Boston Children’s Hospital Reports Findings in Machine Learning (Confederated learning in healthcare: Training machine learning models using disconnected data separated by individual, data type and identity for Large-Scale health system …): Machine Learning

2022 SEP 19 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- New research on Machine Learning is the subject of a report. According to news originating from Boston, Massachusetts, by NewsRx correspondents, research stated, “A patient’s health information is generally fragmented across silos because it follows how care is delivered: multiple providers in multiple settings. Though it is technically feasible to reunite data for analysis in a manner that underpins a rapid learning healthcare system, privacy concerns and regulatory barriers limit data centralization for this purpose.”

Our news journalists obtained a quote from the research from Boston Children’s Hospital, “Machine learning can be conducted in a federated manner on patient datasets with the same set of variables but separated across storage. But federated learning cannot handle the situation where different data types for a given patient are separated vertically across different organizations and when patient ID matching across different institutions is difficult. We call methods that enable machine learning model training on data separated by two or more dimensions ‘confederated machine learning’, which we aim to develop in this study. We propose and evaluate confederated learning for training machine learning models to stratify the risk of several diseases among silos when data are horizontally separated by individual, vertically separated by data type, and separated by identity without patient ID matching. The confederated learning method can be intuitively understood as a distributed learning method with representation learning, generative model, imputation method and data augmentation elements. Our confederated learning method achieves AUCROC (Area Under The Curve Receiver Operating Characteristics) of 0.787 for diabetes prediction, 0.718 for psychological disorders prediction, and 0.698 for Ischemic heart disease prediction using nationwide health insurance claims.”

According to the news editors, the research concluded: “Our proposed confederated learning method successfully trained machine learning models on health insurance data separated by two or more dimensions.”

This research has been peer-reviewed.

For more information on this research see: Confederated learning in healthcare: Training machine learning models using disconnected data separated by individual, data type and identity for Large-Scale health system Intelligence. Journal of Biomedical Informatics, 2022;134:104151. Journal of Biomedical Informatics can be contacted at: Academic Press Inc Elsevier Science, 525 B St, Ste 1900, San Diego, CA 92101-4495, USA. (Elsevier - www.elsevier.com; Journal of Biomedical Informatics - http://www.journals.elsevier.com/journal-of-biomedical-informatics/)

The news correspondents report that additional information may be obtained from Dianbo Liu, Computational Health Informatics Program, Boston Children’s Hospital, Boston, MA, United States. Additional authors for this research include Kathe Fox, Griffin Weber and Tim Miller.

The direct object identifier (DOI) for that additional information is: https://doi.org/10.1016/j.jbi.2022.104151. This DOI is a link to an online electronic document that is either free or for purchase, and can be your direct source for a journal article and its citation.

The publisher’s contact information for the Journal of Biomedical Informatics is: Academic Press Inc Elsevier Science, 525 B St, Ste 1900, San Diego, CA 92101-4495, USA.

(Our reports deliver fact-based news of research and discoveries from around the world.)