Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures

Joshi, Anirudh; Katariya, Namit; Amatriain, Xavier; Kannan, Anitha

doi:10.48550/arxiv.2009.08666

Cited by 5 publications

(15 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite its simplicity, it is effective at improving performance according to both automatic evaluation and human inspection (Section 4.1-4.3) when compared to the baseline approach of simply truncating the input. We also observe good generalization of our fine-tuned models across medical domains and conversation lengths, as shown by example conversations from other papers tackling the same task such as Krishna et al (2020) and Joshi et al (2020) (Section A.4). These examples also show the superior quality of our generated summaries.…”

Section: Introductionsupporting

confidence: 61%

“…Generalization As a qualitative comparison with similar work in the field of medical dialogue summarization, we run inference with our finetuned models on conversations copied from Krishna et al (2020) and Joshi et al (2020)…”

Section: Human Evaluationmentioning

confidence: 99%

“…Krishna et al (2020) attempted the generation of complete SOAP note from doctorpatient conversations by first extracting and clustering noteworthy utterances and then leveraging LSTM and transformer models to generate single sentence summary from each cluster. Joshi et al (2020) showed that quality of generated summaries can be improved by encouraging copying in pointergenerator network and they also proposed alternative metrics to ROUGE for measuring the medical information coverage. There is also research to address the problems of using ROUGE for evaluating summary quality in the medical domain: Zhang et al (2019b) explored improving factual correctness of summaries by optimizing ROUGE and concept-based metrics directly as rewards in a reinforcement learning framework of training their summarization model, although a significant difference from our work is that their task was the summarization of radiology reports instead of medical dialogues.…”

Section: Long Text Summarizationmentioning

confidence: 99%

“…Figure A.7-A.8 display summaries generated on example conversations from (Krishna et al, 2020) and (Joshi et al, 2020).…”

Section: A4 Inference On Out-of-dataset Examplesmentioning

confidence: 99%

“…She had her thyroid panel checked last week. (Joshi et al, 2020). Text with green highlighting shows medical findings common in both summaries.…”

Section: Reference (Other)mentioning

confidence: 99%

See 4 more Smart Citations

Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations

Zhang¹,

Negrinho

Ghosh³

et al. 2021

Preprint

View full text Add to dashboard Cite

Fine-tuning pretrained models for automatically summarizing doctor-patient conversation transcripts presents many challenges: limited training data, significant domain shift, long and noisy transcripts, and high target summary variability. In this paper, we explore the feasibility of using pretrained transformer models for automatically summarizing doctorpatient conversations directly from transcripts. We show that fluent and adequate summaries can be generated with limited training data by fine-tuning BART on a specially constructed dataset. The resulting models greatly surpass the performance of an average human annotator and the quality of previous published work for the task. We evaluate multiple methods for handling long conversations, comparing them to the obvious baseline of truncating the conversation to fit the pretrained model length limit. We introduce a multistage approach that tackles the task by learning two finetuned models: one for summarizing conversation chunks into partial summaries, followed by one for rewriting the collection of partial summaries into a complete summary 1 . Using a carefully chosen fine-tuning dataset, this method is shown to be effective at handling longer conversations, improving the quality of generated summaries. We conduct both an automatic evaluation (through ROUGE and two concept-based metrics focusing on medical findings) and a human evaluation (through qualitative examples from literature, assessing hallucination, generalization, fluency, and general quality of the generated summaries).

show abstract

Section: Introductionsupporting

confidence: 61%

Section: Human Evaluationmentioning

confidence: 99%

Section: Long Text Summarizationmentioning

confidence: 99%

“…Figure A.7-A.8 display summaries generated on example conversations from (Krishna et al, 2020) and (Joshi et al, 2020).…”

Section: A4 Inference On Out-of-dataset Examplesmentioning

confidence: 99%

“…She had her thyroid panel checked last week. (Joshi et al, 2020). Text with green highlighting shows medical findings common in both summaries.…”

Section: Reference (Other)mentioning

confidence: 99%

See 3 more Smart Citations

Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations

Zhang¹,

Negrinho

Ghosh³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

Utility of ChatGPT in Clinical Practice

Liu¹,

Wang²,

Liu³

2023

J Med Internet Res

242

View full text Add to dashboard Cite

ChatGPT is receiving increasing attention and has a variety of application scenarios in clinical practice. In clinical decision support, ChatGPT has been used to generate accurate differential diagnosis lists, support clinical decision-making, optimize clinical decision support, and provide insights for cancer screening decisions. In addition, ChatGPT has been used for intelligent question-answering to provide reliable information about diseases and medical queries. In terms of medical documentation, ChatGPT has proven effective in generating patient clinical letters, radiology reports, medical notes, and discharge summaries, improving efficiency and accuracy for health care providers. Future research directions include real-time monitoring and predictive analytics, precision medicine and personalized treatment, the role of ChatGPT in telemedicine and remote health care, and integration with existing health care systems. Overall, ChatGPT is a valuable tool that complements the expertise of health care providers and improves clinical decision-making and patient care. However, ChatGPT is a double-edged sword. We need to carefully consider and study the benefits and potential dangers of ChatGPT. In this viewpoint, we discuss recent advances in ChatGPT research in clinical practice and suggest possible risks and challenges of using ChatGPT in clinical practice. It will help guide and support future artificial intelligence research similar to ChatGPT in health.

show abstract

ChatGPT in Occupational Medicine: A Comparative Study with Human Experts

Padovan,

Cosci,

Petillo

et al. 2024

Bioengineering

View full text Add to dashboard Cite

The objective of this study is to evaluate ChatGPT’s accuracy and reliability in answering complex medical questions related to occupational health and explore the implications and limitations of AI in occupational health medicine. The study also provides recommendations for future research in this area and informs decision-makers about AI’s impact on healthcare. A group of physicians was enlisted to create a dataset of questions and answers on Italian occupational medicine legislation. The physicians were divided into two teams, and each team member was assigned a different subject area. ChatGPT was used to generate answers for each question, with/without legislative context. The two teams then evaluated human and AI-generated answers blind, with each group reviewing the other group’s work. Occupational physicians outperformed ChatGPT in generating accurate questions on a 5-point Likert score, while the answers provided by ChatGPT with access to legislative texts were comparable to those of professional doctors. Still, we found that users tend to prefer answers generated by humans, indicating that while ChatGPT is useful, users still value the opinions of occupational medicine professionals.

show abstract

Dr. Summarize: Global Summarization of Medical Dialogue by Exploiting Local Structures

Cited by 5 publications

References 0 publications

Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations

Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations

Utility of ChatGPT in Clinical Practice

ChatGPT in Occupational Medicine: A Comparative Study with Human Experts

Contact Info

Product

Resources

About