Description
In this work, we utilize a combination of free-text and structured data to build Acute Respiratory Distress Syndrome (ARDS) prediction models and ARDS phenotype clusters. We derived "Patient Context Vectors" representing patient-specific contextual ARDS risk factors, utilizing deep-learning techniques on ICD and free-text clinical notes data. The Patient Context Vectors were combined with structured data from the first 24 hours of admission, such as vital signs and lab results, to build an ARDS patient prediction model and an ARDS patient mortality prediction model achieving AUC of 90.16 and 81.01 respectively. The ability of Patient Context Vectors to summarize patients' medical history and current conditions is also demonstrated by the automatic clustering of ARDS patients into clinically meaningful phenotypes based on comorbidities, patient history, and presenting conditions. To our knowledge, this is the first study to successfully combine free-text and structured data, without any manual patient risk factor curation, to build real-time ARDS prediction models.
Learning Objective: - Review a state-of-the-art deep learning approach to combining free-text and structured data for predicting patient outcomes.
- Evaluate a deep-learning machine learning approach for real-time ARDS predictions and clinical decision support.
- Review previous approaches to ARDS patient and ARDS patient mortality predictions.
- Review a data-driven summary of ARDS patient phenotypes, medical history, risk factors, comorbidities, current signs and symptoms and associated mortality rates, acknowledging the need for targeted personalized treatments reflecting differences in treatment outcomes across patient subtypes
Authors:
Emilia Apostolova (Presenter)
Language.ai
Amit Uppal, Bellevue Hospital Center
Jessica Galarraga, MedStar Health Research Institute
Ioannis Koutroulis, Children’s National Health System
Tim Tschampel, CTA
Tony Wang, Imedacs
Tom Velez, CTA
Presentation Materials: