Development and Validation of a Deep Learning Model for Detection of Allergic Reactions Using Safety Event Reports Across Hospitals

Abstract

IMPORTANCEAlthough critical to patient safety, health care-related allergic reactions are challenging to identify and monitor. OBJECTIVE To develop a deep learning model to identify allergic reactions in the free-text narrative of hospital safety reports and evaluate its generalizability, efficiency, productivity, and interpretability.

Development and Validation of a Deep Learning Model for Earlier Detection of Cognitive Decline From Clinical Notes in Electronic Health Records

“…The deep learning model was based on a study aiming to detect allergic reactions from free-text hospital safety reports. 19 The algorithm was proven to be accurate and useful in allergic reaction detection. The present study noted the applicability of the deep learning algorithm to clinical notes.…”

“…We implemented a hierarchical attention-based deep learning structure and 4 baseline machine learning algorithms, including logistic regression, random forest, support vector machine, and XGBoost. 18 The deep learning algorithm was developed in a prior study 19 ; it incorporates a convolutional neural network for the purpose of handling word variations, recurrent neural network for context, and attention layers for interpretation of the prediction. In the deep learning model, each note section was regarded as a sequence of tokens (including words and punctuation), with individual words represented by word embeddings, for which we used word2vec and trained 100-dimensional embeddings on a large corpus of 3 729 838 notes from 10 837 patients with an initial MCI diagnosis between January 1, 2017, and February 29, 2020.…”

“…Word weights above the mean weights plus 2 SDs within individual sections were considered high attention. 19 High attended words among the model-predicted positive cases were assembled and compared with the original curated keywords.…”

Allergic Reactions in Two Academic Medical Centers

“…Using a machine learning model trained on the free-text of 9107 manually labeled safety reports (rL, Toronto, Canada) (average area under the receiver operating characteristic curve 0.979, 95% confidence interval 0.973-0.985), 6 we sorted voluntarily filed reports from July 1, 2008, to June 30, 2018, at two United States AMCs by their model-predicted probability of describing an allergic reaction in descending order. Reports were manually reviewed until the last 200 reports contained just one allergic event (i.e., false negative rate of 0.5%).…”

The development of a machine learning algorithm to identify occupational injuries in agriculture using pre-hospital care reports

“…Prieto et al developed a natural language processing method using logistic regression and several keywords to identify opioid misuse in the narrative portion of PCRs [ 17 ]. Yang et al developed a deep neural network to identify cases involving allergic reactions in the free text section of hospital safety reports [ 18 ]. This paper describes the development of a Naïve Bayes machine learning algorithm for pre-hospital care reports (PCR) to identify agricultural occupational injuries along with the algorithm’s utility on untagged datasets.…”