasty and sustained improvement in severe asthma

Juan Carlos Ivancevich Saturday, 10 February 2018 03:19
N. FacciolongoA. DiStefanoV. PietriniC. GaleoneF. BellanovaF. MenzellaN. ScichiloneR. PiroG. L. BajocchiB. BalbiL. AgostiniP. P. SalsiD. Formisano and M. Lusuardi
 
BMC Pulmonary Medicine BMC series – open, inclusive and trusted 201818:29

https://doi.org/10.1186/s12890-017-0554-8

Abstract

Background

Bronchial thermoplasty (BT) is a non-pharmacological intervention for severe asthma whose mechanism of action is not completely explained by a reduction of airway smooth muscle (ASM). In this study we analyzed the effect of BT on nerve fibers and inflammatory components in the bronchial mucosa at 1 year.

Methods

Endobronchial biopsies were obtained from 12 subjects (mean age 47 ± 11.3 years, 50% male) with severe asthma. Biopsies were performed at baseline (T0) and after 1 (T1), 2 (T2) and 12 (T12) months post-BT, and studied with immunocytochemistry and microscopy methods. Clinical data including Asthma Quality of Life Questionnaire (AQLQ) and Asthma Control Questionnaire (ACQ) scores, exacerbations, hospitalizations, oral corticosteroids use were also collected at the same time points.

Results

A statistically significant reduction at T1, T2 and T12 of nerve fibers was observed in the submucosa and in ASM compared to T0. Among inflammatory cells, only CD68 showed significant changes at all time points. Improvement of all clinical outcomes was documented and persisted at the end of follow up.

Conclusions

A reduction of nerve fibers in epithelium and in ASM occurs earlier and persists at one year after BT. We propose that nerve ablation may contribute to mediate the beneficial effects of BT in severe asthma.

Download PDF 

 

Test-retest repeatability of child’s respiratory symptoms and perceived indoor air quality – comparing self- and parent-administered questionnaires

Juan Carlos Ivancevich Sunday, 11 February 2018 14:04
 
Jussi Lampi, Sari Ung-LankiPäivi Santalahti and Juha Pekkanen
 

Abstract

Background

Questionnaires can be used to assess perceived indoor air quality and symptoms in schools. Questionnaires for primary school aged children have traditionally been parent-administered, but self-administered questionnaires would be easier to administer and may yield as good, if not better, information. Our aim was to compare the repeatability of self- and parent-administered indoor air questionnaires designed for primary school aged pupils.

Methods

Indoor air questionnaire with questions on child’s symptoms and perceived indoor air quality in schools was sent to parents of pupils aged 7–12 years in two schools and again after two weeks. Slightly modified version of the questionnaire was administered to pupils aged 9–12 years in another two schools and repeated after a week. 351 (52%) parents and 319 pupils (86%) answered both the first and the second questionnaire. Test-retest repeatability was assessed with intra-class correlation (ICC) and Cohen’s kappa coefficients (k).

Results

Test-retest repeatability was generally between 0.4–0.7 (ICC; k) in both self- and parent-administered questionnaire. In majority of the questions on symptoms and perceived indoor air quality test-retest repeatability was at the same level or slightly better in self-administered compared to parent-administered questionnaire. Agreement of self- and parent administered questionnaires was generally < 0.4 (ICC; k) in reported symptoms and 0.4–0.6 (ICC; k) in perceived indoor air quality.

Conclusions

Children aged 9–12 years can give as, or even more, repeatable information about their respiratory symptoms and perceived indoor air quality than their parents. Therefore, it may be possible to use self-administered questionnaires in future studies also with children.

Download PDF

 

Guidelines for the diagnosis and management of asthma: a look at the key differences between BTS/SIGN and NICE

Super User Thursday, 08 February 2018 11:51
 
Research and Guideline updates
 
Guidelines for the diagnosis and management of asthma: a look at the key differences between BTS/SIGN and NICE
 FREE
 
John White1, James Y Paton2, Robert Niven3, Hilary Pinnock4 on behalf of the British Thoracic Society

The British Thoracic Society (BTS) first produced a guideline on asthma and its management in 1990. The first collaborative guideline with the Scottish Intercollegiate Guideline Network (SIGN) using evidence-based medicine methodology was published in 2003.1 It has since become a mainstay of asthma management across the UK and beyond with updates published regularly every 18–24 months. The latest BTS/SIGN guideline for the management of asthma was published in 2016.2 Both BTS and SIGN are committed to continuing updates with the next update planned for publication in 2019.

Following publication of National Institute for Health and Care Excellence (NICE) guidelines for diagnosis and monitoring, and for management of chronic asthma,3–5 there are now two if not three national guidelines, for England at least, with some (apparently) striking differences. This statement considers the similarities and differences to assist clinical colleagues in the care of people with asthma.

The evidence base considered by the BTS/SIGN and NICE guideline development groups is broadly the same for each guideline, but the methodology used to produce recommendations is significantly different:

  • SIGN methodology is a multidisciplinary clinically led process which employs robust critical appraisal of the literature, coupled with consideration of pragmatic studies to ensure that guidelines provide clinically relevant recommendations.

  • NICE methodology overlays critical appraisal of the literature with health economic modelling, with interpretation supported by advice from a multidisciplinary guideline development group.

These different processes have resulted in some discrepancies in recommendations made by BTS/SIGN and NICE. This article seeks to provide some context to these differences in key areas:

  • Diagnosis

  • Pharmacological management:

    • Treatment at diagnosis.

    • The introduction of leukotriene receptor antagonists (LTRA) after low-dose inhaled corticosteroids (ICS).

    • Maintenance and reliever therapy (MART).

    • Treatment beyond combined inhaler therapy.

    • Some other issues in managing asthma in children.

The BTS/SIGN guideline also provides recommendations for important aspects of asthma management that are not addressed within NICE guidelines. These include guidance on inhaler devices, the management of acute asthma attacks in both adults and children, the management of difficult asthma, guidance on asthma in adolescents, in pregnant women and on occupational factors.

FULL TEXT FREE

PDF

Interasma on Twitter

Interasma RT @Aller_MD: Top story: Kaléo on Twitter: "Some bullies use words, others use food. Togeth… https://t.co/eOHOsmB43X, see more https://t.…
9hreplyretweetfavorite
Interasma RT @Aller_MD: “Epinephrine Nasal Spray for #Anaphylaxis Shows Promise as Potential Alternative to Auto-Injector” https://t.co/qVsbyMfDuL ht…
9hreplyretweetfavorite
Interasma RT @Aller_MD: “Stress-related disorders were significantly associated with risk of subsequent autoimmune disease” https://t.co/9YWUsJgHWp h…
9hreplyretweetfavorite
Interasma RT @Aller_MD: “A Teledermatology Scale-Up Framework and Roadmap for Sustainable Scaling: Evidence-Based Development” https://t.co/nqPSJpsyg
9hreplyretweetfavorite
Interasma RT @Aller_MD: “Tobacco Product Use Among Youths With and Without Lifetime #Asthmahttps://t.co/wnj8AyUM7Z https://t.co/ydFozighl5
9hreplyretweetfavorite

Editor: Juan C. Ivancevich, MD

Copyright © Interasma 2003-2017  •  Terms of Use  •  Privacy Policy  •  Contact Us  •  Sitemap

Powered by FREI SA

InterAsma