Natural language processing in plastic surgery patient consultations

Abstract

Natural language processing (NLP) is the study of systems that allow machines to understand, interpret, and generate human language. With the advent of large language models (LLMs), non-technical industries can also harness the power of NLP. This includes healthcare, specifically surgical care and plastic surgery. This manuscript is an introductory review for plastic surgeons to understand the current state and future potential of NLP in patient consultations. The integration of NLP into plastic surgery patient consultations can transform both documentation and communication. These applications include information extraction, patient chart summarization, ambient transcription, coding, enhancing patient understanding, translation, and a patient-facing chatbot. We discuss the current progress toward building these applications and highlight their challenges. NLP has the potential to personalize care, enhance patient satisfaction, and improve workflows for plastic surgeons. Altogether, NLP can radically transform our current model of consultation into one that is more patient-centered.

Keywords

NLP / Large language models / GPT / transcription / coding / translation / literacy / Chatbot

References

[1] Huang K,Ranganath R.ClinicalBERT: modeling clinical notes and predicting hospital readmission.arXiv2019;arXiv:1904.05342Available from: http://arxiv.org/abs/1904.05342. [accessed 6 Jan 2025]

[2] Van Veen D,Blankemeier L.Clinical text summarization: adapting large language models can outperform human experts.Res Sq2023;rs.3.rs-3483777 PMCID:PMC10635391

[3] Epic and Microsoft bring GPT-4 to EHRs. Available from: https://www.epic.com/epic/post/epic-and-microsoft-bring-gpt-4-to-ehrs/. [Last accessed on 6 Jan 2025]

[4] Seu M,Pigott R.Trends and perceptions of electronic health record usage among plastic surgeons.Plast Reconstr Surg Glob Open2020;8:e2709 PMCID:PMC7209869

[5] Sinsky C,Li L.Allocation of physician time in ambulatory practice: a time and motion study in 4 specialties.Ann Intern Med2016;165:753-60

[6] Arndt BG,Watkinson MD.Tethered to the EHR: primary care physician workload assessment using EHR event log data and time-motion observations.Ann Fam Med2017;15:419-26 PMCID:PMC5593724

[7] Ambience. Available from: https://www.ambiencehealthcare.com/. [Last accessed on 6 Jan 2025]

[8] Nabla Copilot. Enjoy care again. Available from: https://www.nabla.com/. [Last accessed on 6 Jan 2025]

[9] Venkatesh KP,Kvedar JC.Automating the overburdened clinical coding system: challenges and next steps.NPJ Digit Med2023;6:16 PMCID:PMC9898522

[10] Kim BH.Read, attend, and code: pushing the limits of medical codes prediction from clinical notes by machines.arXiv2021;arXiv:2107.10650Available from: https://doi.org/10.48550/arXiv.2107.10650. [accessed 6 Jan 2025]

[11] Talwar AA,Broach RB,Fischer JP.Patient-reported outcomes: a primer for plastic surgeons.J Plast Reconstr Aesthet Surg2023;86:35-47

[12] Abdi S,Hawley M.Exploring the potential of emerging technologies to meet the care and support needs of older people: a Delphi survey.Geriatrics2021;6:19 PMCID:PMC8006038

[13] Nori H,McKinney SM,Horvitz E.Capabilities of GPT-4 on medical challenge problems.arXiv2023;arXiv:2303.13375Available from: https://doi.org/10.48550/arXiv.2303.13375. [accessed 6 Jan 2025]

[14] Singhal K,Tu T.Large language models encode clinical knowledge.arXiv2022;arXiv:2212.13138Available from: https://doi.org/10.48550/arXiv.2212.13138. [accessed 6 Jan 2025]

[15] Gajjar AA,Paliwoda ED.Usefulness and accuracy of artificial intelligence chatbot responses to patient questions for neurosurgical procedures. Neurosurgery. 2024.

[16] Karimov Z,Agayarov OY,Almuradova E.ChatGPT vs UpToDate: comparative study of usefulness and reliability of Chatbot in common clinical presentations of otorhinolaryngology-head and neck surgery.Eur Arch Otorhinolaryngol2024;281:2145-51 PMCID:PMC10942922

[17] Wu J,Li M.Clinical text datasets for medical artificial intelligence and large language models - a systematic review.NEJM AI2024;1:AIra2400012

[18] Shah SV.Accuracy, consistency, and hallucination of large language models when analyzing unstructured clinical notes in electronic medical records.JAMA Network Open2024;7:e2425953

[19] Beutel G,Kielstein JT.Artificial hallucination: GPT on LSD?.Crit Care2023;27:148 PMCID:PMC10114308

[20] Zaretsky J,Baskharoun S.Generative artificial intelligence to transform inpatient discharge summaries to patient-friendly language and format.JAMA Netw Open2024;7:e240357 PMCID:PMC10928500

[21] Kwong JCC,Nickel GC,Kvedar JC.The long but necessary road to responsible use of large language models in healthcare research.NPJ Digit Med2024;7:177 PMCID:PMC11224331

[22] Haider SA,Borna S.Evaluating large language model (LLM) performance on established breast classification systems.Diagnostics2024;14:1491 PMCID:PMC11275570

[23] Schmidl B,Pigorsch S.Assessing the use of the novel tool Claude 3 in comparison to ChatGPT 4.0 as an artificial intelligence tool in the diagnosis and therapy of primary head and neck cancer cases.Eur Arch Otorhinolaryngol2024;281:6099-109 PMCID:PMC11512878

[24] Kunze KN,Mazzucco M.The large language model ChatGPT-4 exhibits excellent triage capabilities and diagnostic performance for patients presenting with various causes of knee pain.Arthroscopy2024;In Press:

[25] Pressman SM,Gomez-Cabello CA,Forte AJ.AI in hand surgery: assessing large language models in the classification and management of hand injuries.J Clin Med2024;13:2832 PMCID:PMC11122623