Construction and Application of Cardiovascular Disease Specialized Database Based on Multimodal Data Model

LUO Hao; LI Huakang; WANG Fei

doi:10.3969/j.issn.1674-1633.20240978

PDF(3425 KB)

China Medical Devices ›› 2025, Vol. 40 ›› Issue (6) : 61-68. DOI: 10.3969/j.issn.1674-1633.20240978

RESEARCH WORK

Construction and Application of Cardiovascular Disease Specialized Database Based on Multimodal Data Model

LUO Hao, LI Huakang, WANG Fei

Author information +

History +

Abstract

Objective To construct a specialized disease database for cardiovascular diseases based on multimodal diagnosis and treatment data, to improve the efficiency of clinical data utilization and assist the analysis and application of specialized disease data in Cardiovascular Medicine Department. Methods By utilizing Hadoop based big data and artificial intelligence technologies such as natural language processing and computer vision, multimodal data of more than 1.2 million patients in Cardiovascular Medicine Department were aggregated and managed, and the specialized disease database function was developed to provide data support services. Results The cardiovascular disease specialized database was designed with 730 structured fields, included data from 445004 patients, integrated 11939686 outpatient records, and correlated and aggregated 12 types of imaging data including ECG, ultrasound, CT, endoscopy and so on. After using the specialized disease database, the average number of patients and fields in each project were significantly higher than those without using the special disease database; and the time for patient enrollment, data cleaning and governance, field data governance and statistical analysis were all significantly shorter than those without using the special disease database, with all differences being statistically significant (P<0.05). The application efficiency of clinical data has been significantly improved. Conclusion The cardiovascular disease specialized database based on multimodal diagnosis and treatment data has improved the diagnosis and treatment level and scientific research output of the department, which plays a positive role in its application.

Key words

cardiovascular disease; multimodal data; specialized database; big data; artificial intelligence; scientific research data

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

LUO Hao, LI Huakang, WANG Fei. Construction and Application of Cardiovascular Disease Specialized Database Based on Multimodal Data Model[J]. China Medical Devices, 2025, 40(6): 61-68 https://doi.org/10.3969/j.issn.1674-1633.20240978

References

[1] 中国心血管健康与疾病报告编写组. 中国心血管健康与疾病报告2022概要[J]. 中国循环杂志, 2023, 38(6): 583-612.
The Writing Committee of the Report on Cardiovascular Health and Diseases in China. Report on Cardiovascular Health and Diseases in China 2022: an updated summary[J]. Chin Circ J, 2023, 38(6): 583-612.
[2] 齐国强, 李竞, 赵永根, 等. 新生儿坏死性小肠结肠炎专病平台构建与研究[J]. 中国医疗设备, 2023, 38(3): 83-88.
Qi GQ, Li J, Zhao YG, et al. Construction and research o f special disease plat fo rm fo r neonatal nec rotizing enterocolitis[J]. China Med Devices, 2023, 38(3): 83-88.
[3] 王飞, 黄艺璠, 汪鹏. 基于多模态数据的肺癌专病库建设研究[J]. 中国数字医学, 2021, 16(12): 85-88.
Wang F, Huang YF, Wang P. Study on the construction of special disease database of lung cancer based on multimodal data[J]. China Digit Med, 2021, 16(12): 85-88.
[4] 杨寒雨, 赵晓永, 王磊. 数据归一化方法综述[J]. 计算机工程与应用, 2023, 59(3): 13-22.
Yang HY, Zhao XY, Wang L. Review of data normalization methods[J]. Comput Eng Appl, 2023, 59(3): 13-22.
[5] World Health Organization. International statistical classification of diseases and related health problems: ICD-10[EB/OL]. (2016) [2024-06-20]. https://icd.who.int/browse10/Content/statichtml/ ICD10Volume2_en_2016.pdf.
[6] World Health Organization. International classification of diseases for oncology: ICD-O-3[EB/OL]. (2013)[2024-06-20]. https://iris. who.int/bitstream/handle/10665/96612/9789241548496_eng.pdf.
[7] World Health Organization. International classification of diseases, ninth revision, clinical modification (ICD-9-CM)[EB/OL]. (2021-11-03)[2024-06-20]. https://archive.cdc.gov/www_cdc_ gov/nchs/icd/icd9cm.htm.
[8] 国家卫生计生委. 关于印发医疗机构临床检验项目目录 (2013年版)的通知[EB/OL]. (2013-08-07)[2024-06-20]. https://www.nhc.gov.cn/wjw/c100175/201308/5ae7b24700c34e 3299bebc8fd88c814c.shtml.
[9] WHO Collaborating Centre for Drug Statistics Methodology. Guidelines for ATC classification and DDD assignment 2011[EB/OL]. (2011)[2024-06-20]. https://atcddd.fhi.no/ filearchive/publications/2011guidelines.pdf.
[10] 张爱华, 高晓娟, 鲁峥. 儿科医院患者主索引系统的建设与应用[J]. 江苏卫生事业管理, 2023, 34(8): 1086-1089.
Zhang AH, Gao XJ, Lu Z. Construction and application of enterprise patient master index system in pediatric hospital[J]. Jiangsu Healthc Adm, 2023, 34(8): 1086-1089.
[11] 程楠, 侯豪, 牛亚军, 等. 基于NLP技术后结构化处理的电子病历应用[J]. 河南医学研究, 2021, 30(24): 4510-4513.
Cheng N, Hou H, Niu YJ, et al. Application of post-structured electronic medical record based on NLP technology[J]. Henan Med Res, 2021, 30(24): 4510-4513.
[12] Zhao G, Liang K, Pan C, et al. Graph convolution based crossnetwork multiscale feature fusion for deep vessel segmentation[J]. IEEE Trans Med Imaging, 2023, 42(1): 183-195.
[13] Wang YJ, Yang K, Wen Y, et al. Screening and diagnosis of cardiovascular disease using artificial intelligence-enabled cardiac magnetic resonance imaging[J]. Nat Med, 2024, 30(5): 1471-1480.
[14] Christensen M, Vukadinovic M, Yuan N, et al. Vision-language foundation model for echocardiogram interpretation[J]. Nat Med, 2024, 30(5): 1481-1488.
[15] Lin A, Manral N, McElhinney P, et al. Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study[J]. Lancet Digit Health, 2022, 4(4): e256-e265.
[16] Team C. Chameleon: mixed-modal early-fusion foundation models[J/OL]. arXiv, 2024[2024-06-20]. DOI: 10.48550/ arXiv.2405.09818.
[17] Alzubaidi L, Zhang J, Humaidi AJ, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions[J]. J Big Data, 2021, 8(1): 53.
[18] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need[A]. NIPS’17: Proceedings of the 31st International Conference on Neural Information Processing Systems[C]. 2017, 6000-6010.
[19] Brown TB, Mann B, Ryder N, et al. Language models are fewshot learners[A]. NIPS’20: Proceedings of the 34th International Conference on Neural Information Processing Systems[C]. 2020, 159: 1877-1901.
[20] Devlin J, Chang M W, Lee K, et al. Bert: pre-training of deep bidirectional transformers for language understanding[J/OL]. arXiv, 2019[2024-06-20]. DOI: 10.48550/arXiv.1810.04805.
[21] Touvron H, Lavril T, Izacard G, et al. LLaMA: open and efficient foundation language models[J/OL]. arXiv, 2023[2024-06-20]. DOI: 10.48550/arXiv.2302.13971.
[22] Bai JZ, Bai S, Chu YF, et al. Qwen technical report[J/OL]. arXiv, 2023[2024-06-20]. DOI: 10.48550/arXiv.2309.16609.
[23] 孙颖, 李超峰, 林丽, 等. 鼻咽癌专病科研数据库建设与应用[J]. 中国数字医学, 2021, 16(1): 7-12.
Sun Y, Li CF, Lin L, et al. Establishment and application of database for nasopharyngeal carcinoma[J]. China Digit Med, 2021, 16(1): 7-12.
[24] 刘芳, 张玉蓉, 李小玲, 等. 儿童哮喘专病库的构建与应用研究[J]. 护理学杂志, 2022, 37(19): 25-28.
Liu F, Zhang YR, Li XL, et al. Construction and application of an asthma-specific database for children[J]. J Nurs Sci, 2022, 37(19): 25-28.