Rule-based and machine learning algorithms identify patients with systemic sclerosis accurately in the electronic health record

Jamian, Lia; Wheless, Lee; Crofford, Leslie J.; Barnado, April

doi:10.1186/s13075-019-2092-7

Cited by 37 publications

(37 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To accurately capture rare diagnoses, other more structured parts of the EHR may be useful such as laboratory results. A well-performing example is a simple classification algorithm for the identification of patients with systemic sclerosis in the EHR by using positive antinuclear antibody titer thresholds 26 .…”

Section: Discussionmentioning

confidence: 99%

Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks

et al. 2021

View full text Add to dashboard Cite

Standard reference terminology of diagnoses and risk factors is crucial for billing, epidemiological studies, and inter/intranational comparisons of diseases. The International Classification of Disease (ICD) is a standardized and widely used method, but the manual classification is an enormously time-consuming endeavor. Natural language processing together with machine learning allows automated structuring of diagnoses using ICD-10 codes, but the limited performance of machine learning models, the necessity of gigantic datasets, and poor reliability of terminal parts of these codes restricted clinical usability. We aimed to create a high performing pipeline for automated classification of reliable ICD-10 codes in the free medical text in cardiology. We focussed on frequently used and well-defined three- and four-digit ICD-10 codes that still have enough granularity to be clinically relevant such as atrial fibrillation (I48), acute myocardial infarction (I21), or dilated cardiomyopathy (I42.0). Our pipeline uses a deep neural network known as a Bidirectional Gated Recurrent Unit Neural Network and was trained and tested with 5548 discharge letters and validated in 5089 discharge and procedural letters. As in clinical practice discharge letters may be labeled with more than one code, we assessed the single- and multilabel performance of main diagnoses and cardiovascular risk factors. We investigated using both the entire body of text and only the summary paragraph, supplemented by age and sex. Given the privacy-sensitive information included in discharge letters, we added a de-identification step. The performance was high, with F1 scores of 0.76–0.99 for three-character and 0.87–0.98 for four-character ICD-10 codes, and was best when using complete discharge letters. Adding variables age/sex did not affect results. For model interpretability, word coefficients were provided and qualitative assessment of classification was manually performed. Because of its high performance, this pipeline can be useful to decrease the administrative burden of classifying discharge diagnoses and may serve as a scaffold for reimbursement and research applications.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Using EMR data, ML has been used to explore electronic health record-phenotyping [86][87][88], to conduct population-based analysis [89], and to evaluate patient experiences [90]. NLP has been used to analyze EMR with the aim to identify atopic dermatitis.…”

Section: Facilitating Large-scale Epidemiology Researchmentioning

confidence: 99%

“…ML methods can also be used to phenotype rare diseases, such as systemic sclerosis in EMR data. One study found that the highest performing ML methods to phenotype systemic sclerosis incorporated clinical data with billing codes [88]. Another study used NLP to develop the first population-based estimates of melanocytic lesions from EMR pathology reports [89].…”

Section: Facilitating Large-scale Epidemiology Researchmentioning

confidence: 99%

Machine Learning in Dermatology: Current Applications, Opportunities, and Limitations

Chan

Reddy

Myers

et al. 2020

Dermatol Ther (Heidelb)

165

108

View full text Add to dashboard Cite

Machine learning (ML) has the potential to improve the dermatologist's practice from diagnosis to personalized treatment. Recent advancements in access to large datasets (e.g., electronic medical records, image databases, omics), faster computing, and cheaper data storage have encouraged the development of ML algorithms with human-like intelligence in dermatology. This article is an overview of the basics of ML, current applications of ML, and potential limitations and considerations for further development of ML. We have identified five current areas of applications for ML in dermatology: (1) disease classification using clinical images; (2) disease classification using dermatopathology images; (3) assessment of skin diseases using mobile applications and personal monitoring devices; (4) facilitating large-scale epidemiology research; and (5) precision medicine. The purpose of this review is to provide a guide for dermatologists to help demystify the fundamentals of ML and its wide range of applications in order to better evaluate its potential opportunities and challenges.

show abstract

“…Manual review of these data is time consuming and laborious, hampering the usability of the data. Advancements in Natural Language Processing and Machine Learning (ML) methods have created great potential for processing format-free text data such as present in EHRs [1,2]. These EHR entries contain the prosaic conclusion of the treating physician, ranging from elaborate discussion of lab results to listed differential diagnoses.…”

Section: Introductionmentioning

confidence: 99%

Handwork Vs Machine; A Comparison of Rheumatoid Arthritis Patient Populations as Identified From Ehr Free-text by Diagnosis Extraction Through Machine-learning or Traditional Criteria-based Chart Review

Maarseveen

Maurits

Niemantsverdriet

et al. 2021

Preprint

View full text Add to dashboard Cite

BackgroundElectronic Health Records (EHRs) offer a wealth of observational data. Machine-Learning (ML) methods are efficient at data extraction, capable of processing the information-rich free-text physician notes in EHRs. The clinical diagnosis contained therein represents physician expert opinion and is more consistently recorded than classification criteria components.ObjectivesTo investigate the overlap and differences between Rheumatoid Arthritis patients as identified either from EHR free-text through extraction of the rheumatologist diagnosis using machine-learning (ML) or through manual chart-review applying the 1987 and 2010 RA classification criteria.MethodsSince EHR initiation, 17,662 patients visited the Leiden outpatient clinic. For ML, we used a Support Vector Machine (SVM) model to identify those who were diagnosed with RA by their rheumatologist. We trained & validated the model on a random selection of 2,000 patients, balancing PPV and Sensitivity to define a cutoff, and assessed performance on a separate 1,000 patients. We then deployed the model on our entire patient selection (including the 3,000). Of those, 1,212 patients had both a 1987 and 2010 EULAR/ACR criteria status at one year after inclusion into the local prospective arthritis cohort. In these 1,212 patients we compared the patient characteristics of RA cases identified with ML and those fulfilling the classification criteria. ResultsThe ML model performed very well in the independent test set (sensitivity=0.85, specificity=0.99, PPV=0.86, NPV=0.99). In our selection of patients with both EHR and classification information, 406 were recognized as RA by ML and 386 and 457 fulfilled the 1987 or 2010 criteria respectively. Eighty percent of the ML-identified cases fulfilled at least one of the criteria sets. Both demographic and clinical parameters did not differ between the ML extracted cases and those identified with EULAR/ACR classification criteria. ConclusionsWith ML methods we enable fast patient extraction from the huge EHR resource. Our ML algorithm accurately identifies patients diagnosed with RA by their rheumatologist. This resulting group of RA patients had a strong overlap with patients identified using the 1987 or 2010 classification criteria and the baseline (disease) characteristics were comparable. ML assisted case labelling enables high-throughput creation of inclusive patient selections for research purposes.

show abstract

Rule-based and machine learning algorithms identify patients with systemic sclerosis accurately in the electronic health record

Cited by 37 publications

References 13 publications

Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks

Automatic multilabel detection of ICD10 codes in Dutch cardiology discharge letters using neural networks

Machine Learning in Dermatology: Current Applications, Opportunities, and Limitations

Handwork Vs Machine; A Comparison of Rheumatoid Arthritis Patient Populations as Identified From Ehr Free-text by Diagnosis Extraction Through Machine-learning or Traditional Criteria-based Chart Review

Contact Info

Product

Resources

About