Covers: theory of Practical Limitations of Deep Learning in HealthCare
Estimated time needed to finish: 40 minutes
Questions this item addresses:
  • Deep Learning has a lot of potential in Healthcare. But why don’t these techniques are adopted in hospitals yet? What are the gaps between academic research and production level code in Deep Learning and Healthcare? How can we mitigate this production level gap in Deep Learning and Healthcare, and what are some of the tools and techniques we can deploy?
How to use this item?

See the whole video to understand the history of neural networks and why DL is good for healthcare and what are the practical limitations and how to resolve some of those limitations

Author(s) / creator(s) / reference(s)
Karthik Bhaskar
0 comment
Recipe
publicShareStar

Deep Learning in Health Care and its Practical Limitations

Collaborators
Total time needed: ~1 hour
Objectives
This Shortlist gives you a brief introduction to Deep Learning in HealthCare and its practical limitations on why deep learning is adopted in hospitals yet?
Potential Use Cases
How to reduce the gap between academic and production level code and how to ship products using Data Augmentation, Data Synthesis, Pre-Trained Models and how to engineer reliable deep learning systems?
Who is this for ?
INTERMEDIATE Data Scientist, Data Analyst, ML Engineer, ML Researchers, Software Engineer, etc
Click on each of the following annotated items to see details.
VIDEO 1. Deep Learning in HealthCare and Its Practical Limitations
  • Deep Learning has a lot of potential in Healthcare. But why don’t these techniques are adopted in hospitals yet? What are the gaps between academic research and production level code in Deep Learning and Healthcare? How can we mitigate this production level gap in Deep Learning and Healthcare, and what are some of the tools and techniques we can deploy?
40 minutes
ARTICLE 2. Why Is Building Machine Learning Products For Healthcare So Hard?
  • What Data is a Nightmare for Healthcare? What are the design challenges? Why Security, Compliance and Regulations slowed down innovation?
10 minutes
PAPER 3. CheXphoto: 10,000+ Photos and Transformations of Chest X-rays for Benchmarking Deep Learning Robustness
  • How to use Data Augmentation to mitigate Small Data problem in Deep Learning?
10 minutes
PAPER 4. Unsupervised Histopathology Image Synthesis
  • How to use Data Synthesis to mitigate Small Data problem in Deep Learning?
10 minutes
PAPER 5. CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT
  • How to use Pre-Trained Models like BERT to mitigate Small Data problem in Deep Learning?
10 minutes
PAPER 6. CheXpedition: Investigating Generalization Challenges for Translation of Chest X-Ray Algorithms to the Clinical Setting
  • How to improve Robustness and Generalization of DL Algorithms?
10 minutes
PAPER 7. Developing a delivery science for artificial intelligence in healthcare
  • How to improve Safety and Regulations in HealthCare?
5 minutes
PAPER 8. Engineering Reliable Deep Learning Systems
  • Why DL Engineering? What are DL Engineering Lifecycle Activities? What are the current challenges in DL Engineering?
15 minutes

Concepts Covered

0 comment