Skip to main content
Download PDF

Prediction model of ICU readmission in Chinese patients with acute type A aortic dissection: a retrospective study

BMC Medical Informatics and Decision Making volume 24, Article number: 358 (2024) Cite this article

Abstract

Background

Readmission to the intensive care unit (ICU) remains a severe challenge, leading to higher rates of death and a greater financial burden. This study aimed to develop a nomogram-based prediction model for individuals with acute type A aortic dissection (ATAAD).

Methods

A total of 846 ATAAD patients were retrospectively enrolled between May 2014 and October 2021. Logistic regression was employed to identify the independent risk factors. The prediction model was evaluated using the Hosmer–Lemeshow (H–L) test, the calibration curve, and the area under the receiver operating characteristic curve (AUC). Decision curve analysis (DCA) was used to assess the clinical utility.

Results

57 (6.7%) ATAAD patients were readmitted to ICU following their release from the ICU. ICU readmission was predicted with age ≥ 65 years old, body mass index (BMI) ≥ 28 kg/m2, tracheotomy, continuous renal replacement therapy (CRRT), and the length of initial ICU stay were predictors of ICU readmission. The AUC was 0.837 (95%CI: 0.789–0.884) and the model fit the data well (H–L test, P = 0.519). DCA also demonstrated good clinical practicability.

Conclusions

This prediction model may be helpful for clinicians to assess the risk of ICU readmission, and facilitate the early identification of ATAAD patients at high risk.

Peer Review reports

Background

Acute type A aortic dissection (ATAAD) is a rare and life-threatening cardiovascular emergency, with challenging treatment for both cardiac surgeons and intensive care physicians [1, 2]. Readmission to the intensive care unit (ICU) after surgery for ATAAD is still a serious concern, which leads to 10 times higher mortality, worse quality of life, and increased socioeconomic burden [3].

The Society for Critical Care Medicine in the United States has advocated ICU readmission as a quality indicator [4]. Patients undergoing aortic surgery have a higher ICU readmission rate compared to other cardiovascular surgeries [5]. However, the relevant research in ATAAD is limited. Reported risk factors of readmission to the ICU, especially after cardiac surgery, are controversial [2, 6]. Accordingly, this study attempts to identify risk factors of ICU readmission in ATAAD patients and develops a prediction model that would assist clinicians to identifying high-risk patients.

Methods

Study design and population

A retrospective study was conducted on ATAAD patients between May 2014 and October 2021 at a hospital in Fujian Province, China. Patients older than 18 and diagnosed with ATAAD by computed tomography angiography were enrolled. Patients were excluded from the study if they (1) did not receive surgery; (2) died before being discharged from the ICU or on the general ward after being discharged from their initial ICU stay; (3) gave up treatment or were transferred to other medical institutions; (4) had incomplete clinical information. The hospital institutional review board approved this retrospective study, with a waiver of informed consent (2022KY128).

Data collection

In this study, ICU readmission was defined as a transfer from the ICU to the wards and then back to the ICU during the same hospitalization [7]. For ATAAD patients who were readmitted to the ICU, only the first admissions were included in the analysis. Collected variables were chosen based on a combination of clinical expertise and evidence from the literature. All data were retrospectively collected from the electronic medical record system.

Preoperative variables included gender, age, diabetes mellitus, hypertension, Marfan’s syndrome, previous cardiac surgery, body mass index (BMI), heart rate, systolic blood pressure, diastolic blood pressure, and left ventricular ejection fraction (LVEF). Intraoperative variables included the surgery with coronary artery bypass surgery (CABG), operating time, cardiopulmonary bypass (CPB) time, and aortic cross-clamping time. Postoperative variables included tracheotomy, continuous renal replacement therapy (CRRT), and prolonged mechanical ventilation (PMV), white blood cell, red blood cell, platelet, hemoglobin, systemic inflammatory response index (SIRI), the length of initial ICU stay, et al. The last laboratory data before discharge from the ICU and the length of initial ICU stay were also collected.

PMV was identified as the duration of mechanical ventilation use > 48 h [8]. In this study, the prediction model of ICU readmission was developed by variables spanning from hospital admission to ICU discharge. Variables required complex calculations were not easy to use for planning ICU discharge [9]. Therefore, we involved easily accessible and broadly available data to construct this model for clinical application.

Over half of ICU beds are occupied by the elderly (≥ 65 years old) [10]. On the other hand, to facilitate the use of the constructed model, age was treated as a categorical variable (≥ 65 years vs. < 65 years) in the process of modeling. In addition, BMI was also categorized as obese (BMI > 28 kg/m2) and non-obese groups according to the Working Group on Obesity in China [11].

Transfer practices

The standard perioperative and surgical management protocols were performed in ATAAD patients. ATAAD patients are all admitted to the cardiovascular ICU for follow-up treatment after surgery. Following the safe staffing policy, the ICU is staffed adequately with the required number of doctors and nurses. The decisions of ICU discharge and ICU readmission were made by the attending physicians and intensivists based on the patient’s health status. Patients were required to meet the following conditions before ICU discharge: stable vital signs, hemodynamically stable, no serious organ dysfunction, spontaneous breathing, and acceptable blood gas analysis index. The ATAAD patients discharged from the ICU were handed over to the surgical team for continued post-operative care in the cardiac surgical ward.

Statistical analysis

The software SPSS 25.0 was used for data analysis. Normal continuous variables were presented as mean ± standard and were compared using Student’s t-test. The non-normal continuous variables were expressed as the median and interquartile range (IQR) and were compared by the Mann–Whitney U test. Categorical variables were summarized using frequency counts and percentages, and tested by the chi-square or Fisher exact test. Variables with a p-value less than 0.05 in univariate analysis were integrated into the multivariate analysis and developed a logistic regression equation model to predict ICU readmission. R software (version 4.1.2) was used to draw the nomogram for visualizing the model. In the nomogram, the score corresponding to each predictor was determined based on the regression coefficients in the model and summed to obtain a total score. The total score corresponded to the risk probability of ICU readmission. The bootstrapping method was used for internal validation, which involved repeatedly extracting the same number of samples 1000 times from the database, then placing them back and evaluating the model in the generated new samples. The area under the receiver operating characteristic curve (AUC) was used to test the discrimination of the model. A tenfold cross validation was adopted for reliability of the model. Model fit was assessed via Hosmer–Lemeshow (H–L) test and calibration curve. Decision curve analysis (DCA) was used to evaluate the clinical net benefit of the prediction model.

Results

Patient characteristics and risk factors

A total of 923 samples were included, of which 77 were excluded, leaving 846 samples for the final analysis, shown in Fig. 1. After exclusions for incomplete data, 57 ATAAD patients (6.7%) were readmitted to the ICU after transfer to the ward.

Fig. 1
figure 1

The flow chart of the study

Full size image

The characteristics of ATAAD patients are shown in Table 1. 651 (77.0%) of participants were male and 110 (13.0%) were older than 65 years. ATAAD patients with bounce backs had longer operating time as compared to non-readmitted patients (337.25 ± 77.37 vs. 311.40 ± 82.78 min, P = 0.022), were more likely to receive CRRT (26.3% vs. 6.2%, P < 0.001) and tracheotomy (14.0% vs. 3.9%, P < 0.001). Compared to the non-readmission group, patients in the readmission group had higher BMI (26.24 ± 3.57 vs. 24.81 ± 3.23 kg/m2, P = 0.001). The results also revealed significant differences in the length of initial ICU stay between two groups (P < 0.001).

Table 1 The characteristics of ATAAD patients
Full size table

Prediction model

The univariate analysis showed that ≥ 65 years old, BMI ≥ 28 kg/m2, operating time, tracheotomy, CRRT, and the length of initial ICU stay were associated with ICU readmission (P < 0.05). There is no collinearity and low correlation among risk factors, with VIF values of variables ranging from 1.023 to 1.118. The multivariate regression model revealed that 5 variables were independent risk factors of ICU readmission in ATAAD patients, including ≥ 65 years old (OR = 2.168, P = 0.039), BMI ≥ 28 kg/m2 (OR = 2.268, P = 0.022), tracheotomy (OR = 6.003, P = 0.001), CRRT (OR = 2.859, P = 0.009), and the length of initial ICU stay (OR = 1.107, P < 0.001), reported in Table 2.

Table 2 Univariate and multivariate logistic regression analysis of ICU readmission
Full size table
Fig. 2
figure 2

Nomogram to predict the probability of ICU readmission with ATAAD patients

Full size image

For visualization and convenience of clinical application, we constructed a nomogram combining the risk value and regression equation. The score of each variable was shown at the top of the scale, and a vertical line down from the total points row to obtain the risk probability. With an increased score, the risk of ICU readmission was additionally increased, presented in Fig. 2.

Qualitative characteristics of the prediction model

The AUC of the prediction model was 0.837 (95%CI: 0.789–0.884). The optimal cutoff value of 0.057 with a sensitivity of 77.2%, specificity of 76.6%, and accuracy of 76.6%. After 1000 bootstrap resamples for internal verification, the average AUC of this model was 0.836 (95%CI: 0.835–0.838). The results of tenfold cross validation demonstrated a mean absolute error of 0.114 and root mean square error of 0.234. The calibration curve also indicated acceptable agreement of the predicted probability with the actual observed probability, presented in Fig. 3. The DCA demonstrated that the benefit curve was higher than the extreme curves when the threshold probability was approximately 5%–52%, which meant the application of the nomogram model would add more benefit than either treat-all strategy and treat-none strategy, presented in Fig. 4.

Fig. 3
figure 3

Calibration plot of the prediction model for ICU readmission in ATAAD patients

Full size image
Fig. 4
figure 4

Decision curve analyses of the model. X-axis: The threshold probability of ICU readmission at which the patient would be classified as being at high risk for being readmitted to the ICU. Y-axis: The net benefit represents that the benefits obtained from preventing ATAAD patients from ICU readmission exceed the potential harm caused by unnecessary prevention

Full size image

Discussion

ICU readmission is regarded as a quality indicator of critical care, associated with higher in-hospital mortality, poorer long-term outcomes, and increased hospitalization costs [12]. The previous findings of being readmitted to cardiovascular ICU remain controversial, and research on ATAAD is lacking [13]. In this study, we included 5 variables to develop a nomogram to predict the risk of ICU readmission in ATAAD patients.

The average rate of ICU readmission for cardiac surgery patients ranges from 1.9% to 3.5% in large-sample investigations [2, 5]. However, we found that 6.7% of ATAAD patients were readmitted to ICU after surgery in this study, which is higher than the previous results. Patients with aorta surgery experienced higher ICU readmission than other cardiovascular diseases [5]. ATAAD is the most lethal aortic condition, however, most patients are referred from the other hospitals in developing countries and take longer times from onset to surgery with worse disease conditions [1, 14]. At the same time, compared to general cardiovascular surgery, the required surgery of ATAAD is more complex with a high incidence of severe postoperative complications, [15, 16] which may result in the relatively high incidence of bouncing back to ICU.

A study targeting Chinese patients undergoing cardiac surgery has shown that elderly individuals have a higher risk of readmission [17]. This is supported by our data. Post-ICU patients are at high risk for adverse events because of the severity of their illness and the complexity of care required. However, compared to young patients, elderly patients have an increased incidence of co-morbidities, poorer ability to meet physiological needs, and longer recovery times [18, 19], especially for ATAAD patients with open surgical repair. Consequently, readmitted patients tend to be older than those not readmitted [20].

Our results indicate that ATAAD patients with high BMI have a higher risk of being readmitted to ICU. In a previous study, for patients undergoing cardiac surgery, high BMI is associated with increased utilization of ICU resources and a high risk of ICU readmission, [21] which is also supported by our data. Aortic dissection patients with high BMI are prone to impaired mobility, balance, and physical function, with a higher incidence of obesity-associated comorbidities [22]. Therefore, the attending should pay more attention to ATAAD patients with high BMI on clinical rounds to prevent ICU readmission.

CRRT is the primary form of renal replacement therapy for patients with kidney injury for providing a slow, gentle, and continuous kidney support [23, 24]. A survey on heart valve surgery found that patients with renal failure have higher risk of ICU readmission [17]. In this study, we also found that ATAAD patients receiving CRRT treatment are also more likely to be readmitted. Clinicians should increase their awareness that how to prevent renal injury during the early postoperative period and avoid excessive use of CRRT.

Tracheotomy is considered the major characteristic of ICU readmission after discharge from critical care [25]. Consistent with the previous finding, ATAAD patients with tracheostomy had a higher risk of ICU readmission. Tracheostomy is indicated for anticipated prolonged ventilation and relief of airway obstruction, [26] however, may lead to complications such as hemorrhage and respiratory infections [27]. In addition, it can also pose an elevated risk of 30-day readmission after discharge from the hospital [9].

The length of initial ICU stay is considered one of the strongest risk factors of ICU readmission [7]. Our study also demonstrates the importance of the length of initial ICU stay in predicting the risk of readmission for ATAAD patients. Prolongation of exposure to the ICU may indicate higher severity of illness and worse physical conditions that increase the possibility of ICU readmission.

A few studies in the past have tried to develop machine learning models of ICU admission [28, 29]. However, tracing the process of these models is difficult for lacking transparency in analysis [30]. In clinical practice, the presence of interpretability barriers in machine learning models makes it difficult for clinicians to judge and guide their decisions [31]. Sean et al. [32] developed a prediction model through a survey of 10,799 patients with cardiac surgery. However, this model excludes patients undergoing complex operations on the aortic arch with more critical postoperative conditions. Given the limitations of previous models, this study has filled the gap in predicting ICU readmission of ATAAD patients. In this study, the AUC was 0.837, which is better than the study in cardiac surgery ICU (AUC = 0.81) and the study in surgical critical care (AUC = 0.78) [6, 7]. Compared with the previous model, [6] this prediction model in ATAAD supplements the collection of treatment information during the ICU period. This model maintains acceptable discrimination and calibration to quickly identify ATAAD patients at high risk of readmission.

The risk assessment of ICU readmission can be conducted before being transferred out of the ICU, for estimating the level of care required in the ward. Patients with higher risk can be discharged to wards with a better nursing-patient ratio for close monitoring and given proactive nursing plans to prevent condition deterioration. In addition, based on the model, rational application of CRRT and tracheotomy, and early transfer planning to avoid prolonged ICU stay all help to reduce the incidence of ICU readmission.

Limitations

This study still has the following several limitations. Based on the retrospectively collected data and the lack of information on the use of drugs such as antibiotics, there are inherent design biases in this study. With small sample size, our model needs to be further verified by large, multi-center, prospective cohort studies.

Conclusions

In this study, we identified the independent risk factors of ICU readmission in ATAAD patients. Based on these factors, we constructed a prediction model using nomogram. The AUC of the model was 0.837 and the model fit well in calibration curve. This model may provide a reference to identify ICU readmission in ATAAD patients.

Data availability

All data generated or analyzed during this study are included in the article.

Abbreviations

ATAAD:

Acute type A aortic dissection

ICU:

Intensive care unit

BMI:

Body mass index

LVEF:

Left ventricular ejection fraction

CABG:

Coronary artery bypass surgery

CPB:

Cardiopulmonary bypass

CRRT:

Continuous renal replacement therapy

PMV:

Prolonged mechanical ventilation

IQR:

Interquartile range

AUC:

Area under the receiver operating characteristic curve

H-T test:

Hosmer–Lemeshow test

DCA:

Decision curve analysis

References

  1. An Z, Sun YY, Fan RX, Yu SQ, Zhu JM, Han QQ, et al. Extensive arch repair with a novel two-branched stent graft in acute type A aortic dissection. Ann Thoracic Cardiovasc Surg. 2022;28(4):255–61.

    Article  Google Scholar 

  2. Kolat P, Guttenberger P, Ried M, Kapahnke J, Haneya A, Schmid C, et al. ICU readmission after cardiac surgery-still a matter of concern? Thorac Cardiovasc Surg. 2020;68(5):384–8.

    Article  PubMed  Google Scholar 

  3. Martin LA, Kilpatrick JA, Al-Dulaimi R, Mone MC, Tonna JE, Barton RG, et al. Predicting ICU readmission among surgical ICU patients: Development and validation of a clinical nomogram. Surgery. 2019;165(2):373–80.

    Article  PubMed  Google Scholar 

  4. Maharaj R, Terblanche M, Vlachos S. The utility of ICU readmission as a quality indicator and the effect of selection. Crit Care Med. 2018;46(5):749–56.

    Article  PubMed  Google Scholar 

  5. Litwinowicz R, Bartus K, Drwila R, Kapelak B, Konstanty-Kalandyk J, Sobczynski R, et al. In-hospital mortality in cardiac surgery patients after readmission to the intensive care unit: a single-center experience with 10,992 patients. J Cardiothorac Vasc Anesth. 2015;29(3):570–5.

    Article  PubMed  Google Scholar 

  6. Magruder JT, Kashiouris M, Grimm JC, Duquaine D, McGuinness B, Russell S, et al. A predictive model and risk score for unplanned cardiac surgery intensive care unit readmissions. J Card Surg. 2015;30(9):685–90.

    Article  PubMed  Google Scholar 

  7. Hammer M, Grabitz SD, Teja B, Wongtangman K, Serrano M, Neves S, et al. A tool to predict readmission to the intensive care unit in surgical critical care patients-the RISC score. J Intensive Care Med. 2021;36(11):1296–304.

    Article  PubMed  Google Scholar 

  8. Sharma V, Rao V, Manlhiot C, Boruvka A, Fremes S, Wasowicz M. A derived and validated score to predict prolonged mechanical ventilation in patients undergoing cardiac surgery. J Thorac Cardiovasc Surg. 2017;153(1):108–15.

    Article  PubMed  Google Scholar 

  9. Haribhakti N, Agarwal P, Vida J, Panahon P, Rizwan F, Orfanos S, et al. A simple scoring tool to predict medical intensive care unit readmissions based on both patient and process factors. J Gen Intern Med. 2021;36(4):901–7.

    Article  PubMed  PubMed Central  Google Scholar 

  10. Bagshaw SM, Webb SA, Delaney A, George C, Pilcher D, Hart GK, et al. Very old patients admitted to intensive care in Australia and New Zealand: a multi-centre cohort analysis. Critical care (London, England). 2009;13(2):R45.

    Article  PubMed  Google Scholar 

  11. Wang Y, Mi J, Shan XY, Wang QJ, Ge KY. Is China facing an obesity epidemic and the consequences? The trends in obesity and chronic disease in China. Int J Obes (2005). 2007;31(1):177–88.

    Article  CAS  Google Scholar 

  12. Oh TK, Song IA, Jeon YT. Impact of Glasgow Coma Scale scores on unplanned intensive care unit readmissions among surgical patients. Ann Transl Med. 2019;7(20):520.

    Article  PubMed  PubMed Central  Google Scholar 

  13. Thomson R, Fletcher N, Valencia O, Sharma V. Readmission to the intensive care unit following cardiac surgery: A derived and validated risk prediction model in 4,869 patients. J Cardiothorac Vasc Anesth. 2018;32(6):2685–91.

    Article  PubMed  Google Scholar 

  14. Gong M, Wu Z, Xu S, Guan X, Li H, Wang X, et al. Protocol for creation of a risk scoring system for acute type A aortic dissection surgery. Int J Surg Prot. 2019;14:19–23.

    Article  Google Scholar 

  15. Feng D, Huang S, Wang Q, Lang X, Liu Y, Zhang K. Hotspots and development frontiers of postoperative complications of AD: Bibliometric analysis - a review. Medicine. 2023;102(10):e33160.

    Article  PubMed  PubMed Central  Google Scholar 

  16. Liu L, Yang Y. Nutritional management mode of early cardiac rehabilitation in patients with stanford type a aortic dissection. Comput Math Methods Med. 2022;2022:2124636.

    PubMed  PubMed Central  Google Scholar 

  17. Li S, Tang BY, Zhang B, Wang CP, Zhang WB, Yang S, et al. Analysis of risk factors and establishment of a risk prediction model for cardiothoracic surgical intensive care unit readmission after heart valve surgery in China: A single-center study. Heart Lung. 2019;48(1):61–8.

    Article  PubMed  Google Scholar 

  18. Akuffu AM, Zhao H, Zheng J, Ni Y. Prosthesis-patient mismatch after mitral valve replacement: a single-centered retrospective analysis in East China. J Cardiothorac Surg. 2018;13(1):100.

    Article  PubMed  PubMed Central  Google Scholar 

  19. Woldhek AL, Rijkenberg S, Bosman RJ, van der Voort PH. Readmission of ICU patients: A quality indicator? J Crit Care. 2017;38:328–34.

    Article  PubMed  Google Scholar 

  20. Elliott M, Worrall-Carter L, Page K. Intensive care readmission: a contemporary review of the literature. Intensive Crit Care Nurs. 2014;30(3):121–37.

    Article  PubMed  Google Scholar 

  21. Rosvall BR, Forgie K, MacLeod JB, Yip AM, Aguiar C, Lutchmedial S, et al. Impact of obesity on intensive care unit resource utilization after cardiac operations. Ann Thorac Surg. 2017;104(6):2009–15.

    Article  PubMed  Google Scholar 

  22. Kreibich M, Rylski B, Bavaria JE, Branchetti E, Dohle D, Moeller P, et al. Outcome after operation for aortic dissection type a in morbidly obese patients. Ann Thorac Surg. 2018;106(2):491–7.

    Article  PubMed  Google Scholar 

  23. Wang AY, Bellomo R. Renal replacement therapy in the ICU: intermittent hemodialysis, sustained low-efficiency dialysis or continuous renal replacement therapy? Curr Opin Crit Care. 2018;24(6):437–42.

    Article  CAS  PubMed  Google Scholar 

  24. Karkar A, Ronco C. Prescription of CRRT: a pathway to optimize therapy. Ann Intens Care. 2020;10(1):32.

    Article  Google Scholar 

  25. Son YJ, Kim GO, Lee YM, Oh M, Choi J. Predictors of Early and Late Unplanned Intensive Care Unit Readmission: A Retrospective Cohort Study. J Nurs Scholarship. 2021;53(4):400–7.

    Article  Google Scholar 

  26. Whitmore KA, Townsend SC, Laupland KB. Management of tracheostomies in the intensive care unit: a scoping review. BMJ open respiratory research. 2020;7(1):e000651.

  27. Ishihara T, Tanaka H. Factors affecting tracheostomy in critically ill paediatric patients in Japan: a data-based analysis. BMC Pediatr. 2020;20(1):237.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  28. Rojas JC, Carey KA, Edelson DP, Venable LR, Howell MD, Churpek MM. Predicting intensive care unit readmission with machine learning using electronic health record data. Ann Am Thorac Soc. 2018;15(7):846–53.

    Article  PubMed  PubMed Central  Google Scholar 

  29. de Hond AAH, Kant IMJ, Fornasa M, Cina G, Elbers PWG, Thoral PJ, et al. Predicting readmission or death after discharge from the ICU: External validation and retraining of a machine learning model. Crit Care Med. 2023;51(2):291–300.

    Article  PubMed  Google Scholar 

  30. Karadaghy OA, Shew M, New J, Bur AM. Development and Assessment of a Machine Learning Model to Help Predict Survival Among Patients With Oral Squamous Cell Carcinoma. JAMA Otolaryngol HeadNeck Surg. 2019;145(12):1115–20.

    Article  Google Scholar 

  31. Wang Y, Zhang H, Fan Y, Ying P, Li J, Xie C, et al. Propofol anesthesia depth monitoring based on self-attention and residual structure convolutional neural network. Comput Math Methods Med. 2022;2022:8501948.

    PubMed  PubMed Central  Google Scholar 

  32. van Diepen S, Graham MM, Nagendran J, Norris CM. Predicting cardiovascular intensive care unit readmission after cardiac surgery: derivation and validation of the Alberta Provincial Project for Outcomes Assessment in Coronary Heart Disease (APPROACH) cardiovascular intensive care unit clinical prediction model from a registry cohort of 10,799 surgical cases. Critical care (London, England). 2014;18(6):651.

    Article  PubMed  Google Scholar 

Download references

Acknowledgements

We would also like to thank the hospital for supporting data collection of this study.

Funding

This research was funded by Fujian Provincial Finance Special Project [grant number: 2021XH019], Key Laboratory of Cardio-Thoracic Surgery (Fujian Medical University), Fujian Province University, and The Fifth Batch of Hospital Key Discipline Construction Projects [grant number: 2022YYZDXK01].

Author information

Author notes

  1. Hong Ni, Yanchun Peng and Qiong Pan are first co-authors.

Authors and Affiliations

  1. Department of Nursing, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, China

    Hong Ni, Yanchun Peng, Qiong Pan & Yanjuan Lin

  2. Department of Neurology, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, China

    Hong Ni & Zhuling Gao

  3. Department of Cardiac Surgery, Fujian Medical University Union Hospital, Fuzhou, Fujian Province, China

    Sailan Li, Liangwan Chen & Yanjuan Lin

Authors
  1. Hong Ni
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Yanchun Peng
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Qiong Pan
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Zhuling Gao
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Sailan Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  6. Liangwan Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  7. Yanjuan Lin
    View author publications

    You can also search for this author inPubMed Google Scholar

Contributions

YJ Lin and LW Chen designed and conceived the whole study. H Ni and YC Peng analyzed and interpreted the data. H Ni and Q Pan drafted the manuscript. ZL G and SL L collected the data. All authors provided an important revision of this manuscript.

Corresponding authors

Correspondence to Liangwan Chen or Yanjuan Lin.

Ethics declarations

Ethics approval and consent to participate

This study was approved by the ethical review committee of the Fujian Medical University Union Hospital (2022KY128). The research ethics committee waived the requirement for informed consent for retrospective samples.

Consent for publication

All authors have given their consent for publication.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ni, H., Peng, Y., Pan, Q. et al. Prediction model of ICU readmission in Chinese patients with acute type A aortic dissection: a retrospective study. BMC Med Inform Decis Mak 24, 358 (2024). https://doiorg.publicaciones.saludcastillayleon.es/10.1186/s12911-024-02770-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doiorg.publicaciones.saludcastillayleon.es/10.1186/s12911-024-02770-2

Keywords

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us