This preprint is under consideration at Scientific Reports. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
Research Article
Haomin Li
Children's Hospital of Zhejiang University
Corresponding Author
License:
This work is licensed under a CC BY 4.0 License. Read Full License
The quality of treatment and prognosis after pediatric congenital heart surgery remains unsatisfactory. A reliable prediction model for postoperative complications of congenital heart surgery patients is essential to enable prompt initiation of therapy and improve the quality of prognosis. Here, we develop an interpretable machine-learning-based model that integrates patient demographics, surgery-specific features and intraoperative blood pressure data for accurately predicting complications after pediatric congenital heart surgery. We used blood pressure variability and the k-means algorithm combined with a smoothed formulation of dynamic time wrapping to extract features from time series data. In addition, SHAP framework was used to provide explanations of the prediction. Our model achieved the best performance both in binary and multi-label classification compared with other consensus-based risk models. In addition, this explainable model explains why a prediction was made to help improve the clinical understanding of complication risk and generate actionable knowledge in practice. The combination of model performance and interpretability is easy for clinicians to trust and provide insight into how they should respond before the condition worsens after pediatric congenital heart surgery.
Keywords
SHAP, RACHS-1, STS-EACTS, Aristotle Basic Complexity
Figure 1
Figure 2
Figure 3
Figure 4
No competing interests reported.
This is a list of supplementary files associated with this preprint. Click to download.
- Supplementaryinformation.docx
Table S1. Definition of postoperative complications. Table S2. Experimental results of different categories in multi-label classification on validation set. Fig. S1. Flowchart of selection process of eligible participants included in this analysis. Fig. S2. Determining the optimal number of clusters in k-means clustering. Fig. S3. Mean and 95% confidence interval of blood pressure readings of different clusters. Fig. S4. Averaged feature importance estimates by our proposed method for each category of complication. Fig. S5. The influence of varying top 15 features values at different phases on complication prediction.
Loading...
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 1
Posted 16 Feb, 2021
No community comments so far
Editorial decision: Major revision
On 30 Jun, 2021
Reviews received
Received 11 Jun, 2021
Reviewers agreed
On 26 May, 2021
Reviews received
Received 07 May, 2021
Reviewers agreed
On 26 Apr, 2021
Reviewers agreed
On 21 Apr, 2021
Reviewers invited
Invitations sent on 19 Apr, 2021
Editor assigned
On 16 Apr, 2021
Editor invited
On 10 Feb, 2021
Submission checks complete
On 10 Feb, 2021
First submitted
On 08 Feb, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
Learn more about our company.
A new preprint design is coming!
We have improved readability, clarity, accessibility, and opportunities for engagement.
This preprint is under consideration at Scientific Reports. A preprint is a preliminary version of a manuscript that has not completed peer review at a journal. Research Square does not conduct peer review prior to posting preprints. The posting of a preprint on this server should not be interpreted as an endorsement of its validity or suitability for dissemination as established information or for guiding clinical practice.
Learn more about In Review
Research Article
Haomin Li
Children's Hospital of Zhejiang University
Corresponding Author
Badges
Prescreen
This manuscript passed our Prescreen assessment
Complete author information
Appropriate declaration statements
Potential risks to human health
Prescreen
Peer Review Timeline
CURRENT STATUS: Under Review
Version 1
Posted 16 Feb, 2021
No community comments so far
Editorial decision: Major revision
On 30 Jun, 2021
Reviews received
Received 11 Jun, 2021
Reviewers agreed
On 26 May, 2021
Reviews received
Received 07 May, 2021
Reviewers agreed
On 26 Apr, 2021
Reviewers agreed
On 21 Apr, 2021
Reviewers invited
Invitations sent on 19 Apr, 2021
Editor assigned
On 16 Apr, 2021
Editor invited
On 10 Feb, 2021
Submission checks complete
On 10 Feb, 2021
First submitted
On 08 Feb, 2021
Metrics
Comments: 0
PDF Downloads: ...
HTML Views: ...
License:
This work is licensed under a CC BY 4.0 License. Read Full License
The quality of treatment and prognosis after pediatric congenital heart surgery remains unsatisfactory. A reliable prediction model for postoperative complications of congenital heart surgery patients is essential to enable prompt initiation of therapy and improve the quality of prognosis. Here, we develop an interpretable machine-learning-based model that integrates patient demographics, surgery-specific features and intraoperative blood pressure data for accurately predicting complications after pediatric congenital heart surgery. We used blood pressure variability and the k-means algorithm combined with a smoothed formulation of dynamic time wrapping to extract features from time series data. In addition, SHAP framework was used to provide explanations of the prediction. Our model achieved the best performance both in binary and multi-label classification compared with other consensus-based risk models. In addition, this explainable model explains why a prediction was made to help improve the clinical understanding of complication risk and generate actionable knowledge in practice. The combination of model performance and interpretability is easy for clinicians to trust and provide insight into how they should respond before the condition worsens after pediatric congenital heart surgery.
Figure 1
Figure 2
Figure 3
Figure 4
No competing interests reported.
This is a list of supplementary files associated with this preprint. Click to download.
- Supplementaryinformation.docx
Table S1. Definition of postoperative complications. Table S2. Experimental results of different categories in multi-label classification on validation set. Fig. S1. Flowchart of selection process of eligible participants included in this analysis. Fig. S2. Determining the optimal number of clusters in k-means clustering. Fig. S3. Mean and 95% confidence interval of blood pressure readings of different clusters. Fig. S4. Averaged feature importance estimates by our proposed method for each category of complication. Fig. S5. The influence of varying top 15 features values at different phases on complication prediction.
Loading...