Ignite Creation Date:
2024-05-06 @ 3:29 PM
Last Modification Date:
2024-10-26 @ 1:50 PM
Study NCT ID:
NCT04643665
Status:
COMPLETED
Last Update Posted:
2020-11-25
First Post:
2020-11-19
Brief Title:
Prediction of Pulmonary Graft Dysfunction After Double-lung Transplantation PGD3-AI Study
Sponsor:
Hopital Foch
Organization:
Hopital Foch
Study Overview
Official Title:
Prediction of Grade 3 Pulmonary Graft Dysfunction After Double-lung Transplantation From Donor Recipient and Intraoperative Variables
Status:
COMPLETED
Status Verified Date:
2020-11
Last Known Status:
None
Delayed Posting:
No
If Stopped, Why?:
Not Stopped
Has Expanded Access:
False
If Expanded Access, NCT#:
N/A
Has Expanded Access, NCT# Status:
N/A
Acronym:
None
Brief Summary:
The thundering evolution of lung transplantation management during the past ten years and primary graft dysfunction PGD new definition have led to new predictive factors of PGD Therefore we retrospectively analyzed a monocentric database using a machine-learning method to determine the predictive factors of grade 3 PGD PGD3 defined as a PaO2FiO2 ratio 200 or being under extracorporeal membrane oxygenation ECMO at postoperative day 3
We included all double lung transplantation from 2012 to 2019 and excluded multi-organ transplant cardiopulmonary bypass or repeated transplantation during the study period for the same patient Recipient donor and intraoperative data were added in a gradient boosting algorithm step-by-step according to standard transplantation stages Dataset will be split randomly as 80 training set and 20 testing set Relationship between predictive factors and PGD3 will be represented as ShHapley Additive exPlanation SHAP values
We included all double lung transplantation from 2012 to 2019 and excluded multi-organ transplant cardiopulmonary bypass or repeated transplantation during the study period for the same patient Recipient donor and intraoperative data were added in a gradient boosting algorithm step-by-step according to standard transplantation stages Dataset will be split randomly as 80 training set and 20 testing set Relationship between predictive factors and PGD3 will be represented as ShHapley Additive exPlanation SHAP values
Detailed Description:
The standardized anesthetic management has been previously described 18 and is detailed on the web site httpanesthesie-fochorgprotocoles-anesthesie The Foch lung transplant anesthesia protocol
Continuous variables are presented as median interquartile range IQR or mean and 95CI and were compared using independent T-test or Mann-Whitney test Categorical variables are presented as n and were compared using Chi-squared test or Fishers exact test We applied machine learning algorithm to predict 3-day ahead primary graft dysfunction after lung transplant surgery among patients Machine learning is a branch of artificial intelligence where computer systems can learn from available data and identify patterns with minimal human intervention Machine learning algorithm tests on data and performance metrics were used to obtain the higher performing algorithm In this study we performed a XGBoost Gradient Boosting algorithm which was a combination of decisions trees Each decision tree typically learned from its precursor and passed on the improved function to the following The weighted combination of these trees provided the prediction
No particular data transformation has been performed on numerical variables Categorical variables have been encoded as integer without any further pre-processing steps In particular no specific processing has been performed to deal with missing data The default behavior of XGBoost has been used It consists in treating missing data as a specific modality During the training step of XGBoost models missing values are treated as other values and left or right decisions at any branch of a tree are learned by optimizing the outcome
In order to reflect the sequential nature of this predictive medicine problem nine steps have been defined to take into account incrementally observed variables acquired at various stages of the surgery
Step 1 recipient variables Step 2 donor variables Step 3 arrival in the OR Step 4 after anesthetic induction Step 5 during first pneumonectomy Step 6 after first graft implantation Step 7 second pneumonectomy Step 8 second graft implantation Step 9 end surgery status At each of the nine steps a cross-validation procedure is employed to assess the predictive performance of a machine learning model XGBoost One repetition of the cross-validation procedure is designed as follows the dataset of subjects is randomly split into eight disjoint parts Successively the performance of the XGBoost model on each of the eight subsetwhile training the machine learning model using the remaining seven subsets For such a repetition the predictive probability of 3-day ahead primary graft dysfunction for each subject is retained to finally compute the area under ROC receiving operator curve To evaluate the variability of the predictive performance of the machine learning model this cross-validation procedure is repeated fifty times with randomly chosen subjects partitions For each of the fifty times eight times nine repetitions partitions surgical steps hence 3600 models training a conservative approach has been adopted for XGBoost training consisting in a unique set of training parameters These parameters have been chosen to prevent overfitting due to a relatively small number of subjects compared to the number of variables especially categorical variables which yield a high degree of freedom Specifically XGBoost has been trained for 400 rounds no early stopping a maximum depth of 5 for each tree a minimum child weight of 3 and a learning parameter eta equals to 00002 Besides those conservative parameters chosen to prevent overfitting only 40 percents of available columns are selected for tree construction at each round and 95 of subjects These parameters have been kept fixed and chosen to ensure stability of results Small perturbations around these values could result in local performance improvements but would not be practically chosen given the size of the dataset
In order to gain some insights into the most useful variables in terms of predictive power we then conducted a post-hoc analysis based on the following methodology at each surgical step 400 models have been trained for the repeated cross-validation procedure For each model we retain the rank of each variable as given by the variable importance procedure of XGBoost The average rank of each variable for each step is then computed by averaging the ranks obtained by variables for each of the 400 models At step 9 variables are ordered based on their average rank increasing average ranks They are then incrementally used as input of a new cross-validation procedure repeated 20 times
Continuous variables are presented as median interquartile range IQR or mean and 95CI and were compared using independent T-test or Mann-Whitney test Categorical variables are presented as n and were compared using Chi-squared test or Fishers exact test We applied machine learning algorithm to predict 3-day ahead primary graft dysfunction after lung transplant surgery among patients Machine learning is a branch of artificial intelligence where computer systems can learn from available data and identify patterns with minimal human intervention Machine learning algorithm tests on data and performance metrics were used to obtain the higher performing algorithm In this study we performed a XGBoost Gradient Boosting algorithm which was a combination of decisions trees Each decision tree typically learned from its precursor and passed on the improved function to the following The weighted combination of these trees provided the prediction
No particular data transformation has been performed on numerical variables Categorical variables have been encoded as integer without any further pre-processing steps In particular no specific processing has been performed to deal with missing data The default behavior of XGBoost has been used It consists in treating missing data as a specific modality During the training step of XGBoost models missing values are treated as other values and left or right decisions at any branch of a tree are learned by optimizing the outcome
In order to reflect the sequential nature of this predictive medicine problem nine steps have been defined to take into account incrementally observed variables acquired at various stages of the surgery
Step 1 recipient variables Step 2 donor variables Step 3 arrival in the OR Step 4 after anesthetic induction Step 5 during first pneumonectomy Step 6 after first graft implantation Step 7 second pneumonectomy Step 8 second graft implantation Step 9 end surgery status At each of the nine steps a cross-validation procedure is employed to assess the predictive performance of a machine learning model XGBoost One repetition of the cross-validation procedure is designed as follows the dataset of subjects is randomly split into eight disjoint parts Successively the performance of the XGBoost model on each of the eight subsetwhile training the machine learning model using the remaining seven subsets For such a repetition the predictive probability of 3-day ahead primary graft dysfunction for each subject is retained to finally compute the area under ROC receiving operator curve To evaluate the variability of the predictive performance of the machine learning model this cross-validation procedure is repeated fifty times with randomly chosen subjects partitions For each of the fifty times eight times nine repetitions partitions surgical steps hence 3600 models training a conservative approach has been adopted for XGBoost training consisting in a unique set of training parameters These parameters have been chosen to prevent overfitting due to a relatively small number of subjects compared to the number of variables especially categorical variables which yield a high degree of freedom Specifically XGBoost has been trained for 400 rounds no early stopping a maximum depth of 5 for each tree a minimum child weight of 3 and a learning parameter eta equals to 00002 Besides those conservative parameters chosen to prevent overfitting only 40 percents of available columns are selected for tree construction at each round and 95 of subjects These parameters have been kept fixed and chosen to ensure stability of results Small perturbations around these values could result in local performance improvements but would not be practically chosen given the size of the dataset
In order to gain some insights into the most useful variables in terms of predictive power we then conducted a post-hoc analysis based on the following methodology at each surgical step 400 models have been trained for the repeated cross-validation procedure For each model we retain the rank of each variable as given by the variable importance procedure of XGBoost The average rank of each variable for each step is then computed by averaging the ranks obtained by variables for each of the 400 models At step 9 variables are ordered based on their average rank increasing average ranks They are then incrementally used as input of a new cross-validation procedure repeated 20 times
Study Oversight
Has Oversight DMC:
None
Is a FDA Regulated Drug?:
False
Is a FDA Regulated Device?:
False
Is an Unapproved Device?:
None
Is a PPSD?:
None
Is a US Export?:
None
Is an FDA AA801 Violation?:
None