• Corpus ID: 59567904

5 J un 2 01 8 Opportunities in Machine Learning for Healthcare

  title={5 J un 2 01 8 Opportunities in Machine Learning for Healthcare},
  author={Marzyeh Ghassemi},
Healthcare is a natural arena for the application of machine learning, especially as modern electronic health records (EHRs) provide increasingly large amounts of data to answer clinically meaningful questions. However, clinical data and practice present unique challenges that complicate the use of common methodologies. This article serves as a primer on addressing these challenges and highlights opportunities for members of the machine learning and data science communities to contribute to… 



Predicting Clinical Outcomes Across Changing Electronic Health Record Systems

This work evaluates their method using two different intensive care unit (ICU) databases and on two clinically relevant tasks, in-hospital mortality and prolonged length of stay, finding a feature representation mapping EHR-specific events to a shared set of clinical concepts yields better results than using EHR -specific events alone.

Scalable and accurate deep learning with electronic health records

A representation of patients’ entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format is proposed, and it is demonstrated that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization.

Big Data and Machine Learning in Health Care.

To understand the degree to which a predictive or diagnostic algorithm can be said to be an instance of machine learning requires understanding how much of its structure or parameters were predetermined by humans.

Multi-task Prediction of Disease Onsets from Longitudinal Lab Tests

This work trains a Long Short-Term Memory recurrent neural network and two novel convolutional neural networks for multi-task prediction of disease onset for 133 conditions based on 18 common lab tests measured over time in a cohort of 298K patients derived from 8 years of administrative claims data.

Electronic medical record phenotyping using the anchor and learn framework

A phenotype library that uses both structured and unstructured data from the EMR to represent patients for real-time clinical decision support and Learning with anchors presents a method of efficiently learning statistically driven phenotypes with minimal manual intervention is developed.

Clinical Intervention Prediction and Understanding with Deep Neural Networks

This work compares both long short-term memory networks (LSTM) and convolutional neural networks (CNN) for prediction of five intervention tasks and shows that the models are able to significantly outperform baselines for intervention prediction, and provide insight into model learning.

Semi-Supervised Learning for Electronic Phenotyping in Support of Precision Medicine

Electronic record phenotyping refers to the task of determining, from an electronic medical record entry, a concise descriptor of the patient, comprising of their medical history, current problems, presentation, etc.

Finding the missing link for big biomedical data.

Both technical and social challenges to linking these data must be addressed before big biomedical data can have their full influence on health care.

GRAM: Graph-based Attention Model for Healthcare Representation Learning

Compared to the basic RNN, GRAM achieved 10% higher accuracy for predicting diseases rarely observed in the training data and 3% improved area under the ROC curve for predicting heart failure using an order of magnitude less training data.

Enabling phenotypic big data with PheNorm

PheNorm fully automates the generation of accurate phenotyping algorithms and demonstrates the capacity for EHR-driven annotations to scale to the next level - phenotypic big data.