The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
The future of healthcare using multimodal AI: Technology that can read, see, hear and sense
Open accessAbstract
With the emergence of large language models like ChatGPT, Artificial Intelligence (AI) has rapidly advanced, garnering widespread usage in various fields, including healthcare. This article explores the trajectory of AI in medicine, examining the transition from unimodal deep learning models to multimodal AI systems capable of processing diverse data formats. MM models that integrate text, images, and other sensory data, offer unprecedented capabilities, from providing comprehensive patient histories to aiding in differential diagnosis. However, ethical and security concerns accompany the use of extensive patient data. While multimodal models show promise, they are not infallible. By automating routine tasks, AI affords clinicians more time to focus on patient care, emphasizing the importance of human empathy and expertise in healthcare delivery. The article underscores the potential of multimodal AI in healthcare, provided it is developed and deployed responsibly with human clinical expertise.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Relying on a single modality risk overlooking critical information, whereas combining complementary signals enhances robustness, reduces the chance of diagnostic error, and can help mitigate bias by ensuring that predictions are not disproportionately dependent on a single data type (9).”
From The role of multimodality in clinical disease diagnosis: advances, challenges, and opportunities (2026) · cites this paper as [9]
Citations
Cites
Cascella, M., Montomoli, J., Bellini, V., & Bignami, E. (2023) · Journal of Medical Systems · doi:10.1007/s10916-023-01925-4 · Cited by 1,120
Diagnostic Accuracy of a Large Language Model in Pediatric Case Studies
Barile, J. G., Margolis, A., Cason, G., Kim, R., Kalash, S., Tchaconas, A., & Milanaik, R. L. (2024) · Archives of Pediatrics and Adolescent Medicine · doi:10.1001/jamapediatrics.2023.5750 · Cited by 101
Cited by
The role of multimodality in clinical disease diagnosis: advances, challenges, and opportunities
Nawaz, A., Edinat, A., Rana, M. R. R., Ali, T., Mustafa, G., Tahir, S., & Lee, S. W. (2026) · Frontiers in public health · doi:10.3389/fpubh.2026.1788454 · Cited by 3
“Relying on a single modality risk overlooking critical information, whereas combining complementary signals enhances robustness, reduces the chance of diagnostic error, and can help mitigate bias by ensuring that predictions are not disproportionately dependent on a single data type (9).”
Metadata
- Authors
- Rao, D.
- Affiliations
- Manipal Academy of Higher Education (IN)
- Corresponding author
- Rao, Divya
- ORCID
- Rao, Divya
- Venue
- Oral Oncology Reports
- Publisher
- Elsevier BV
- Published
- 2024-06
- Volume
- 10
- Pages
- 100340
- ISSN
- 2772-9060 (ISSN-L)
- OpenAlex
- W4394859564
- Cited by
- 12
- References
- 2
- Citations by year
- 2026: 5 · 2025: 6 · 2024: 1
- FWCI
- 1.14
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Oral Oncology Reports (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- 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
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
- Keywords
- multimodal AI, large language models, ChatGPT, artificial intelligence in healthcare, differential diagnosis, medical history, patient data privacy, ethical considerations, clinical decision support, automation of routine tasks, oral oncology
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
