-
Categories
-
Pharmaceutical Intermediates
-
Active Pharmaceutical Ingredients
-
Food Additives
- Industrial Coatings
- Agrochemicals
- Dyes and Pigments
- Surfactant
- Flavors and Fragrances
- Chemical Reagents
- Catalyst and Auxiliary
- Natural Products
- Inorganic Chemistry
-
Organic Chemistry
-
Biochemical Engineering
- Analytical Chemistry
- Cosmetic Ingredient
-
Pharmaceutical Intermediates
Promotion
ECHEMI Mall
Wholesale
Weekly Price
Exhibition
News
-
Trade Service
In order to explore the feasibility of using machine learning technology to predict the risk of recurrence after surgery for stage IV colorectal cancer, the Yang Jianjun team of the Department of Anesthesiology and Perioperative Medicine of the First Affiliated Hospital of Zhengzhou University used 4 machine learning algorithms (logistic regression, decision tree, GradientBoosting).
And lightGBM), the data set is randomly divided into a training group and a test group at a ratio of 8 to 2
.
The team included 999 patients with stage IV colorectal cancer into the study
.
In the training group, GradientBoosting has the highest AUC value of 0.
881; Logistic has the lowest AUC value of 0.
734; GradientBoosting has the highest F1 score (0.
912)
.
In the test group, Logistic has the lowest AUC value (0.
692); the GradientBoosting algorithm has a AUC value of 0.
734, this model can still predict cancer recurrence; however, the gbm algorithm model has the highest AUC value (0.
761) and F1 score (0.
974) )
.
The performance of GradientBoosting and gbm algorithm is better than the other two algorithms
.
The weight analysis of the GradientBoosting algorithm shows that chemotherapy, age, LogCEA, CEA and anesthesia time may be the top 5 related factors for tumor recurrence
.
These four machine learning algorithms can predict the risk of recurrence in patients with stage IV colorectal cancer after surgery
.
Among them, GradientBoosting and gbm performed best
.
In addition, the weight analysis of the GradientBoosting algorithm shows that the top five related variables that affect postoperative tumor recurrence are chemotherapy, age, LogCEA, CEA, and anesthesia time
.
© naturedoi: 10.
1038/s41598-020-59115-y
And lightGBM), the data set is randomly divided into a training group and a test group at a ratio of 8 to 2
.
The team included 999 patients with stage IV colorectal cancer into the study
.
In the training group, GradientBoosting has the highest AUC value of 0.
881; Logistic has the lowest AUC value of 0.
734; GradientBoosting has the highest F1 score (0.
912)
.
In the test group, Logistic has the lowest AUC value (0.
692); the GradientBoosting algorithm has a AUC value of 0.
734, this model can still predict cancer recurrence; however, the gbm algorithm model has the highest AUC value (0.
761) and F1 score (0.
974) )
.
The performance of GradientBoosting and gbm algorithm is better than the other two algorithms
.
The weight analysis of the GradientBoosting algorithm shows that chemotherapy, age, LogCEA, CEA and anesthesia time may be the top 5 related factors for tumor recurrence
.
These four machine learning algorithms can predict the risk of recurrence in patients with stage IV colorectal cancer after surgery
.
Among them, GradientBoosting and gbm performed best
.
In addition, the weight analysis of the GradientBoosting algorithm shows that the top five related variables that affect postoperative tumor recurrence are chemotherapy, age, LogCEA, CEA, and anesthesia time
.
© naturedoi: 10.
1038/s41598-020-59115-y