Correction to: Qualitative Assessment of Adult Patients’ Perception of Atopic Dermatitis Using Natural Language Processing Analysis in a Cross-Sectional Study

BACKGROUND The increasing adoption of electronic health records (EHRs) in clinical practice holds the promise of improving care and advancing research by serving as a rich source of data, but most EHRs allow clinicians to enter data in a text format without much structure. Natural language processing (NLP) may reduce reliance on manual abstraction of these text data by extracting clinical features directly from unstructured clinical digital text data and converting them into structured data. OBJECTIVE This study aimed to assess the performance of a commercially available NLP tool for extracting clinical features from free-text consult notes. METHODS We conducted a pilot, retrospective, cross-sectional study of the accuracy of NLP from dictated consult notes from our tuberculosis clinic with manual chart abstraction as the reference standard. Consult notes for 130 patients were extracted and processed using NLP. We extracted 15 clinical features from these consult notes and grouped them a priori into categories of simple, moderate, and complex for analysis. RESULTS For the primary outcome of overall accuracy, NLP performed best for features classified as simple, achieving an overall accuracy of 96% (95% CI 94.3-97.6). Performance was slightly lower for features of moderate clinical and linguistic complexity at 93% (95% CI 91.1-94.4), and lowest for complex features at 91% (95% CI 87.3-93.1). CONCLUSIONS The findings of this study support the use of NLP for extracting clinical features from dictated consult notes in the setting of a tuberculosis clinic. Further research is needed to fully establish the validity of NLP for this and other purposes.

Download Full-text

Sick Leave and Factors Influencing Sick Leave in Adult Patients with Atopic Dermatitis: A Cross-Sectional Study

Journal of Clinical Medicine ◽

10.3390/jcm4040535 ◽

2015 ◽

Vol 4 (4) ◽

pp. 535-547 ◽

Cited By ~ 5

Author(s):

Harmieke van Os-Medendorp ◽

Simone Appelman-Noordermeer ◽

Carla Bruijnzeel-Koomen ◽

Marjolein de Bruin-Weller

Keyword(s):

Atopic Dermatitis ◽

Sick Leave ◽

Cross Sectional Study ◽

Adult Patients ◽

Sectional Study ◽

Cross Sectional ◽

Factors Influencing

Download Full-text

Suicidal Ideation in Adult Patients with Atopic Dermatitis: A German Cross-sectional Study

Acta Dermato Venereologica ◽

10.2340/00015555-2741 ◽

2017 ◽

Vol 97 (10) ◽

pp. 1189-1195 ◽

Cited By ~ 18

Author(s):

J Dieris-Hirche ◽

U Gieler ◽

F Petrak ◽

W Milch ◽

B Wildt ◽

...

Keyword(s):

Atopic Dermatitis ◽

Suicidal Ideation ◽

Cross Sectional Study ◽

Adult Patients ◽

Sectional Study ◽

Cross Sectional

Download Full-text

Extracting Clinical Features From Dictated Ambulatory Consult Notes Using a Commercially Available Natural Language Processing Tool: Pilot, Retrospective, Cross-Sectional Validation Study

JMIR Medical Informatics ◽

10.2196/12575 ◽

2019 ◽

Vol 7 (4) ◽

pp. e12575

Author(s):

Jeremy Petch ◽

Jane Batt ◽

Joshua Murray ◽

Muhammad Mamdani

Keyword(s):

Natural Language Processing ◽

Natural Language ◽

Clinical Features ◽

Language Processing ◽

A Priori ◽

Cross Sectional Study ◽

Free Text ◽

Cross Sectional ◽

Text Data ◽

Complex Features

Background The increasing adoption of electronic health records (EHRs) in clinical practice holds the promise of improving care and advancing research by serving as a rich source of data, but most EHRs allow clinicians to enter data in a text format without much structure. Natural language processing (NLP) may reduce reliance on manual abstraction of these text data by extracting clinical features directly from unstructured clinical digital text data and converting them into structured data. Objective This study aimed to assess the performance of a commercially available NLP tool for extracting clinical features from free-text consult notes. Methods We conducted a pilot, retrospective, cross-sectional study of the accuracy of NLP from dictated consult notes from our tuberculosis clinic with manual chart abstraction as the reference standard. Consult notes for 130 patients were extracted and processed using NLP. We extracted 15 clinical features from these consult notes and grouped them a priori into categories of simple, moderate, and complex for analysis. Results For the primary outcome of overall accuracy, NLP performed best for features classified as simple, achieving an overall accuracy of 96% (95% CI 94.3-97.6). Performance was slightly lower for features of moderate clinical and linguistic complexity at 93% (95% CI 91.1-94.4), and lowest for complex features at 91% (95% CI 87.3-93.1). Conclusions The findings of this study support the use of NLP for extracting clinical features from dictated consult notes in the setting of a tuberculosis clinic. Further research is needed to fully establish the validity of NLP for this and other purposes.

Download Full-text

Auditory dysfunction in adult patients operated for cleft palate: a cross-sectional study

European Journal of Oral and Maxillofacial Surgery ◽

10.23736/s2532-3466.19.00162-0 ◽

2019 ◽

Vol 3 (2) ◽

Author(s):

Sneha Pendem ◽

Dhivya Arunachalam ◽

Poornima Ravi ◽

V. Krishnakumar Raja

Keyword(s):

Cleft Palate ◽

Cross Sectional Study ◽

Adult Patients ◽

Sectional Study ◽

Cross Sectional ◽

Auditory Dysfunction

Download Full-text

Cow’s milk exposure and atopic dermatitis after six months of age

Paediatrica Indonesiana ◽

10.14238/pi56.6.2016.325-9 ◽

2017 ◽

Vol 56 (6) ◽

pp. 325

Author(s):

Surya Jayanti Kadek ◽

Dewi Kumara Wati Ketut ◽

Karyana Putu Gede

Keyword(s):

Atopic Dermatitis ◽

Maternal Diet ◽

Multiple Logistic Regression Analysis ◽

Cross Sectional Study ◽

Cow’S Milk ◽

Milk Formula ◽

Sectional Study ◽

Cross Sectional ◽

Cow's Milk ◽

Study Population

Background About 60% of individuals with atopic dermatitis (AD) develop their first manifestation during infancy. Cow’s milk (CM) exposure is considered to be a risk factor for AD.Objective To evaluate for an association between cow’s milk exposure and atopic dermatitis in infants > 6 months of age. Methods This cross-sectional study consisted of subjects from a previous study and new subjects recruited in order to meet the minimum required number of subjects. Our study population comprised 120 infants, born between 1 February and 30 November, 2012 in Sanglah Hospital, Denpasar. Subjects were divided into CM and non-CM groups and analyzed for their risk of AD. Subjects were included to CM group if they were fed with cow’s milk/formula and included to non-CM group if they were breastfeed exclusively in the first six months of life. Other possible risk factors were assessed by multivariate analysis. Results One hundred twenty subjects were enrolled and analyzed (59 in the CM and 61 in the non-CM groups). The prevalence of AD was 30%. Multiple logistic regression analysis revealed a significant association between CM exposure and AD, with odds ratio (OR) 2.37 (95%CI 1.036 to 5.420; P=0.04). In addition, maternal diet including eggs and/or cow’s milk during the breastfeeding period was significantly associated with AD in infants (OR 3.18; 95%CI 1.073 to 9.427; P=0.04).Conclusion Cow’s milk exposure is significantly associated with atopic dermatitis in infants > six months of age.

Download Full-text