Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression
Type 1 diabetes (T1Ds) is a chronic, for now, incurable multifactorial disease caused by the immune-mediated destruction of insulin-producing pancreatic <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula>-cells, causing devastating and...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of Instrumentation and Measurement |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10929762/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850185656679006208 |
|---|---|
| author | Niels F. Cleymans Mark Van De Casteele Julie Vandewalle Aster K. Desouter Frans K. Gorus Kurt Barbe |
| author_facet | Niels F. Cleymans Mark Van De Casteele Julie Vandewalle Aster K. Desouter Frans K. Gorus Kurt Barbe |
| author_sort | Niels F. Cleymans |
| collection | DOAJ |
| description | Type 1 diabetes (T1Ds) is a chronic, for now, incurable multifactorial disease caused by the immune-mediated destruction of insulin-producing pancreatic <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula>-cells, causing devastating and costly acute and chronic complications, despite lifelong insulin treatment. Abrupt clinical onset is preceded by an asymptomatic disease phase of highly variable duration which is marked by the sequential appearance of various types of <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula>-cell autoantibodies (AAbs). Optimized predictions of time to clinical onset facilitate early diagnosis which is also key to reducing the incidence of inaugural life-threatening diabetic ketoacidosis and planning novel prevention trials in the asymptomatic stage. Research in first-degree relatives of known T1D patients has shown that disease progression can be predicted by genetic and immune biomarkers, but these predictions are limited by using the traditional statistical approaches such as Cox regression models. This explorative study aims to uncover the potential of random forest machine learning algorithms as survival models within the biomedical context of T1D. Two random forest survival models were constructed in R. The first constructed model predicts how long it will take for individuals to go from single to multiple AAb positivity (AAb+), a crucial step in T1D development. The second model predicts the transition from multiple AAb+ to the onset of T1D. This article demonstrates that our random forest survival models outperform traditional Cox regression methods; we conduct a detailed analysis of variable importance to uncover novel biomarker interactions; and we establish a refined framework for precise measurement and risk stratification of T1D, paving the way for earlier and more targeted intervention. |
| format | Article |
| id | doaj-art-ebcdef3f1b3248c7a17e2e5794d938c6 |
| institution | OA Journals |
| issn | 2768-7236 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of Instrumentation and Measurement |
| spelling | doaj-art-ebcdef3f1b3248c7a17e2e5794d938c62025-08-20T02:16:39ZengIEEEIEEE Open Journal of Instrumentation and Measurement2768-72362025-01-01411110.1109/OJIM.2025.355183710929762Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes ProgressionNiels F. Cleymans0https://orcid.org/0009-0007-5014-7878Mark Van De Casteele1https://orcid.org/0000-0002-8594-9260Julie Vandewalle2https://orcid.org/0000-0002-6419-9448Aster K. Desouter3https://orcid.org/0000-0001-9070-3882Frans K. Gorus4https://orcid.org/0000-0002-9007-6177Kurt Barbe5https://orcid.org/0000-0002-7825-9077Biostatistics and Medical Informatics Research Group, Vrije Universiteit Brussel, Brussels, BelgiumDiabetes Research Center, Vrije Universiteit Brussel, Brussels, BelgiumDiabetes Research Center, Vrije Universiteit Brussel, Brussels, BelgiumDiabetes Research Center, Vrije Universiteit Brussel, Brussels, BelgiumDiabetes Research Center, Vrije Universiteit Brussel, Brussels, BelgiumBiostatistics and Medical Informatics Research Group, Vrije Universiteit Brussel, Brussels, BelgiumType 1 diabetes (T1Ds) is a chronic, for now, incurable multifactorial disease caused by the immune-mediated destruction of insulin-producing pancreatic <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula>-cells, causing devastating and costly acute and chronic complications, despite lifelong insulin treatment. Abrupt clinical onset is preceded by an asymptomatic disease phase of highly variable duration which is marked by the sequential appearance of various types of <inline-formula> <tex-math notation="LaTeX">$\beta $ </tex-math></inline-formula>-cell autoantibodies (AAbs). Optimized predictions of time to clinical onset facilitate early diagnosis which is also key to reducing the incidence of inaugural life-threatening diabetic ketoacidosis and planning novel prevention trials in the asymptomatic stage. Research in first-degree relatives of known T1D patients has shown that disease progression can be predicted by genetic and immune biomarkers, but these predictions are limited by using the traditional statistical approaches such as Cox regression models. This explorative study aims to uncover the potential of random forest machine learning algorithms as survival models within the biomedical context of T1D. Two random forest survival models were constructed in R. The first constructed model predicts how long it will take for individuals to go from single to multiple AAb positivity (AAb+), a crucial step in T1D development. The second model predicts the transition from multiple AAb+ to the onset of T1D. This article demonstrates that our random forest survival models outperform traditional Cox regression methods; we conduct a detailed analysis of variable importance to uncover novel biomarker interactions; and we establish a refined framework for precise measurement and risk stratification of T1D, paving the way for earlier and more targeted intervention.https://ieeexplore.ieee.org/document/10929762/Biomarkersbiomedical computingbiostatisticscomputer-assisted diagnosisdecision treesdiabetes |
| spellingShingle | Niels F. Cleymans Mark Van De Casteele Julie Vandewalle Aster K. Desouter Frans K. Gorus Kurt Barbe Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression IEEE Open Journal of Instrumentation and Measurement Biomarkers biomedical computing biostatistics computer-assisted diagnosis decision trees diabetes |
| title | Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression |
| title_full | Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression |
| title_fullStr | Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression |
| title_full_unstemmed | Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression |
| title_short | Analyzing Random Forest’s Predictive Capability for Type 1 Diabetes Progression |
| title_sort | analyzing random forest x2019 s predictive capability for type 1 diabetes progression |
| topic | Biomarkers biomedical computing biostatistics computer-assisted diagnosis decision trees diabetes |
| url | https://ieeexplore.ieee.org/document/10929762/ |
| work_keys_str_mv | AT nielsfcleymans analyzingrandomforestx2019spredictivecapabilityfortype1diabetesprogression AT markvandecasteele analyzingrandomforestx2019spredictivecapabilityfortype1diabetesprogression AT julievandewalle analyzingrandomforestx2019spredictivecapabilityfortype1diabetesprogression AT asterkdesouter analyzingrandomforestx2019spredictivecapabilityfortype1diabetesprogression AT franskgorus analyzingrandomforestx2019spredictivecapabilityfortype1diabetesprogression AT kurtbarbe analyzingrandomforestx2019spredictivecapabilityfortype1diabetesprogression |