Skip to main content

Foundation Models for Healthcare: Innovations in Generative AI, Computer Vision, Language Models, and Multimodal Systems

Cover image for Research Topic "Foundation Models for Healthcare: Innovations in Generative AI, Computer Vision, Language Models, and Multimodal Systems"
100kviews
Editorial26 November 2025
Editorial: Foundation models for healthcare: innovations in generative AI, computer vision, language models, and multimodal systems

Second, large language models are emerging as practical tools to generate realistic synthetic clinical data. to generate perioperative tabular datasets and found that most parameters' distributions were statistically similar to an open real dataset, suggesting LLM-based synthetic data could alleviate privacy and access bottlenecks for secondary analyses and method development. However, synthetic realism does not automatically equate clinical utility or bias-free data; rigorous validation is still required. • Clinical validation pathways: Fund and run prospective trials and real-world deployments (not only retrospective benchmarks) to verify clinical value and safety. • Explainability & human-in-the-loop design: Integrate clinicians in the loop and deploy explainability tools that matter for decision-making and error detection.

The Frontiers Research Topic brings together work that illustrates both the promise and the complexity of applying foundation models in healthcare. From zero-shot microscopy segmentation to LLM-driven synthetic data generation and multimodal prognostic systems, the field is moving rapidly. The path to clinical applications requires rigorous validation, improved evaluation frameworks, and multidisciplinary coordination among AI researchers, clinicians, ethicists, and regulators. The papers in this Topic are a valuable step forward and provide concrete starting points for the coordinated effort needed to translate foundation models into safe, equitable, and useful clinical tools.

2,745 views

1 citations

ORIGINAL RESEARCH
26 September 2025
Research on a machine learning method for predicting discharge time of thyroid cancer patients receiving 131I treatment: a retrospective study
Chen Zhang, 2 more and Feng Tian

5,353 views

3 citations

ORIGINAL RESEARCH
30 July 2025
Deep learning for vision screening in resource-limited settings: development of multi-branch CNN for refractive error detection based on smartphone image
Muhammad Syauqie, 3 more and Nila Djuwita Farieda Moeloek

3,776 views

3 citations

ORIGINAL RESEARCH
19 June 2025
Leveraging foundation models and goal-dependent annotations for automated cell confluence assessment
Maximilian Josef Joas, 3 more and Jan Ewald

3,073 views

1 citations

ORIGINAL RESEARCH
9 July 2025
Assessing the consistency of CT-based ventilation imaging under noise reduction processing with simulated quantum noise using a nonrigid alveoli phantom
Shin Miyakawa, 7 more and Tatsuya Fujisaki

1,794 views

1 citations

REVIEW
9 April 2025
CNN based 2D object detection techniques: a review
Badri Raj Lamichhane, 1 more and Teerayut Horanont

18,641 views

34 citations

BackgroundClinical data is instrumental to medical research, machine learning (ML) model development, and advancing surgical care, but access is often constrained by privacy regulations and missing data. Synthetic data offers a promising solution to preserve privacy while enabling broader data access. Recent advances in large language models (LLMs) provide an opportunity to generate synthetic data with reduced reliance on domain expertise, computational resources, and pre-training.ObjectiveThis study aims to assess the feasibility of generating realistic tabular clinical data with OpenAI’s GPT-4o using zero-shot prompting, and evaluate the fidelity of LLM-generated data by comparing its statistical properties to the Vital Signs DataBase (VitalDB), a real-world open-source perioperative dataset.MethodsIn Phase 1, GPT-4o was prompted to generate a dataset with qualitative descriptions of 13 clinical parameters. The resultant data was assessed for general errors, plausibility of outputs, and cross-verification of related parameters. In Phase 2, GPT-4o was prompted to generate a dataset using descriptive statistics of the VitalDB dataset. Fidelity was assessed using two-sample t-tests, two-sample proportion tests, and 95% confidence interval (CI) overlap.ResultsIn Phase 1, GPT-4o generated a complete and structured dataset comprising 6,166 case files. The dataset was plausible in range and correctly calculated body mass index for all case files based on respective heights and weights. Statistical comparison between the LLM-generated datasets and VitalDB revealed that Phase 2 data achieved significant fidelity. Phase 2 data demonstrated statistical similarity in 12/13 (92.31%) parameters, whereby no statistically significant differences were observed in 6/6 (100.0%) categorical/binary and 6/7 (85.71%) continuous parameters. Overlap of 95% CIs were observed in 6/7 (85.71%) continuous parameters.ConclusionZero-shot prompting with GPT-4o can generate realistic tabular synthetic datasets, which can replicate key statistical properties of real-world perioperative data. This study highlights the potential of LLMs as a novel and accessible modality for synthetic data generation, which may address critical barriers in clinical data access and eliminate the need for technical expertise, extensive computational resources, and pre-training. Further research is warranted to enhance fidelity and investigate the use of LLMs to amplify and augment datasets, preserve multivariate relationships, and train robust ML models.

12,419 views

48 citations

ORIGINAL RESEARCH
22 January 2025
Toward improving precision and complexity of transformer-based cost-sensitive learning models for plant disease detection
Manh-Tuan Do, 2 more and Oscal Tzyh-Chiang Chen

3,378 views

10 citations

ORIGINAL RESEARCH
20 December 2024
Multimodal MRI radiomics-based stacking ensemble learning model with automatic segmentation for prognostic prediction of HIFU ablation of uterine fibroids: a multicenter study
Bing Wen, 4 more and Fuqiang Zhou

3,120 views

13 citations

ORIGINAL RESEARCH
29 July 2024
Multimodal AI techniques for pain detection: integrating facial gesture and paralanguage analysis
Rommel Gutierrez, 1 more and William Villegas-Ch

6,218 views

21 citations