Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes
Summary: Background: Individuals with long standing diabetes duration can experience damage to small microvascular blood vessels leading to diabetes complications (DCs) and increased mortality. Precision diagnostic tailors a diagnosis to an individual by using biomedical information. Blood small mo...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-06-01
|
| Series: | EBioMedicine |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352396422002134 |
| _version_ | 1818230230438903808 |
|---|---|
| author | Naba Al-Sari Svetlana Kutuzova Tommi Suvitaival Peter Henriksen Flemming Pociot Peter Rossing Douglas McCloskey Cristina Legido-Quigley |
| author_facet | Naba Al-Sari Svetlana Kutuzova Tommi Suvitaival Peter Henriksen Flemming Pociot Peter Rossing Douglas McCloskey Cristina Legido-Quigley |
| author_sort | Naba Al-Sari |
| collection | DOAJ |
| description | Summary: Background: Individuals with long standing diabetes duration can experience damage to small microvascular blood vessels leading to diabetes complications (DCs) and increased mortality. Precision diagnostic tailors a diagnosis to an individual by using biomedical information. Blood small molecule profiling coupled with machine learning (ML) can facilitate the goals of precision diagnostics, including earlier diagnosis and individualized risk scoring. Methods: Using data in a cohort of 537 adults with type 1 diabetes (T1D) we predicted five-year progression to DCs. Prediction models were computed first with clinical risk factors at baseline and then with clinical risk factors and blood-derived molecular data at baseline. Progression of diabetic kidney disease and diabetic retinopathy were predicted in two complication-specific models. Findings: The model predicts the progression to diabetic kidney disease with accuracy: 0.96 ± 0.25 and 0.96 ± 0.06 area under curve, AUC, with clinical measurements and with small molecule predictors respectively and highlighted main predictors to be albuminuria, glomerular filtration rate, retinopathy status at baseline, sugar derivatives and ketones. For diabetic retinopathy, AUC 0.75 ± 0.14 and 0.79 ± 0.16 with clinical measurements and with small molecule predictors respectively and highlighted key predictors, albuminuria, glomerular filtration rate and retinopathy status at baseline. Individual risk scores were built to visualize results. Interpretation: With further validation ML tools could facilitate the implementation of precision diagnosis in the clinic. It is envisaged that patients could be screened for complications, before these occur, thus preserving healthy life-years for persons with diabetes. Funding: This study has been financially supported by Novo Nordisk Foundation grant NNF14OC0013659. |
| first_indexed | 2024-12-12T10:31:12Z |
| format | Article |
| id | doaj.art-894a854b1c2d4e6f82a36df6e28af443 |
| institution | Directory Open Access Journal |
| issn | 2352-3964 |
| language | English |
| last_indexed | 2024-12-12T10:31:12Z |
| publishDate | 2022-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | EBioMedicine |
| spelling | doaj.art-894a854b1c2d4e6f82a36df6e28af4432022-12-22T00:27:22ZengElsevierEBioMedicine2352-39642022-06-0180104032Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetesNaba Al-Sari0Svetlana Kutuzova1Tommi Suvitaival2Peter Henriksen3Flemming Pociot4Peter Rossing5Douglas McCloskey6Cristina Legido-Quigley7Steno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, DenmarkNovo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, Vej Building 220, Lyngby DK-2800, DenmarkSteno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, DenmarkSteno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, DenmarkSteno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, Denmark; Department of Clinical Medicine, University of Copenhagen, DenmarkSteno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, Denmark; Department of Clinical Medicine, University of Copenhagen, Denmark; Corresponding authors at: Steno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, Denmark.Novo Nordisk Foundation Center for Biosustainability, Technical University of Denmark, Vej Building 220, Lyngby DK-2800, Denmark; Corresponding author.Steno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, Denmark; Institute of Pharmaceutical Science, King's College London, UK; Corresponding authors at: Steno Diabetes Center Copenhagen, Niels Steensens Vej 2-4, Gentofte DK-2820, Denmark.Summary: Background: Individuals with long standing diabetes duration can experience damage to small microvascular blood vessels leading to diabetes complications (DCs) and increased mortality. Precision diagnostic tailors a diagnosis to an individual by using biomedical information. Blood small molecule profiling coupled with machine learning (ML) can facilitate the goals of precision diagnostics, including earlier diagnosis and individualized risk scoring. Methods: Using data in a cohort of 537 adults with type 1 diabetes (T1D) we predicted five-year progression to DCs. Prediction models were computed first with clinical risk factors at baseline and then with clinical risk factors and blood-derived molecular data at baseline. Progression of diabetic kidney disease and diabetic retinopathy were predicted in two complication-specific models. Findings: The model predicts the progression to diabetic kidney disease with accuracy: 0.96 ± 0.25 and 0.96 ± 0.06 area under curve, AUC, with clinical measurements and with small molecule predictors respectively and highlighted main predictors to be albuminuria, glomerular filtration rate, retinopathy status at baseline, sugar derivatives and ketones. For diabetic retinopathy, AUC 0.75 ± 0.14 and 0.79 ± 0.16 with clinical measurements and with small molecule predictors respectively and highlighted key predictors, albuminuria, glomerular filtration rate and retinopathy status at baseline. Individual risk scores were built to visualize results. Interpretation: With further validation ML tools could facilitate the implementation of precision diagnosis in the clinic. It is envisaged that patients could be screened for complications, before these occur, thus preserving healthy life-years for persons with diabetes. Funding: This study has been financially supported by Novo Nordisk Foundation grant NNF14OC0013659.http://www.sciencedirect.com/science/article/pii/S2352396422002134Diabetes complicationsDiabetic kidney diseaseDiabetic retinopathyMachine learningMicrovascular complications |
| spellingShingle | Naba Al-Sari Svetlana Kutuzova Tommi Suvitaival Peter Henriksen Flemming Pociot Peter Rossing Douglas McCloskey Cristina Legido-Quigley Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes EBioMedicine Diabetes complications Diabetic kidney disease Diabetic retinopathy Machine learning Microvascular complications |
| title | Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes |
| title_full | Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes |
| title_fullStr | Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes |
| title_full_unstemmed | Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes |
| title_short | Precision diagnostic approach to predict 5-year risk for microvascular complications in type 1 diabetes |
| title_sort | precision diagnostic approach to predict 5 year risk for microvascular complications in type 1 diabetes |
| topic | Diabetes complications Diabetic kidney disease Diabetic retinopathy Machine learning Microvascular complications |
| url | http://www.sciencedirect.com/science/article/pii/S2352396422002134 |
| work_keys_str_mv | AT nabaalsari precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT svetlanakutuzova precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT tommisuvitaival precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT peterhenriksen precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT flemmingpociot precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT peterrossing precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT douglasmccloskey precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes AT cristinalegidoquigley precisiondiagnosticapproachtopredict5yearriskformicrovascularcomplicationsintype1diabetes |