Automated clinical diagnosis: The role of content in various sections of a clinical document

Datla, Vivek V.; Hasan, Sadid A.; Qadir, Ashequl; Lee, Kathy; Yuan, Ling; Liu, Joey; Farri, Oladimeji

doi:10.1109/bibm.2017.8217794

Cited by 11 publications

(8 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our domain phrase (DP) generation algorithm works as follows. First, we extract clinical concepts from the radiology reports based on SNOMED-CT ontology [38] using a hybrid clinical NLP engine [39]. Then, our algorithm uses the extracted clinical concepts to form the DPs based on two heuristics: (1) we combine the consecutive clinical concepts occurred in the same sentence as one domain phrase.…”

Section: Domain Phrase Attention Mechanismmentioning

confidence: 99%

Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification

Banerjee

Yuan

Chen

et al. 2019

Artificial Intelligence in Medicine

Self Cite

197

View full text Add to dashboard Cite

This paper explores cutting-edge deep learning methods for information extraction from medical imaging free text reports at a multi-institutional scale and compares them to the state-of-the-art domain-specific rule-based system -PEFinder and traditional machine learning methods -SVM and Adaboost. We proposed two distinct deep learning models -(i) CNN Word -Glove, and (ii) Domain phrase attention-based hierarchical recurrent neural network (DPA-HNN), for synthesizing information on pulmonary emboli (PE) from over 7,370 clin-ical thoracic computed tomography (CT) free-text radiology reports collected from four major healthcare centers. Our proposed DPA-HNN model encodes domain-dependent phrases into an attention mechanism and represents a radiology report through a hierarchical RNN structure composed of word-level, sentence-level and document-level representations. Experimental results suggest that the performance of the deep learning models that are trained on a single institutional dataset, are better than rule-based PEFinder on our multi-institutional test sets. The best F1 score for the presence of PE in an adult patient population was 0.99 (DPA-HNN) and for a pediatrics population was 0.99 (HNN) which shows that the deep learning models being trained on adult data, demonstrated generalizability to pediatrics population with comparable accuracy. Our work suggests feasibility of broader usage of neural network models in automated classification of multi-institutional imaging text reports for a variety of applications including evaluation of imaging utilization, g

show abstract

Section: Domain Phrase Attention Mechanismmentioning

confidence: 99%

Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification

Banerjee

Yuan

Chen

et al. 2019

Artificial Intelligence in Medicine

Self Cite

197

View full text Add to dashboard Cite

show abstract

“…Researchers have used patient admission notes to predict diagnoses [11]. Using content from certain specific sections of the note improves performance of diagnosis extraction models when compared to using the entire note [4]. In our work too, making diagnosis predictions on a smaller part of conversations consisting of filtered noteworthy sentences leads to better model performance.…”

Section: Related Workmentioning

confidence: 78%

Extracting Structured Data from Physician-Patient Conversations By Predicting Noteworthy Utterances

Krishna¹,

Pavel²,

Schloss³

et al. 2020

Preprint

View full text Add to dashboard Cite

Despite diverse efforts to mine various modalities of medical data, the conversations between physicians and patients at the time of care remain an untapped source of insights. In this paper, we leverage this data to extract structured information that might assist physicians with post-visit documentation in electronic health records, potentially lightening the clerical burden. In this exploratory study, we describe a new dataset consisting of conversation transcripts, post-visit summaries, corresponding supporting evidence (in the transcript), and structured labels. We focus on the tasks of recognizing relevant diagnoses and abnormalities in the review of organ systems (RoS). One methodological challenge is that the conversations are long (around 1500 words), making it difficult for modern deep-learning models to use them as input. To address this challenge, we extract noteworthy utterances-parts of the conversation likely to be cited as evidence supporting some summary sentence. We find that by first filtering for (predicted) noteworthy utterances, we can significantly boost predictive performance for recognizing both diagnoses and RoS abnormalities.

show abstract

“…Previous research has shown it is feasible to generate inferences from structured clinical notes like those found in EHRs (Li et al, 2017;Guo et al, 2019;Lipton et al, 2016;Johnson et al, 2016). For example, clinical diagnoses have been inferred both from highly structured data, like specific symptoms from a medical ontology (Datla et al, 2017), as well as from unstructured prose written by a medical professional (Li et al, 2017). Even more recently, less structured data such as prose has also been automated using summarization techniques (Alsentzer and Kim, 2018;Liang et al, 2019).…”

Section: Related Workmentioning

confidence: 99%

Towards an Automated SOAP Note: Classifying Utterances from Medical Conversations

Schloss¹,

Konam²

2020

Preprint

View full text Add to dashboard Cite

Summaries generated from medical conversations can improve recall and understanding of care plans for patients and reduce documentation burden for doctors. Recent advancements in automatic speech recognition (ASR) and natural language understanding (NLU) offer potential solutions to generate these summaries automatically, but rigorous quantitative baselines for benchmarking research in this domain are lacking. In this paper, we bridge this gap for two tasks: classifying utterances from medical conversations according to (i) the SOAP section and (ii) the speaker role. Both are fundamental building blocks along the path towards an end-to-end, automated SOAP note for medical conversations. We provide details on a dataset that contains human and ASR transcriptions of medical conversations and corresponding machine learning optimized SOAP notes. We then present a systematic analysis in which we adapt an existing deep learning architecture to the two aforementioned tasks. The results suggest that modelling context in a hierarchical manner, which captures both word and utterance level context, yields substantial improvements on both classification tasks. Additionally, we develop and analyze a modular method for adapting our model to ASR output.

show abstract

Automated clinical diagnosis: The role of content in various sections of a clinical document

Cited by 11 publications

References 23 publications

Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification

Comparative effectiveness of convolutional neural network (CNN) and recurrent neural network (RNN) architectures for radiology text report classification

Extracting Structured Data from Physician-Patient Conversations By Predicting Noteworthy Utterances

Towards an Automated SOAP Note: Classifying Utterances from Medical Conversations

Contact Info

Product

Resources

About