Ontology-Aware Clinical Abstractive Summarization

MacAvaney, Sean; Sotudeh, Sajad; Cohan, Arman; Goharian, Nazli; Talati, Ish A.; Filice, Ross W.

doi:10.1145/3331184.3331319

Cited by 61 publications

(47 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al (2018) first studied the problem of automatic generation of radiology impressions by summarizing textual radiology findings, and showed that an augmented pointer-generator model achieves high overlap with human references. MacAvaney et al (2019) extended this model with an ontologyaware pointer-generator and showed improved summarization quality. Li et al (2019) and studied generating textual descriptions of radiology findings from medical images, and proposed RL-based approaches to tackle this problem.…”

Section: Related Workmentioning

confidence: 99%

Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports

Zhang¹,

Merck²,

Tsai³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

120

View full text Add to dashboard Cite

Neural abstractive summarization models are able to generate summaries which have high overlap with human references. However, existing models are not optimized for factual correctness, a critical metric in real-world applications. In this work, we develop a general framework where we evaluate the factual correctness of a generated summary by factchecking it automatically against its reference using an information extraction module. We further propose a training strategy which optimizes a neural summarization model with a factual correctness reward via reinforcement learning. We apply the proposed method to the summarization of radiology reports, where factual correctness is a key requirement. On two separate datasets collected from hospitals, we show via both automatic and human evaluation that the proposed approach substantially improves the factual correctness and overall quality of outputs over a competitive neural summarization system, producing radiology summaries that approach the quality of humanauthored ones.Human Summary: pneumothorax is seen. bilateral pleural effusions continue.Summary A (ROUGE-L = 0.77): no pneumothorax is observed. bilateral pleural effusions continue.Summary B (ROUGE-L = 0.44): pneumothorax is observed on radiograph. bilateral pleural effusions continue to be seen.

show abstract

Section: Related Workmentioning

confidence: 99%

Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports

Zhang¹,

Merck²,

Tsai³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

120

View full text Add to dashboard Cite

show abstract

“…having all major information, or missing key points. Figure . 2 presents the human evaluation results using histograms and arrow plots as done in (MacAvaney et al, 2019), comparing our system's Impressions versus human-written Impressions. The histograms indicate the distribution of scores, and arrows show how the scores changed between ours and human-written.…”

Section: Expert Evaluationmentioning

confidence: 99%

Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization

Gharebagh¹,

Goharian²,

Filice³

2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Sequence-to-sequence (seq2seq) network is a well-established model for text summarization task. It can learn to produce readable content; however, it falls short in effectively identifying key regions of the source. In this paper, we approach the content selection problem for clinical abstractive summarization by augmenting salient ontological terms into the summarizer. Our experiments on two publicly available clinical data sets (107,372 reports of MIMIC-CXR, and 3,366 reports of OpenI) show that our model statistically significantly boosts state-of-the-art results in terms of ROUGE metrics (with improvements: 2.9% RG-1, 2.5% RG-2, 1.9% RG-L), in the healthcare domain where any range of improvement impacts patients' welfare.

show abstract

“…Recently, there has been growing interest in applying the capacity of AI to investigate specific datasets in medical fields [42][43][44][45][46][47][48][49] . AI has special image processing capabilities to discern multi-faceted features that would otherwise elude trained pathologists.…”

Section: Introductionmentioning

confidence: 99%

Label-free screening of brain tissue myelin content using phase imaging with computational specificity (PICS)

Fanous

Shi

Caputo

et al. 2021

Preprint

View full text Add to dashboard Cite

Inadequate myelination in the central nervous system is associated with neurodevelopmental complications. Thus, quantitative, high spatial resolution measurements of myelin levels are highly desirable. We used spatial light interference microcopy (SLIM), a highly sensitive quantitative phase imaging (QPI) technique, to correlate the dry mass content of myelin in piglet brain tissue with dietary changes and gestational size. We combined SLIM micrographs with an AI classifying model that allows us to discern subtle disparities in myelin distributions with high accuracy. This concept of combining QPI label-free data with AI for the purpose of extracting molecular specificity has recently been introduced by our laboratory as phase imaging with computational specificity (PICS). Training on nine thousand SLIM images of piglet brain tissue with the 71-layer transfer learning model Xception, we created a two-parameter classification to differentiate gestational size and diet type with an accuracy of 82% and 80%, respectively. To our knowledge, this type of evaluation is impossible to perform by an expert pathologist or other techniques.

show abstract

Ontology-Aware Clinical Abstractive Summarization

Cited by 61 publications

References 12 publications

Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports

Optimizing the Factual Correctness of a Summary: A Study of Summarizing Radiology Reports

Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization

Label-free screening of brain tissue myelin content using phase imaging with computational specificity (PICS)

Contact Info

Product

Resources

About