Machine learning to predict outcomes of type B aortic dissection patients following thoracic endovascular aortic repair
| ISRCTN | ISRCTN12803806 |
|---|---|
| DOI | https://doi.org/10.1186/ISRCTN12803806 |
| Secondary identifying numbers | National Natural Science Foundation of China ref: 82270513 |
- Submission date
- 12/04/2025
- Registration date
- 17/04/2025
- Last edited
- 16/04/2025
- Recruitment status
- No longer recruiting
- Overall study status
- Completed
- Condition category
- Circulatory System
Plain English summary of protocol
Background and study aims
Thoracic endovascular aneurysm repair (TEVAR) in patients with type B aortic dissection (TBAD) may entail postoperative risks. Nevertheless, there is no adopted predictive tool for assessing patients' outcomes. This study seeks to employ machine learning (ML) to develop a predictive model that predicts 1-year mortality following TEVAR. This study aimed to construct a predictive model for 1-year mortality in TBAD patients utilizing ML methodologies. The study's significance is underscored by its potential to facilitate timely interventions and treatments, thereby contributing to a reduction in the mortality rate among TBAD patients.
Who can participate?
Patients diagnosed with TBAD at Changhai Hospital (Shanghai, China) from January 2011 to June 2023.
What does the study involve?
This retrospective cohort study included TBAD patients who underwent TEVAR between January 2011 and June 2023. A total of 57 preoperative demographic variables were considered as input features. The primary outcome was all-cause mortality at one year. Data were split into training (70%) and test (30%) sets. Five machine learning models were developed to predict outcomes, with the area under the curve (AUC) serving as the primary metric for model evaluation. Shapley Additive Explanations (SHAP) were utilized to assess the significance of the clinical features in the output model.
What are the possible benefits and risks of participating?
No benefits and risks provided at registration
Where is the study run from?
Department of Vascular Surgery, Changhai Hospital of the Navy Medical University, China
When is the study starting and how long is it expected to run for?
July 2020 to June 2023
Who is funding the study?
The National Natural Science Foundation of China, China
Who is the main contact?
Prof Jian Zhou, zhoujian1_3@163.com
Contact information
Principal Investigator
No. 168, Changhai Road, Yangpu District
Shanghai
200433
China
| Phone | +86 13818896067 |
|---|---|
| zhoujian1_3@163.com |
Scientific
No. 168, Changhai Road, Yangpu District
Shanghai
200433
China
| Phone | +86 15821678296 |
|---|---|
| zkwgly@163.com |
Public
No. 225, Changhai Road, Yangpu District
Shanghai
200438
China
| Phone | +86 13611826460 |
|---|---|
| lishuangshuangfy@163.com |
Study information
| Study design | Observational single-center retrospective cohort study |
|---|---|
| Primary study design | Observational |
| Secondary study design | Cohort study |
| Study setting(s) | Medical and other records |
| Study type | Prevention, Treatment |
| Participant information sheet | No participant information sheet available |
| Scientific title | Construction and evaluation of an early warning model for prognostic adverse events in acute aortic dissection |
| Study objectives | This study aimed to construct a predictive model for 1-year mortality in TBAD patients utilizing ML methodologies. The study's significance is underscored by its potential to facilitate timely interventions and treatments, thereby contributing to a reduction in the mortality rate among TBAD patients. |
| Ethics approval(s) |
Approved 24/08/2020, Shanghai Changhai Hospital Ethics Committee (No.168, Changhai Road, Yangpu District, Shanghai, 200433, China; +86-21-31162338; changhaiec@126.com), ref: CHEC-Y2020-042 |
| Health condition(s) or problem(s) studied | Prediction of 1-year all-cause mortality in thoracic aortic dissection (TBAD) patients undergoing thoracic endovascular aortic repair (TEVAR) |
| Intervention | This retrospective cohort study evaluates thoracic aortic dissection (TBAD) patients who underwent thoracic endovascular aortic repair (TEVAR) between January 2011 and June 2023. A total of 57 preoperative demographic variables are considered as input features. The primary outcome focuses on all-cause mortality at one year. Data are split into training (70%) and test (30%) sets. Five machine learning models are developed to predict outcomes, with the area under the curve (AUC) serving as the primary evaluation metric. Shapley Additive Explanations (SHAP) are utilized to assess the clinical significance of features in the final model. |
| Intervention type | Procedure/Surgery |
| Primary outcome measure | 1-year all-cause mortality measured using data collected from a retrospective cohort thoracic aortic dissection (TBAD) patients who underwent thoracic endovascular aortic repair (TEVAR) between January 2011 and June 2023 at one timepoint |
| Secondary outcome measures | There are no secondary outcome measures |
| Overall study start date | 01/07/2020 |
| Completion date | 01/06/2023 |
Eligibility
| Participant type(s) | Patient |
|---|---|
| Age group | Not Specified |
| Lower age limit | 18 Years |
| Upper age limit | 110 Years |
| Sex | Both |
| Target number of participants | 1674 |
| Total final enrolment | 1335 |
| Key inclusion criteria | Patients diagnosed with TBAD at Changhai Hospital (Shanghai, China) from January 2011 to June 2023. |
| Key exclusion criteria | 1. Cases of traumatic aortic injury and iatrogenic aortic dissection 2. The presence of Turner syndrome, Marfan syndrome, Ehlers-Danlos syndrome, bicuspid aortic valve, giant cell arteritis, ankylosing spondylitis, Behçet's disease, or Takayasu arteritis 3. A history of previous aortic surgical interventions 4. A documented history of malignancy 5. A lack of baseline data |
| Date of first enrolment | 24/08/2020 |
| Date of final enrolment | 01/06/2023 |
Locations
Countries of recruitment
- China
Study participating centre
Shanghai
200433
China
Sponsor information
Hospital/treatment centre
No. 168, Changhai Road, Yangpu District
Shanghai
200433
China
| Phone | +86 02131162338 |
|---|---|
| lishuangshuangfy@163.com | |
"ROR" |
https://ror.org/02bjs0p66 |
Funders
Funder type
Government
Government organisation / National government
- Alternative name(s)
- Chinese National Science Foundation, Natural Science Foundation of China, National Science Foundation of China, NNSF of China, NSF of China, 国家自然科学基金委员会, National Nature Science Foundation of China, Guójiā Zìrán Kēxué Jījīn Wěiyuánhuì, NSFC, NNSF, NNSFC
- Location
- China
Results and Publications
| Intention to publish date | 31/12/2025 |
|---|---|
| Individual participant data (IPD) Intention to share | Yes |
| IPD sharing plan summary | Available on request |
| Publication and dissemination plan | Planned publication in a peer reviewed journal |
| IPD sharing plan | The datasets generated during and analysed during the current study will be available upon request from the corresponding author, Prof Jian Zhou, zhoujian1_3@163.com |
Editorial Notes
15/04/2025: Study's existence confirmed by the Shanghai Changhai Hospital Ethics Committee.
