Improving Primary Healthcare Workflow Using Extreme Summarization of
Scientific Literature Based on Generative AI
- URL: http://arxiv.org/abs/2307.15715v1
- Date: Mon, 24 Jul 2023 21:42:27 GMT
- Title: Improving Primary Healthcare Workflow Using Extreme Summarization of
Scientific Literature Based on Generative AI
- Authors: Gregor Stiglic, Leon Kopitar, Lucija Gosak, Primoz Kocbek, Zhe He,
Prithwish Chakraborty, Pablo Meyer, Jiang Bian
- Abstract summary: Our objective is to investigate the potential of generative artificial intelligence in diminishing the cognitive load experienced by practitioners.
Our research demonstrates that the use of generative AI for literature review is efficient and effective.
- Score: 8.901148687545103
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Primary care professionals struggle to keep up to date with the latest
scientific literature critical in guiding evidence-based practice related to
their daily work. To help solve the above-mentioned problem, we employed
generative artificial intelligence techniques based on large-scale language
models to summarize abstracts of scientific papers. Our objective is to
investigate the potential of generative artificial intelligence in diminishing
the cognitive load experienced by practitioners, thus exploring its ability to
alleviate mental effort and burden. The study participants were provided with
two use cases related to preventive care and behavior change, simulating a
search for new scientific literature. The study included 113 university
students from Slovenia and the United States randomized into three distinct
study groups. The first group was assigned to the full abstracts. The second
group was assigned to the short abstracts generated by AI. The third group had
the option to select a full abstract in addition to the AI-generated short
summary. Each use case study included ten retrieved abstracts. Our research
demonstrates that the use of generative AI for literature review is efficient
and effective. The time needed to answer questions related to the content of
abstracts was significantly lower in groups two and three compared to the first
group using full abstracts. The results, however, also show significantly lower
accuracy in extracted knowledge in cases where full abstract was not available.
Such a disruptive technology could significantly reduce the time required for
healthcare professionals to keep up with the most recent scientific literature;
nevertheless, further developments are needed to help them comprehend the
knowledge accurately.
Related papers
- ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models [56.08917291606421]
ResearchAgent is a large language model-powered research idea writing agent.
It generates problems, methods, and experiment designs while iteratively refining them based on scientific literature.
We experimentally validate our ResearchAgent on scientific publications across multiple disciplines.
arXiv Detail & Related papers (2024-04-11T13:36:29Z) - A survey of recent methods for addressing AI fairness and bias in
biomedicine [48.46929081146017]
Artificial intelligence systems may perpetuate social inequities or demonstrate biases, such as those based on race or gender.
We surveyed recent publications on different debiasing methods in the fields of biomedical natural language processing (NLP) or computer vision (CV)
We performed a literature search on PubMed, ACM digital library, and IEEE Xplore of relevant articles published between January 2018 and December 2023 using multiple combinations of keywords.
We reviewed other potential methods from the general domain that could be applied to biomedicine to address bias and improve fairness.
arXiv Detail & Related papers (2024-02-13T06:38:46Z) - Neural Causal Abstractions [63.21695740637627]
We develop a new family of causal abstractions by clustering variables and their domains.
We show that such abstractions are learnable in practical settings through Neural Causal Models.
Our experiments support the theory and illustrate how to scale causal inferences to high-dimensional settings involving image data.
arXiv Detail & Related papers (2024-01-05T02:00:27Z) - Generative AI in Writing Research Papers: A New Type of Algorithmic Bias
and Uncertainty in Scholarly Work [0.38850145898707145]
Large language models (LLMs) and generative AI tools present challenges in identifying and addressing biases.
generative AI tools are susceptible to goal misgeneralization, hallucinations, and adversarial attacks such as red teaming prompts.
We find that incorporating generative AI in the process of writing research manuscripts introduces a new type of context-induced algorithmic bias.
arXiv Detail & Related papers (2023-12-04T04:05:04Z) - De-identification of clinical free text using natural language
processing: A systematic review of current approaches [48.343430343213896]
Natural language processing has repeatedly demonstrated its feasibility in automating the de-identification process.
Our study aims to provide systematic evidence on how the de-identification of clinical free text has evolved in the last thirteen years.
arXiv Detail & Related papers (2023-11-28T13:20:41Z) - Experimental Evidence on Negative Impact of Generative AI on Scientific
Learning Outcomes [0.0]
Using AI for summarization significantly improved both quality and output.
Individuals with a robust background in the reading topic and superior reading/writing skills benefitted the most.
arXiv Detail & Related papers (2023-09-23T21:59:40Z) - The Role of AI in Drug Discovery: Challenges, Opportunities, and
Strategies [97.5153823429076]
The benefits, challenges and drawbacks of AI in this field are reviewed.
The use of data augmentation, explainable AI, and the integration of AI with traditional experimental methods are also discussed.
arXiv Detail & Related papers (2022-12-08T23:23:39Z) - Modular Self-Supervision for Document-Level Relation Extraction [17.039775384229355]
We propose decomposing document-level relation extraction into relation detection and argument resolution.
We conduct a thorough evaluation in biomedical machine reading for precision oncology, where cross-paragraph relation mentions are prevalent.
Our method outperforms prior state of the art, such as multi-scale learning and graph neural networks, by over 20 absolute F1 points.
arXiv Detail & Related papers (2021-09-11T20:09:18Z) - Low Resource Recognition and Linking of Biomedical Concepts from a Large
Ontology [30.324906836652367]
PubMed, the most well known database of biomedical papers, relies on human curators to add these annotations.
Our approach achieves new state-of-the-art results for the UMLS in both traditional recognition/linking and semantic indexing-based evaluation.
arXiv Detail & Related papers (2021-01-26T06:41:12Z) - What's New? Summarizing Contributions in Scientific Literature [85.95906677964815]
We introduce a new task of disentangled paper summarization, which seeks to generate separate summaries for the paper contributions and the context of the work.
We extend the S2ORC corpus of academic articles by adding disentangled "contribution" and "context" reference labels.
We propose a comprehensive automatic evaluation protocol which reports the relevance, novelty, and disentanglement of generated outputs.
arXiv Detail & Related papers (2020-11-06T02:23:01Z) - Automatic Text Summarization of COVID-19 Medical Research Articles using
BERT and GPT-2 [8.223517872575712]
We take advantage of the recent advances in pre-trained NLP models, BERT and OpenAI GPT-2.
Our model provides abstractive and comprehensive information based on keywords extracted from the original articles.
Our work can help the the medical community, by providing succinct summaries of articles for which the abstract are not already available.
arXiv Detail & Related papers (2020-06-03T00:54:44Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.