PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH

Diabetes mellitus as a metabolic disease characterized by hyperglycemia can be dangerous if it cannot be handled properly. Early detection of existing symptoms can reduce the impact of delays in treatment. This study aims to carry out early-detection patients with diabetes mellitus using a machine l...

Full description

Saved in:
Bibliographic Details
Main Authors: Novia Permatasari, Shafiyah Asy Syahidah, Aldo Leofiro Irfiansyah, M. Ghozy Al-Haqqoni
Format: Article
Language:English
Published: Universitas Pattimura 2022-06-01
Series:Barekeng
Subjects:
Online Access:https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/5273
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849762842474971136
author Novia Permatasari
Shafiyah Asy Syahidah
Aldo Leofiro Irfiansyah
M. Ghozy Al-Haqqoni
author_facet Novia Permatasari
Shafiyah Asy Syahidah
Aldo Leofiro Irfiansyah
M. Ghozy Al-Haqqoni
author_sort Novia Permatasari
collection DOAJ
description Diabetes mellitus as a metabolic disease characterized by hyperglycemia can be dangerous if it cannot be handled properly. Early detection of existing symptoms can reduce the impact of delays in treatment. This study aims to carry out early-detection patients with diabetes mellitus using a machine learning approach through data from MIT’s GOSSIS (Global Open Source Severity of Illness Score). By using Shapley Additive Explanation (SHAP) which enables prioritization of feature that determine compound classification, this study shows that the CatBoost classifier has 14 features that significantly can be used for classification with feature ‘d1_glucose_max’ or the highest glucose concentration of the patient in their serum or plasma during the first 24 hours of their unit stay has the highest impact to classify diabetes mellitus patients, then followed by age and glucose APACHE. The selected features are then classified and get the validation AUC score of 86.86%.
format Article
id doaj-art-d1b8ff43d05e400ebf3d79e8d809e0d6
institution DOAJ
issn 1978-7227
2615-3017
language English
publishDate 2022-06-01
publisher Universitas Pattimura
record_format Article
series Barekeng
spelling doaj-art-d1b8ff43d05e400ebf3d79e8d809e0d62025-08-20T03:05:38ZengUniversitas PattimuraBarekeng1978-72272615-30172022-06-0116261562410.30598/barekengvol16iss2pp615-6245273PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACHNovia Permatasari0Shafiyah Asy Syahidah1Aldo Leofiro Irfiansyah2M. Ghozy Al-Haqqoni3BPS-Statistics IndonesiaBPS-Statistics IndonesiaStatistics Sula Islands DistrictBPS-Statistics IndonesiaDiabetes mellitus as a metabolic disease characterized by hyperglycemia can be dangerous if it cannot be handled properly. Early detection of existing symptoms can reduce the impact of delays in treatment. This study aims to carry out early-detection patients with diabetes mellitus using a machine learning approach through data from MIT’s GOSSIS (Global Open Source Severity of Illness Score). By using Shapley Additive Explanation (SHAP) which enables prioritization of feature that determine compound classification, this study shows that the CatBoost classifier has 14 features that significantly can be used for classification with feature ‘d1_glucose_max’ or the highest glucose concentration of the patient in their serum or plasma during the first 24 hours of their unit stay has the highest impact to classify diabetes mellitus patients, then followed by age and glucose APACHE. The selected features are then classified and get the validation AUC score of 86.86%.https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/5273machine learningclassificationcatboostshap valuediabetes mellitus
spellingShingle Novia Permatasari
Shafiyah Asy Syahidah
Aldo Leofiro Irfiansyah
M. Ghozy Al-Haqqoni
PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH
Barekeng
machine learning
classification
catboost
shap value
diabetes mellitus
title PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH
title_full PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH
title_fullStr PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH
title_full_unstemmed PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH
title_short PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH
title_sort predicting diabetes mellitus using catboost classifier and shapley additive explanation shap approach
topic machine learning
classification
catboost
shap value
diabetes mellitus
url https://ojs3.unpatti.ac.id/index.php/barekeng/article/view/5273
work_keys_str_mv AT noviapermatasari predictingdiabetesmellitususingcatboostclassifierandshapleyadditiveexplanationshapapproach
AT shafiyahasysyahidah predictingdiabetesmellitususingcatboostclassifierandshapleyadditiveexplanationshapapproach
AT aldoleofiroirfiansyah predictingdiabetesmellitususingcatboostclassifierandshapleyadditiveexplanationshapapproach
AT mghozyalhaqqoni predictingdiabetesmellitususingcatboostclassifierandshapleyadditiveexplanationshapapproach