Transformer-Based Abstract Generation of Medical Case Reports
Anusha Verma Chandraju1, Lydia J Gnanasigamani2
1Anusha Verma Chandraju, SCOPE, Vellore Institute of Technology, Vellore, India.
2Lydia J Gnanasigamani, SCOPE, Vellore Institute of Technology, Vellore, India.
Manuscript received on 29 September 2022 | Revised Manuscript received on 07 October 2022 | Manuscript Accepted on 15 October 2022 | Manuscript published on 30 October 2022 | PP: 110-113 | Volume-12 Issue-1, October 2022 | Retrieval Number: 100.1/ijeat.A38531012122 | DOI: 10.35940/ijeat.A3853.1012122
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: A medical case report gives medical researchers and healthcare providers a thorough account of the symptoms, treatment, and diagnosis of a specific patient. This clinical data is essential because they aid in diagnosing novel or uncommon illnesses, analyzing specific medical occurrences, and enhancing knowledge of current medical education. The summary of the medical case report is needed so that one can decide on further reading as going through the entire contents of a medical case report istime-consuming. In this paper, we present a deep learning methodology for the generation of the automatic summaries of the medical case reports. The final proposed fine-tuned summarizer on the test data set generated a mean precision of 0.4481 and Rouge-1 Score of 0.2803.
Keywords: Transformers, Healthcare, Extractive Summarization, Abstractive Summarization, Medical Research
Scope of the Article: Healthcare Informatics