Search

Objective: In an effort to improve the efficiency of computer algorithms applied to screening for coronavirus disease 2019 (COVID-19) testing, we used natural language processing and artificial intelligence-based methods with unstructured patient data collected through telehealth visits., Materials and Methods: After segmenting and parsing documents, we conducted analysis of overrepresented words in patient symptoms. We then developed a word embedding-based convolutional neural network for predicting COVID-19 test results based on patients' self-reported symptoms., Results: Text analytics revealed that concepts such as smell and taste were more prevalent than expected in patients testing positive. As a result, screening algorithms were adapted to include these symptoms. The deep learning model yielded an area under the receiver-operating characteristic curve of 0.729 for predicting positive results and was subsequently applied to prioritize testing appointment scheduling., Conclusions: Informatics tools such as natural language processing and artificial intelligence methods can have significant clinical impacts when applied to data streams early in the development of clinical systems for outbreak response., (© The Author(s) 2020. Published by Oxford University Press on behalf of the American Medical Informatics Association.)

Background: Social isolation is an important social determinant that impacts health outcomes and mortality among patients. The National Academy of Medicine recently recommended that social isolation be documented in electronic health records (EHR). However, social isolation usually is not recorded or obtained as coded data but rather collected from patient self-report or documented in clinical narratives. This study explores the feasibility and effectiveness of natural language processing (NLP) strategy for identifying patients who are socially isolated from clinical narratives., Method: We used data from the Medical University of South Carolina (MUSC) Research Data Warehouse. Patients 18 years-of-age or older who were diagnosed with prostate cancer between January 1, 2014 and May 31, 2017 were eligible for this study. NLP pipelines identifying social isolation were developed via extraction of notes on progress, history and physical, consult, emergency department provider, telephone encounter, discharge summary, plan of care, and radiation oncology. Of 4195 eligible prostate cancer patients, we randomly sampled 3138 patients (75%) as a training dataset. The remaining 1057 patients (25%) were used as a test dataset to evaluate NLP algorithm performance. Standard performance measures for the NLP algorithm, including precision, recall, and F-measure, were assessed by expert manual review using the test dataset., Results: A total of 55,516 clinical notes from 3138 patients were included to develop the lexicon and NLP pipelines for social isolation. Of those, 35 unique patients (1.2%) had social isolation mention(s) in 217 notes. Among 24 terms relevant to social isolation, the most prevalent were "lack of social support," "lonely," "social isolation," "no friends," and "loneliness". Among 1057 patients in the test dataset, 17 patients (1.6%) were identified as having social isolation mention(s) in 40 clinical notes. Manual review identified four false positive mentions of social isolation and one false negatives in 154 notes from randomly selected 52 controls. The NLP pipeline demonstrated 90% precision, 97% recall, and 93% F-measure. The major reasons for a false positive included the ambiguities of the experiencer of social isolation, negation, and alternate meaning of words., Conclusions: Our NLP algorithms demonstrate a highly accurate approach to identify social isolation.

Background and Purpose: This project assessed performance of natural language processing (NLP) and machine learning (ML) algorithms for classification of brain MRI radiology reports into acute ischemic stroke (AIS) and non-AIS phenotypes., Materials and Methods: All brain MRI reports from a single academic institution over a two year period were randomly divided into 2 groups for ML: training (70%) and testing (30%). Using "quanteda" NLP package, all text data were parsed into tokens to create the data frequency matrix. Ten-fold cross-validation was applied for bias correction of the training set. Labeling for AIS was performed manually, identifying clinical notes. We applied binary logistic regression, naïve Bayesian classification, single decision tree, and support vector machine for the binary classifiers, and we assessed performance of the algorithms by F1-measure. We also assessed how n-grams or term frequency-inverse document frequency weighting affected the performance of the algorithms., Results: Of all 3,204 brain MRI documents, 432 (14.3%) were labeled as AIS. AIS documents were longer in character length than those of non-AIS (median [interquartile range]; 551 [377-681] vs. 309 [164-396]). Of all ML algorithms, single decision tree had the highest F1-measure (93.2) and accuracy (98.0%). Adding bigrams to the ML model improved F1-mesaure of naïve Bayesian classification, but not in others, and term frequency-inverse document frequency weighting to data frequency matrix did not show any additional performance improvements., Conclusions: Supervised ML based NLP algorithms are useful for automatic classification of brain MRI reports for identification of AIS patients. Single decision tree was the best classifier to identify brain MRI reports with AIS., Competing Interests: Drs. Kim, Zhu and Obeid have no competing interests. Dr. Lenert is a member of the Board of Directors of the ATCC. This does not alter the authors' adherence to PLOS ONE policies on sharing data and materials.

Quality reporting that relies on coded administrative data alone may not completely and accurately depict providers' performance. To assess this concern with a test case, we developed and evaluated a natural language processing (NLP) approach to identify falls risk screenings documented in clinical notes of patients without coded falls risk screening data. Extracting information from 1,558 clinical notes (mainly progress notes) from 144 eligible patients, we generated a lexicon of 38 keywords relevant to falls risk screening, 26 terms for pre-negation, and 35 terms for post-negation. The NLP algorithm identified 62 (out of the 144) patients who falls risk screening documented only in clinical notes and not coded. Manual review confirmed 59 patients as true positives and 77 patients as true negatives. Our NLP approach scored 0.92 for precision, 0.95 for recall, and 0.93 for F-measure. These results support the concept of utilizing NLP to enhance healthcare quality reporting.

Background: Child abuse and neglect (CAN) is prevalent, associated with long-term adversities, and often undetected. Primary care settings offer a unique opportunity to identify CAN and facilitate referrals, when warranted. Electronic health records (EHR) contain extensive information to support healthcare decisions, yet time constraints preclude most providers from thorough EHR reviews that could indicate CAN. Strategies that summarize EHR data to identify CAN and convey this to providers has potential to mitigate CAN-related sequelae. This study used expert review/consensus and Natural Language Processing (NLP) to develop and test a lexicon to characterize children who have experienced or are at risk for CAN and compared machine learning methods to the lexicon + NLP approach to determine the algorithm's performance for identifying CAN. Methods: Study investigators identified 90 CAN terms and invited an interdisciplinary group of child abuse experts for review and validation. We then used NLP to develop pipelines to finalize the CAN lexicon. Data for pipeline development and refinement were drawn from a randomly selected sample of EHR from patients seen at pediatric primary care clinics within a U.S. academic health center. To explore a machine learning approach for CAN identification, we used Support Vector Machine algorithms. Results: The investigator-generated list of 90 CAN terms were reviewed and validated by 25 invited experts, resulting in a final pool of 133 terms. NLP utilized a randomly selected sample of 14,393 clinical notes from 153 patients to test the lexicon, and.03% of notes were identified as CAN positive. CAN identification varied by clinical note type, with few differences found by provider type (physicians versus nurses, social workers, etc.). An evaluation of the final NLP pipelines indicated 93.8% positive CAN rate for the training set and 71.4% for the test set, with decreased precision attributed primarily to false positives. For the machine learning approach, SVM pipeline performance was 92% for CAN + and 100% for non-CAN, indicating higher sensitivity than specificity. Conclusions: The NLP algorithm's development and refinement suggest that innovative tools can identify youth at risk for CAN. The next key step is to refine the NLP algorithm to eventually funnel this information to care providers to guide clinical decision making. [ABSTRACT FROM AUTHOR]