Deep learning for healthcare: review, opportunities and challenges
Глубокое обучение в здравоохранении: обзор, возможности и проблемы
2017-04-05
SCID: 54.1/98taff7v
Discuss with AI
biomedical datadeep learningelectronic health recordshealthcareinterpretable architectures
Figures from the paper
Abstract (AI)
Gaining knowledge and actionable insights from complex, high-dimensional and heterogeneous biomedical data remains a key challenge in transforming health care. Various types of data have been emerging in modern biomedical research, including electronic health records, imaging, -omics, sensor data and text, which are complex, heterogeneous, poorly annotated and generally unstructured. Traditional data mining and statistical learning approaches typically need to first perform feature engineering to obtain effective and more robust features from those data, and then build prediction or clustering models on top of them. There are lots of challenges on both steps in a scenario of complicated data and lacking of sufficient domain knowledge. The latest advances in deep learning technologies provide new effective paradigms to obtain end-to-end learning models from complex data. In this article, we review the recent literature on applying deep learning technologies to advance the health care domain. Based on the analyzed work, we suggest that deep learning approaches could be the vehicle for translating big biomedical data into improved human health. However, we also note limitations and needs for improved methods development and applications, especially in terms of ease-of-understanding for domain experts and citizen scientists. We discuss such challenges and suggest developing holistic and meaningful interpretable architectures to bridge deep learning models and human interpretability.
Key Findings
1
Biomedical data from electronic health records, imaging, omics, sensors, and text are high-dimensional, heterogeneous, poorly annotated, and often unstructured.
2
Deep learning offers end-to-end learning paradigms that can extract useful representations from complex biomedical data while reducing reliance on manual feature engineering.
3
Major challenges include limited interpretability for healthcare experts and citizen scientists, motivating holistic architectures that better connect deep learning with human understanding.
4
The reviewed literature suggests deep learning could help translate large-scale biomedical data into improved healthcare and human health outcomes.
5
Traditional data mining and statistical learning methods face difficulties because they require effective feature engineering and sufficient domain knowledge.
Research Object
complex, high-dimensional and heterogeneous biomedical data in healthcare, including electronic health records, imaging, -omics, sensor data, and text
Research Subject
the application of deep learning to extract actionable insights and build interpretable end-to-end predictive or clustering models from biomedical data
Publication Details
Publication Date
2017-04-05
Journal
Publisher
ISSN
Cited by
3074
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai11
ImageNet classification with deep convolutional neural networks2017
Gradient-based learning applied to document recognition1998
"Why Should I Trust You?": Explaining the Predictions of Any Classifier2016
Reducing the Dimensionality of Data with Neural Networks2006
Sequence to Sequence Learning with Neural Networks2014
Representation Learning: A Review and New Perspectives2013
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups2012
Machine learning: Trends, perspectives, and prospects2015
On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
Deep Learning with Differential Privacy2016
The Rise of Consumer Health Wearables: Promises and Barriers2016
Cited by6
Artificial Intelligence in Cardiology2018
Deep learning modelling techniques: current progress, applications, advantages, and challenges2023
Introducing Artificial Intelligence Training in Medical Education2019
Artificial intelligence in reproductive medicine2019
Split Learning for collaborative deep learning in healthcare2019
Explainable AI: A review of applications to neuroimaging data2022