Dynamic risk prediction for diabetes using biomarker change measurements
Abstract Background Dynamic risk models, which incorporate disease-free survival and repeated measurements over time, might yield more accurate predictions of future health status compared to static models. The objective of this study was to develop and apply a dynamic prediction model to estimate t...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2019-08-01
|
| Series: | BMC Medical Research Methodology |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s12874-019-0812-y |
| _version_ | 1818319203531227136 |
|---|---|
| author | Layla Parast Megan Mathews Mark W. Friedberg |
| author_facet | Layla Parast Megan Mathews Mark W. Friedberg |
| author_sort | Layla Parast |
| collection | DOAJ |
| description | Abstract Background Dynamic risk models, which incorporate disease-free survival and repeated measurements over time, might yield more accurate predictions of future health status compared to static models. The objective of this study was to develop and apply a dynamic prediction model to estimate the risk of developing type 2 diabetes mellitus. Methods Both a static prediction model and a dynamic landmark model were used to provide predictions of a 2-year horizon time for diabetes-free survival, updated at 1, 2, and 3 years post-baseline i.e., predicting diabetes-free survival to 2 years and predicting diabetes-free survival to 3 years, 4 years, and 5 years post-baseline, given the patient already survived past 1 year, 2 years, and 3 years post-baseline, respectively. Prediction accuracy was evaluated at each time point using robust non-parametric procedures. Data from 2057 participants of the Diabetes Prevention Program (DPP) study (1027 in metformin arm, 1030 in placebo arm) were analyzed. Results The dynamic landmark model demonstrated good prediction accuracy with area under curve (AUC) estimates ranging from 0.645 to 0.752 and Brier Score estimates ranging from 0.088 to 0.135. Relative to a static risk model, the dynamic landmark model did not significantly differ in terms of AUC but had significantly lower (i.e., better) Brier Score estimates for predictions at 1, 2, and 3 years (e.g. 0.167 versus 0.099; difference − 0.068 95% CI − 0.083 to − 0.053, at 3 years in placebo group) post-baseline. Conclusions Dynamic prediction models based on longitudinal, repeated risk factor measurements have the potential to improve the accuracy of future health status predictions. |
| first_indexed | 2024-12-13T10:05:23Z |
| format | Article |
| id | doaj.art-238db898423f41039c505006dcc6a062 |
| institution | Directory Open Access Journal |
| issn | 1471-2288 |
| language | English |
| last_indexed | 2024-12-13T10:05:23Z |
| publishDate | 2019-08-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Research Methodology |
| spelling | doaj.art-238db898423f41039c505006dcc6a0622022-12-21T23:51:33ZengBMCBMC Medical Research Methodology1471-22882019-08-0119111210.1186/s12874-019-0812-yDynamic risk prediction for diabetes using biomarker change measurementsLayla Parast0Megan Mathews1Mark W. Friedberg2RAND CorporationRAND CorporationRAND CorporationAbstract Background Dynamic risk models, which incorporate disease-free survival and repeated measurements over time, might yield more accurate predictions of future health status compared to static models. The objective of this study was to develop and apply a dynamic prediction model to estimate the risk of developing type 2 diabetes mellitus. Methods Both a static prediction model and a dynamic landmark model were used to provide predictions of a 2-year horizon time for diabetes-free survival, updated at 1, 2, and 3 years post-baseline i.e., predicting diabetes-free survival to 2 years and predicting diabetes-free survival to 3 years, 4 years, and 5 years post-baseline, given the patient already survived past 1 year, 2 years, and 3 years post-baseline, respectively. Prediction accuracy was evaluated at each time point using robust non-parametric procedures. Data from 2057 participants of the Diabetes Prevention Program (DPP) study (1027 in metformin arm, 1030 in placebo arm) were analyzed. Results The dynamic landmark model demonstrated good prediction accuracy with area under curve (AUC) estimates ranging from 0.645 to 0.752 and Brier Score estimates ranging from 0.088 to 0.135. Relative to a static risk model, the dynamic landmark model did not significantly differ in terms of AUC but had significantly lower (i.e., better) Brier Score estimates for predictions at 1, 2, and 3 years (e.g. 0.167 versus 0.099; difference − 0.068 95% CI − 0.083 to − 0.053, at 3 years in placebo group) post-baseline. Conclusions Dynamic prediction models based on longitudinal, repeated risk factor measurements have the potential to improve the accuracy of future health status predictions.http://link.springer.com/article/10.1186/s12874-019-0812-yDiabetesPredictionStatistical methods |
| spellingShingle | Layla Parast Megan Mathews Mark W. Friedberg Dynamic risk prediction for diabetes using biomarker change measurements BMC Medical Research Methodology Diabetes Prediction Statistical methods |
| title | Dynamic risk prediction for diabetes using biomarker change measurements |
| title_full | Dynamic risk prediction for diabetes using biomarker change measurements |
| title_fullStr | Dynamic risk prediction for diabetes using biomarker change measurements |
| title_full_unstemmed | Dynamic risk prediction for diabetes using biomarker change measurements |
| title_short | Dynamic risk prediction for diabetes using biomarker change measurements |
| title_sort | dynamic risk prediction for diabetes using biomarker change measurements |
| topic | Diabetes Prediction Statistical methods |
| url | http://link.springer.com/article/10.1186/s12874-019-0812-y |
| work_keys_str_mv | AT laylaparast dynamicriskpredictionfordiabetesusingbiomarkerchangemeasurements AT meganmathews dynamicriskpredictionfordiabetesusingbiomarkerchangemeasurements AT markwfriedberg dynamicriskpredictionfordiabetesusingbiomarkerchangemeasurements |