Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy
BACKGROUND: Secondary and retrospective use of hospital-hosted clinical data provides a time- and cost-efficient alternative to prospective clinical trials for biomarker development. This study aims to create a retrospective clinical dataset of Magnetic Resonance Images (MRI) and clinical records of...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
BioMed Central
2020
|
| Online Access: | https://hdl.handle.net/1721.1/126245 |
| _version_ | 1811078366246207488 |
|---|---|
| author | Weiss, Rebecca J Bates, Sara V Song, Ya’nan Zhang, Yue Herzberg, Emily M Chen, Yih-Chieh Gong, Maryann M. Chien, Isabel Zhang, Lily Murphy, Shawn N Gollub, Randy L Grant, P. E Ou, Yangming |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Weiss, Rebecca J Bates, Sara V Song, Ya’nan Zhang, Yue Herzberg, Emily M Chen, Yih-Chieh Gong, Maryann M. Chien, Isabel Zhang, Lily Murphy, Shawn N Gollub, Randy L Grant, P. E Ou, Yangming |
| author_sort | Weiss, Rebecca J |
| collection | MIT |
| description | BACKGROUND: Secondary and retrospective use of hospital-hosted clinical data provides a time- and cost-efficient alternative to prospective clinical trials for biomarker development. This study aims to create a retrospective clinical dataset of Magnetic Resonance Images (MRI) and clinical records of neonatal hypoxic ischemic encephalopathy (HIE), from which clinically-relevant analytic algorithms can be developed for MRI-based HIE lesion detection and outcome prediction. METHODS: This retrospective study will use clinical registries and big data informatics tools to build a multi-site dataset that contains structural and diffusion MRI, clinical information including hospital course, short-term outcomes (during infancy), and long-term outcomes (~ 2 years of age) for at least 300 patients from multiple hospitals. DISCUSSION: Within machine learning frameworks, we will test whether the quantified deviation from our recently-developed normative brain atlases can detect abnormal regions and predict outcomes for individual patients as accurately as, or even more accurately, than human experts. |
| first_indexed | 2024-09-23T10:58:22Z |
| format | Article |
| id | mit-1721.1/126245 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T10:58:22Z |
| publishDate | 2020 |
| publisher | BioMed Central |
| record_format | dspace |
| spelling | mit-1721.1/1262452022-10-01T00:20:25Z Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy Weiss, Rebecca J Bates, Sara V Song, Ya’nan Zhang, Yue Herzberg, Emily M Chen, Yih-Chieh Gong, Maryann M. Chien, Isabel Zhang, Lily Murphy, Shawn N Gollub, Randy L Grant, P. E Ou, Yangming Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory BACKGROUND: Secondary and retrospective use of hospital-hosted clinical data provides a time- and cost-efficient alternative to prospective clinical trials for biomarker development. This study aims to create a retrospective clinical dataset of Magnetic Resonance Images (MRI) and clinical records of neonatal hypoxic ischemic encephalopathy (HIE), from which clinically-relevant analytic algorithms can be developed for MRI-based HIE lesion detection and outcome prediction. METHODS: This retrospective study will use clinical registries and big data informatics tools to build a multi-site dataset that contains structural and diffusion MRI, clinical information including hospital course, short-term outcomes (during infancy), and long-term outcomes (~ 2 years of age) for at least 300 patients from multiple hospitals. DISCUSSION: Within machine learning frameworks, we will test whether the quantified deviation from our recently-developed normative brain atlases can detect abnormal regions and predict outcomes for individual patients as accurately as, or even more accurately, than human experts. 2020-07-17T19:27:08Z 2020-07-17T19:27:08Z 2019-11 2020-06-26T11:04:42Z Article http://purl.org/eprint/type/JournalArticle 1479-5876 https://hdl.handle.net/1721.1/126245 Weiss, Rebecca J. et al. "Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy." Journal of Translational Medicine 17 (Nov. 2019): no. 385 doi 10.1186/s12967-019-2119-5 ©2019 Author(s) en 10.1186/s12967-019-2119-5 Journal of Translational Medicine Creative Commons Attribution https://creativecommons.org/licenses/by/4.0/ The Author(s) application/pdf BioMed Central BioMed Central |
| spellingShingle | Weiss, Rebecca J Bates, Sara V Song, Ya’nan Zhang, Yue Herzberg, Emily M Chen, Yih-Chieh Gong, Maryann M. Chien, Isabel Zhang, Lily Murphy, Shawn N Gollub, Randy L Grant, P. E Ou, Yangming Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy |
| title | Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy |
| title_full | Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy |
| title_fullStr | Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy |
| title_full_unstemmed | Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy |
| title_short | Mining multi-site clinical data to develop machine learning MRI biomarkers: application to neonatal hypoxic ischemic encephalopathy |
| title_sort | mining multi site clinical data to develop machine learning mri biomarkers application to neonatal hypoxic ischemic encephalopathy |
| url | https://hdl.handle.net/1721.1/126245 |
| work_keys_str_mv | AT weissrebeccaj miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT batessarav miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT songyanan miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT zhangyue miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT herzbergemilym miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT chenyihchieh miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT gongmaryannm miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT chienisabel miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT zhanglily miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT murphyshawnn miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT gollubrandyl miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT grantpe miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy AT ouyangming miningmultisiteclinicaldatatodevelopmachinelearningmribiomarkersapplicationtoneonatalhypoxicischemicencephalopathy |