Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2025 Mar 26;17(3):e81243.
doi: 10.7759/cureus.81243. eCollection 2025 Mar.

Inspired Spine Smart Universal Resource Identifier (SURI): An Adaptive AI Framework for Transforming Multilingual Speech Into Structured Medical Reports

Jiawen Zhan  1 , Dominic Moore  2 , Yuanzhe Lu  3 , Hamid Abbasi  4
Affiliations

Inspired Spine Smart Universal Resource Identifier (SURI): An Adaptive AI Framework for Transforming Multilingual Speech Into Structured Medical Reports

Jiawen Zhan et al. Cureus. .

Abstract

Medical documentation is a major part of delivering healthcare worldwide and is gaining more importance in developing countries as well. The global spread of multilingual communities in medical documentation poses unique challenges, particularly regarding maintaining accuracy and consistency across diverse languages. Inspired Spine Smart Universal Resource Identifier (SURI), an adaptive artificial intelligence (AI) framework, addresses these challenges by transforming multilingual speech into structured medical reports. Utilizing state-of-the-art automatic speech recognition (ASR) and natural language processing (NLP) technologies, SURI converts doctor-patient dialogues into detailed clinical documentation. This paper presents SURI's development, focusing on its multilingual capabilities, effective report generation, and continuous improvement through real-time feedback. Our evaluation indicates a 60% reduction in documentation errors and a 70% decrease in time spent on medical reporting compared to traditional methods. SURI not only provides a practical solution to a pressing issue in healthcare but also sets a benchmark for integrating AI into medical communication workflows.

Keywords: artificial intelligence in medicine; dictation software; language interpretation services; large language model(llm); multilingual; patient encounter.

PubMed Disclaimer

Conflict of interest statement

Human subjects: All authors have confirmed that this study did not involve human participants or tissue. Animal subjects: All authors have confirmed that this study did not involve animal subjects or tissue. Conflicts of interest: In compliance with the ICMJE uniform disclosure form, all authors declare the following: Payment/services info: All authors have declared that no financial support was received from any organization for the submitted work. Financial relationships: All authors have declared that they have no financial relationships at present or within the previous three years with any organizations that might have an interest in the submitted work. Other relationships: All authors have declared that there are no other relationships or activities that could appear to have influenced the submitted work.

Figures

Figure 1
Figure 1. Distribution of all AI-generated medical records samples by modification percentage: This histogram categorizes documents based on the percentage of modifications required, grouped in 10% increments. It visually represents the number of documents that required different levels of changes, highlighting the frequency of minimal, moderate, and extensive modifications.
Image Credits: Jiawen Zhan
Figure 2
Figure 2. A sample workflow in text illustrating Inspired Spine Smart Universal Resource Identifier’s transcription and documentation process, showcasing the transformation of diverse input sources into a structured and organized output.
Image Credits: Jiawen Zhan
Figure 3
Figure 3. A sample workflow visually illustrating Inspired Spine Smart Universal Resource Identifier’s transcription and documentation process, showcasing the transformation of diverse input sources into a structured and organized output.
Image Credits: Jiawen Zhan
Figure 4
Figure 4. A sample workflow illustrating Inspired Spine Smart Universal Resource Identifier’s audio recognition function, demonstrating how natural language input is processed and transformed into actionable outputs executed by the system.
Image Credits: Jiawen Zhan
Figure 5
Figure 5. Overview of Inspired Spine Smart Universal Resource Identifier's mainframe structure and its interconnected functions. The diagram illustrates the core components of Inspired Spine Smart Universal Resource Identifier, including documentation, transcription, billing, scheduling, data analysis, prior authorization, and coding, along with their specific tasks such as categorization, summarization, and assignment. Each function interacts seamlessly with the mainframe to support efficient and streamlined medical operations.
Image Credits: Jiawen Zhan
See this image and copyright information in PMC

References

    1. Burnout related to electronic health record use in primary care. Budd J. J Prim Care Community Health. 2023;14:21501319231166921. - PMC - PubMed
    1. High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR. Banerjee S, Agarwal A, Ghosh P. https://arxiv.org/abs/2412.00055 Cor Uni. 2024
    1. Automatic recognition of spoken digits. Davis KH, Biddulph R, Balashek S. https://pubs.aip.org/asa/jasa/article-abstract/24/6/637/618458/Automatic... Jr Aco Soc Amr. 1952;24:637–642.
    1. Trainable grammars for speech recognition. Baker JK. https://pubs.aip.org/asa/jasa/article/65/S1/S132/739840/Trainable-gramma... IEEE. 1975;23:24–29.
    1. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. Hinton G, Deng Li, Yu Dong, et al. https://ieeexplore.ieee.org/document/6296526 IEEE. 2012;29:82–97.

LinkOut - more resources