ABSTRACT
Large Language Models (LLMs) based on pretrained transformer architectures, such as Generative Pretrained Transformer 4 (GPT-4) from OpenAI, are on the cutting age of artificial intelligence research. Along with generating abundant academic literature, these models are the basis of numerous practical systems widely utilized by end users and organizations. In healthcare information systems, there are many case studies and research prototypes demonstrating the promise of applying GPT-like programs to numerous practical natural language processing tasks. At the same time, current limitations of LLMs prevent their safe deployments in professional environments. In this study, we give an overview of capabilities, limitations, and risks associated with current iterations of LLMs. We provide an overview of literature on using LLMs in healthcare context. Finally, we present a framework of generic healthcare IT system utilizing LLMs, and discuss avenues for future research.
- Lameck Mbangula Amugongo, Alexander Kriebitz, Auxane Boch, and Christoph Lütge. 2023. Operationalising AI Ethics Through The Agile Software Development Lifecycle: A Case Study Of AI-enabled Mobile Health Applications. AI Ethics (2023). https://doi.org/10.1007/s43681-023-00331-3Google ScholarCross Ref
- Kriti Bhattarai, Inez Y Oh, Jonathan M Sierra, Philip R Payne, Zachary B Abrams, and Albert M Lai. 2023. Leveraging GPT-4 for Identifying Clinical Phenotypes in Electronic Health Records: A Performance Comparison between GPT-4, GPT-3.5-turbo and spaCy's Rule-based & Machine Learning-based Methods. bioRxiv (2023), 2023--09.Google Scholar
- Chia-Chun Chiang, Man Luo, Gina Dumkrieger, Shubham Trivedi, Yi-Chieh Chen, Chieh-Ju Chao, Todd J Schwedt, Abeed Sarker, and Imon Banerjee. 2023. A Large Language Model-Based Generative Natural Language Processing Framework Finetuned on Clinical Notes Accurately Extracts Headache Frequency from Electronic Health Records. medRxiv (2023).Google ScholarCross Ref
- Bharath Chintagunta, Namit Katariya, Xavier Amatriain, and Anitha Kannan. 2021. Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization. In Machine Learning for Healthcare Conference. PMLR, Virtual, 354--372.Google ScholarCross Ref
- Corti. [n.d.]. AI-Powered Patient Triaging. https://www.corti.ai/solutions/engageGoogle Scholar
- Sabyasachi Dash, Sushil Kumar Shakyawar, Mohit Sharma, and Sandeep Kaushik. 2019. Big Data in Healthcare: Management, Analysis and Future Prospects. Journal of Big Data 6, 1 (2019), 1--25.Google ScholarCross Ref
- Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805 (2018).Google Scholar
- Luciano Floridi and Massimo Chiriatti. 2020. GPT-3: Its Nature, Scope, Limits, and Consequences. Minds and Machines 30 (2020), 681--694.Google ScholarDigital Library
- Alexandre Goossens and Jan Vanthienen. 2023. Integrating GPT-Technologies with Decision Models for Explainability. In World Conference on Explainable Artificial Intelligence. Springer Nature Switzerland, 428--448.Google Scholar
- Claudia E Haupt and Mason Marks. 2023. AI-generated Medical Advice---GPT and Beyond. Jama 329, 16 (2023), 1349--1350.Google ScholarCross Ref
- Anne-Christin Hauschild, Roman Martin, Sabrina Celine Holst, Joachim Wienbeck, and Dominik Heider. 2022. Guideline for Software Life Cycle in Health Informatics. iScience 25, 12 (2022).Google Scholar
- Jasper. 2020. The 16 Best GPT-3 Tools To Help You Write Faster. https://www.jasper.ai/blog/gpt3-toolsGoogle Scholar
- Virapat Kieuvongngam, Bowen Tan, and Yiming Niu. 2020. Automatic Text Summarization of COVID-19 Medical Research Articles Using BERT and GPT-2. arXiv preprint arXiv:2006.01997 (2020).Google Scholar
- Richard Lenz and Klaus A Kuhn. 2004. Towards a Continuous Evolution and Adaptation of Information Systems in Healthcare. International Journal of Medical Informatics 73, 1 (2004), 75--89.Google ScholarCross Ref
- Donald Macfarlane. 2023. Professional Report Generation Using Lexeme Theories and OpenAI's Generative Pretrained Transformer, GPT-4: A Comparison. Medical Research Archives 11, 11 (2023).Google ScholarCross Ref
- N Mathai, MF Shiratudin, and F Sohel. 2017. Electronic Health Record Management: Expectations, Issues, and Challenges. Journal of Health & Medical Informatics 8, 3 (2017).Google Scholar
- Majid Moshirfar, Amal W Altaf, Isabella M Stoakes, Jared J Tuttle, and Phillip C Hoopes. 2023. Artificial Intelligence in Ophthalmology: A Comparative Analysis of GPT-3.5, GPT-4, and Human Expertise in Answering StatPearls Questions. Cureus 15, e40822 (2023).Google Scholar
- A Maria Nancy and R Maheswari. 2020. A Review on Unstructured Data in Medical Data. J. Crit. Rev. 7 (2020), 2202--2208.Google Scholar
- BBC News. 2023. ChatGPT Banned in Italy over Privacy Concerns. (April 1 2023).Google Scholar
- OpenAI. [n. d.]. ChatGPT. https://openai.com/Google Scholar
- OpenAI. 2020. GPT-3 Powers the Next Generation of Apps. https://openai.com/blog/gpt-3-apps/Google Scholar
- Carl Preiksaitis and Christian Rose. 2023. Opportunities, Challenges, and Future Directions of Generative Artificial Intelligence in Medical Education: Scoping Review. JMIR Medical Education 9 (2023), e48785.Google ScholarCross Ref
- R. Rada (Ed.). 2007. Information Systems and Healthcare Enterprises. IGI Global.Google Scholar
- Alec Radford, Rafal Jozefowicz, and Ilya Sutskever. 2017. Learning to Generate Reviews and Discovering Sentiment. arXiv preprint arXiv:1704.01444 (2017).Google Scholar
- Alec Radford, Karthik Narasimhan, Tim Salimans, and Ilya Sutskever. 2018. Improving Language Understanding with Unsupervised Learning. Technical Report.Google Scholar
- Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, Ilya Sutskever, et al. 2019. Language Models are Unsupervised Multitask Learners. Technical Report.Google Scholar
- Emre Sezgin, Joseph Sirrianni, and Simon L Linwood. 2022. Operationalizing and Implementing Pretrained, Large Artificial Intelligence Models in the US Health Care System: Outlook of Generative Pretrained Transformer 3 (GPT-3) as a Service Model. JMIR medical informatics 10, 2 (2022), e32875.Google Scholar
- Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and Efficient Foundation Language Models. Technical Report.Google Scholar
- Thomas Vakili and Hercules Dalianis. 2021. Are Clinical BERT Models Privacy Preserving? The Difficulty of Extracting Patient-Condition Associations. In HUMAN@ AAAI Fall Symposium.Google Scholar
- Michael R Waters, Sanjay Aneja, and Julian C Hong. 2023. Unlocking the Power of ChatGPT, Artificial Intelligence, and Large Language Models: Practical Suggestions for Radiation Oncologists. Practical Radiation Oncology 13, 6 (2023), e484-e490.Google ScholarCross Ref
- Xiaodong Wu, Ran Duan, and Jianbing. Ni. 2023. Unveiling Security, Privacy, and Ethical Concerns of ChatGPT. Journal of Information and Intelligence (2023).Google Scholar
- Qianqian Xie, Edward J Schenck, He S Yang, Yong Chen, Yifan Peng, and Fei Wang. 2023. Faithful AI in Healthcare and Medicine. medRxiv (2023), 2023--04.Google Scholar
- Jiacheng Yang, Mingxuan Wang, Hao Zhou, Chengqi Zhao, Weinan Zhang, Yong Yu, and Lei Li. 2020. Towards Making the Most of bert in Neural Machine Translation. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34. New York, USA, 9378--9385.Google ScholarCross Ref
- Travis Zack, Eric Lehman, Mirac Suzgun, Jorge A Rodriguez, Leo Anthony Celi, Judy Gichoya, Dan Jurafsky, Peter Szolovits, David W Bates, Raja-Elie E Abdulnour, et al. 2024. Assessing the Potential of GPT-4 to Perpetuate Racial and Gender Biases in Health Care: a Model Evaluation Study. The Lancet Digital Health 6, 1 (2024), e12-e22.Google ScholarCross Ref
- Peng Zhang and Maged N Kamel Boulos. 2023. Generative AI in Medicine and Healthcare: Promises, Opportunities and Challenges. Future Internet 15, 9 (2023), 286.Google ScholarCross Ref
Index Terms
- Promise and Challenges of Generative AI in Healthcare Information Systems
Recommendations
The Use of Health Information Technology in Ambulatory Surgery Centers
HICSS '14: Proceedings of the 2014 47th Hawaii International Conference on System SciencesMany of the more than 1.2 billion ambulatory care visits in the United States in 2011 resulted in a patient being handed-off from one outpatient provider to another. As patients transition from one outpatient provider to another, information gaps ...
Healthcare information system: a facilitator of primary care for underprivileged elderly via mobile clinic
ICSH'13: Proceedings of the 2013 international conference on Smart HealthAgeing is a global challenge. As health conditions gradually deteriorate, elders are prone to suffering from multiple chronic diseases. The impact of ageing on the heath system is therefore unprecedented. Primary and preventive care is important to ...
Large language models for qualitative research in software engineering: exploring opportunities and challenges
AbstractThe recent surge in the integration of Large Language Models (LLMs) like ChatGPT into qualitative research in software engineering, much like in other professional domains, demands a closer inspection. This vision paper seeks to explore the ...
Comments