Chief complaint classification with recurrent neural networks

Lee, Scott H.; Levin, Drew; Finley, Patrick D.; Heilig, Charles M.

doi:10.1016/j.jbi.2019.103158

Cited by 26 publications

(10 citation statements)

References 28 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They used Naïve Bayes for text classification, while we implemented a neural network. Neural networks have been shown to perform better than traditional machine learning mod-els 26,27 for text classification, in addition to other tasks like image classification. Rather than relying on the topics provided by Press Ganey, Doing-Harris et al 15 performed automatic topic modeling.…”

Section: Discussionmentioning

confidence: 99%

Natural Language Processing to Extract Meaningful Information from Patient Experience Feedback

Nawab¹,

Ramsey²,

Schreiber

2020

Appl Clin Inform

View full text Add to dashboard Cite

Background Due to reimbursement tied in part to patients' perception of their care, hospitals continue to stress obtaining patient feedback and understanding it to plan interventions to improve patients' experience. We demonstrate the use of natural language processing (NLP) to extract meaningful information from patient feedback obtained through Press Ganey surveys. Methods The first step was to standardize textual data programmatically using NLP libraries. This included correcting spelling mistakes, converting text to lowercase, and removing words that most likely did not carry useful information. Next, we converted numeric data pertaining to each category based on sentiment and care aspect into charts. We selected care aspect categories where there were more negative comments for more in-depth study. Using NLP, we made tables of most frequently appearing words, adjectives, and bigrams. Comments with frequent words/combinations underwent further study manually to understand factors contributing to negative patient feedback. We then used the positive and negative comments as the training dataset for a neural network to perform sentiment analysis on sentences obtained by splitting mixed reviews. Results We found that most of the comments were about doctors and nurses, confirming the important role patients ascribed to these two in patient care. “Room,” “discharge” and “tests and treatments” were the three categories that had more negative than positive comments. We then tabulated commonly appearing words, adjectives, and two-word combinations. We found that climate control, housekeeping and noise levels in the room, time delays in discharge paperwork, conflicting information about discharge plan, frequent blood draws, and needle sticks were major contributors to negative patient feedback. None of this information was available from numeric data alone. Conclusion NLP is an effective tool to gain insight from raw textual patient feedback to extract meaningful information, making it a powerful tool in processing large amounts of patient feedback efficiently.

show abstract

Section: Discussionmentioning

confidence: 99%

Natural Language Processing to Extract Meaningful Information from Patient Experience Feedback

Nawab¹,

Ramsey²,

Schreiber

2020

Appl Clin Inform

View full text Add to dashboard Cite

show abstract

“…Moreover, the ML methods are used for syndromic surveillance based on chief complaint field to detect disease outbreaks. For example, Lee et al 14 compared two recurrent ANN models based on LSTM and gated recurrent unit (GRU) cells, multinomial naive Bayes (MNB) and support vector machine (SVM) to improve the syndromic surveillance. Volkova et al 15 utilized ANNs to forecast the influenza-like illness dynamics for military populations.…”

mentioning

confidence: 99%

Prediction of the Vaccine-derived Poliovirus Outbreak Incidence: A Hybrid Machine Learning Approach

Hemedan

Elaziz

Jiao

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Recently, significant attention has been devoted to vaccine-derived poliovirus (VDPV) surveillance due to its severe consequences. Prediction of the outbreak incidence of VDPF requires an accurate analysis of the alarming data. the overarching aim to this study is to develop a novel hybrid machine learning approach to identify the key parameters that dominate the outbreak incidence of VDPV. The proposed method is based on the integration of random vector functional link (RVFL) networks with a robust optimization algorithm called whale optimization algorithm (WOA). WOA is applied to improve the accuracy of the RVFL network by finding the suitable parameter configurations for the algorithm. The classification performance of the WOA-RVFL method is successfully validated using a number of datasets from the UCI machine learning repository. Thereafter, the method is implemented to track the VDPV outbreak incidences recently occurred in several provinces in Lao People's Democratic Republic. The results demonstrate the accuracy and efficiency of the WOA-RVFL algorithm in detecting the VDPV outbreak incidences, as well as its superior performance to the traditional RVFL method.Poliovirus (PV) surveillance is considered as one of the most challenging issues in countries with suboptimal vaccination coverage levels due to the repetitive silent circulation of the vaccine derived poliovirus (VDPV). Despite its durable intestinal and humoral immunity, VDPV is genetically instable that might revert to wild-type virulence. According to a number of studies 1 , vaccines can cause vaccine-associated flaccid paralysis. Noteworthy, it can replicate for a prolonged time coinciding with the suboptimal vaccination 1 . Interaction of PV and CD155 receptors facilitates its entry 2 . Thereafter, the viral RNA is released. The genome enclosed in the viral particle is used as mRNA and translated by the host cell. The virus hijacks the cell's translation, leading to inhibition of protein synthesis during viral protein production. Ribosome entry site directs the viral RNA translation and synthesis of (+) RNA occurs. Some of the (+) RNA are used as templates for (−) RNA synthesis, some function as mRNA, and some are destined to be the genomes of virus progeny 1 .Globally, the concerted surveillance with the continuous integration and interpretation of health-related data are required to keep the prevention and elimination programs updated. PV surveillance is considered as one of the most important element of the Global Polio Eradication Initiative (GPEI) endgame strategy, which is also useful in detecting VDPV. There are mainly two types of PV surveillance, including (1) the environmental surveillance (ES) that analyzes wastewater to detect if the current collected samples carry PV 3,4 , and (2) the acute flaccid paralysis surveillance (AFPS) that depends on clinical presentation. However, the traditional PV surveillance methods are resource intensive to maintain the system of AFPS for the long term 2 . Still, combatting disease outbreaks signif...

show abstract

“…Our other main measure of epidemiological validity is to see whether we can predict diagnoses from the synthetic chief complaints as well as we can from the real ones. Although there are many methods for performing this task (see Conway, Dowling, and Chapman 23 for an overview), we use a kind of RNN called a gated recurrent unit (GRU), which Lee et al 24 show to have superior performance to the multinomial naive Bayes classifiers employed by several chief complaint classifiers currently in use (details on model architecture and training procedures are provided in the Supplementary Methods). After training the model on the record-sentence pairs in our training set, we then generate predicted Clinical Classification Software (CCS) 17 codes for the authentic chief complaints in the test set and evaluate diagnostic accuracy using weighted macro sensitivity, positive predictive value, and F1 score.…”

Section: Methodsmentioning

confidence: 99%

Natural language generation for electronic health records

Lee

2018

npj Digital Med

Self Cite

View full text Add to dashboard Cite

One broad goal of biomedical informatics is to generate fully-synthetic, faithfully representative electronic health records (EHRs) to facilitate data sharing between healthcare providers and researchers and promote methodological research. A variety of methods existing for generating synthetic EHRs, but they are not capable of generating unstructured text, like emergency department (ED) chief complaints, history of present illness, or progress notes. Here, we use the encoder–decoder model, a deep learning algorithm that features in many contemporary machine translation systems, to generate synthetic chief complaints from discrete variables in EHRs, like age group, gender, and discharge diagnosis. After being trained end-to-end on authentic records, the model can generate realistic chief complaint text that appears to preserve the epidemiological information encoded in the original record-sentence pairs. As a side effect of the model’s optimization goal, these synthetic chief complaints are also free of relatively uncommon abbreviation and misspellings, and they include none of the personally identifiable information (PII) that was in the training data, suggesting that this model may be used to support the de-identification of text in EHRs. When combined with algorithms like generative adversarial networks (GANs), our model could be used to generate fully-synthetic EHRs, allowing healthcare providers to share faithful representations of multimodal medical data without compromising patient privacy. This is an important advance that we hope will facilitate the development of machine-learning methods for clinical decision support, disease surveillance, and other data-hungry applications in biomedical informatics.

show abstract

Chief complaint classification with recurrent neural networks

Cited by 26 publications

References 28 publications

Natural Language Processing to Extract Meaningful Information from Patient Experience Feedback

Natural Language Processing to Extract Meaningful Information from Patient Experience Feedback

Prediction of the Vaccine-derived Poliovirus Outbreak Incidence: A Hybrid Machine Learning Approach

Natural language generation for electronic health records

Contact Info

Product

Resources

About