Dataset Information

Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources.

ABSTRACT:

Objective

Analysis of narrative (text) data from electronic health records (EHRs) can improve population-scale phenotyping for clinical and genetic research. Currently, selection of text features for phenotyping algorithms is slow and laborious, requiring extensive and iterative involvement by domain experts. This paper introduces a method to develop phenotyping algorithms in an unbiased manner by automatically extracting and selecting informative features, which can be comparable to expert-curated ones in classification accuracy.

Materials and methods

Comprehensive medical concepts were collected from publicly available knowledge sources in an automated, unbiased fashion. Natural language processing (NLP) revealed the occurrence patterns of these concepts in EHR narrative notes, which enabled selection of informative features for phenotype classification. When combined with additional codified features, a penalized logistic regression model was trained to classify the target phenotype.

Results

The authors applied our method to develop algorithms to identify patients with rheumatoid arthritis and coronary artery disease cases among those with rheumatoid arthritis from a large multi-institutional EHR. The area under the receiver operating characteristic curves (AUC) for classifying RA and CAD using models trained with automated features were 0.951 and 0.929, respectively, compared to the AUCs of 0.938 and 0.929 by models trained with expert-curated features.

Discussion

Models trained with NLP text features selected through an unbiased, automated procedure achieved comparable or slightly higher accuracy than those trained with expert-curated features. The majority of the selected model features were interpretable.

Conclusion

The proposed automated feature extraction method, generating highly accurate phenotyping algorithms with improved efficiency, is a significant step toward high-throughput phenotyping.

SUBMITTER: Yu S

PROVIDER: S-EPMC4986664 | biostudies-literature | 2015 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources.

Yu Sheng S Liao Katherine P KP Shaw Stanley Y SY Gainer Vivian S VS Churchill Susanne E SE Szolovits Peter P Murphy Shawn N SN Kohane Isaac S IS Cai Tianxi T

Journal of the American Medical Informatics Association : JAMIA 20150429 5

<h4>Objective</h4>Analysis of narrative (text) data from electronic health records (EHRs) can improve population-scale phenotyping for clinical and genetic research. Currently, selection of text features for phenotyping algorithms is slow and laborious, requiring extensive and iterative involvement by domain experts. This paper introduces a method to develop phenotyping algorithms in an unbiased manner by automatically extracting and selecting informative features, which can be comparable to exp ...[more]

PMID: 25929596

Similar Datasets

Project description:OBJECTIVE:Phenotyping algorithms can efficiently and accurately identify patients with a specific disease phenotype and construct electronic health records (EHR)-based cohorts for subsequent clinical or genomic studies. Previous studies have introduced unsupervised EHR-based feature selection methods that yielded algorithms with high accuracy. However, those selection methods still require expert intervention to tweak the parameter settings according to the EHR data distribution for each phenotype. To further accelerate the development of phenotyping algorithms, we propose a fully automated and robust unsupervised feature selection method that leverages only publicly available medical knowledge sources, instead of EHR data. METHODS:SEmantics-Driven Feature Extraction (SEDFE) collects medical concepts from online knowledge sources as candidate features and gives them vector-form distributional semantic representations derived with neural word embedding and the Unified Medical Language System Metathesaurus. A number of features that are semantically closest and that sufficiently characterize the target phenotype are determined by a linear decomposition criterion and are selected for the final classification algorithm. RESULTS:SEDFE was compared with the EHR-based SAFE algorithm and domain experts on feature selection for the classification of five phenotypes including coronary artery disease, rheumatoid arthritis, Crohn's disease, ulcerative colitis, and pediatric pulmonary arterial hypertension using both supervised and unsupervised approaches. Algorithms yielded by SEDFE achieved comparable accuracy to those yielded by SAFE and expert-curated features. SEDFE is also robust to the input semantic vectors. CONCLUSION:SEDFE attains satisfying performance in unsupervised feature selection for EHR phenotyping. Both fully automated and EHR-independent, this method promises efficiency and accuracy in developing algorithms for high-throughput phenotyping.

Project description:BackgroundAutomated ICD coding on medical texts via machine learning has been a hot topic. Related studies from medical field heavily relies on conventional bag-of-words (BoW) as the feature extraction method, and do not commonly use more complicated methods, such as word2vec (W2V) and large pretrained models like BERT. This study aimed at uncovering the most effective feature extraction methods for coding models by comparing BoW, W2V and BERT variants.MethodsWe experimented with a Chinese dataset from Fuwai Hospital, which contains 6947 records and 1532 unique ICD codes, and a public Spanish dataset, which contains 1000 records and 2557 unique ICD codes. We designed coding tasks with different code frequency thresholds (denoted as [Formula: see text]), with a lower threshold indicating a more complex task. Using traditional classifiers, we compared BoW, W2V and BERT variants on accomplishing these coding tasks.ResultsWhen [Formula: see text] was equal to or greater than 140 for Fuwai dataset, and 60 for the Spanish dataset, the BERT variants with the whole network fine-tuned was the best method, leading to a Micro-F1 of 93.9% for Fuwai data when [Formula: see text], and a Micro-F1 of 85.41% for the Spanish dataset when [Formula: see text]. When [Formula: see text] fell below 140 for Fuwai dataset, and 60 for the Spanish dataset, BoW turned out to be the best, leading to a Micro-F1 of 83% for Fuwai dataset when [Formula: see text], and a Micro-F1 of 39.1% for the Spanish dataset when [Formula: see text]. Our experiments also showed that both the BERT variants and BoW possessed good interpretability, which is important for medical applications of coding models.ConclusionsThis study shed light on building promising machine learning models for automated ICD coding by revealing the most effective feature extraction methods. Concretely, our results indicated that fine-tuning the whole network of the BERT variants was the optimal method for tasks covering only frequent codes, especially codes that represented unspecified diseases, while BoW was the best for tasks involving both frequent and infrequent codes. The frequency threshold where the best-performing method varied differed between different datasets due to factors like language and codeset.

Dataset Information

Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources.

Objective

Materials and methods

Results

Discussion

Conclusion

Publications

Toward high-throughput phenotyping: unbiased automated feature extraction and selection from knowledge sources.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets