Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees
We define an iterative method for dimensionality reduction using categorical gradient boosted trees and Shapley values and created four machine learning models which potentially could be used as diagnostic tests for acute myeloid leukaemia (AML). For the final Catboost model we use a dataset of 2177...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Heliyon |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023077381 |
| _version_ | 1797646546796281856 |
|---|---|
| author | Athanasios Angelakis Ioanna Soulioti Michael Filippakis |
| author_facet | Athanasios Angelakis Ioanna Soulioti Michael Filippakis |
| author_sort | Athanasios Angelakis |
| collection | DOAJ |
| description | We define an iterative method for dimensionality reduction using categorical gradient boosted trees and Shapley values and created four machine learning models which potentially could be used as diagnostic tests for acute myeloid leukaemia (AML). For the final Catboost model we use a dataset of 2177 individuals using as features 16 probe sets and the age in order to classify if someone has AML or is healthy. The dataset is multicentric and consists of data from 27 organizations, 25 cities, 15 countries and 4 continents. The performance of our last model is specificity: 0.9909, sensitivity: 0.9985, F1-score: 0.9976 and its ROC-AUC: 0.9962 using ten fold cross validation. On an inference dataset the perormance is: specificity: 0.9909, sensitivity: 0.9969, F1-score: 0.9969 and its ROC-AUC: 0.9939. To the best of our knowledge the performance of our model is the best one in the literature, as regards the diagnosis of AML using similar or not data. Moreover, there has not been any bibliographic reference which associates AML or any other type of cancer with the 16 probe sets we used as features in our final model. |
| first_indexed | 2024-03-11T15:04:18Z |
| format | Article |
| id | doaj.art-e188e06b8e4841d4a75f70166f3fd500 |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-11T15:04:18Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-e188e06b8e4841d4a75f70166f3fd5002023-10-30T06:06:28ZengElsevierHeliyon2405-84402023-10-01910e20530Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted treesAthanasios Angelakis0Ioanna Soulioti1Michael Filippakis2Department of Epidemiology and Data Science, Amsterdam University Medical Centers, Amsterdam Public Health Research Institute, University of Amsterdam Data Science Center, Netherlands; Corresponding author.Department of Biology, National and Kapodistrian University of Athens, GreeceDepartment of Digital Systems, University of Piraeus, GreeceWe define an iterative method for dimensionality reduction using categorical gradient boosted trees and Shapley values and created four machine learning models which potentially could be used as diagnostic tests for acute myeloid leukaemia (AML). For the final Catboost model we use a dataset of 2177 individuals using as features 16 probe sets and the age in order to classify if someone has AML or is healthy. The dataset is multicentric and consists of data from 27 organizations, 25 cities, 15 countries and 4 continents. The performance of our last model is specificity: 0.9909, sensitivity: 0.9985, F1-score: 0.9976 and its ROC-AUC: 0.9962 using ten fold cross validation. On an inference dataset the perormance is: specificity: 0.9909, sensitivity: 0.9969, F1-score: 0.9969 and its ROC-AUC: 0.9939. To the best of our knowledge the performance of our model is the best one in the literature, as regards the diagnosis of AML using similar or not data. Moreover, there has not been any bibliographic reference which associates AML or any other type of cancer with the 16 probe sets we used as features in our final model.http://www.sciencedirect.com/science/article/pii/S2405844023077381 |
| spellingShingle | Athanasios Angelakis Ioanna Soulioti Michael Filippakis Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees Heliyon |
| title | Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees |
| title_full | Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees |
| title_fullStr | Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees |
| title_full_unstemmed | Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees |
| title_short | Diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees |
| title_sort | diagnosis of acute myeloid leukaemia on microarray gene expression data using categorical gradient boosted trees |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023077381 |
| work_keys_str_mv | AT athanasiosangelakis diagnosisofacutemyeloidleukaemiaonmicroarraygeneexpressiondatausingcategoricalgradientboostedtrees AT ioannasoulioti diagnosisofacutemyeloidleukaemiaonmicroarraygeneexpressiondatausingcategoricalgradientboostedtrees AT michaelfilippakis diagnosisofacutemyeloidleukaemiaonmicroarraygeneexpressiondatausingcategoricalgradientboostedtrees |