AI trained to detect cancer cells in blood tests!
01/07/24 12:33
A simple blood test may be all there is needed to detect cancer, and even pre-cancer cells, in the future!
How it works:
Scientists have trained an AI model to look at DNA fragments in order to detect and differentiate cancer cells from healthy DNA. In each individual body, all DNA cells are identical. Cancer cells, however, have a different DNA than the body they live in because they are a mutation. An AI model can’t replace healthcare workers, but it can be a great tool as it’s both faster and more reliable in detecting differences at cell level.
Pros:
This AI model can detect cancer and even the initial stages of a mutating cell before it can develop into cancer. It can also spot relapse in cancer patients faster than we are able to today. We already know that early detection can be the difference between life and death when it comes to healthcare.
Cons:
The AI model is so effective that it can detect pre-cancer cells, however, far from all pre-cancer cells develop into actual cancer. As a result, a lot of people can potentially get very invasive medical intervention which would not have been necessary. Not only is this a huge cost in terms of money but also in terms of quality of life for those patients.
Another issue is that the AI model can’t specify where in the body the cancer is located, only that there is cancer or pre-cancer cells present in the blood. In other words; the healthcare workers have to do some detective work to locate it after detection!
Challenge:
The initial research studies for this AI model have been made with a limited group of patients with different types of cancer. To develop a reliable cancer detection AI tool, there is a need for more studies with much more data. Both larger groups of patients and specific studies for each different type of cancer is necessary.
In relation to the BETTER project:
While both this cancer detecting AI model and the BETTER project are AI to be used in the healthcare sector, they are in no way competing with each other. On the contrary!
The cancer detecting AI model is a tool for hands-on healthcare directly involved with patients. All it needs is more research studies and more data to be used.
The BETTER project is working towards a tool for researching, developing, and improving treatment by creating a robust decentralised infrastructure which will enable healthcare professionals to exploit the full potential of larger sets of multi-source health data via tailor-made AI tools useful to compare, integrate, and analyse in a secure, cost-effective fashion across national borders, fully complying with present GDPR privacy guidelines.
Potentially BETTER could in the future be the tool to help develop technology like this cancer detecting AI by helping gather data!
The study has been published in the journal Nature Medicine:
https://www.nature.com/articles/s41591-024-03040-4
“Ultrasensitive plasma-based monitoring of tumor burden using machine-learning-guided signal enrichment”
How it works:
Scientists have trained an AI model to look at DNA fragments in order to detect and differentiate cancer cells from healthy DNA. In each individual body, all DNA cells are identical. Cancer cells, however, have a different DNA than the body they live in because they are a mutation. An AI model can’t replace healthcare workers, but it can be a great tool as it’s both faster and more reliable in detecting differences at cell level.
Pros:
This AI model can detect cancer and even the initial stages of a mutating cell before it can develop into cancer. It can also spot relapse in cancer patients faster than we are able to today. We already know that early detection can be the difference between life and death when it comes to healthcare.
Cons:
The AI model is so effective that it can detect pre-cancer cells, however, far from all pre-cancer cells develop into actual cancer. As a result, a lot of people can potentially get very invasive medical intervention which would not have been necessary. Not only is this a huge cost in terms of money but also in terms of quality of life for those patients.
Another issue is that the AI model can’t specify where in the body the cancer is located, only that there is cancer or pre-cancer cells present in the blood. In other words; the healthcare workers have to do some detective work to locate it after detection!
Challenge:
The initial research studies for this AI model have been made with a limited group of patients with different types of cancer. To develop a reliable cancer detection AI tool, there is a need for more studies with much more data. Both larger groups of patients and specific studies for each different type of cancer is necessary.
In relation to the BETTER project:
While both this cancer detecting AI model and the BETTER project are AI to be used in the healthcare sector, they are in no way competing with each other. On the contrary!
The cancer detecting AI model is a tool for hands-on healthcare directly involved with patients. All it needs is more research studies and more data to be used.
The BETTER project is working towards a tool for researching, developing, and improving treatment by creating a robust decentralised infrastructure which will enable healthcare professionals to exploit the full potential of larger sets of multi-source health data via tailor-made AI tools useful to compare, integrate, and analyse in a secure, cost-effective fashion across national borders, fully complying with present GDPR privacy guidelines.
Potentially BETTER could in the future be the tool to help develop technology like this cancer detecting AI by helping gather data!
The study has been published in the journal Nature Medicine:
https://www.nature.com/articles/s41591-024-03040-4
“Ultrasensitive plasma-based monitoring of tumor burden using machine-learning-guided signal enrichment”
What can healthcare learn from true crime?
14/06/24 12:01
Even if you’re not a fan of true crime documentaries or podcasts, you’re probably familiar with some of the well-known serial killers from USA in the 1980s. Ted Bundy, Jeffrey Dahmer, and the Golden State Killer to name a few.
Now what does this have to do with healthcare and the BETTER project? I promise there is a connection other than justifying my consumption of true crime podcasts during office hours!
It can get so frustrating to watch true crime documentaries where the serial killer is caught much too late because they committed their crimes in different states and the police stations didn’t share information across borders. In their defence, the technology wasn’t developed to do this effectively at the time!
And looking back, it’s frustrating to know that lives could have been saved if only the technology and knowledge was as good back then as it is today. But they had to start somewhere, and they did learn to share information across borders to save lives!
Now, what does serial killers have to do with improving healthcare?
You see, much like how the police stations not sharing information and experience about a possible serial killer on the loose with other police stations; The same thing could be happening in hospitals about treatment of new or rare illnesses.
Maybe the right information is already discovered in one country, but not in another and the patients suffer because of it! The frustrating feeling about the slow catching of serial killers? Imagine that frustration many years into the future when it’s common practise for healthcare researchers to share experience and wondering why we didn’t already do this back in 2024.
To get there, we need to start somewhere. And this is where the BETTER project comes in, for BETTER healthcare in the future!
Now what does this have to do with healthcare and the BETTER project? I promise there is a connection other than justifying my consumption of true crime podcasts during office hours!
It can get so frustrating to watch true crime documentaries where the serial killer is caught much too late because they committed their crimes in different states and the police stations didn’t share information across borders. In their defence, the technology wasn’t developed to do this effectively at the time!
And looking back, it’s frustrating to know that lives could have been saved if only the technology and knowledge was as good back then as it is today. But they had to start somewhere, and they did learn to share information across borders to save lives!
Now, what does serial killers have to do with improving healthcare?
You see, much like how the police stations not sharing information and experience about a possible serial killer on the loose with other police stations; The same thing could be happening in hospitals about treatment of new or rare illnesses.
Maybe the right information is already discovered in one country, but not in another and the patients suffer because of it! The frustrating feeling about the slow catching of serial killers? Imagine that frustration many years into the future when it’s common practise for healthcare researchers to share experience and wondering why we didn’t already do this back in 2024.
To get there, we need to start somewhere. And this is where the BETTER project comes in, for BETTER healthcare in the future!
Exciting collaboration
15/05/24 13:54 Filed in: Status | Project News
Frameworks, Technologies and Digital Solutions for Building the European Health Data Spaces: two EU Horizon Europe projects are joining forces and strengthening synergies
The Coordinators of the Better AI Health project aiming to build a real-world health-data distributed analytics research platform with the goal to promote a federated learning framework for decentralised AI for real-world health data, and the VELES Smart Health Excellence Hub that has as mission to transform the Smart Health landscape in South-East Europe by pioneering the European Health Data Space and building the first Regional Smart Health Data Space started a cordial and constructive dialogue.
The aim is to find commonalities and areas needing intervention and support that can improve not only the quality of the work within each of the two consortia, but can also increase the outreach and impact of the two projects.
Dr. Irena Pavlova, Coordinator of VELES (grant agreement No 101087483) and Dr. Matteo Bregonzio, PhD, Coordinator of Better AI Health ( grant agreement No 101136262), with the support of Dr. Adamantios Koumpis of the University Hospital Cologne that is partner of Better AI Health, have converged to a flexible format that will enable effective clustering activities between the two projects to take place over the next years of projects’ implementation.
“We do not want to over promise at all – and given the fact that our clustering is voluntary, we prefer to start with small, but very targeted steps” said Irena Pavlova. Matteo Bregonzio explains that “a collaborative effort in communication and dissemination can only amplify the reach and broadcast our missions to a larger public. Furthermore, cross-validation of ideas and methodologies will be very valuable to assess how to deploy federated healthcare use cases at scale as foreseen by the European Health Data Space agenda”. Irena concludes that “it is only if we see how to join efforts that we shall achieve something bigger. And joining efforts starts from developing a mutual understanding”.
The consortiums shall start a series of Webinars that will be structured and informed by the research agendas of the two projects and address not only the researchers of the participating institutions but a wider audience of interested parties.
Dr. Irena Pavlova is with the Sofia University St. Kliment Ohridski, which is the largest university in Bulgaria, through its Centre of Excellence in Big Data GATE Institute. Dr. Matteo Bregonzio, PhD is CTO of Datrix | Embrace the AI Challenge, Italy leading a group of deeptech companies bringing hashtag
#AI to vertical markets. Dr. Adamantios Koumpis is Research and Teaching Officer at the Institute of Biomedical Informatics at the University Hospital Cologne and the Medical Faculty at the University of Cologne.
#AI
#EuropeanHealthDataSpace
#HorizonEurope
#BETTER
#VELES
#Federate
The Coordinators of the Better AI Health project aiming to build a real-world health-data distributed analytics research platform with the goal to promote a federated learning framework for decentralised AI for real-world health data, and the VELES Smart Health Excellence Hub that has as mission to transform the Smart Health landscape in South-East Europe by pioneering the European Health Data Space and building the first Regional Smart Health Data Space started a cordial and constructive dialogue.
The aim is to find commonalities and areas needing intervention and support that can improve not only the quality of the work within each of the two consortia, but can also increase the outreach and impact of the two projects.
Dr. Irena Pavlova, Coordinator of VELES (grant agreement No 101087483) and Dr. Matteo Bregonzio, PhD, Coordinator of Better AI Health ( grant agreement No 101136262), with the support of Dr. Adamantios Koumpis of the University Hospital Cologne that is partner of Better AI Health, have converged to a flexible format that will enable effective clustering activities between the two projects to take place over the next years of projects’ implementation.
“We do not want to over promise at all – and given the fact that our clustering is voluntary, we prefer to start with small, but very targeted steps” said Irena Pavlova. Matteo Bregonzio explains that “a collaborative effort in communication and dissemination can only amplify the reach and broadcast our missions to a larger public. Furthermore, cross-validation of ideas and methodologies will be very valuable to assess how to deploy federated healthcare use cases at scale as foreseen by the European Health Data Space agenda”. Irena concludes that “it is only if we see how to join efforts that we shall achieve something bigger. And joining efforts starts from developing a mutual understanding”.
The consortiums shall start a series of Webinars that will be structured and informed by the research agendas of the two projects and address not only the researchers of the participating institutions but a wider audience of interested parties.
Dr. Irena Pavlova is with the Sofia University St. Kliment Ohridski, which is the largest university in Bulgaria, through its Centre of Excellence in Big Data GATE Institute. Dr. Matteo Bregonzio, PhD is CTO of Datrix | Embrace the AI Challenge, Italy leading a group of deeptech companies bringing hashtag
#AI to vertical markets. Dr. Adamantios Koumpis is Research and Teaching Officer at the Institute of Biomedical Informatics at the University Hospital Cologne and the Medical Faculty at the University of Cologne.
#AI
#EuropeanHealthDataSpace
#HorizonEurope
#BETTER
#VELES
#Federate
First meeting with the BETTER project was a success!
17/04/24 13:50 Filed in: Status | Project News
First meeting with the BETTER project was a success!
The Grand Hotel Bristol, and the landscape around the city of Stresa, Italy, was a beautiful backdrop for our first meeting in the innovative BETTER project. To grow innovation you need diversity, and what is more diverse than a collaboration of people across both international borders as well as across fields of expertises? It doesn’t get more diverse than the impressive group of bright, ambitious, and determined minds working together in BETTER!
Online meetings are great for working internationally, but nothing beats the good old-fashioned face-to-face meeting. So many conversations and ideas happen during the coffee break or on the walk to the dinner restaurant after the scheduled program of the day. Face-to-face meetings make online meetings easier afterwards, because we now know each other a little better.
Some of us have met before in other projects, however, most of us were introduced for the very first time in Stresa. During the meeting we presented our progress in each work package and use case so far, and discussing the next steps. With new inspiration and motivation in our minds, we all go home and continue our work.
We are looking forward to see what we can accomplish together in the next three years!
The Grand Hotel Bristol, and the landscape around the city of Stresa, Italy, was a beautiful backdrop for our first meeting in the innovative BETTER project. To grow innovation you need diversity, and what is more diverse than a collaboration of people across both international borders as well as across fields of expertises? It doesn’t get more diverse than the impressive group of bright, ambitious, and determined minds working together in BETTER!
Online meetings are great for working internationally, but nothing beats the good old-fashioned face-to-face meeting. So many conversations and ideas happen during the coffee break or on the walk to the dinner restaurant after the scheduled program of the day. Face-to-face meetings make online meetings easier afterwards, because we now know each other a little better.
Some of us have met before in other projects, however, most of us were introduced for the very first time in Stresa. During the meeting we presented our progress in each work package and use case so far, and discussing the next steps. With new inspiration and motivation in our minds, we all go home and continue our work.
We are looking forward to see what we can accomplish together in the next three years!
Making a project home page
01/04/24 15:20 Filed in: Communication
When designing and making a Horizon project home page, a lot of considerations have to be done and a lot of people need to be involved, even though their daily focus is not what is communicated but rather what is researched.
When you start the web page, you also consider how to update it, and if it should be stored in a database with access for all, including being an easy target for cyber-criminals or a static page, which we ended up with here. The blog posts are hosted statically, so there is only the webadmins who can change anything, which has both security and monetary advantages (hosting a database is not for free), and the disadvantage that only one person at a time with the right tools can access it.
As the project is also funded by respectively the EU and the UK, there needs to be sufficient links to these organisations and we always have to remember to ask for permission for cookies and have an updated privacy form.
The Design was partially given by a vote on the logo and the page with color scheme evolved from there, also being part of our design manual that is forthcoming. It is intended to be easy to find what you look for and not to be plain walls of text. Later we will add videos both on the front page and in the blogs, describing the research. We will of course also add other communications either as downloadable results or as more traditional blog posts, and will ensure that all news will be announced on our related social media channels.
An issue that is difficult to work around from the outset is photos and logos. When so many partners are to be presented, first of all, it is difficult to find the right person to help, and secondly, when they are helping it may be difficult to get a common thread in the presentations and format, as the web page may change during the design and development process. We will likely update the graphics over time, where needed and where possible. The same goes for all the written contents. As we have 4 target groups, it is also a task in itself to try to address as many as possible this way.
We hope that you like the first version that we present here today, but you are always welcome to send us comments to make it better!
Happy and fruitful reading!
The Rheasoft BETTER communication team!
When you start the web page, you also consider how to update it, and if it should be stored in a database with access for all, including being an easy target for cyber-criminals or a static page, which we ended up with here. The blog posts are hosted statically, so there is only the webadmins who can change anything, which has both security and monetary advantages (hosting a database is not for free), and the disadvantage that only one person at a time with the right tools can access it.
As the project is also funded by respectively the EU and the UK, there needs to be sufficient links to these organisations and we always have to remember to ask for permission for cookies and have an updated privacy form.
The Design was partially given by a vote on the logo and the page with color scheme evolved from there, also being part of our design manual that is forthcoming. It is intended to be easy to find what you look for and not to be plain walls of text. Later we will add videos both on the front page and in the blogs, describing the research. We will of course also add other communications either as downloadable results or as more traditional blog posts, and will ensure that all news will be announced on our related social media channels.
An issue that is difficult to work around from the outset is photos and logos. When so many partners are to be presented, first of all, it is difficult to find the right person to help, and secondly, when they are helping it may be difficult to get a common thread in the presentations and format, as the web page may change during the design and development process. We will likely update the graphics over time, where needed and where possible. The same goes for all the written contents. As we have 4 target groups, it is also a task in itself to try to address as many as possible this way.
We hope that you like the first version that we present here today, but you are always welcome to send us comments to make it better!
Happy and fruitful reading!
The Rheasoft BETTER communication team!
