{"id":{"repo_id":"mit","oai_identifier":"oai:dspace.mit.edu:1721.1/162719"},"canonical_url":"https://search.dev.ndltd.org/etd/mit/oai:dspace.mit.edu:1721.1/162719","repository":{"repo_id":"mit","name":"MIT","base_url":"https://dspace.mit.edu/oai/request"},"display":{"title":"Self-Supervised ECG Learning for Multimodal Clinical Tasks","abstract":"We present a multimodal clinical AI framework that integrates time series, images, and text to support robust diagnostic reasoning across diverse input combinations. We first introduce ECG-JEPA, a self-supervised encoder pretrained on multiple ECG datasets to learn generalizable time series representations. This unimodal pretraining improves ECG classification, achieving a 23-point AUC gain on the underrepresented Ga dataset. We then align and fuse these ECG embeddings with chest X-rays and EHR text using a vision–language model backbone, enabling end-to-end multimodal inference. Our results show that incorporating ECG signals meaningfully improves diagnostic performance, highlighting the value of multitask time series pretraining and modular fusion for clinical AI.","abstract_html":"We present a multimodal clinical AI framework that integrates time series, images, and text to support robust diagnostic reasoning across diverse input combinations. We first introduce ECG-JEPA, a self-supervised encoder pretrained on multiple ECG datasets to learn generalizable time series representations. This unimodal pretraining improves ECG classification, achieving a 23-point AUC gain on the underrepresented Ga dataset. We then align and fuse these ECG embeddings with chest X-rays and EHR text using a vision–language model backbone, enabling end-to-end multimodal inference. Our results show that incorporating ECG signals meaningfully improves diagnostic performance, highlighting the value of multitask time series pretraining and modular fusion for clinical AI.","abstract_has_math":false,"creators":["Chen, Peilin"],"institution":"Massachusetts Institute of Technology","degree_name":"Master","degree_level":null,"degree_discipline":null,"degree_department":"Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science","school":null,"contributors":[],"advisors":["Liang, Paul"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-05","date_published":"2025-05","updated_at":"2026-07-22T22:21:50Z","subjects":[],"languages":[],"rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"rights_urls":["https://rightsstatements.org/page/InC-EDU/1.0/"],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1721.1/162719","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Liang, Paul"]},{"key":"dc:contributor.department","label":"Department","values":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"]},{"key":"dc:creator","label":"Author","values":["Chen, Peilin"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-09-18T14:28:56Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-09-18T14:28:56Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-05"]},{"key":"dc:publisher","label":"Institution","values":["Massachusetts Institute of Technology"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master","Master of Engineering in Electrical Engineering and Computer Science"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"]},{"key":"dc:rights.uri","label":"Rights URI","values":["https://rightsstatements.org/page/InC-EDU/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1721.1/162719"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["We present a multimodal clinical AI framework that integrates time series, images, and text to support robust diagnostic reasoning across diverse input combinations. We first introduce ECG-JEPA, a self-supervised encoder pretrained on multiple ECG datasets to learn generalizable time series representations. This unimodal pretraining improves ECG classification, achieving a 23-point AUC gain on the underrepresented Ga dataset. We then align and fuse these ECG embeddings with chest X-rays and EHR text using a vision–language model backbone, enabling end-to-end multimodal inference. Our results show that incorporating ECG signals meaningfully improves diagnostic performance, highlighting the value of multitask time series pretraining and modular fusion for clinical AI."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["M.Eng."]},{"key":"dc:title","label":"Title","values":["Self-Supervised ECG Learning for Multimodal Clinical Tasks"]}]}],"canonical_facts":{"dc:contributor.advisor":["Liang, Paul"],"dc:contributor.department":["Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science"],"dc:creator":["Chen, Peilin"],"dc:date.accessioned":["2025-09-18T14:28:56Z"],"dc:date.available":["2025-09-18T14:28:56Z"],"dc:date.issued":["2025-05"],"dc:description.abstract":["We present a multimodal clinical AI framework that integrates time series, images, and text to support robust diagnostic reasoning across diverse input combinations. We first introduce ECG-JEPA, a self-supervised encoder pretrained on multiple ECG datasets to learn generalizable time series representations. This unimodal pretraining improves ECG classification, achieving a 23-point AUC gain on the underrepresented Ga dataset. We then align and fuse these ECG embeddings with chest X-rays and EHR text using a vision–language model backbone, enabling end-to-end multimodal inference. Our results show that incorporating ECG signals meaningfully improves diagnostic performance, highlighting the value of multitask time series pretraining and modular fusion for clinical AI."],"dc:description.degree":["M.Eng."],"dc:identifier.uri":["https://hdl.handle.net/1721.1/162719"],"dc:publisher":["Massachusetts Institute of Technology"],"dc:rights":["In Copyright - Educational Use Permitted","Copyright retained by author(s)"],"dc:rights.uri":["https://rightsstatements.org/page/InC-EDU/1.0/"],"dc:title":["Self-Supervised ECG Learning for Multimodal Clinical Tasks"],"dc:type":["Thesis"],"thesis:degree_name":["Master","Master of Engineering in Electrical Engineering and Computer Science"]},"updated_at":"2026-07-22T22:21:50Z"}