CoChat
Sign Up
Cited by 324Artificial Intelligence in Healthcare and EducationMultimodal Machine Learning ApplicationsDental Radiography and Imaging

The DOI matches its Crossref record; 120 of the 120 references it cites were found in a registry or an index.

ChatGPT for shaping the future of dentistry: the potential of multi-modal large language model

Open access
Huang, Hanyao, Zheng, Ou, Wang, Dongdong, Yin, Jiayi, Wang, Zijin, Ding, Shengxuan, Yin, Heng, Xu, Chuan, Yang, Renjie, Zheng, Qian, Shi, Bing·2023·International Journal of Oral Science
DOI 10.1038/s41368-023-00239-yPMC PMC10382494
Open this paper in CoChat — free accountOpen PDF

Abstract

The ChatGPT, a lite and conversational variant of Generative Pretrained Transformer 4 (GPT-4) developed by OpenAI, is one of the milestone Large Language Models (LLMs) with billions of parameters. LLMs have stirred up much interest among researchers and practitioners in their impressive skills in natural language processing tasks, which profoundly impact various fields. This paper mainly discusses the future applications of LLMs in dentistry. We introduce two primary LLM deployment methods in dentistry, including automated dental diagnosis and cross-modal dental diagnosis, and examine their potential applications. Especially, equipped with a cross-modal encoder, a single LLM can manage multi-source data and conduct advanced natural language reasoning to perform complex clinical operations. We also present cases to demonstrate the potential of a fully automatic Multi-Modal LLM AI system for dentistry clinical application. While LLMs offer significant potential benefits, the challenges, such as data privacy, data quality, and model bias, need further study. Overall, LLMs have the potential to revolutionize dental diagnosis and treatment, which indicates a promising avenue for clinical application and research in dentistry.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41368-023-00239-y

Cites

120 of 120 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Examples of a text mining application for extracting a patient’s historical record with an LLM like ChatGPT. Keywords are highlighted in red
Fig. 1 Examples of a text mining application for extracting a patient’s historical record with an LLM like ChatGPT. Keywords are highlighted in redCC BY · PubMed Central
Fig. 2 Examples of natural language reasoning (NLR) application of medication suggestions derived from a patient’s record. Keywords are highlighted in red
Fig. 2 Examples of natural language reasoning (NLR) application of medication suggestions derived from a patient’s record. Keywords are highlighted in redCC BY · PubMed Central
Fig. 3 Example of a narrative output of the Patient’s record generated from keywords with NLG
Fig. 3 Example of a narrative output of the Patient’s record generated from keywords with NLGCC BY · PubMed Central
Fig. 4 Framework of generating synthetic quasi-EHRs data by LLMs
Fig. 4 Framework of generating synthetic quasi-EHRs data by LLMsCC BY · PubMed Central
Fig. 5 Schematic of dental condition diagnosis with a vision-language model of ALBEF
Fig. 5 Schematic of dental condition diagnosis with a vision-language model of ALBEFCC BY · PubMed Central
Fig. 6 A VQA example framework with the assistance of BLIP-2
Fig. 6 A VQA example framework with the assistance of BLIP-2CC BY · PubMed Central
Fig. 7 2D semantic segmentation with 3D reconstruction for lesion identification
Fig. 7 2D semantic segmentation with 3D reconstruction for lesion identificationCC BY · PubMed Central
Fig. 8 Example of visual data generation
Fig. 8 Example of visual data generationCC BY · PubMed Central
Fig. 9 Example of the audio waveform and spectrogram analysis in speaking a “baba” and b “mama” with TorchAudio of normal people and patients with velopharyngeal insufficiency
Fig. 9 Example of the audio waveform and spectrogram analysis in speaking a “baba” and b “mama” with TorchAudio of normal people and patients with velopharyngeal insufficiencyCC BY · PubMed Central
Fig. 10 Schematic of audio-language assisted diagnosis based upon audio waveform and spectrogram analysis with TorchAudio
Fig. 10 Schematic of audio-language assisted diagnosis based upon audio waveform and spectrogram analysis with TorchAudioCC BY · PubMed Central
Fig. 11 Concept of automatic multi-modal LLM AI system for dentistry application
Fig. 11 Concept of automatic multi-modal LLM AI system for dentistry applicationCC BY · PubMed Central
Fig. 12 Application of the multi-modal LLM AI system in dental caries
Fig. 12 Application of the multi-modal LLM AI system in dental cariesCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 3

  1. Choi, E., Xiao, C., Stewart, W. & Sun, J. MiME: multilevel medical embedding of electronic health records for predictive healthcare. Adv. Neural Inf. Process. Syst. 31, 19 (2018).
  2. Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A. & Sutskever, I. Zero-shot text-to-image generation. In International Conference on Machine Learning, pp. 8821–8831 (PMLR, 2021).
  3. Gurram, S., Chan, D., Fang, A., & Canny, J. LAVA: Language Audio Vision Alignment for Data-Efficient Video Pre-Training. In First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML (2023).

Cited by

Sorted by citations

See all 324

Related

See all

Metadata

Authors
Huang, H., Zheng, O., Wang, D., Yin, J., Wang, Z., Ding, S., Yin, H., Xu, C., Yang, R., Zheng, Q., & Shi, B.
Affiliations
  • Sichuan University (CN)
  • University of Central Florida (US)
  • Southwest Jiaotong University (CN)
Corresponding author
  • Huang, Hanyao
  • Zheng, Ou
ORCID
Venue
International Journal of Oral Science
Publisher
Springer Science and Business Media LLC
Published
2023-07-28
Volume
15
Issue
1
Pages
29-29
ISSN
  • 1674-2818 (ISSN-L)
  • 2049-3169
DOI
10.1038/s41368-023-00239-y
PMC
PMC10382494
OpenAlex
W4385346108
Cited by
324
References
97
Citations by year
2026: 68 · 2025: 119 · 2024: 107 · 2023: 30
FWCI
3.81
Type
journal article
Language
en
Open access
Licence
Locations
  • International Journal of Oral Science (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • arXiv (Cornell University) (cc-by)
Funders
  • Sichuan Provincial Postdoctoral Science Foundation (TB2022005)
  • Sichuan University (RD-02-202107)
  • Sichuan Province Science and Technology Support Program (2022NSFSC0743)
  • West China Hospital, Sichuan University
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Health Sciences › Dentistry › Oral Surgery › Dental Radiography and Imaging
Keywords
ChatGPT, large language models, multimodal large language models, dental diagnosis, automated diagnosis, natural language reasoning, clinical decision support, data privacy, model bias, data quality
MeSH terms
Artificial Intelligence, Dentistry

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review