Tuesday, July 5, 2022
No Result
View All Result
Medical Finance
  • Home
  • News
  • Interviews
  • Mediknowledge
  • Insights From Industry
  • Thought Leaders
  • Coronavirus
  • Whitepapers
  • Home
  • News
  • Interviews
  • Mediknowledge
  • Insights From Industry
  • Thought Leaders
  • Coronavirus
  • Whitepapers
No Result
View All Result
Medical Finance
No Result
View All Result
Home Mediknowledge

The Surge of Sensationalist COVID-19 AI Research

by Medical Finance
in Mediknowledge
The Surge of Sensationalist COVID-19 AI Research
9
SHARES
101
VIEWS
Share on FacebookShare on Twitter

There seems to be a tendency to hastily use imperfect and questionable data to train an AI solution for COVID-19, a dangerous trend that not only does not help any patient or physician but also damages the reputation of the AI community. Dealing with a pandemic – as significant as it is – does not suspend basic scientific principles. Data has to be curated by medical experts, and full and rigorous validations have to be performed, and results have to be reviewed by peers before we deploy any solution or even proposal into the world, particularly when the society is dealing with many uncertainties.

sensational

It is safe to say that we are all deeply concerned about the COVID-19 pandemic. This coronavirus has drastically changed our reality: stress, restrictions, quarantines, heroic sacrifices of caregivers including staff, nurses and physicians, losing loved ones, economic hardships, and massive uncertainties about what is in store in the coming months. Under such circumstances, it is only natural that many of us are thinking of ways to help – in the fastest ways possible. The AI community is not an exception.

Machine learning methods live from data. They learn from labeled data to classify, predict and estimate. The quality and reliability of any AI method directly depend on the quality and reliability of the labeled data. In computer science, we talk about “garbage in, garbage out” (GIGO) which summarizes the experience that low-quality input data generates unreliable output or “garbage”. This becomes even more critical when we are dealing with highly complex data modalities, such as medical images – data that generally require highly specialized knowledge for correct interpretations.

Within the AI community, we are fully dependent on data. As long as the domain is not sensitive (finance, healthcare, surveillance, etc.), we usually assemble our datasets by using different methods; From the manual gathering of samples up to highly sophisticated crawlers to parse through the Internet and other publicly available repositories. In medical imaging, we deal with a highly sensitive domain in which a long process is generally required to curate and access a set of labeled images. Needless to say, the curation has to happen within the walls of a hospital not just because the experts are there, but also due to the required de-identification of images to comply with privacy regulations.

But, sometimes we get impatient; we create our toy datasets by the manual collection of publicly accessible sources (e.g., online journals) – and there is generally no concern about this approach. Most of the time we – as AI researchers with no clinical or medical competency – create our toy datasets to run initial investigations and get a feeling for the challenges to come. This usually happens in anticipation of receiving a professionally curated dataset, a process that is often slowed down by ethic reviews and intellectual property negotiations.  

To be clear, a “toy dataset” in the medical imaging domain is not a toy just because it is commonly very small, but more importantly because it has been created by engineers and computer scientists, and not by physicians and medical/clinical experts. And, nobody would complain if we play with our toys inside our AI labs to get prepared to deal with the actual data from the hospital.

Radiologists around the world are understandably very busy, to put it mildly; it is not the best time to forge collaborations with radiologists if you are an overambitious AI researcher who wants to help. So, some of us have started to assemble our own dataset to get prepared for future tasks.

Collections of x-ray and partly CT images – scraped from the Internet – seem to emerge here and there and appear to be evolving as the creators continue to add images. Because of the availability of such datasets on one side and the ubiquity of basic AI knowledge and tools on the other side, many AI enthusiasts and start-ups have impulsively begun to develop solutions for COVID-19 in x-ray images. One finds websites and blogs that advise how to detect COVID-19 from x-ray scans with high accuracy. Others provide a sort of tutorial on detecting COVID-19 in X-ray images. We are even starting to see non-peer-reviewed papers that go a step further and baptize their solution with aggrandizing names like “COVID-Net”. This type of works commonly lacks many experimental details to explain how one has dealt with a few images from a very small number of patients to feed the deep network. Such papers report no validation, and no radiologist has guided the experiments. Many of these works were hurriedly made public before the creators of datasets could even provide sufficient explanation about their collection process. In an attempt to overcome the small data size, AI enthusiasts and start-ups mix the few COVID-19 images with other public datasets, i.e., pneumonia datasets. This is generally quite clever but I looked more closely at one case and the trouble is that the pneumonia cases were pediatric images; so the COVID-Nets are comparing pediatric pneumonia (children one to five years old) with adult COVID-19 patients. Well, this happens when we exclude radiologists from research that needs expert oversight.

Why are we rushing to publish faulty AI results on tiny datasets mixed with wrong anatomies, with no radiological backing, and with no validation? Do we want to help COVID-19 patients?

Perhaps the abundance of funding opportunity announcements in recent days, and the possibility of getting exposure for our research is misleading us into faulty research conduct; we cannot abandon fundamental scientific principles due to lockdowns and quarantines. AI is neither a ventilator nor a vaccine nor a pill; it is extremely unlikely that the exhausted radiologists in Wuhan, Qom or Bergamo download the Python code of our poorly trained network (using insufficient and improper data and described in quickly written papers and blogs) to just obtain a flawed second opinion.

Yes, we all want to help. Let us wait for real data from hospitals, let us do the ethics clearance and de-identification, and let us work with radiologists to develop solutions for chest issues of the future. Otherwise, we may create the impression that we are doing sensational research and are more concerned with self-promotion than with the well-being of patients. Radiologists are working day and night to understand the manifestation of this virus in medical images [1,2]. Let us work with them and learn from them to unleash the true potential of AI for combating viral infections in the future.

Sources

  1. Imaging Findings of CoVID-19: More Than Just Ground Glass Opacities, by Henry Guo, MD, PhD. YouTube: https://www.youtube.com/watch?v=Bt9KQ8q6WJE
  2. Radiology Preparedness for COVID-19: Radiology Scientific Expert Review Panel. YouTube: https://www.youtube.com/watch?v=1T98zMYxrKU

.

About Professor Hamid R. Tizhoosh

Dr. Hamid R. Tizhoosh is a Professor in the Faculty of Engineering at University of Waterloo since 2001 where he leads the KIMIA Lab (Laboratory for Knowledge Inference in Medical Image Analysis). Since 1993, his research activities encompass artificial intelligence, computer vision and medical imaging. He has developed algorithms for medical image filtering, segmentation and search. He is the author of two books, 14 book chapters, and more than 150 journal and conference papers. Dr. Tizhoosh has extensive industrial experience and has worked with numerous companies. He is also a Faculty Affiliate to the Vector Institute, Toronto, Canada, and a member of the Waterloo AI Institute, University of Waterloo, Canada.


Disclaimer: This article has not been subjected to peer review and is presented as the personal views of a qualified expert in the subject in accordance with the general terms and condition of use of the News-Medical.Net website.

Total
0
Shares
Share 0
Tweet 0
Pin it 0
Share 0
Medical Finance

Medical Finance

Related Posts

Image Credit: MAD.vertise/Shutterstock.com

Pediatric Robotic Surgery: past, present and potential

by Medical Finance
July 5, 2022
0

Written by Keynote Contributor, Dr. Joseph G. Barone. The orderly is shocked because a child is undergoing surgery, but no...

prioritizing efficacy when considering quality of life

prioritizing efficacy when considering quality of life

by Medical Finance
July 4, 2022
0

Written by Keynote Contributor, Dr. Cristina Suárez. It is an exciting yet challenging time to be a treating physician in...

Genetic disease

Computational biology in rare disease research

by Medical Finance
July 4, 2022
0

Written by Keynote Contributor, Professor Damian Smedley. Rare diseases affect 6-8% of the world’s population and, although we know that...

Depression and Insomnia

clinical treatments for a common comorbidity

by Medical Finance
July 3, 2022
0

Given these strong sleep-mood relationships, it is not surprising that insomnia and depression frequently co-occur. For example, up to 90%...

World mental health support and the effect of stigma and discrimination

World mental health support and the effect of stigma and discrimination

by Medical Finance
July 3, 2022
0

Produced by James Ives, MPsych The global burden of mental health and the need for mental health support services remain...

Mediastinal Mass

Treatment and Prognosis of Mediastinitis

by Medical Finance
July 3, 2022
0

Mediastinal infections (jointly referred to as mediastinitis) are primarily related to surgery, perforation of the esophagus and infectious spread from...

Next Post
Depression and Insomnia

clinical treatments for a common comorbidity

Study: Daily Lactobacillus Probiotic versus Placebo in COVID-19-Exposed Household Contacts (PROTECT-EHC): A Randomized Clinical Trial. Image Credit: Double Brain/Shutterstock

Study shows probiotics can reduce symptoms of COVID-19 when taken post-exposure

0 0 votes
Article Rating
Subscribe
Login
Notify of
guest
guest
0 Comments
Inline Feedbacks
View all comments

Support

  • Contact
  • Disclaimer
  • Home
  • Privacy Policy
  • Terms And Conditions

Categories

  • Coronavirus
  • Insights From Industry
  • Interviews
  • Mediknowledge
  • News
  • Thought Leaders
  • Whitepapers

More News

  • 3D illustration egg cells embryo. Embryo cells with red nucleuses in center. Hum Rost9 M1 3c512a7b78a9417e986aa778a4cf4559 620x480
    CellPort software joins the tetra partner network to help customers accelerate cell development and manufacturing
  • Study: Observations and perspectives on adaptive immunity to SARS-CoV-2. Image Credit: Design_Cells / Shutterstock
    Scientists show how T cells may help protect against severe COVID
  • Home
  • Privacy Policy
  • Contact
  • Disclaimer
  • Terms And Conditions

© 2022 Medical Finance - Latest Financial and Business News

No Result
View All Result
  • Interviews
  • Mediknowledge
  • News
  • Insights From Industry
  • Coronavirus
  • Thought Leaders
  • Whitepapers
wpDiscuz
0
0
Would love your thoughts, please comment.x
()
x
| Reply