Dataset Information

Expert guided natural language processing using one-class classification.

ABSTRACT:

Introduction

Automatically identifying specific phenotypes in free-text clinical notes is critically important for the reuse of clinical data. In this study, the authors combine expert-guided feature (text) selection with one-class classification for text processing.

Objectives

To compare the performance of one-class classification to traditional binary classification; to evaluate the utility of feature selection based on expert-selected salient text (snippets); and to determine the robustness of these models with respects to irrelevant surrounding text.

Methods

The authors trained one-class support vector machines (1C-SVMs) and two-class SVMs (2C-SVMs) to identify notes discussing breast cancer. Manually annotated visit summary notes (88 positive and 88 negative for breast cancer) were used to compare the performance of models trained on whole notes labeled as positive or negative to models trained on expert-selected text sections (snippets) relevant to breast cancer status. Model performance was evaluated using a 70:30 split for 20 iterations and on a realistic dataset of 10?000 records with a breast cancer prevalence of 1.4%.

Results

When tested on a balanced experimental dataset, 1C-SVMs trained on snippets had comparable results to 2C-SVMs trained on whole notes (F?=?0.92 for both approaches). When evaluated on a realistic imbalanced dataset, 1C-SVMs had a considerably superior performance (F?=?0.61 vs. F?=?0.17 for the best performing model) attributable mainly to improved precision (p?=?.88 vs. p?=?.09 for the best performing model).

Conclusions

1C-SVMs trained on expert-selected relevant text sections perform better than 2C-SVMs classifiers trained on either snippets or whole notes when applied to realistically imbalanced data with low prevalence of the positive class.

SUBMITTER: Joffe E

PROVIDER: S-EPMC4986669 | biostudies-literature | 2015 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Expert guided natural language processing using one-class classification.

Joffe Erel E Pettigrew Emily J EJ Herskovic Jorge R JR Bearden Charles F CF Bernstam Elmer V EV

Journal of the American Medical Informatics Association : JAMIA 20150610 5

<h4>Introduction</h4>Automatically identifying specific phenotypes in free-text clinical notes is critically important for the reuse of clinical data. In this study, the authors combine expert-guided feature (text) selection with one-class classification for text processing.<h4>Objectives</h4>To compare the performance of one-class classification to traditional binary classification; to evaluate the utility of feature selection based on expert-selected salient text (snippets); and to determine t ...[more]

PMID: 26063744

Similar Datasets

Project description:BackgroundMedical notes are a rich source of patient data; however, the nature of unstructured text has largely precluded the use of these data for large retrospective analyses. Transforming clinical text into structured data can enable large-scale research studies with electronic health records (EHR) data. Natural language processing (NLP) can be used for text information retrieval, reducing the need for labor-intensive chart review. Here we present an application of NLP to large-scale analysis of medical records at 2 large hospitals for patients hospitalized with COVID-19.ObjectiveOur study goal was to develop an NLP pipeline to classify the discharge disposition (home, inpatient rehabilitation, skilled nursing inpatient facility [SNIF], and death) of patients hospitalized with COVID-19 based on hospital discharge summary notes.MethodsText mining and feature engineering were applied to unstructured text from hospital discharge summaries. The study included patients with COVID-19 discharged from 2 hospitals in the Boston, Massachusetts area (Massachusetts General Hospital and Brigham and Women's Hospital) between March 10, 2020, and June 30, 2020. The data were divided into a training set (70%) and hold-out test set (30%). Discharge summaries were represented as bags-of-words consisting of single words (unigrams), bigrams, and trigrams. The number of features was reduced during training by excluding n-grams that occurred in fewer than 10% of discharge summaries, and further reduced using least absolute shrinkage and selection operator (LASSO) regularization while training a multiclass logistic regression model. Model performance was evaluated using the hold-out test set.ResultsThe study cohort included 1737 adult patients (median age 61 [SD 18] years; 55% men; 45% White and 16% Black; 14% nonsurvivors and 61% discharged home). The model selected 179 from a vocabulary of 1056 engineered features, consisting of combinations of unigrams, bigrams, and trigrams. The top features contributing most to the classification by the model (for each outcome) were the following: "appointments specialty," "home health," and "home care" (home); "intubate" and "ARDS" (inpatient rehabilitation); "service" (SNIF); "brief assessment" and "covid" (death). The model achieved a micro-average area under the receiver operating characteristic curve value of 0.98 (95% CI 0.97-0.98) and average precision of 0.81 (95% CI 0.75-0.84) in the testing set for prediction of discharge disposition.ConclusionsA supervised learning-based NLP approach is able to classify the discharge disposition of patients hospitalized with COVID-19. This approach has the potential to accelerate and increase the scale of research on patients' discharge disposition that is possible with EHR data.

Project description:BackgroundThe medical problem list is an important part of the electronic medical record in development in our institution. To serve the functions it is designed for, the problem list has to be as accurate and timely as possible. However, the current problem list is usually incomplete and inaccurate, and is often totally unused. To alleviate this issue, we are building an environment where the problem list can be easily and effectively maintained.MethodsFor this project, 80 medical problems were selected for their frequency of use in our future clinical field of evaluation (cardiovascular). We have developed an Automated Problem List system composed of two main components: a background and a foreground application. The background application uses Natural Language Processing (NLP) to harvest potential problem list entries from the list of 80 targeted problems detected in the multiple free-text electronic documents available in our electronic medical record. These proposed medical problems drive the foreground application designed for management of the problem list. Within this application, the extracted problems are proposed to the physicians for addition to the official problem list.ResultsThe set of 80 targeted medical problems selected for this project covered about 5% of all possible diagnoses coded in ICD-9-CM in our study population (cardiovascular adult inpatients), but about 64% of all instances of these coded diagnoses. The system contains algorithms to detect first document sections, then sentences within these sections, and finally potential problems within the sentences. The initial evaluation of the section and sentence detection algorithms demonstrated a sensitivity and positive predictive value of 100% when detecting sections, and a sensitivity of 89% and a positive predictive value of 94% when detecting sentences.ConclusionThe global aim of our project is to automate the process of creating and maintaining a problem list for hospitalized patients and thereby help to guarantee the timeliness, accuracy and completeness of this information.

Project description:BackgroundElectronic health records (EHR) contain large volumes of unstructured free-form text notes that richly describe a patient's health and medical comorbidities. It is unclear if perioperative risk stratification can be performed directly from these notes without manual data extraction. We conduct a feasibility study using natural language processing (NLP) to predict the American Society of Anesthesiologists Physical Status Classification (ASA-PS) as a surrogate measure for perioperative risk. We explore prediction performance using four different model types and compare the use of different note sections versus the whole note. We use Shapley values to explain model predictions and analyze disagreement between model and human anesthesiologist predictions.MethodsSingle-center retrospective cohort analysis of EHR notes from patients undergoing procedures with anesthesia care spanning all procedural specialties during a 5 year period who were not assigned ASA VI and also had a preoperative evaluation note filed within 90 days prior to the procedure. NLP models were trained for each combination of 4 models and 8 text snippets from notes. Model performance was compared using area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC). Shapley values were used to explain model predictions. Error analysis and model explanation using Shapley values was conducted for the best performing model.ResultsFinal dataset includes 38,566 patients undergoing 61,503 procedures with anesthesia care. Prevalence of ASA-PS was 8.81% for ASA I, 31.4% for ASA II, 43.25% for ASA III, and 16.54% for ASA IV-V. The best performing models were the BioClinicalBERT model on the truncated note task (macro-average AUROC 0.845) and the fastText model on the full note task (macro-average AUROC 0.865). Shapley values reveal human-interpretable model predictions. Error analysis reveals that some original ASA-PS assignments may be incorrect and the model is making a reasonable prediction in these cases.ConclusionsText classification models can accurately predict a patient's illness severity using only free-form text descriptions of patients without any manual data extraction. They can be an additional patient safety tool in the perioperative setting and reduce manual chart review for medical billing. Shapley feature attributions produce explanations that logically support model predictions and are understandable to clinicians.

Project description:Allergic reactions to medication range from mild to severe or even life-threatening. Proper documentation of patient allergy information is critical for safe prescription, avoiding drug interactions, and reducing healthcare costs. Allergy information is regularly obtained during the medical interview, but is often poorly documented in electronic health records (EHRs). While many EHRs allow for structured adverse drug reaction (ADR) reporting, a free-text entry is still common. The resulting information is neither interoperable nor easily reusable for other applications, such as clinical decision support systems and prescription alerts. Current approaches require pharmacists to review and code ADRs documented by healthcare professionals. Recently, the effectiveness of machine algorithms in natural language processing (NLP) has been widely demonstrated. Our study aims to develop and evaluate different NLP algorithms that can encode unstructured ADRs stored in EHRs into institutional symptom terms. Our dataset consists of 79,712 pharmacist-reviewed drug allergy records. We evaluated three NLP techniques: Naive Bayes—Support Vector Machine (NB-SVM), Universal Language Model Fine-tuning (ULMFiT), and Bidirectional Encoder Representations from Transformers (BERT). We tested different general-domain pre-trained BERT models, including mBERT, XLM-RoBERTa, and WanchanBERTa, as well as our domain-specific AllergyRoBERTa, which was pre-trained from scratch on our corpus. Overall, BERT models had the highest performance. NB-SVM outperformed ULMFiT and BERT for several symptom terms that are not frequently coded. The ensemble model achieved an exact match ratio of 95.33%, a F1 score of 98.88%, and a mean average precision of 97.07% for the 36 most frequently coded symptom terms. The model was then further developed into a symptom term suggestion system and achieved a Krippendorff’s alpha agreement coefficient of 0.7081 in prospective testing with pharmacists. Some degree of automation could both accelerate the availability of allergy information and reduce the efforts for human coding.

Dataset Information

Expert guided natural language processing using one-class classification.

Introduction

Objectives

Methods

Results

Conclusions

Publications

Expert guided natural language processing using one-class classification.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets