Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context
Summary: Background: Type 2 diabetes mellitus (T2DM) is a significant global public health concern that has steadily increased over the past few decades. Thus, this study aimed to predict the incidence of T2DM within 5 years and the risk of mortality following the onset of T2DM. Data from three ind...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | EClinicalMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S258953702500001X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832595339494817792 |
|---|---|
| author | Hayeon Lee Seung Ha Hwang Seoyoung Park Yunjeong Choi Sooji Lee Jaeyu Park Yejun Son Hyeon Jin Kim Soeun Kim Jiyeon Oh Lee Smith Damiano Pizzol Sang Youl Rhee Hyunji Sang Jinseok Lee Dong Keon Yon |
| author_facet | Hayeon Lee Seung Ha Hwang Seoyoung Park Yunjeong Choi Sooji Lee Jaeyu Park Yejun Son Hyeon Jin Kim Soeun Kim Jiyeon Oh Lee Smith Damiano Pizzol Sang Youl Rhee Hyunji Sang Jinseok Lee Dong Keon Yon |
| author_sort | Hayeon Lee |
| collection | DOAJ |
| description | Summary: Background: Type 2 diabetes mellitus (T2DM) is a significant global public health concern that has steadily increased over the past few decades. Thus, this study aimed to predict the incidence of T2DM within 5 years and the risk of mortality following the onset of T2DM. Data from three independent cohorts worldwide were used. Methods: We utilized data from three independent, large-scale, general population-based, and worldwide cohort studies. The Korean cohort (NHIS-NSC cohort; discovery cohort; n = 973,303), conducted between 1 January, 2002 and 31 December, 2013, was used for training and internal validation, whereas the Japanese cohort (JMDC cohort; validation cohort A; n = 12,143,715) and UK cohort (UK Biobank; validation cohort B; n = 416,656) were used for external validation. We employed various machine learning (ML)-based models, using 18 features, to predict the incidence of T2DM within five years of regular health checkups and calculated the Shapley Additive Explanation (SHAP) values. To ensure the robustness of our ML-based prediction model, we investigated the potential association between the model probability divided into tertiles and the risk of mortality following the onset of T2DM. Findings: In the discovery cohort, the ensemble model using voting with logistic regression and adaptive boosting achieved a balanced accuracy of 72.6% and an area under the receiver operating characteristics curve (AUROC) of 0.792. The SHAP value analysis of our proposed model revealed that age was the most important predictor of incident T2DM, followed by fasting blood glucose, hemoglobin, γ-glutamyl transferase level, and body mass index. The model probability is associated with an increased risk of mortality (T1: adjusted hazard ratio, 2.82 [95% CI, 2.01–3.94]; T2: 3.89 [2.74–5.53]; and T3: 7.73 [5.37–11.12]). Similar patterns and trends were observed in the validation cohorts (T1: 1.74 [1.49–2.03], T2: 1.97 [1.69–2.30], and T3: 3.31 [2.82–3.38] in validation cohort A; T1: 1.33 [1.03–1.71], T2: 1.54 [1.21–1.96], and T3: 1.73 [1.36–2.20] in validation cohort B). Interpretation: This study derived and validated an ML-based model to predict the incidence of T2DM within 5 years across three countries (South Korea, Japan, and the UK), showing that the model probability is associated with an increased risk of mortality. Funding: Institute of Information & Communications Technology Planning & Evaluation, South Korea. |
| format | Article |
| id | doaj-art-938ac8969ae147b68f4708221d4a51d5 |
| institution | Kabale University |
| issn | 2589-5370 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EClinicalMedicine |
| spelling | doaj-art-938ac8969ae147b68f4708221d4a51d52025-01-19T06:26:31ZengElsevierEClinicalMedicine2589-53702025-02-0180103069Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in contextHayeon Lee0Seung Ha Hwang1Seoyoung Park2Yunjeong Choi3Sooji Lee4Jaeyu Park5Yejun Son6Hyeon Jin Kim7Soeun Kim8Jiyeon Oh9Lee Smith10Damiano Pizzol11Sang Youl Rhee12Hyunji Sang13Jinseok Lee14Dong Keon Yon15Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Biomedical Engineering, Kyung Hee University, Yongin, South Korea; Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Biomedical Engineering, Kyung Hee University, Yongin, South Korea; Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Precision Medicine, Kyung Hee University College of Medicine, Seoul, South KoreaDepartment of Biomedical Engineering, Kyung Hee University, Yongin, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Regulatory Science, Kyung Hee University, Seoul, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Precision Medicine, Kyung Hee University College of Medicine, Seoul, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Regulatory Science, Kyung Hee University, Seoul, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Precision Medicine, Kyung Hee University College of Medicine, Seoul, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South KoreaCentre for Health Performance and Wellbeing, Anglia Ruskin University, Cambridge, UKHealth Unit Eni, Maputo, Mozambique; Health Unit, Eni, San Donato Milanese, ItalyCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Precision Medicine, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Regulatory Science, Kyung Hee University, Seoul, South Korea; Department of Endocrinology and Metabolism, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, South KoreaCenter for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Endocrinology and Metabolism, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, South Korea; Corresponding author. Department of Endocrinology and Metabolism, Kyung Hee University College of Medicine, 23 Kyungheedae-ro, Dongdaemun-gu, Seoul, 02447, South Korea.Department of Biomedical Engineering, Kyung Hee University, Yongin, South Korea; Department of Electronics and Information Convergence Engineering, Kyung Hee University, Yongin, South Korea; Corresponding author. Department of Biomedical Engineering, Kyung Hee University, 1732, Deogyeong-daero, Giheung-gu, Yongin-si, Gyeonggi-do, Yongin, 17104, South Korea.Center for Digital Health, Medical Science Research Institute, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Biomedical Engineering, Kyung Hee University, Yongin, South Korea; Department of Precision Medicine, Kyung Hee University College of Medicine, Seoul, South Korea; Department of Regulatory Science, Kyung Hee University, Seoul, South Korea; Department of Pediatrics, Kyung Hee University Medical Center, Kyung Hee University College of Medicine, Seoul, South Korea; Corresponding author. Department of Pediatrics, Kyung Hee University College of Medicine, 23 Kyungheedae-ro, Dongdaemun-gu, Seoul, 02447, South Korea.Summary: Background: Type 2 diabetes mellitus (T2DM) is a significant global public health concern that has steadily increased over the past few decades. Thus, this study aimed to predict the incidence of T2DM within 5 years and the risk of mortality following the onset of T2DM. Data from three independent cohorts worldwide were used. Methods: We utilized data from three independent, large-scale, general population-based, and worldwide cohort studies. The Korean cohort (NHIS-NSC cohort; discovery cohort; n = 973,303), conducted between 1 January, 2002 and 31 December, 2013, was used for training and internal validation, whereas the Japanese cohort (JMDC cohort; validation cohort A; n = 12,143,715) and UK cohort (UK Biobank; validation cohort B; n = 416,656) were used for external validation. We employed various machine learning (ML)-based models, using 18 features, to predict the incidence of T2DM within five years of regular health checkups and calculated the Shapley Additive Explanation (SHAP) values. To ensure the robustness of our ML-based prediction model, we investigated the potential association between the model probability divided into tertiles and the risk of mortality following the onset of T2DM. Findings: In the discovery cohort, the ensemble model using voting with logistic regression and adaptive boosting achieved a balanced accuracy of 72.6% and an area under the receiver operating characteristics curve (AUROC) of 0.792. The SHAP value analysis of our proposed model revealed that age was the most important predictor of incident T2DM, followed by fasting blood glucose, hemoglobin, γ-glutamyl transferase level, and body mass index. The model probability is associated with an increased risk of mortality (T1: adjusted hazard ratio, 2.82 [95% CI, 2.01–3.94]; T2: 3.89 [2.74–5.53]; and T3: 7.73 [5.37–11.12]). Similar patterns and trends were observed in the validation cohorts (T1: 1.74 [1.49–2.03], T2: 1.97 [1.69–2.30], and T3: 3.31 [2.82–3.38] in validation cohort A; T1: 1.33 [1.03–1.71], T2: 1.54 [1.21–1.96], and T3: 1.73 [1.36–2.20] in validation cohort B). Interpretation: This study derived and validated an ML-based model to predict the incidence of T2DM within 5 years across three countries (South Korea, Japan, and the UK), showing that the model probability is associated with an increased risk of mortality. Funding: Institute of Information & Communications Technology Planning & Evaluation, South Korea.http://www.sciencedirect.com/science/article/pii/S258953702500001XDiabetes mellitusJapanMachine learningMortalitySouth KoreaUnited Kingdom |
| spellingShingle | Hayeon Lee Seung Ha Hwang Seoyoung Park Yunjeong Choi Sooji Lee Jaeyu Park Yejun Son Hyeon Jin Kim Soeun Kim Jiyeon Oh Lee Smith Damiano Pizzol Sang Youl Rhee Hyunji Sang Jinseok Lee Dong Keon Yon Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context EClinicalMedicine Diabetes mellitus Japan Machine learning Mortality South Korea United Kingdom |
| title | Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context |
| title_full | Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context |
| title_fullStr | Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context |
| title_full_unstemmed | Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context |
| title_short | Prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from South Korea, Japan, and the UK: a model development and validation studyResearch in context |
| title_sort | prediction model for type 2 diabetes mellitus and its association with mortality using machine learning in three independent cohorts from south korea japan and the uk a model development and validation studyresearch in context |
| topic | Diabetes mellitus Japan Machine learning Mortality South Korea United Kingdom |
| url | http://www.sciencedirect.com/science/article/pii/S258953702500001X |
| work_keys_str_mv | AT hayeonlee predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT seunghahwang predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT seoyoungpark predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT yunjeongchoi predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT soojilee predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT jaeyupark predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT yejunson predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT hyeonjinkim predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT soeunkim predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT jiyeonoh predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT leesmith predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT damianopizzol predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT sangyoulrhee predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT hyunjisang predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT jinseoklee predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext AT dongkeonyon predictionmodelfortype2diabetesmellitusanditsassociationwithmortalityusingmachinelearninginthreeindependentcohortsfromsouthkoreajapanandtheukamodeldevelopmentandvalidationstudyresearchincontext |