Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions.
The development of mobile-health technology has the potential to revolutionize personalized medicine. Biomedical sensors (e.g., wearables) can assist with determining treatment plans for individuals, provide quantitative information to healthcare providers, and give objective measurements of health,...
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-08-01
|
| Series: | PLoS Computational Biology |
| Online Access: | https://doi.org/10.1371/journal.pcbi.1009303 |
| _version_ | 1828310522929348608 |
|---|---|
| author | Jason Liu Daniel J Spakowicz Garrett I Ash Rebecca Hoyd Rohan Ahluwalia Andrew Zhang Shaoke Lou Donghoon Lee Jing Zhang Carolyn Presley Ann Greene Matthew Stults-Kolehmainen Laura M Nally Julien S Baker Lisa M Fucito Stuart A Weinzimer Andrew V Papachristos Mark Gerstein |
| author_facet | Jason Liu Daniel J Spakowicz Garrett I Ash Rebecca Hoyd Rohan Ahluwalia Andrew Zhang Shaoke Lou Donghoon Lee Jing Zhang Carolyn Presley Ann Greene Matthew Stults-Kolehmainen Laura M Nally Julien S Baker Lisa M Fucito Stuart A Weinzimer Andrew V Papachristos Mark Gerstein |
| author_sort | Jason Liu |
| collection | DOAJ |
| description | The development of mobile-health technology has the potential to revolutionize personalized medicine. Biomedical sensors (e.g., wearables) can assist with determining treatment plans for individuals, provide quantitative information to healthcare providers, and give objective measurements of health, leading to the goal of precise phenotypic correlates for genotypes. Even though treatments and interventions are becoming more specific and datasets more abundant, measuring the causal impact of health interventions requires careful considerations of complex covariate structures, as well as knowledge of the temporal and spatial properties of the data. Thus, interpreting biomedical sensor data needs to make use of specialized statistical models. Here, we show how the Bayesian structural time series framework, widely used in economics, can be applied to these data. This framework corrects for covariates to provide accurate assessments of the significance of interventions. Furthermore, it allows for a time-dependent confidence interval of impact, which is useful for considering individualized assessments of intervention efficacy. We provide a customized biomedical adaptor tool, MhealthCI, around a specific implementation of the Bayesian structural time series framework that uniformly processes, prepares, and registers diverse biomedical data. We apply the software implementation of MhealthCI to a structured set of examples in biomedicine to showcase the ability of the framework to evaluate interventions with varying levels of data richness and covariate complexity and also compare the performance to other models. Specifically, we show how the framework is able to evaluate an exercise intervention's effect on stabilizing blood glucose in a diabetes dataset. We also provide a future-anticipating illustration from a behavioral dataset showcasing how the framework integrates complex spatial covariates. Overall, we show the robustness of the Bayesian structural time series framework when applied to biomedical sensor data, highlighting its increasing value for current and future datasets. |
| first_indexed | 2024-04-13T15:46:13Z |
| format | Article |
| id | doaj.art-3f635a2ba0d14b759832399e7ba01013 |
| institution | Directory Open Access Journal |
| issn | 1553-734X 1553-7358 |
| language | English |
| last_indexed | 2024-04-13T15:46:13Z |
| publishDate | 2021-08-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS Computational Biology |
| spelling | doaj.art-3f635a2ba0d14b759832399e7ba010132022-12-22T02:40:59ZengPublic Library of Science (PLoS)PLoS Computational Biology1553-734X1553-73582021-08-01178e100930310.1371/journal.pcbi.1009303Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions.Jason LiuDaniel J SpakowiczGarrett I AshRebecca HoydRohan AhluwaliaAndrew ZhangShaoke LouDonghoon LeeJing ZhangCarolyn PresleyAnn GreeneMatthew Stults-KolehmainenLaura M NallyJulien S BakerLisa M FucitoStuart A WeinzimerAndrew V PapachristosMark GersteinThe development of mobile-health technology has the potential to revolutionize personalized medicine. Biomedical sensors (e.g., wearables) can assist with determining treatment plans for individuals, provide quantitative information to healthcare providers, and give objective measurements of health, leading to the goal of precise phenotypic correlates for genotypes. Even though treatments and interventions are becoming more specific and datasets more abundant, measuring the causal impact of health interventions requires careful considerations of complex covariate structures, as well as knowledge of the temporal and spatial properties of the data. Thus, interpreting biomedical sensor data needs to make use of specialized statistical models. Here, we show how the Bayesian structural time series framework, widely used in economics, can be applied to these data. This framework corrects for covariates to provide accurate assessments of the significance of interventions. Furthermore, it allows for a time-dependent confidence interval of impact, which is useful for considering individualized assessments of intervention efficacy. We provide a customized biomedical adaptor tool, MhealthCI, around a specific implementation of the Bayesian structural time series framework that uniformly processes, prepares, and registers diverse biomedical data. We apply the software implementation of MhealthCI to a structured set of examples in biomedicine to showcase the ability of the framework to evaluate interventions with varying levels of data richness and covariate complexity and also compare the performance to other models. Specifically, we show how the framework is able to evaluate an exercise intervention's effect on stabilizing blood glucose in a diabetes dataset. We also provide a future-anticipating illustration from a behavioral dataset showcasing how the framework integrates complex spatial covariates. Overall, we show the robustness of the Bayesian structural time series framework when applied to biomedical sensor data, highlighting its increasing value for current and future datasets.https://doi.org/10.1371/journal.pcbi.1009303 |
| spellingShingle | Jason Liu Daniel J Spakowicz Garrett I Ash Rebecca Hoyd Rohan Ahluwalia Andrew Zhang Shaoke Lou Donghoon Lee Jing Zhang Carolyn Presley Ann Greene Matthew Stults-Kolehmainen Laura M Nally Julien S Baker Lisa M Fucito Stuart A Weinzimer Andrew V Papachristos Mark Gerstein Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions. PLoS Computational Biology |
| title | Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions. |
| title_full | Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions. |
| title_fullStr | Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions. |
| title_full_unstemmed | Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions. |
| title_short | Bayesian structural time series for biomedical sensor data: A flexible modeling framework for evaluating interventions. |
| title_sort | bayesian structural time series for biomedical sensor data a flexible modeling framework for evaluating interventions |
| url | https://doi.org/10.1371/journal.pcbi.1009303 |
| work_keys_str_mv | AT jasonliu bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT danieljspakowicz bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT garrettiash bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT rebeccahoyd bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT rohanahluwalia bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT andrewzhang bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT shaokelou bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT donghoonlee bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT jingzhang bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT carolynpresley bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT anngreene bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT matthewstultskolehmainen bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT lauramnally bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT juliensbaker bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT lisamfucito bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT stuartaweinzimer bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT andrewvpapachristos bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions AT markgerstein bayesianstructuraltimeseriesforbiomedicalsensordataaflexiblemodelingframeworkforevaluatinginterventions |