Dataset Information

A hybrid approach to automatic de-identification of psychiatric notes.

ABSTRACT: De-identification, or identifying and removing protected health information (PHI) from clinical data, is a critical step in making clinical data available for clinical applications and research. This paper presents a natural language processing system for automatic de-identification of psychiatric notes, which was designed to participate in the 2016 CEGS N-GRID shared task Track 1. The system has a hybrid structure that combines machine leaning techniques and rule-based approaches. The rule-based components exploit the structure of the psychiatric notes as well as characteristic surface patterns of PHI mentions. The machine learning components utilize supervised learning with rich features. In addition, the system performance was boosted with integration of additional data to the training set through domain adaptation. The hybrid system showed overall micro-averaged F-score 90.74 on the test set, second-best among all the participants of the CEGS N-GRID task.

SUBMITTER: Lee HJ

PROVIDER: S-EPMC5705430 | biostudies-literature | 2017 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A hybrid approach to automatic de-identification of psychiatric notes.

Lee Hee-Jin HJ Wu Yonghui Y Zhang Yaoyun Y Xu Jun J Xu Hua H Roberts Kirk K

Journal of biomedical informatics 20170607

De-identification, or identifying and removing protected health information (PHI) from clinical data, is a critical step in making clinical data available for clinical applications and research. This paper presents a natural language processing system for automatic de-identification of psychiatric notes, which was designed to participate in the 2016 CEGS N-GRID shared task Track 1. The system has a hybrid structure that combines machine leaning techniques and rule-based approaches. The rule-base ...[more]

PMID: 28602904

Similar Datasets

Project description:The degree of production efficiency and the quality of the commodities produced may both be directly impacted by the presence of illnesses in tea leaves. These days, this procedure may be automated with the use of artificial intelligence tools, and a number of approaches have been put out to satisfy these needs. Nonetheless, current research efforts have focused on improving diagnosis accuracy and expanding the variety of illnesses that might affect tea leaves. In this article, a new method is proposed for accurately diagnosing tea leaf diseases using artificial intelligence techniques. In the proposed method, the input images are preprocessed to remove redundant information. Then, a hybrid pooling-based Convolutional Neural Network (CNN) is employed to extract image features. In this method, the pooling layers of the CNN model are randomly adjusted based on either max pooling or average pooling functions. This strategy can enhance the efficiency of the CNN-based feature extraction model. In this method, the pooling layers of the CNN model are randomly adjusted based on either max pooling or average pooling functions. This strategy can enhance the efficiency of the CNN-based feature extraction model. After feature extraction, a weighted Random Forest (WRF) model is used for the detection of tea leaf diseases. The outputs of the decision tree models and their corresponding weights are used to identify tea leaf illnesses in this classification model, where each tree in the random forest is given a weight depending on how well it performs. The Cuckoo Search Optimization (CSO) method is used in the proposed classification model to give a weight to each tree. Tea Sickness Dataset (TSD) has been used as the basis for evaluating the suggested method's effectiveness. The findings show that the suggested approach has an average accuracy of 92.47% in identifying seven different forms of tea leaf illnesses. Additionally, the recall and accuracy metrics indicate results of 92.35 and 92.26, respectively, indicating improvements over earlier techniques.

Project description:BackgroundPhysician notes routinely recorded during patient care represent a vast and underutilized resource for human disease studies on a population scale. Their use in research is primarily limited by the need to separate confidential patient information from clinical annotations, a process that is resource-intensive when performed manually. This study seeks to create an automated method for de-identifying physician notes that does not require large amounts of private information: in addition to training a model to recognize Protected Health Information (PHI) within private physician notes, we reverse the problem and train a model to recognize non-PHI words and phrases that appear in public medical texts.MethodsPublic and private medical text sources were analyzed to distinguish common medical words and phrases from Protected Health Information. Patient identifiers are generally nouns and numbers that appear infrequently in medical literature. To quantify this relationship, term frequencies and part of speech tags were compared between journal publications and physician notes. Standard medical concepts and phrases were then examined across ten medical dictionaries. Lists and rules were included from the US census database and previously published studies. In total, 28 features were used to train decision tree classifiers.ResultsThe model successfully recalled 98% of PHI tokens from 220 discharge summaries. Cost sensitive classification was used to weight recall over precision (98% F10 score, 76% F1 score). More than half of the false negatives were the word "of" appearing in a hospital name. All patient names, phone numbers, and home addresses were at least partially redacted. Medical concepts such as "elevated white blood cell count" were informative for de-identification. The results exceed the previously approved criteria established by four Institutional Review Boards.ConclusionsThe results indicate that distributional differences between private and public medical text can be used to accurately classify PHI. The data and algorithms reported here are made freely available for evaluation and improvement.

Project description:This paper presents a novel method for automatically recognizing symptom severity by using natural language processing of psychiatric evaluation records to extract features that are processed by machine learning techniques to assign a severity score to each record evaluated in the 2016 RDoC for Psychiatry Challenge from CEGS/N-GRID. The natural language processing techniques focused on (a) discerning the discourse information expressed in questions and answers; (b) identifying medical concepts that relate to mental disorders; and (c) accounting for the role of negation. The machine learning techniques rely on the assumptions that (1) the severity of a patient's positive valence symptoms exists on a latent continuous spectrum and (2) all the patient's answers and narratives documented in the psychological evaluation records are informed by the patient's latent severity score along this spectrum. These assumptions motivated our two-step machine learning framework for automatically recognizing psychological symptom severity. In the first step, the latent continuous severity score is inferred from each record; in the second step, the severity score is mapped to one of the four discrete severity levels used in the CEGS/N-GRID challenge. We evaluated three methods for inferring the latent severity score associated with each record: (i) pointwise ridge regression; (ii) pairwise comparison-based classification; and (iii) a hybrid approach combining pointwise regression and the pairwise classifier. The second step was implemented using a tree of cascading support vector machine (SVM) classifiers. While the official evaluation results indicate that all three methods are promising, the hybrid approach not only outperformed the pairwise and pointwise methods, but also produced the second highest performance of all submissions to the CEGS/N-GRID challenge with a normalized MAE score of 84.093% (where higher numbers indicate better performance). These evaluation results enabled us to observe that, for this task, considering pairwise information can produce more accurate severity scores than pointwise regression - an approach widely used in other systems for assigning severity scores. Moreover, our analysis indicates that using a cascading SVM tree outperforms traditional SVM classification methods for the purpose of determining discrete severity levels.

Dataset Information

A hybrid approach to automatic de-identification of psychiatric notes.

Publications

A hybrid approach to automatic de-identification of psychiatric notes.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets