This is a great opportunity for students and researchers to contribute and help solve real world problems in the Open Access landscape. Additionally, successful teams will be invited to present their results at a prestigious international conference and their results and methods will be published in the conference proceedings.
Extracting Research Themes
For this task, teams will be asked to develop a model that can identify and label research papers with a research theme. There will be a total of 36 themes, each paper will be labeled with a single theme.
Competitors will be provided with 2 files, train.csv and test.csv. The train.csv file will contain the details for each paper in question and the class label (the research theme). The test.csv file should then be used for evaluating your trained models.
Task participants are required to:
Develop methods addressing the task and submit the results via Kaggle
Document and submit their method as a short paper as specified on the SDP 2022 website
The deadline is 31 July. You can submit your results to us (ronin@iris.ai). After submitting there will be a screening process and the winner will be invited to the conference to present it (October 16-17).
On May 25th 2022, we hosted a webinar together with Materiom where we shared details about our collaboration and the project. Here, you can read more about it or watch it below.
Sustainability needs innovation and innovation needs R&D. However, R&D needs time- the most precious commodity we all have in common. As a consequence of all the world’s current challenges, such as advancing global warming but with too slow progress on carbon capture, energy insecurity, or food supply crisis, researchers need time more than ever to drive innovation for a sustainable future across all industries.
In this webinar we answer:
How can NLP, a subdiscipline of ML, save vastly more time for R&D to innovate?
How can systematized data extractions uncover hidden knowledge scattered in thousands of research papers to contribute to the success of R&D teams and impactful projects like Materiom´s.
Materiom’s mission is to grow a regenerative materials economy. The company is building a suite of solutions that can help holistically to grow the market of petroleum alternatives. Together, we are attempting to pool the world’s data on biomaterial development and performance and make it useful to the world’s entrepreneurs.
Interview with Alysia Garmulewicz, the Co-Founder of Materiom:
How did you get this idea to create such a database?
My co-CEO Liz Corbin and I had a meeting of minds a few years ago upon founding Materiom that really crystallized a lot of our research and doctoral work. I’d been working in the sustainability world for a while in terms of being able to understand the key points that were preventing the cycling of materials. One of the main issues in a centralized manufacturing system where all of this has to go back into production is that it’s very difficult to imagine just being able to take up all those little distributed bits and put it back. In nature there is a much more distributed and nested way of cycling nutrients within local and regional ecosystems.
That was a model that we saw as very compelling but the material economy doesn’t actually work that way. The biomaterial world and the way that you can source feedstock locally and put that back into production at local and regional scales was a very compelling approach to unlocking this systemic rigidity.
The main issue about how we can unlock more local and regional capacity for making materials and making them effective at those scales is data and access to information. That was the galvanizing point of developing Materiom. The goal is to create a starting point for R&D and get to market faster. Since then it’s built into having deep dives, talking to entrepreneurs in the field, businesses that are making amazing plastics and biomaterial alternatives and seeing the challenges they face. It’s deepened over time but that was the genesis of really understanding that the missing link was access to information. If we’re going to have a more systemic change from a very centralized manufacturing system and centralized material economy to a more distributed one that allows for regenerative sources of biomass to be effective.
How did you hear about Iris and why did you choose us as a collaboration partner?
Liz (Co-CEO) was the one who stumbled across Iris. I can’t remember the exact point of reference, but it certainly stood out to us as being a solution that we were looking for specifically focused on the scientific literature. We’ve been aware that the field of natural language processing is growing but Iris.ai’s specific focus on scientific papers and scientific data itself made the most sense so it was an obvious fit from that perspective.
How would you describe our collaboration so far and do you think that we already had some major challenges that we had to overcome together?
One of the most interesting and important challenges that has shaped the first stage of our collaboration has been getting the grip of the nature of the information that we’re trying to extract. I’ve really been grateful for the amount of feedback and transparency in terms of what the challenges are and what the team is working on and being able to feed in with our domain knowledge when it’s needed. I’m sure there’s gonna be more challenges along the way but I think grappling first with just the type of information how it’s portrayed was the main one that I’ve seen in this first stage.
We are very happy to be collaborating with you. It’s always very helpful when our clients are very responsive and give feedback and tell us the questions. Sometimes you’re so deeply into the topic that maybe you don’t understand which words the outside world might not understand, so it’s very helpful to have open communication. This already leads me to my last question – what would you tell someone thinking to be collaborating with us or any other AI startup? What they should be expecting or what they should have in the back of the head?
I think one of the main things that I would emphasize is the importance of the journey – being able to learn and iterate and be responsive to the challenges along the way. It’s certainly a field or an area of solution space that really requires a lot of engagement with the topic. It’s not magic that just suddenly will appear at your doorstep. The technology is incredible but it’s even more incredible when you have the partnership between two companies – in our case Iris.ai and Materiom. That can really enrich the process and make the journey enjoyable. The more you put into it, the more you can get out of it. I really enjoy that process of working with the team and I think that it’s a really exciting learning process for us to understand how far you can push the technology and what results you can get and how that fits with the mission and the time frame and the goals that we have. It’s definitely a learning process and I think that should be enjoyed.
Have you ever heard of the expression tl;dr? It stands for “Too long, didn’t read”. It likely originated on the comedy forum Something Awful around 2002, and spread to other online forums. Nowadays it is used by authors when they give a short overview of their text. Does it sound like something you might have said before too?
There are a lot of good examples for when you prefer to have a short summary of the document for instance if you are not sure yet if it is of interest for you or when you actually only need the essence of it to continue with your work.
A good example for that might be the book “On the Origin of Species” by Charles Darwin. Most likely all of us know his famous ideas on evolution on natural selection but only a handful of people have bothered to read that 502 pages long book. Simply because for us it has not been necessary to understand all the details but the main messages.
Article overload
The number of published papers and patents grows exponentially. About 2 million papers are published per year, that’s about 5,500 per day. And the growth is growing! So, to stay on top of all the new findings one has to navigate through a vast amount of literature. And after a long search for the right papers, one then has to read each paper and summarise it or at least understand the main takeaways. Instead of reading through lengthy papers; Wouldn’t you prefer to quickly understand the main messages of the paper and if it is interesting of course, go ahead and read it as your night time lecture?
If we can quickly assess the main findings and messages of one or a couple of similar papers, patents and internal documents, we would use less of our valuable time reading and summarizing papers. Hence, we can allocate our resources to more important tasks like using the empirical findings on inventing a new product or drug.
Iris.ai Summarization Tool
Our Summary Tool, as the name indicates, automatically produces summaries of any given document for you. In general, there are two types of summaries – extractive and abstractive. With an extractive summary one identifies the relevant information that is then extracted and grouped together to form a concise summary. In contrast to that, the Iris.ai Summary Tool creates abstractive summaries, meaning that the machine rewrites the entire document by building internal semantic representation, and then a summary is created using natural language processing.
The tool can make a summary of one as well as multiple documents. For the multi documents the machine identifies the parts of text in common and only makes a summary of that. Additionally, the summary can be based on abstract only or full text. The user can also adjust the length of the summary. We can take this feature a step further – for example, by you providing a topic of focus and the machine summarizing only text related to that, not the full texts. Let’s say you want a summary of only the experiments, or only the methods, or only one of the topics covered. This is still experimental but very exciting.
The tool can be integrated with your systems and the user interface can be customized.
Watch the full demo alongside with the peak behind the curtain of the technology we’re using here:
In pharmacovigilance, post market surveillance and many other areas of drug development, highly skilled team members spend an enormous amount of time systematically mapping out publications. This includes going through clinical trial reports and real world evidence, and extracting key data points such as adverse effects.
In this webinar, we covered how to:
👉 Automatically filter based on entities of interest and specific context.
👉 Extract data such as adverse effects, treatment and patient baseline characteristics.
Iris.ai provides multidimensional research for exploring possibilities and limitation in applying Augmented reality to surgical settings
Last week we hosted a Scithon in collaboration with Stryker and the Freiburg University Medical Center. For this Scithon, three teams were trying to find a solution for this research question: What research and development work is necessary to build a “ready to use” adaptive augmented reality (AR) system for surgeons to teach them how to perform a surgical procedure? The judges were looking for the teams to find solutions involving four different dimensions of the question; identifying the capabilities of the technology, outlining the training process for doctors, describing the human interaction and UX and how it would be integrated into the surgical flow. Over the course of the day, we had several conversations with participating doctors and members of the Stryker team which gave us valuable insight and solid background information for the research problem we were trying to solve.
The Scithon’s winning team cited just 13 papers using Iris.ai which allowed them to successfully cover all four of the required angles. The team concluded that the prospect of AR in surgical environments is absolutely feasible however the current technology needs further testing to prove reliability and other improvements to meet surgical requirements. They were able to outline specific uses of the technology and identified that ‘the more rigid and basic the surgical system the easier it is to implement augmented reality applications to improve results.’
The team placing second used traditional research methods to reach their conclusion and while they found more papers, 46 in total, those papers had a much more narrow focus, with most of them targeting a single topic area. The reason being, traditional methods rely on the existing knowledge of the user, where users typically search for more of what they know instead of discovering new, related topics that were previously unknown to them. Their conclusion ascertained that presently there is no technology that encompasses all of the features needed to create an AR system to satisfy all of the requirements named in the problem statement. However, research data and solutions on the key aspects of technical limitations are available and provide the foundation for the development of the envisioned system.
Similar to the winning team, the team that placed third was also using Iris.ai and was able to reach their conclusion using a few number of papers citing 15. While the judges were conflicted on the depth on which they covered the various aspects of the research question, they were able to cover 3 out of 4 of them. Their solution asserted that it is possible to build an AR system comprising of existing surgery navigation platforms, real-time intraoperative imaging and 3D visualization display devices. However, these technologies are not without shortcomings like the need to reconfigure display devices that are too bulky, have limited capabilities and autonomy limitations and improve the tracking of surgical instruments and automatic relevant medical information extraction.
The results of the Scithon spoke to the benefit of Iris.ai’s serendipitous search enabling a multi-faceted approach to research. Whereas traditional search limits the output to singular aspects of the problem, that doesn’t connect all of the possible angles. Current keyword search engines return results that can be biased based on the user’s search history and experience. Iris.ai produces unbiased, objective results creating a multidimensional approach for research discovery. Most research problems require several topic areas to be considered before a solution can be found and Iris.ai enables teams to find the research to cover each and every one of them.
Gaining context for the research problem we’re trying to help solve
Last week, we hosted a Scithon in collaboration with Stryker, Augmented Vision and Freiburg University Medical Center. We put a group of medical engineers, IT experts, neurosurgeons and urologists in a room to discuss and research methods for advancing Augmented Reality/Virtual Reality in surgical settings. What made this particular group of Scithon Participants unique was the high level of expertise related to the research topic subject matter. Even before beginning to research the feasibility of AR/VR surgical innovations, almost all of the doctors already had a good baseline of specific features or use cases that would be most beneficial to them. And the views between neurosurgeons and urologists regarding the usability and implementation of innovative technology in the Operating Room varied greatly. It seemed clear that no matter the outcome of the day’s research, the feasibility of using AR/VR in the OR wasn’t the biggest obstacle to overcome. So, before we outline the results of the research, we want to the highlight a few of the learnings from the discussions that took place over the course of the Scithon. These learnings provided valuable context for the day’s research and gave us better insight into the pain points behind the research question.
Coming into the Scithon, it was interesting to see what types of technologies the doctors had begun to familiarize themselves with and which ones they preferred. One of the urologists touted his ‘bootstrapped’ method of incorporating Google’s Cardboard into his work while other teams of neurosurgeons already begun investigating how best to use Microsoft’s HoloLens. Other doctors expressed frustration at the speed of their colleagues’ ability to embrace and adapt to new technologies. And still, others, questioned the practicality of implementing a new technology that will need to be replaced in 3 years or even worse, could be obsolete in that same period of time. Even with the ability to use groundbreaking technology, there are other issues creating barriers for implementation. Hospital budgets, time spent training doctors, access to up to date research and data, IT maintenance, etc are all factors in delayed or even non-use of state of the art technology.
How residents and doctors time is spent was a recurring theme mentioned throughout the day. The finite preciousness of doctor’s time is a never ending issue. Several participants stated it was difficult being able to attend today’s Scithon, let alone focus on their own research. The sacrifice of their time did pay off, as all they agreed that the Scithon was a valuable use of their time. It allowed for a ‘meeting of the minds’ type atmosphere facilitating extensive discussions among a range of medical specialties. And many were interested in the long-term possibilities of using Iris.AI’s platform to expedite their institution’s research. Ability to save time was a vital feature that all participants were interested in, regardless of specific technology.
We gained numerous insights from the medical technology provider and manufacturer group of participants as well. We could relate to them as we were both in the position of watching, in real time, others using our products and platform. The participants from Stryker shared a few industry insights like Microsoft’s shift from AR back to their primary Cloud based product offerings and how that might affect their future involvement with the AR field. They also discussed a slight gap between product features and product implementation in the medical field, as some doctors had mentioned their products were too complex for what they needed. Simply put, the current technological solutions were overbuilt. The feedback is at the forefront of their minds as they continue to create products for the medical community.
They say if you build it, they will come it. Well, now the question is, can they build it? Does AR/VR have a place in surgical settings and if so, how can it best be implemented?
Can Virtual and Augmented reality improve the medical training process?
Virtual Reality & Augmented Reality are changing the world as we know it, every day we are discovering new uses for these innovative technologies. The medical field is one that is especially excited to see the applications of VR and AR evolve, as the implementation of these frontier technologies could improve medical education considerably. The nature of practical medical training has changed minimally over the last decades. However, the feasible application of VR & AR for medical education purposes could modernize the training process for medical students, requiring less training performed on patients. Understandably when education for treatment methods improves it allows for medical staff to address the needs of patients in an increasingly comprehensive manner. And it It is these notions that form the basis for our upcoming Scithon.
Next week researchers from the Division of Urotechnology, University Medical Center Freiburg, in cooperation with the Department of Augmented Vision, German Center for Artificial Intelligence, and the Stryker Stryker Leibinger GmbH & Co. KG, will gather to compete to find the best approach to implementing these technologies. VR & AR are ever growing fields, with new information published daily, so the teams will us Iris.AI to find the most relevant papers to this query. Because Iris.AI shortens the amount of time needed for research discovery, it enables teams to move to the next stage in research & development more quickly. This correlates to identifying new solutions and avenues for treatment of patients more quickly which can ultimately save lives.
We are excited to put Iris to work on such a considerable task with far reaching results and benefits. We look forward to sharing these promising results with you next week.
Hitting a roadblock in your research? Struggling with the drudgery part of the R&D process?
Here at Iris.AI we thrive on addressing multifaceted issues head on and love being able to use our AI to help others elevate their innovation process. In fact, we love it so much that we are dedicating our summer to do just that by running a tour of Scithons in London, Stockholm and San Francisco in collaboration with Founders Factory.
Each Scithon (think of Hackathons for research!) is a day-long research sprint where teams of driven researchers use Iris.AI to summarize the most relevant research on an R&D challenge in one day. Teams, invited to the event by Iris.AI, compete to win a cash prize by pioneering a tangible solution to the question at hand.
At the end of the day you will receive the winning team’s solution which will contain:
– A full overview of all identified cross-disciplinary research on the challenge
– Their conclusion on how to go about solving the problem
– The key papers outlining this solution.
– You will also have contact details of the team’s participants in order to continue the dialogue with them.
We are now looking for innovation-driven organizations to join us for the sprint in one of the three cities. Simply send us your research question. We’ll take care of everything else including the sourcing of multidisciplinary and driven researchers.
Iris.ai gives students, researchers, and engineers alike, the tools to realize and actualize their (spatial) dreams. And in this case, dreams of making aerospace history.
Two months after SpaceX’s Dragon launch mission, Iris.AI hosted a science hackathon or Scithon as we like to call it, in partnership with the leading composite materials research institute Swerea SICOMP. At the Scithon, we challenged researchers to find solutions to this question, “Can you create a reusable rocket using composite materials?” A concept that SpaceX has been pursuing for 15 years while the research community has been exploring such possibilities for much longer than that. Yesterday’s historic launch was the first step in achieving that milestone by attempting to mimic the reusable nature, lifespan and quick turnaround of planes used for air travel.
Before launch, SpaceX engineers pointed out that there are a thousand ways to fail, but only one way to succeed and identified the areas of possible failure; manufacturing error and material fatigue and wear out. The areas identified by SpaceX were a generalization of the known obstacles at the time of the Scithon; composite performance issues at extreme temperatures, limited durability against UV exposure and space radiation, and chemical resistance issues with rocket fuels. Over the course of the Scithon researchers uncovered hundreds of papers to support their claims around creating reusable rockets. One of the conclusions reached suggested that nanostructured coatings provide better high-temperature performance and corrosion protection, based on this paper on the development of radiation shielding of composite space enclosures as a core element of their solution.
The Falcon X launch was supported by multitudes of research, some of which is similar to the conclusions of the Scithon teams. Two factors aiding to the success of the mission were the ability to quantify the catalytic properties of reusable thermal elements and simulating data for the design of high-temperature composites, method designed by NASA. And both of these principles relate to the conclusions reached by one of the Scithon teams.
The success of Falcon X coupled with the Sciton results argues that using Iris.AI individuals with no direct background expertise were also able to conduct innovative and groundbreaking research, often reaching similar conclusions to those of dedicated scientists, engineers, and researchers.
Addressing the challenge of achieving healthier lifestyles
Last week, we were at the Lapland University of Applied Science, in Finland, where we held a Science Hackathon in collaboration with Hotus and Skhole Oy. The goal of this intensive day long research sprint was to identify the most effective interventions to sustain healthy lifestyles in healthcare. During the sprint, teams of students and researchers collectively sourced over 200 research papers. As a single source, Iris.ai accounted for more than half of all papers. The final results showed that the more time the team spent using Iris.ai, the better it performed during the Scithon.
Each year noncommunicable diseases (NCDs) kill roughly 38 million people, according to World Health Organization estimates. We are well informed about the cause of those deaths, which are driven primarily by four major lifestyle factors: 1) tobacco use, 2) lack of physical activity, 3) the harmful use of alcohol and 4) unhealthy diets. Howeve, we lack extensive information on the most impactful health care interventions to prevent NCD’s.
Working in collaboration with WHO, Hotus, the nursing research foundation, and Skhole, a healthcare eLearning platform, strive to produce reputable evidence-based frameworks and teaching materials to better inform clinical decision-making. NDC’s are one of the major areas of focus for both organisations. Therefore, to accomplish impactful frameworks, researchers devote countless hours to analyzing hundreds of research articles, a daunting task for human minds. The artificial intelligence of Iris.ai is optimized for precisely such tasks. This created a great opportunity to co-host a Scithon.
“Our plan is to create a nursing guideline and evidence summaries related to impacting lifestyles in healthcare. I think that the results from the Scithon are a great starting point for that work. We will use the material as one of the sources for the drafting process.” — Virpi Jylhä Researcher, Hotus Nursing Research Foundation
At the Scithon, seven teams comprised of cross-disciplinary students, researchers and professionals gathered to identify impactful measures that enable healthy lifestyles. The teams were asked to use Iris.ai exclusively for the first hour and then were welcome to use any outside research tools of their choice. To find the best possible solutions to the problem statement, the teams were evaluated on both qualitative and quantitative fronts. Judges looked at the team’s research strategy, as well as the quality of their findings and insights (e.g., Did they follow current research trends? Was their conclusion well-supported?). Additionally, the number of papers they found, as well as the relevance of those papers, was factored into their scores.
“What surprised me and the other judges was the versatility and the scope of the results. The teams managed to find a wide range of relevant knowledge within a short period of time.” –Virpi Jylhä Researcher, Hotus Nursing Research Foundation
The winning team, Mindhack, concluded that change is a process, not an event. The team is comprised of Annika Lehmus-Sun, a Master student at the University of Helsinki, Johanna Töyräs, a student Nurse at the Lapland UAS and Niko Männikkö, Ph.D. Candidate at the University of Oulu. They asserted that both proper stress management and healthy gut bacteria contributed to a healthier lifestyle. A substantial portion of their conclusion was based on research from Plos One on the combined impact of lifestyle changes in body weight and Jama Internal Medicine’s paper on meditation programs for psychological well-being and stress.
Coming in second was Team Etelä-Savon Digiloikkarit, consisting of team members Santeri Seppälä, Licentiate of Medicine, Mikko Lampi, M.Cs. Information Systems, Anu Salpakoski, Doctor of Health Science, and Pirjo Hilama, a Master student at the University of Eastern Finland. Rounding out the top three was Anagrammi Imperfektissä whose team members included Aarni Karjalainen, Markus Sillanpää and Ville Vilén, all students at Lapland UAS.
Based on the efforts of the seven teams, it was evident that more the maps the team created, the better they fared in the competition.On average teams spent a quarter of the allotted time using Iris.AI, with the winning team spending over half of their time, on the tool. The overall average number of papers found by all teams was about 30 and when looking at the top three teams the average jumps to 48 papers. In total, over 85 research maps were created during the Scithon. The winning team generated the highest number of maps, 18, further proving that the increased use of Iris.ai increases research productivity.