In the context of the continuous progress of medical electronic informatization,   Massachusetts Institute of Technology and Beth Israel Deaconess Medical Center jointly developed the Medical Information Mart for Intensive Care (MIMIC) database aiming to integrate intensive care unit data and promote medical research and interdisciplinary cooperation. The MIMIC database has evolved through several versions, and each version has been continuously improved in terms of data volume, time range and sources, etc. It consists of multi-level structure and diverse data types supporting various analytical methods, such as basic statistics, inference, machine learning, and multimodal integration. The MIMIC database offers reliable data sources and comprehensive content, but it still faces issues such as missing data, time precision inconsistencies, compatibility with system changes, and potential biases, which require careful handling. The global influence of the MIMIC database is manifested in multiple aspects including medical research, healthcare improvement, international collaboration, informatization development, and advancements in critical care medicine. In the future, data privacy protection and quality control will remain important development directions for the MIMIC database. This paper reviews the development and version iterations of the MIMIC database, analyzes its data quality and potential biases, and explores its global influence, providing a reference for researchers to quickly understand the MIMIC database.

1.Lee J, Scott DJ, Villarroel M, et al. Open-access MIMIC-II database for intensive care research[J]. Annu Int Conf IEEE Eng Med Biol Soc, 2011, 2011: 8315-8318. DOI: 10.1109/IEMBS.2011.6092050.

2.Johnson AE, Pollard TJ, Shen L, et al. MIMIC-III, a freely accessible critical care database[J]. Sci Data, 2016, 3: 160035. DOI: 10.1038/sdata.2016.35.

3.Johnson AEW, Bulgarelli L, Shen L, et al. MIMIC-IV, a freely accessible electronic health record dataset[J]. Sci Data, 2023, 10(1): 1. DOI: 10.1038/s41597-022-01899-x.

4.Shi Y, Shi Y, Liu Y, et al. Association between neutrophil percentage to serum albumin ratio and in-hospital mortality of patients with chronic obstructive pulmonary disease in intensive care unit: a retrospective cohort study[J]. Int J Chron Obstruct Pulmon Dis, 2025, 20: 1227-1237. DOI: 10.2147/COPD.S508964.

5.范勇, 赵宇卓, 李沛尧, 等. 危急重症监护数据库MIMIC-Ⅲ疾病谱分析[J]. 中华危重病急救医学, 2018, 30(6): 531-537. [Fan Y, Zhao YZ, Li PY, et al. Analysis of diseases distribution in Medical Information Mart for Intensive Care Ⅲ database[J]. Chinese Critical Care Medicine, 2018, 30(6): 531-537.] DOI: 10.3760/cma.j.issn.2095-4352.2018.06.006.

6.Zhou Y, Hu J. The association between pan-immune-inflammation value with mortality in critically ill patients with sepsis-associated acute kidney injury[J]. BMC Infect Dis, 2025, 25(1): 486. DOI: 10.1186/s12879-025-10880-z.

7.Deng Y, Li S, Li J, et al. Enhancing mortality prediction in intensive care units: improving APACHE II, SOFA, and SAPS II scoring systems using long short-term memory[J]. Intern Emerg Med, 2025. DOI: 10.1007/s11739-025-03896-5.

8.Ghaderi H, Foreman B, Reddy CK, et al. Discovery of generalizable TBI phenotypes using multivariate time-series clustering[J]. Comput Biol Med, 2024, 180: 108997. DOI: 10.1016/j.compbiomed.2024.108997.

9.Chen J, Li Q, Liu F, et al. M3T-LM: a multi-modal multi-task learning model for jointly predicting patient length of stay and mortality[J]. Comput Biol Med, 2024, 183: 109237. DOI: 10.1016/j.compbiomed.2024.109237.

10.Kurniati AP, Rojas E, Hogg D, et al. The assessment of data quality issues for process mining in healthcare using Medical Information Mart for Intensive Care III, a freely available e-health record database[J]. Health Informatics J, 2019, 25(4): 1878-1893. DOI: 10.1177/1460458218810760.

11.Cui Z, Dong Y, Yang H, et al. Machine learning prediction models for multidrug-resistant organism infections in ICU ventilator-associated pneumonia patients: analysis using the MIMIC-IV database[J]. Comput Biol Med, 2025, 190: 110028. DOI: 10.1016/j.compbiomed.2025.110028.

12.Lei J, Zheng LZ, Chen KY, et al. Independent effect of influenza vaccination on all-cause mortality in critically ill patients with atrial fibrillation: a retrospective study from the MIMIC-IV database[J]. Int J Cardiol, 2025, 433: 133246. DOI: 10.1016/j.ijcard.2025.133246.

13.Hu Y, Zhao Y, Zhang J, et al. The association between triglyceride glucose-body mass index and all-cause mortality in critically ill patients with atrial fibrillation: a retrospective study from MIMIC-IV database[J]. Cardiovasc Diabetol, 2024, 23(1): 64. DOI: 10.1186/s12933-024-02153-x.

14.Hu C, Li L, Li Y, et al. Explainable machine-learning model for prediction of in-hospital mortality in septic patients requiring intensive care unit readmission[J]. Infect Dis Ther, 2022, 11(4): 1695-1713. DOI: 10.1007/s40121-022-00671-3.

15.Zhou S, Zeng Z, Wei H, et al. Early combination of albumin with crystalloids administration might be beneficial for the survival of septic patients: a retrospective analysis from MIMIC-IV database[J]. Ann Intensive Care, 2021, 11(1): 42. DOI: 10.1186/s13613-021-00830-8.

16.Xiao LX, Zhu DL, Chen J, et al. Exploring the therapeutic role of early heparin administration in ARDS management: a MIMIC-IV database analysis[J]. J Intensive Care, 2024, 12(1): 9. DOI: 10.1186/s40560-024-00723-5.

17.Guo Y, Qiu Y, Xue T, et al. Association between glycemic variability and short-term mortality in patients with acute kidney injury: a retrospective cohort study of the MIMIC-IV database[J]. Sci Rep, 2024, 14(1): 5945. DOI: 10.1038/s41598-024-56564-7.

18.Tomazini BM, Besen BAMP, Taniguchi LU, et al. Association between piperacillin/tazobactam use and acute kidney injury in critically ill patients: a retrospective multicentre cohort study[J]. J Antimicrob Chemother, 2024, 79(3): 552-558. DOI: 10.1093/jac/dkae001.

19.Meng C, Trinh L, Xu N, et al. Interpretability and fairness evaluation of deep learning models on MIMIC-IV dataset[J]. Sci Rep, 2022, 12(1): 7166. DOI: 10.1038/s41598-022-11012-2.

20.Jabbour G, Nolin-Lapalme A, Tastet O, et al. Prediction of incident atrial fibrillation using deep learning, clinical models, and polygenic scores[J]. Eur Heart J, 2024, 45(46): 4920-4934. DOI: 10.1093/eurheartj/ehae595.

21.杨美程, 李润发, 陈辉, 等. 人工智能辅助诊疗在脓毒症管理中的应用进展[J]. 药学进展, 2023, 47(10): 758-768. [Yang MC, Li RF, Chen H, et al. Advances in the Application of Artificial Intelligence-Assisted Diagnosis and Treatment in Sepsis Management[J]. Progress in Pharmaceutical Sciences, 2023, 47(10): 758-768.] DOI: 10.20053/j.issn1001-5094.2023.10.006.

22.梁瀚文. 合并严重高碳酸血症的ARDS患者呼吸频率与预后的关系研究及预后预测模型的建立[D]. 广州: 广州医科大学, 2023. [Liang HW. Analyzing the association between respiratory rate and outcomes of invasively ventilated acute respiratory distress syndrome patients with severe hypercapnia and constructing a predictive model of hospital mortality[D]. Guangzhou: Guangzhou Medical University, 2023.] DOI: 10.27043/d.cnki.ggzyc.2023.000770.

23.郑晓博, 张中伟. 人工智能在重症医学教学中的应用展望[J]. 西南医科大学学报, 2023, 46(6): 468-472. [Zheng XB, Zhang ZW. Application prospect of artificial intelligence in critical care medicine teaching[J]. Journal of Southwest Medical University, 2023, 46(6): 468-472.] DOI: 10.3969/j.issn.2096-3351.2023.06.002.