Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation

Shieh, Alexander Te-Wei; Chuang, Yung-Sung; Su, Shang‐Yu; Chen, Yun-Nung

doi:10.18653/v1/d19-6214

Cited by 3 publications

(3 citation statements)

References 16 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…4 5 Yet, they are limited to generating new text, without any focus on predicting subsequent text, which is one of the overarching capabilities of GPT in natural language generation. Current applications are toward creating synthetic clinical notes to increase data size, 6 generating summaries of medical trials, 7 and generating simplified clinical notes for patients. 8…”

Section: Introductionmentioning

confidence: 99%

Medical Text Prediction and Suggestion Using Generative Pretrained Transformer Models with Dental Medical Notes

et al. 2022

View full text Add to dashboard Cite

Background: Generative pre-trained transformer (GPT) models are one of the latest large pre-trained natural language processing (NLP) models, which enables model training with limited datasets, and reduces dependency on large datasets which are scarce and costly to establish and maintain. There is a rising interest to explore the use of GPT models in healthcare. Objective: We investigate the performance of GPT-2 and GPT-Neo models for medical text prediction using 374,787 free-text dental notes. Methods: We fine-tune pre-trained GPT-2 and GPT-Neo models for next word prediction on a dataset of over 374,000 manually written sections of dental clinical notes. Each model was trained on 80% of the dataset, validated on 10%, and tested on the remaining 10%. We report model performance in terms of next word prediction accuracy and loss. Additionally, we analyze the performance of the models on different types of prediction tokens for categories. For comparison, we also fine-tuned a non-GPT pre-trained neural network model, XLNet (large), for next word prediction. We annotate each token in 100 randomly sampled notes by category (e.g. Names, Abbreviations, Clinical Terms, Punctuation, etc.) and compare the performance of each model by token category. Results: Models present acceptable accuracy scores (GPT-2: 76%, GPT-Neo: 53%), and the GPT-2 model also performs better in manual evaluations, especially for names, abbreviations, and punctuation. Both GPT models outperformed XLNet in terms of accuracy. The results suggest that pre-trained models have the potential to assist medical charting in the future. We share the lessons learned, insights, and suggestions for future implementations. Conclusion: The results suggest that pre-trained models have the potential to assist medical charting in the future. Our study presented one of the first implementations of the GPT model used with medical notes.

show abstract

Section: Introductionmentioning

confidence: 99%

Medical Text Prediction and Suggestion Using Generative Pretrained Transformer Models with Dental Medical Notes

et al. 2022

View full text Add to dashboard Cite

show abstract

“…The impression is the most critical part of a radiology report, but the process of summarizing findings is normally time-consuming and could be prone to errors for inexperienced radiologists. Therefore, automatic impression generation (AIG) has drawn substantial attention in recent years, and there are many methods proposed in this area (Zhang et al, 2018;Gharebagh et al, 2020;MacAvaney et al, 2019;Shieh et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Graph Enhanced Contrastive Learning for Radiology Findings Summarization

Hu¹,

Li²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

The impression section of a radiology report summarizes the most prominent observation from the findings section and is the most important section for radiologists to communicate to physicians. Summarizing findings is time-consuming and can be prone to error for inexperienced radiologists, and thus automatic impression generation has attracted substantial attention. With the encoder-decoder framework, most previous studies explore incorporating extra knowledge (e.g., static pre-defined clinical ontologies or extra background information). Yet, they encode such knowledge by a separate encoder to treat it as an extra input to their models, which is limited in leveraging their relations with the original findings. To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i.e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation. In detail, for each input findings, it is encoded by a text encoder, and a graph is constructed through its entities and dependency tree. Then, a graph encoder (e.g., graph neural networks (GNNs)) is adopted to model relation information in the constructed graph. Finally, to emphasize the key words in the findings, contrastive learning is introduced to map positive samples (constructed by masking non-key words) closer and push apart negative ones (constructed by masking key words). The experimental results on OpenI and MIMIC-CXR confirm the effectiveness of our proposed method. 1

show abstract

“…Yet, they are limited to generating new text, without any focus on predicting subsequent text, which is one of the overarching capabilities of GPT in natural language generation. Current applications are towards creating synthetic clinical notes to increase data size 6 , generating summaries of medical trials 7 , and generating simplified clinical notes for patients 8 .…”

Section: Introductionmentioning

confidence: 99%

Medical text prediction and suggestion using generative pre-trained transformer models with dental medical notes

Sirriani

Sezgın

Claman

et al. 2022

Preprint

View full text Add to dashboard Cite

BackgroundGenerative pre-trained transformer (GPT) models are one of the latest large pre-trained natural language processing (NLP) models, which enables model training with limited datasets, and reduces dependency on large datasets which are scarce and costly to establish and maintain. There is a rising interest to explore the use of GPT models in healthcare.ObjectiveWe investigate the performance of GPT-2 and GPT-Neo models for medical text prediction using 374,787 free-text dental notes.MethodsWe fine-tune pre-trained GPT-2 and GPT-Neo models for next word prediction on a dataset of over 374,000 manually written sections of dental clinical notes. Each model was trained on 80% of the dataset, validated on 10%, and tested on the remaining 10%. We report model performance in terms of next word prediction accuracy and loss. Additionally, we analyze the performance of the models on different types of prediction tokens for categories. We annotate each token in 100 randomly sampled notes by category (e.g. Names, Abbreviations, Clinical Terms, Punctuation, etc.) and compare the performance of each model by token category.ResultsModels present acceptable accuracy scores (GPT-2: 76%, GPT-Neo: 53%), and the GPT-2 model also performs better in manual evaluations, especially for names, abbreviations, and punctuation. The results suggest that pre-trained models have the potential to assist medical charting in the future. We share the lessons learned, insights, and suggestions for future implementations.ConclusionThe results suggest that pre-trained models have the potential to assist medical charting in the future. Our study presented one of the first implementations of the GPT model used with medical notes.

show abstract

Towards Understanding of Medical Randomized Controlled Trials by Conclusion Generation

Cited by 3 publications

References 16 publications

Medical Text Prediction and Suggestion Using Generative Pretrained Transformer Models with Dental Medical Notes

Medical Text Prediction and Suggestion Using Generative Pretrained Transformer Models with Dental Medical Notes

Graph Enhanced Contrastive Learning for Radiology Findings Summarization

Medical text prediction and suggestion using generative pre-trained transformer models with dental medical notes

Contact Info

Product

Resources

About