Europe leads the world in quality of care and patient safety, yet delivering truly personalized treatments remains a challenge. Stringent data rules, complex validation and reimbursement processes demand innovation that moves carefully but keeps pace with technology. This track explores how life sciences organizations can accelerate innovation while ensuring compliance. From navigating EU data regulations and redesigning validation for tailored therapies to leveraging AI discovery tools, microfluidics and digital platforms, you’ll see how regulatory constraints can become drivers of responsible, patient-centred innovation. Check out the presentations from the Innovation Day of 2024 on:

• The light microscope: An evolving tool for advancing cancer therapy
  By Didier Beghuin, Business Line Officer of Life Sciences at Lambda-X Verhaert High-Tech
• Accelerating data validation with digital platforms
  By Margo Billen, Customer Success Manager at Verhaert Product Innovation and Niko De Bruyne, AI Engineer at Verhaert Digital Innovation
• Scaling innovation from within: Baxter’s acceleration program
  By Wouter Hendrickx, Customer Success Manager at Verhaert Strategic Innovation

View the presentation

The post Life sciences – Advancing personalized care in a regulated world appeared first on Verhaert Masters in Innovation.

The post Life sciences – Advancing personalized care in a regulated world appeared first on Verhaert Masters in Innovation.

Why high-quality data is essential for valuable AI

AI models learn patterns and make decisions based on the data they’re trained on. If the input data is flawed, the output will be unreliable: garbage in, garbage out. Because AI systems require substantial time and effort to build, you’ll want certain assurances it’ll be worth the investment. That’s why high-quality data is essential for ensuring accurate predictions, valuable insights, and effective automation.

And why poor data quality allows for serious risks. Bias in training data can result in unfair or misleading outcomes. At the same time, inconsistencies and missing values can cause AI to misinterpret information, leading to unpredictable results. And outdated data may drive decisions based on obsolete trends. The biggest threat? AI might generate results that appear correct but are fundamentally inaccurate, making it difficult to distinguish between right and wrong. Without a strong data foundation, even the most advanced AI models can fail. So when do you have a strong data foundation?

What about using AI as a data cleaner?

AI isn’t just dependent on high-quality data, it can also help improve it. Intelligent algorithms can fill in missing values for more complete data. Anomaly detection helps identify outliers and inconsistencies that might otherwise go unnoticed. AI can also identify redundant or conflicting entries, streamlining datasets. Finally, normalization and standardization enforce consistency, making data more structured and reliable for AI applications.

However, AI-driven data cleaning isn’t foolproof. If there’s a flaw somewhere in the process, AI may reinforce incorrect patterns rather than fix them. To prevent this, organizations should implement safeguards: either maintain a small, verified dataset for validation or have human experts review AI-refined data. Even with these precautions, AI-driven data cleaning can significantly speed up the process.

Fixing data at the source

Although AI-driven data cleaning can be a powerful tool when you know you don’t have high-quality data, there are other, sometimes better, options.

• Generating synthetic data: Simulations can be a fast solution for data scarcity. By defining specific parameters, simulations can produce endless data, helping identify trends and patterns when real-world data is lacking or insufficient.
• Leveraging external data sources: Both paid and freely available, external data from sources like governments, research institutions, and other companies can enrich your dataset, providing additional context and improving the AI model’s accuracy.
• Using alternative data sources: Gathering data from different systems or creating new collection methods can improve data relevance and accuracy. For example, you might not have a sensor in place that captures when a machine breaks down, but maybe your conveyor belt stops working and sends an alert as a result, which can be captured.
• Improving existing databases and collection methods: A more long-term solution is focusing on improving their existing databases and data collection methods. Even when you’re still building the AI system, better-designed data systems can automate reporting and even simulate basic insights AI might provide in the future.
• Implementing federated learning models: In privacy-sensitive sectors, federated learning allows you to train AI models using decentralized data without compromising privacy, as the raw data is never shared across systems.

From imperfect to powerful

High-quality data is the cornerstone of effective AI, but no dataset is perfect. By leveraging a combination of continuous improvements and proactive data-gathering strategies, businesses can refine their data to unlock their full AI potential. So how do you know which strategy will work best for you? You have to define what you want to do before you define how to get there. Typically, this is why we set up dedicated ideation workshops in which we get to the bottom of why you want to invest in AI and what you want to get out of it. This helps define clear data strategies, assess data quality, set up improved data-gathering processes, or even algorithmically improve your existing dataset. That’s how, with the right approach, AI can transform not only your insights but also the way you manage and improve your data over time.

The post Garbage in, garbage out: The importance of data quality for AI and how it can be improved appeared first on Verhaert Masters in Innovation.

The post Garbage in, garbage out: The importance of data quality for AI and how it can be improved appeared first on Verhaert Masters in Innovation.

Artificial intelligence

I know we’re kicking in an open door, but if you think we’re at the peak of AI in innovation, think again. Where last year companies were experimenting with generative AI, and machine learning in general, these experiments will reach maturity in 2024 and the first outcomes and successes will only spark further innovation. AI will become more and more integrated into our daily private and working lives.

The technology will further prove its opportunities to increase productivity, boost customer experiences and improve decision-making based on facts and insights. Think copilots, autonomous vehicles, facial recognition, AR, disease detection, threat prevention, the list goes on. Effectively incorporating AI into the digital transformation journey to create true added value will prepare businesses for the future.

• Watch our webinar on AI-infused innovation
• Explore the potential of connected appliances and AI

Clean technologies

As everyone continues to admire the opportunities with (generative) AI and machine learning, it’s very easy to forget about the massive impact these technologies have on our environment. Take ChatGPT for example. Current (conservative) calculations estimate that the tool generates about 43.000kg of CO2 per day. That’s the equivalent of the carbon footprint of 80 people. Per day, and that’s just to keep it running.

This issue will only grow as more and more applications are being released, more and more data is collected, which then again will be used to train more and larger (and smarter) models. Will 2024 be the year we also focus on making them more clean and energy efficient?

• Learn how to design energy-efficient deep-learning algorithms
• Watch our webinar on the future of energy-efficient AI systems

Independent platform development

If we can believe current predictions, BigTech will only continue to grow in the coming years. So why then do we believe independent solutions are also on the rise? Relying on ready-made solutions from tech giants like Microsoft, Apple, Google, Intel and NVIDIA means a lack of personalization and competitive features. And those happen to be two of the most pressing issues of digital solutions, your differentiation toward competitors.

They are following the example of companies like Tesla, take back ownership and developing platforms and components custom to your company’s needs. This allows them flexibility and out-of-the-box offerings. It reflects a desire for autonomy in technology development, aligning solutions precisely with organizational needs and market demands, while maintaining control over costs, data, and strategic direction.

• Discover how Tesla redefined the driving experience
• Learn how Cowboy redefined the e-bikes with a software-first approach

Data-driven innovation

It’s clear that data will continue to be at the heart of digital transformation in 2024. The rise of smart and connected products and services, not only enables companies to provide better and instant experiences for the end user, it could also give them a lot of data. Using that data strategically will help you set up the right systems from the start to collect not just any data, but valuable data.

Leveraging these large and complex datasets with advanced AI then allows you to extract crucial insights to put you at the forefront of innovation. Going beyond efficiency gains, these strategic insights can help you in the decision-making process as well as create new added value. The first step in every process is awareness, then you can dig deeper into those insights to get to the root of it.

• Find out how to accelerate digital innovation with data
• Discover how Cochlear collects and uses user data

AR/VR/MR

A question that comes back every year, is if AR, MR and VR will make their big comeback. And year after year, we come to the realization it did’t really take off. Nevertheless, these systems did continue advancing and especially the surge of AI could make them more accessible and attractive to businesses and consumers.

So could this mean that AR, MR and VR will get a strong foolhold in not just in the gaming industry, but also in retail, maintenance, healthcare, learning and navigation?
We for sure believe there are many opportunities for grabs, like virtual try-ons, home previews, remote assistance, patient follow-ups, online and virtual training, safety measures (virtually) and so much more.

• Discover Reynaers’ dashboard update with VR product visualizer
• Introducing REISS, marking new era in minimally-invasive spine surgery

And what about…

Web3.0, blockchain, NFTs, the metaverse, quantum computing, AGI, drones, robots, traveling to Mars, creating brain interfaces, self-driving cars, room temperature superconductors, hyperloops, nuclear fusion, streaming games, super fast internet from space, self-healing materials, autonomous vessels, TikTok’s world domination, X, … we’re all following that up for you. Stay tuned!

2024 is already showing it’ll be a pivotal year for digital innovation, where strategic decisions will shape the future of businesses. Time to embrace these trends and stay ahead in an ever-evolving digital landscape!

Ready to chart your course in the digital revolution? Get in touch to start your journey to digital excellence!

The post Digital innovation in 2024: what’s in, what’s out appeared first on Verhaert Masters in Innovation.

The post Digital innovation in 2024: what’s in, what’s out appeared first on Verhaert Masters in Innovation.

Let’s start with an example of the training process of a large language model. Don’t fall off your chair reading the rest of this sentence, but that process can produce up to five times the amount of carbon emissions of an average car over its entire lifetime. Yes, you read that right: up to 5 times! Take a moment to let that sink in because this issue will only grow over time as more and more data is being collected annually and more and larger (smarter) models are being trained on this data. So what can we do to deal with this growing problem?

The premise above might sound familiar if you’ve already read the blog by Jente or seen the talk by Bart De Vos and Niels on this topic. If not, we definitely recommend doing so first to get a general scope. In this perspective we dive deeper into this issue, shifting the scope to techniques focused on reducing the energy consumption of deep learning algorithms.

Decision-making AI

Let’s start by asking a very obvious question: “Do we really need a prediction that frequently?”. A prediction is not always needed, sometimes it’s perfectly fine to wait a bit or to even skip it completely. Reducing the number of inference tasks means a reduction of computations and subsequently also the energy consumption.
For connected devices, a second question comes up: ”Where should the inference be performed?”. Both cloud and edge have their advantages and disadvantages that need to be balanced against each other to determine the best choice.

The post Designing energy-efficient deep learning algorithms appeared first on Verhaert Masters in Innovation.

The post Designing energy-efficient deep learning algorithms appeared first on Verhaert Masters in Innovation.

AI isn’t just a cornerstone of digital transformation and process optimization. Artificial intelligence and machine learning open the doors for creative opportunities in sustainable production processes. Much easier than ever expected, they enable you to reduce waste, resources, energy consumption and minimize downtimes. Find out in this webinar from Guy Clarysse, Coordinator AILab, and Yvette Plaisier, Manager Innovation Acceleration Services – Strategic Innovation.

Watch the recording

View the presentation

The post AI-enabled sustainability through process optimization appeared first on Verhaert Masters in Innovation.

The post AI-enabled sustainability through process optimization appeared first on Verhaert Masters in Innovation.

The centerpiece of the blockchain concept is recording data in a decentralized and distributed manner. Whereas most companies within the logistics and supply chain are hesitant to share data on their processes, there’s additional reluctance because everyone would be able to access all data. That is why too much of the logistics world is still stuck in the era of paper documents. Blockchain could solve this and create visibility, transparency and traceability. In this perspective, several experts will share their knowledge and debate whether or not blockchain is the holy grail for logistics.

Standardized platform

Technology enables transparency in the supply chain, improves efficiency and reduces costs. The purpose is to bring and create transparency, providing a trustworthy platform, and to create revenues. Geert De Wilde, CEO of Nxtport International puts clear challenges on the table: “The main challenge is that each company has a different data model, which can’t be pushed into one model.” The backbone of this technology is blockchain. However, in terms of integrability it’s not mature enough to be the only platform, supporting all data formats that are interfacing with the fragmented landscape. Therefore a first step towards standardization is to be encouraged.

Master data management

Technical limitations of blockchain can never be an issue. The former limitations such as technicalities, securities and scalability don’t cause problems anymore. The technology has significantly evolved and become mature. There are lots of buzz and promises around blockchain, but what can we fulfill? A digital certificate could be interesting for different participants who work on the same logistics network, where blockchain is in the middle, such as digital messages and data usage. Nevertheless, once standardization will have evolved, blockchain together with physical internet and AI can add significant value. If we want to go to that future, we need to manage these technologies together, a so-called master data management. Michiel Valee, Founder and Tech Lead of Dockflow states: “Blockchain creates value for larger companies, whereas due to the current lack of standardization it doesn’t make sense for smaller companies and use cases yet.”

Download the perspective to continue reading about the economic value and implementation of blockchain in ports and logistics

The post The added value of blockchain in ports & logistics appeared first on Verhaert Masters in Innovation.

The post The added value of blockchain in ports & logistics appeared first on Verhaert Masters in Innovation.

Indirect data monetization encompasses the ways in which data impacts revenues when data is used without this data leaving the organization. In this case data is used to improve company process, product performances, create data layers, or to enhance or introduce offerings.

Data monetization in health care?

Direct monetization however is not limited to just selling raw data. Another example is when a company sells analyzed data executed from devices, test kit or instruments that were purchased as classical product sales. By integrating a direct data monetization strategy into existing products or services, you can create new and more differentiates values and help learning to become effective in this kind of business models. However, data-driven business models are necessary for outcome-focused strategies.

The future of monetizing innovation in the digital health space is built upon business models that focus on patient’s health outcomes. These can either be business-to-business models or direct business-to-consumer models (often called patient-pay solutions). Nevertheless, patient-pay digital health solutions remain quite rare to this day, and are too big of a change for many traditional MedTech companies. On top of that, European mainland citizens, compared to US and UK citizens, are still quite reluctant to pay out-of-pocket for care. In addition, they expect all health-related technology to be supported by reimbursement. The fast increase in smart watches for health monitoring show a different story, and could be a clear starting point.

Digital health drivers

The following aspects are allowing more effective health care and futuristic outcome-based care to become reality:

• Fierce market competition due to cost pressure and increased worldwide competition for medical device commoditization
  Technological advances at lower costs are enabling remote monitoring, AI supporting diagnostics and enhanced imaging. Moreover, big data is enabling new insights and data visualization.
• Pressure from policy and regulatory organization which introducing changes like the increase in consolidation of hospitals.
  This focus on hospital cost control leads to a shift from:
  • inpatient to outpatient treatment
  • treatment to preventive medicine
  • disease-oriented care to personalized medicine
  • government-pay to patient-pay solutions

If MedTech companies can successfully analyze, treat, use and finally market future data-driven products and services, data monetization will be one of the hottest innovation topics in health care and a new base for building concepts and prototypes.

Any questions on this post? Submit them below and we’ll get back to you soon!

The post Data monetization for digital health appeared first on Verhaert Masters in Innovation.

The post Data monetization for digital health appeared first on Verhaert Masters in Innovation.

Many MedTech companies should realize that they are well-positioned to help replacing our current illness-focused health care system to a preventive, personalized, therapy-focused system. These companies have traditionally focused on developing hardware such as surgical equipment and robots, active and passive implants, diagnostic equipment and drug delivery. However, software, along with data collection and analysis on surgical treatment, diagnostic patient data and much more can be captured with their devices and merged with other datasets. This would need the organization to transform from a product oriented R&D company to a data-driven service and customer-centric organization.

Data-driven organizations

A data-driven and new technology-driven organization is an organization that develops its data analytics capabilities, because data will be more valuable than the hardware itself in the future. Data-driven organization can enable new applications such as digital therapeutics and AI-based wellness coaching. This could help society to enable the so much required behavioral change to avoid or limit needing surgery or hospitalization. New technology adoption can stimulate opening up new applications to allow surgeons and medical practitioners to improve and bring their quality of service to a next level. They can leverage new cognitive and augmented technology to improve data representation and augmented and guided surgical treatment.

In the future data will become more valuable than the soft- and hardware itself

There are many technologies in a high maturity level that are currently becoming extremely interesting to enable the transition to Healthcare2.0, such as AI-controlled robots to assist surgeons and improve treatment outcome, nanotechnology, … Nevertheless, a data-driven organization should be aware that data ecosystems are required to achieve this transition. They need to cooperate with consumer goods or healthcare institutions to add data and will probably have to gain health information correlated to preventive actions and treatments.

Service-oriented organizations

Building a customer-centric and service-oriented organization will allow transforming from a product-centric to a service company. Services represent a fundamental shift in the traditional MedTech business model. However, this required that companies start facing competition based on their underlying software and technology capabilities rather than product performances when it comes to best in-class services. This requires a deep understanding of the consumer, or patients, which is only possible through collecting and activating vast amounts of data.

Service-oriented medical organizations require a deep understanding of patients, which is only possible through collecting and activating vast amounts of data

MedTech companies need to broaden their horizon from the typical products like in a surgical treatment, to the complete patient journey. They need to enable data-savvy consumers interactions so as to evolve towards preventive treatment services. Through these services they can then get much closer to the consumer, which are their patients, and remain relevant. An example of such a service is remote patient monitoring, which could revolutionize the way MedTech companies research disease states, conduct clinical trials and develop products enabling the required data generation. Other examples that can be explored are:

• Services responding to clinical efficiency, by delivering insights and analytics for care givers, patients and medical practitioners
• Health professionals trainings on how to treat patients
• Technologies that help design cost-effective clinical trials

Conclusion

In order to become a preventive and personalized treatment company, transitioning the organization will be rather complex and full of challenging hurdles. You need to balance attention between customer-centric and go-to-market, and focus on service design instead of product design as a value added top layer. The R&D division needs to switch to a data-driven platform organization where products are merely developed to start gathering data. It will be a difficult switch as suddenly the value capturing will be through services, and value creation will come from data. You need to add a completely new value stack that reflects the organization in innovation methods, new teams and new competences.

Any questions on this post? Submit them below and we’ll get back to you soon!

The post Focusing patient treatment on prevention & personalization appeared first on Verhaert Masters in Innovation.

The post Focusing patient treatment on prevention & personalization appeared first on Verhaert Masters in Innovation.

Calculating low-cost routing solutions is very complex. You have to consider production, materials, storage and destination. How can algebraic modeling optimize the supply chain? Find out from Jan Buytaert, Consultant PhysicsLab at Verhaert, during the webinar on reinventing the chemical logistics chain.

Watch the recording

You can watch the recording of this webinar on the YouTube channel of The Beacon.

View the presentation

The post End-to-end optimization of supply chain management appeared first on Verhaert Masters in Innovation.

The post End-to-end optimization of supply chain management appeared first on Verhaert Masters in Innovation.

The challenge

The advent of 5G and edge Artificial Intelligence platforms introduces the opportunity for distributed AI systems. Meaning, devices can be connected in a network of nodes, each generating their own local data from sensors or users and each with their own computational resources. The network allows to share the locally learned knowledge between all nodes in the network. 

In the first place, these nodes perform predictions based on machine learning models. In the case of iterative learning, nodes also generate data to learn from. The machine learning model learns from this data. The model both provides predictions in the edge whilst also improving performance by learning continuously. The main challenge is to share the learnings of the different edge nodes over the entire distributed system.

The current approach to distributed learning raises some critical issues in the application of distributed edge AI namely, data privacy, data security, data access rights and access to heterogeneous data. We dive deeper here to understand why and how federated learning can solve these issues.

Classical approach to distributed learning

The classical approach to iterative, distributed learning relies on data to learn from that is typically generated locally on sensors or by users (mobile phone input, health bands, etc.). In the last decade, the general approach was to have a centralized machine learning model in a server, that receives data which is sent integrally from the distributed nodes to the central server where the data is aggregated and fed to the machine learning model. The machine learning model learns from the data. In turn, the improved model is then sent to the nodes to use locally to perform predictions.

This architecture requires the owner of the edge device to send their data integrally to the main server. This means risk for privacy, giving up data ownership and security risks. Federated learning solve these issues.

Federated learning provides solution

Federated learning solves the issues of data ownership and privacy by making sure the data never leaves the distributed node devices, whilst ensuring that a central model is updated and shared to all nodes in the network.

Federated learning enables multiple nodes to build a common, robust machine learning model without sharing data. This is achieved in 4 general steps:

• Randomized central model sharing: The central model is shared to all edge nodes by storing local copies of the network.
• Local optimization: The local networks are updated by learning on the local data samples.
  
  • Security measure 1: The “learning” is encoded in neural network weights of the model. This step is hard to reverse, meaning it is hard to take these weights and decode them to get the original data.
  • Security measure 2: These learned model weights are then encrypted. To send to the central server.
• Local update sharing: All local updates are sent in an encrypted way to the central server.
• Secure model update: The central server receives the weight updates of all local models and aggregates them without undoing the encryption (based on Homomorphic Encryption encryptions) or decoding the weights to reconstruct original data (since this is very difficult). During the aggregation, the central model takes into account the amount of samples each local used for updating its model. More data means, higher impact on the global model.
• Restart at step 1 by sharing the updated network to all local devices.

State of the art (SoTa)

Federated learning is at this point not widely used. One of the most prominent uses is the Gboard application in which google uses federated learning to improve the performance of your smartphone keyboard. It takes the data generated by all users on their local cell phone and improves the central spelling corrector without ever sending your data to the central server.

Federated learning has also been applied to Unmanned Aerial Vehicles (UAV). UAV swarms must exploit machine learning in order to execute various tasks ranging from coordinated trajectory planning to cooperative target recognition. However, due to the lack of continuous connections between the UAV swarm and ground base stations, using centralized machine learning will be challenging, particularly when dealing with a large volume of data. In the referenced paper, a novel framework is proposed to implement distributed federated learning algorithms within a UAV swarm that consists of a leading UAV and several following UAVs.

The low adoption rate of federated learning is in stark contrast to the technology readiness. The big deep learning frameworks already support federated learning:

• TensorFlow federated: An extension to the TensorFlow deep learning framework to enable federated learning.
• Pysift: An extension to the pytorch deep learning framework
  to enable federated learning.

Future applications of federated learning

There are 4 ingredients to unleash the power of federated learning:

• A distributed network of nodes.
• The nodes are performing a local algorithm for prediction.
• The nodes can gather local data for learning.
• Data privacy, security and ownership are critical.

Any machine learning model used on personal devices like smartphones, cars, smart home applications or even smart appliances can make use of federated learning to improve the user experience of each individual user:

• In the coming decade, transportation will get more autonomous. The driving factor in this technology will be the data that is generated and gathered by car makers to develop their algorithms. Federated learning allows to learn from the cameras in your Tesla, without sharing your actual footage to the main model.
• Image a smart fridge that tracks your consumption and advises you in your grocery planning. The model might learn patterns in consumption that are general to human behaviour in general. These general learning can be shared with all smart fridge users safely without sharing your personal consumption data.
• Image a smartwatch that is used for workout tracking. The applications can detect your level of exertion by analyzing your movement and heart rate. The data you are generating locally could be used to improve the application for all users, by means of machine learning. Federated learning allows to share these learnings to all smart watches without ever having the data leave your device.
• Image a smart thermostat that can learn patterns that are common to all users to improve the overall experience, without ever sharing your personal data to a central point.

AI and big data systems will need to adapt in the future and wide acceptance and adoption will only happen when end users feel the AI and data systems is trustworthy and safe to handle that means having upmost respect for the consumer.

This requires organization to take ownership of the usage of end user data by having a strong data strategy and governance framework in place. Federated learning can bean important part and solve part of the promise we end users expect from these systems:

• Protecting the individual’s right to privacy
• Making the individual aware of how their data is being used
• Giving the individual greater control over their data
• Ensuring the individual’s data is stored securely

Download the perspective

The post Federated learning: embedding privacy in the learning algorithm appeared first on Verhaert Masters in Innovation.

The post Federated learning: embedding privacy in the learning algorithm appeared first on Verhaert Masters in Innovation.