All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values
Background/Objectives: Diabetes mellitus (DM) is a prevalent disease with an increased risk of complications. Identifying risk factors for mortality in these patients is crucial, as early recognition can facilitate prompt therapeutic intervention. Machine learning (ML) models have proved to be valua...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Diabetology |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4540/6/1/5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588716186533888 |
|---|---|
| author | Oana Mirea Mostafa Ghelich Oghli Oana Neagoe Mihaela Berceanu Eugen Țieranu Liviu Moraru Victor Raicea Ionuț Donoiu |
| author_facet | Oana Mirea Mostafa Ghelich Oghli Oana Neagoe Mihaela Berceanu Eugen Țieranu Liviu Moraru Victor Raicea Ionuț Donoiu |
| author_sort | Oana Mirea |
| collection | DOAJ |
| description | Background/Objectives: Diabetes mellitus (DM) is a prevalent disease with an increased risk of complications. Identifying risk factors for mortality in these patients is crucial, as early recognition can facilitate prompt therapeutic intervention. Machine learning (ML) models have proved to be valuable tools in different scenarios of healthcare decision making. We aimed to develop and test an ML model to predict all-cause mortality in a large cohort of subjects with DM. Methods: We included 1969 consecutive patients with DM type 1 (T1DM, <i>n</i> = 255) and type 2 (T2DM, <i>n</i> = 1714). eXtreme Gradient Boosting (XGBoost) was used for the prediction of all-cause mortality in this cohort and the Shapley additive explanation (SHAP) was used to assess the importance of each feature of the classifier. The missing values were imputed using the Missforest methodology. Results: The all-cause mortality rate was 21% during 5.5 ± 1.1 years of follow-up. The ML model achieved 90% sensitivity and 87% specificity with an AUC of 0.88 and an accuracy of 88% for predicting all-cause mortality. The SHAP analysis identified a lower glomerular filtration rate (eGFR), duration of insulin therapy, and a lower level of hemoglobin as the first three factors that contribute to the higher mortality rate. Conclusions: ML models can become valuable tools in clinical practice due to their unique ability to simultaneously assess the cumulative influence of multiple parameters and discover high-order interactions. The application of such models in clinical practice could improve the early identification of subjects at risk for complications and mortality and prompt early therapeutical interventions. |
| format | Article |
| id | doaj-art-a2d176fd0dfd415a8c9babaf439a1a03 |
| institution | Kabale University |
| issn | 2673-4540 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diabetology |
| spelling | doaj-art-a2d176fd0dfd415a8c9babaf439a1a032025-01-24T13:28:46ZengMDPI AGDiabetology2673-45402025-01-0161510.3390/diabetology6010005All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley ValuesOana Mirea0Mostafa Ghelich Oghli1Oana Neagoe2Mihaela Berceanu3Eugen Țieranu4Liviu Moraru5Victor Raicea6Ionuț Donoiu7Department of Cardiology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, RomaniaResearch and Development Department, Med Fanavaran Plus Co., Karaj 3187411213, IranDepartment of Cardiology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, RomaniaDepartment of Cardiology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, RomaniaDepartment of Cardiology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, RomaniaDepartment of Anatomy, “George Emil Palade” University of Medicine, Pharmacy, Sciences and Technology, 540142 Târgu Mureș, RomaniaDepartment of Cardiovascular Surgery, University of Medicine and Pharmacy of Craiova, 200349 Craiova, RomaniaDepartment of Cardiology, University of Medicine and Pharmacy of Craiova, 200349 Craiova, RomaniaBackground/Objectives: Diabetes mellitus (DM) is a prevalent disease with an increased risk of complications. Identifying risk factors for mortality in these patients is crucial, as early recognition can facilitate prompt therapeutic intervention. Machine learning (ML) models have proved to be valuable tools in different scenarios of healthcare decision making. We aimed to develop and test an ML model to predict all-cause mortality in a large cohort of subjects with DM. Methods: We included 1969 consecutive patients with DM type 1 (T1DM, <i>n</i> = 255) and type 2 (T2DM, <i>n</i> = 1714). eXtreme Gradient Boosting (XGBoost) was used for the prediction of all-cause mortality in this cohort and the Shapley additive explanation (SHAP) was used to assess the importance of each feature of the classifier. The missing values were imputed using the Missforest methodology. Results: The all-cause mortality rate was 21% during 5.5 ± 1.1 years of follow-up. The ML model achieved 90% sensitivity and 87% specificity with an AUC of 0.88 and an accuracy of 88% for predicting all-cause mortality. The SHAP analysis identified a lower glomerular filtration rate (eGFR), duration of insulin therapy, and a lower level of hemoglobin as the first three factors that contribute to the higher mortality rate. Conclusions: ML models can become valuable tools in clinical practice due to their unique ability to simultaneously assess the cumulative influence of multiple parameters and discover high-order interactions. The application of such models in clinical practice could improve the early identification of subjects at risk for complications and mortality and prompt early therapeutical interventions.https://www.mdpi.com/2673-4540/6/1/5diabetes mellitusmachine learningall-cause mortality |
| spellingShingle | Oana Mirea Mostafa Ghelich Oghli Oana Neagoe Mihaela Berceanu Eugen Țieranu Liviu Moraru Victor Raicea Ionuț Donoiu All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values Diabetology diabetes mellitus machine learning all-cause mortality |
| title | All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values |
| title_full | All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values |
| title_fullStr | All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values |
| title_full_unstemmed | All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values |
| title_short | All-Cause Mortality Prediction in Subjects with Diabetes Mellitus Using a Machine Learning Model and Shapley Values |
| title_sort | all cause mortality prediction in subjects with diabetes mellitus using a machine learning model and shapley values |
| topic | diabetes mellitus machine learning all-cause mortality |
| url | https://www.mdpi.com/2673-4540/6/1/5 |
| work_keys_str_mv | AT oanamirea allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT mostafaghelichoghli allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT oananeagoe allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT mihaelaberceanu allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT eugentieranu allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT liviumoraru allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT victorraicea allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues AT ionutdonoiu allcausemortalitypredictioninsubjectswithdiabetesmellitususingamachinelearningmodelandshapleyvalues |