Artificial Intelligence Algorithms and Natural Language Processing for the Recognition of Syncope Patients on Emergency Department Medical Records

Abstract

Background: Enrollment of large cohorts of syncope patients from administrative data is crucial for proper risk stratification but is limited by the enormous amount of time required for manual revision of medical records. Aim: To develop a Natural Language Processing (NLP) algorithm to automatically identify syncope from Emergency Department (ED) electronic medical records (EMRs). Methods: De-identified EMRs of all consecutive patients evaluated at Humanitas Research Hospital ED from 1 December 2013 to 31 March 2014 and from 1 December 2015 to 31 March 2016 were manually annotated to identify syncope. Records were combined in a single dataset and classified. The performance of combined multiple NLP feature selectors and classifiers was tested. Primary Outcomes: NLP algorithms’ accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and F3 score. Results: 15,098 and 15,222 records from 2013 and 2015 datasets were analyzed. Syncope was present in 571 records. Normalized Gini Index feature selector combined with Support Vector Machines classifier obtained the best F3 value (84.0%), with 92.2% sensitivity and 47.4% positive predictive value. A 96% analysis time reduction was computed, compared with EMRs manual review. Conclusions: This artificial intelligence algorithm enabled the automatic identification of a large population of syncope patients using EMRs.

Classification of Syncope Cases in Norwegian Medical Records

“…We compared a keyword matching baseline to two linear classifiers, a Logistic Regression (LR) classifier and an SVM, and to neural models, namely CNNs. These learning algorithms have been commonly and successfully used in previous NLP studies, including the clinical domain (Dipaola et al, 2019;Karimi et al, 2017).…”

“…The best neural model W2V-R, achieved .92 accuracy and a sensitivity of .93. To put these results into perspective, Dipaola et al (2019) reported a sensitivity of .92 for an SVMbased syncope classification model for Italian.…”

“…Incorporating such models into clinical data processing pipelines is thus an advantage only if they can demonstrate a clear advantage over their simpler counterparts. Dipaola et al (2019) developed linear classifiers with manually and automatically selected n-grams as features for classifying syncope in Italian medical records. A frequent target of investigations has been the 2007 Computational Medicine Challenge (CMC) dataset, focusing on automatic ICD coding in radiology reports.…”

Machine Learning and Syncope Management in the ED: The Future Is Coming

“…All these data, in structured or free text form, are routinely generated during patient visits and can be easily extracted from EHRs through the use of NLP-based algorithms. In a previous study [ 91 ], which was conducted on over 30,000 EHRs of patients evaluated in our hospital ED, we described a syncope detection algorithm based on natural language analysis applied to the episode reported by triage operators, the patient’s history and the ED physician evaluation, the ED discharge diagnosis description and the relative ICD 9 code. Overall, our SVMs classifier-based model was able to identify syncope patients with a sensitivity of 92% and a precision of 47%.…”

Predicting Prodromal Dementia Using Linguistic Patterns and Deficits

“…Likewise, when equals to 2 and 3, they are called "bigram" and "trigram" respectively. Our -gram vocabulary spaces in this study include bigrams and trigrams as 1 < ≤ , where equals to 3, which were seen to perform optimally in other NLP tasks [65]. We left high order spaces of -grams for future investigations.…”