Blog

September 30, 2020

Xavier AI Summit and Workshop 2020 Reflections

Xavier Summit logo
I was sad to not get to see so many faces this year due to COVID, but moving to the safer, digital format didn’t mean that there weren't some great takeaways. I have my two favorites, though.

The first one was the AI Maturity Model that we created in the AI Operations Team. It was our new initiative where pharma companies can self-identify themselves to which level they are in terms of AI adoption. But not only that, they are able to describe what is the journey that they want to take in order to achieve the expected final level in terms of AI adoption. This was a big undertaking which included the FDA’s involvement as well as many pharma companies in conjunction with the AI Operations Team at Xavier University led the AI Maturity Level initiative. This model is free and available on the Xavier site. This is exciting to me because this demonstrates what happens when universities, regulatory bodies, and private enterprises come together to solve problems.

My second favorite takeaway is that AI can be demonstrated as something real in pharma now. This year, we were able to present different use cases. We saw use cases with Pfizer and with AstraZeneca. I had the pleasure to interview Matt Schmucki, the Quality Lean Coach from AstraZeneca, where he explained the process that the AI Operations Task Force did with him and his AstraZeneca team to identify critical factors and potential problems in the granulation operation at AstraZeneca. Matt said, “The results gave the team a new way to look at the data that we wouldn’t have gotten to without using AI.” He continued that, “with over a hundred different process parameters, it’s difficult to know which multivariable interaction to focus on but AI is very good at looking at these numbers and these trends.” This is incredible and wouldn’t have been possible just a few years ago.

It’s a wonderful time to be a part of AI in pharma. AI is real and we have a maturity level model that points to the journey we can follow to realize the promises this technology can bring.

By Toni Manzano, AI Operations Team Lead for Xavier University and Chief Science Officer for Aizon

Toni Manzano is a co-founder and Chief Science Officer of Aizon, a SaaS company that is transforming manufacturing operations with the use of AI and IIoT technologies for pharmaceutical and biotech companies. For over two decades, he has led software projects for international pharmaceutical companies covering the entire production process and supply chain. Today, Toni is a part of the scientific committee with PDA Europe and with the AI Xavier Manufacturing team. He worked as a researcher at the University of Barcelona as a physicist and teaches big data and artificial intelligence in postgraduate courses at the UAB. He is also a member of the Science Experts in the Spanish Parliament on big data and artificial intelligence. He has written numerous articles and holds a dozen international patents related to the encryption, transmission, storage, and processing of large volumes of data for regulated environments in the cloud.

August 24, 2020

The AI World Team and Why it’s Important

We were honored to be at the inaugural meeting of the AI World Team in February. This collaborative forum was created by people from organizations like Xavier University, Philips, AMA, AAMI, MITA, MHRA, Electronic Registry Systems, AdvaMed, Abbott, and the World Health Organization to enable the advancement of world health by expanding access to, and accelerating the development of, artificial intelligence solutions for healthcare. The goal of this consortium is to accelerate the AI implementation in the pharma and healthcare context by means of the active collaboration of all the members in order to improve worldwide quality of healthcare.

We all know that the pharmaceutical industry is slow to adopt new technologies and there is good reason to be cautious. Patient’s lives are ultimately the goal and, as an industry, we are sensitive to make sure those drugs are the safest we can make them. On the other hand, we also know that other industries are able to take advantage of these leaps in technology, including AI, to see tremendous gains in speed and accuracy. At Bigfinite, we are completely aligned with the AI World Team to bring you the best practices and experiences possible where it comes to AI and real information about how it can transform your healthcare initiatives to improve the lives of patients.

We are so honored to be working with this team of talented people and can’t wait to get started!

Learn more about the progress of the AI World Team at this week’s Xavier University AI Summit where I’m speaking and where we have announced the FDA is joining our community!

August 18, 2020

JPST Publishes First Study Showing AI Algorithms Can Be Qualified for Regulated Pharmaceutical Manufacturing

Guidelines from Agnostic Methodology Applicable to All AI Algorithms

SAN FRANCISCO, CA – (August 18, 2020) – Bigfinite, Inc. (Bigfinite), the leading manufacturing artificial intelligence (AI) and advanced analytics platform company for regulated industries, today announced that a new study, published online in the Parenteral Drug Association’s Journal of Pharmaceutical Science and Technology (PDA JPST), demonstrates that AI algorithms can be qualified for pharmaceutical product and medical device productivity chains. Qualification was achieved using Bigfinite’s GxP-compliant AI software-as-a-service (SaaS) platform.

AI algorithms are extremely valuable to the highly regulated life sciences and healthcare industries because they can be used to make critical decisions during drug and medical device manufacturing processes. However, AI algorithms must first be qualified to ensure that they enable established manufacturing goals. Until now, such a procedure did not exist in GxP environments.

“Our study specifically qualified the Isolation Forest outlier detection algorithm, but it did so from an agnostic perspective, which enables the resulting guidelines to be abstracted to other AI algorithms for regulated drug and medical device manufacturing environments,” said Toni Manzano, Ph.D., Chief Science Officer and Co-founder of Bigfinite, and principle study investigator. “Now, for the first time ever, AI algorithms can be qualified and applied by AI models as the foundation for decision making to leverage productivity and quality for critical processes in pharmaceutical and medical device manufacturing.”

Manufacturing decision making that is informed by qualified AI algorithms can potentially lower costs and increase profitability related to pharmaceutical and medical device production. Leveraging AI as a multivariate tool can help optimize processes, as well as predict and fix anomalies in industrial environments. As a result, products and devices that are safer, more efficient and effective, and of higher quality can be made accessible to patients and healthcare providers.

The study used a Quality by Design (QbD) approach and data generated from equipment called bigBox, which was designed specifically for the research by Bigfinite. Real-time data related to four parameters (MS Main, MS Brake, MS Misalignment, MS Imbalance) was relayed from bigBox to Bigfinite’s GxP-compliant, AI SaaS platform every five seconds. A structured Design of Experiment (DoE) was performed using all the operational ranges of bigBox, as well as outliers in the experiments, since the algorithm being qualified was Isolation Forest. Use of QbD allowed characterization of the algorithm and identification of which designed space areas built into the synthetic data sets performed better. The devised DoE and experiment strategy resulted in a valid qualification for the Isolation Forest algorithm.

The study, AI Algorithm Qualification, is currently available online will be published in the January/February 2021 issue of PDA JPST.

About Bigfinite, Inc.

Bigfinite is a software provider that transforms manufacturing operations with the use of advanced analytics, artificial intelligence, and pharma 4.0 technologies focused on optimizing pharmaceutical and biotech companies. The Bigfinite analytics platform seamlessly integrates unlimited sources of structured and unstructured data to deliver actionable insights across all manufacturing sites. Bigfinite offers an intuitive way to gain meaningful operational intelligence with data by enabling real-time visibility and predictive insights in a GxP compliant manner with end-to-end data integrity. Founded in 2014, the company is based in San Francisco, California and also has a European office in Barcelona, Spain.

About PDA JPST

PDA JPST is the primary source of peer-reviewed scientific and technical papers on topics related to pharmaceutical/biopharmaceutical manufacturing, sterile product production, aseptic processing, pharmaceutical microbiology, quality, packaging science, and other topics relevant to PDA members. PDA JPST is an internationally recognized source that receives over a quarter of a million visitors annually.

April 27, 2020

AI Algorithm Qualification

Pharmaceuticals and Biotech companies have no doubt that Artificial Intelligence (AI) is here to stay. Nonetheless, the opportunities AI technology offers are developing at a slow pace in a rather conservative manufacturing industry, aimed at managing production risks under controls that are subject to strong regulations. Fear of change? Risk aversion? Likely not.

Pharma and Biotech industries have been relying on physical laws and chemical reactions for years, all explainable through mathematics and statistics, and there is absolutely no reason why this should change. In the end, AI is all about that: math and stats… but maybe a bit more intricate. In fact, the underlying algorithms in today’s Machine Learning (ML) models are formulated in a non-explicit way, such that the continuous increase in computational power e.g., of GPUs, has made them faster at calculations. However, there is still some black box kind of magic behind AI algorithms that the industry tends to avoid, as neither quality control teams nor regulators feel comfortable with the validation of ML models underpinned by such algorithms.

Since AI algorithms are at the core of any ML model, there is a strong need to know that the algorithms are performing as expected when applied to data with known characteristics. As when crafting a table, you need a saw. Your first goal is to know that the saw you have at hand is suited to deal with the wood you selected for your table. In other words, you need to qualify the algorithm (the “saw”) to reassure customers that they can create an ML model (a “table”) using such an algorithm applied to their process data (their “wood”).

The final goal of AI algorithm qualification is not only to ensure that an algorithm produces satisfying results in a given set of conditions, but also to somehow open the “black box” in a way that allows for an understanding of the limitations of that algorithm, and to identify the factors that could contribute to the malfunctioning of the resulting ML model. This predicate aligns well with the Quality by Design principles that are widely applied in GxP-based manufacturing environments [1] that Bigfinite has adopted for AI algorithms through its own 6-step algorithm qualification policy:

  • Definition of the acceptance criteria
  • Risk assessment
  • Design of the experiment
  • Dataset generation
  • Execution of the experiments
  • Analysis of the results against the acceptance criteria

At Bigfinite, we are working on the qualification of AI algorithms used in AI widgets aimed at providing our customers with maximum confidence in the creation of ML models using our GxP AI platform.

[1] GAMP, ISPE.5: A Risk-Based Approach to Compliant GxP Computerized Systems. ISPE, Tampa, FL, 2008.

Learn more by joining us for a webinar, How to Qualify AI Algorithms, on May 5, 2020.

February 11, 2020

Why Biotech and Pharma Need GxP for their Digital Transformation Projects

The promises of what a digital transformation can bring are new and exciting but also challenging and complex. For pharmaceutical and biotech companies, the use of digital technologies may be challenging and more complex due to their knowledge of how digital technologies work and the possible impact it could have on patients. The industry is still looking for the best standard for its digitalization strategy, looking for a secure plan due to strict regulations and GxP compliance.

As we look to the future of pharmaceutical and biotech industries, novel digital transformation technologies such as artificial intelligence, deep learning, and machine learning will absolutely play a part in their growth, success, and ability to stay afloat in the growing, competitive market. It’s no secret that the industry is facing pressure to innovate due to an increase of personalized medicine, stricter regulations from the FDA, and competition creating a need for faster time to market. So as the Pharma 4.0 shift begins to take place, GxP compliance, data integrity, and regulations is something that needs to be considered when creating a digital strategy.

Why is GxP compliance important?

  • Regulations become more strict due to personalized medicines, gene therapies, etc.
  • “Early choices matter” – starting with a GxP compliant platform will allow you to project the cost of your projects. Knowing the cost from the beginning will allow you to budget correctly
  • Understand your processes better and have unlimited possibilities with a GxP platform. Starting with a GxP platform earlier will allow you to see your manufacturing site holistically, allowing you to better understand your processes and make improvements if need be. This will also keep you from having to go backward in a project if you need a platform that is GxP compliant
  • Also, the MHRA (Medicines and Healthcare products Regulatory Agency) in the UK established a GxP Data Integrity Guidance for cloud providers including Software-as-a-Service, Platform-as-a-Service, and Infrastructure-as-a-Service
  • And the FDA (Food and Drugs Administration) has incorporated cloud technology into their Emerging Technology Team recognizing that it will influence how quality systems will be assessed by the FDA

An effective and successful digital transformation can bring a magnitude of benefits, improving speed and efficiency while maintaining compliance. Ultimately, the most important goal is to provide better treatments for patients and as regulations become more strict, companies must consider GxP compliance and ensure data integrity when creating and executing their digital strategy and culture.  At Bigfinite, we consider ourselves to be enablers of Pharma 4.0 and inspirers of AI in regulated environments. The Bigfinite platform was born from the new digital technologies with a unique focus on Life Sciences and specifically pharmaceutical and biotech manufacturing.

Learn more by joining us for a webinar, Why Biotech and Pharma Need GxP for their Digital Transformation Projects Now, on March 9, 2020!

January 8, 2020

Technological Enhancements with Principal Component Analysis Combined with Artificial Intelligence

Principal Component Analysis (PCA) is a widely accepted method to use when exploring large, complex data sets to interpret relationships between variables. It transforms complex data tables or data sets to a simpler version with fewer dimensions which contain the same amount of relevant information but makes it easier to visualize the main variations in the data. This makes it more manageable to find similarities and identify why samples are different and which variables contribute to the difference between your samples.

PCA plays an important role in exploratory analysis. It is an unsupervised method which can be used for visualization, data compression for further models, check groups on data (i.e. grouping of different batches), trends in the data (i.e. trends during a manufacturing process), detect outliers visually which may not be easy to identify when checking the variables one at a time since they are multivariate outliers. It is also used in multivariate process control to combine all available data from a process to a single trace or fingerprint for each operation or group of operations.

Until now, this has been largely a manual effort but technological advances like Industrial Internet of Things (IIoT), cloud, big data, and artificial intelligence (AI) have opened the door to access computational resources which were not available previously.

Today, Bigfinite brings the PCA application to market as a ready-to-use component of our GxP AI-enabled cloud platform, specifically designed to provide root cause analysis and predictive deviations capabilities for pharma and biotech manufacturing. The new PCA application uses advanced, multivariate statistics combined with AI to aid pharma and biotech manufacturers to better analyze and control their processes.

Process experts can easily create a scalable PCA model by themselves through a drag-and-drop interface. Furthermore, the PCA tool can be set to work in real-time, ingesting values produced in the moment by the process variables and crunching them into principal component representations; in this way, a process defined by the variation of tens, hundreds or thousands of variables, can be represented in real-time in human-understandable 2D or 3D visual representations of the principal components. Whenever new data is collected, it can be projected into principal components and the new samples plotted in real-time overlapping with previous runs making it possible to identify how similar it is to the current process compared with the previous runs used to create this model.

To learn more about Bigfinite’s GxP AI-enabled platform and PCA, email us at sales@bigfinite.com or watch our demo on Multivariate Root Cause Analysis.

Software screen shots:

Image 1: If the PCA is created using data describing a single phase within the process, a slight variation of a single variable triggers the orthogonal representation of the principal components outside of the standard PC1 – PC2 fingerprinting/mapping of the phase.

Image 2: If the PCA is created using data describing the entire process, a slight variation of multiple variables triggers the orthogonal representation of the principal components outside of the standard PC1 – PC2 fingerprinting/mapping of the process. The variations can be small enough not to trigger any alarm in a single-variate process control, but the PCA perfectly captures variations within a multivariate statistical process control scenario.

November 4, 2019

Bigfinite Closes Series B Financing with Atlantic Bridge and Honeywell Ventures to Drive Disruption in Manufacturing Analytics

SAN FRANCISCO, CA – (November 4, 2019) – Bigfinite, Inc. (Bigfinite), the leading manufacturing data analytics platform company for regulated industries, announced that it has closed $15 million in financing with Atlantic Bridge, Honeywell Ventures and Institut Català de Finances. The new funding will be used to support the market expansion of Bigfinite’s SaaS platform, an AI-powered solution that helps pharmaceutical and biotech companies discover new ways to optimize manufacturing processes, reduce quality issues, and enhance regulatory compliance.

“Atlantic Bridge has an extraordinary track record of investment into the next wave of computing including in artificial intelligence (AI), big data, and Industry 4.0 while Honeywell Ventures’ expertise in the Internet of Things, analytics, and advanced manufacturing make this an ideal investment partnership for Bigfinite,” said CEO and co-founder, Pep Gubau. “We are honored and look forward to partnering with these organizations to further scale Bigfinite’s footprint within the life science manufacturing industry.”

“It is well known that billions of dollars annually could be saved through manufacturing process improvements and that a tremendous amount of data is never used,” said Andrew Smyth, Investment Director at Atlantic Bridge. “Bigfinite’s practical use of AI to provide predictive models will save the industry millions in lost product and dramatic reduction of effort to ensure compliance and data integrity.”

“Manufacturers around the world, particularly those in highly regulated industries, are looking for new and innovative ways to use data to optimize their operations,” said Murray Grainger, managing director, Honeywell Ventures. “Honeywell is pleased to make a strategic investment in Bigfinite, whose innovative platform will allow for life sciences manufacturing to be conducted in a faster and more productive manner, while enhancing compliance.”

Existing investors including Uncork Capital, Crosslink Capital and La Famiglia all participated in this funding round, bringing the total funding to date to more than $23.5 million.

About Bigfinite, Inc.
Bigfinite is a solutions provider that transforms manufacturing operations with the use of advanced analytics, artificial intelligence, and pharma 4.0 technologies focused on optimizing pharmaceutical and biotech companies. The Bigfinite analytics platform seamlessly integrates unlimited sources of structured and unstructured data to deliver actionable insights across all manufacturing sites. Bigfinite offers an intuitive way to gain meaningful operational intelligence with data by enabling real-time visibility and predictive insights in a GxP compliant manner with end-to-end data integrity. Founded in 2014, the company is based in San Francisco, California and also has a European office in Barcelona, Spain.

About Atlantic Bridge
Atlantic Bridge is a Global Growth Equity Technology Firm with over €900 million of assets under management across seven Funds, investing in technology companies in Europe and the US. We have offices and staff based in Palo Alto, London, Dublin, Munich and Paris.

About Honeywell Ventures
Honeywell (www.honeywell.com) is a Fortune 100 technology company that delivers industry specific solutions that include aerospace products and services; control technologies for buildings and industry; and performance materials globally. Our technologies help everything from aircraft, buildings, manufacturing plants, supply chains, and workers become more connected to make our world smarter, safer, and more sustainable. For more news and information on Honeywell, please visit www.honeywell.com/newsroom.

September 13, 2019

2019 Xavier University AI Summit Reflections – Two Industries Ready for Change

Now that the dust has settled from the Xavier University AI Summit and our team is back to business, we’ve had time to process some of the highlights and key takeaways from the exciting event.  In the past few years, there has been a significant increase in the implementation of digital technologies into various industries that subsequently impacted the way we live, travel, and do business.  From driverless cars to 24/7 customer support chatbots, innovation and technology continue to spiral upward and as we’ve entered the 4th industrial revolution, and healthcare + biopharma should be no exception.  The Xavier University AI Summit is a great event that brings together a range of relevant stakeholders with common focus on artificial intelligence (AI). Together we address the challenges of AI, share initiatives and success stories, and ultimately get a pulse check on where the pharmaceutical and medical device industries are regarding the use of AI.

  • As a first take, this year’s attendee list included the expected top healthcare companies in addition to leading technology companies, like AWS.  The engagement of these tech companies coming from outside of the healthcare industry is a true testament to the major paradigm shift the industry is going through nowadays.  From FDA presentations on the exploration of the power of AI to fireside chats on discovery and innovation, there was an underlying message throughout the summit – the industry needs the pharma 4.0 technologies.  To those who may not have a clear understanding of what we mean by pharma 4.0, check out our blog post where we bring more color to the new wave of disruptive technologies.
  • Secondly, this summit’s focus was on AI and the benefits it can bring to an industry that is known to lack in innovative technologies due to strong regulation. The message was clear – it is almost irresponsible not to pursue the advantages offered by AI, to help deserving patients get better treatments and therapies.  AI is the combination of statistics, software, and computation to provide predictions, recommendations, classifications and patterns in a similar way than humans do. The benefits of AI are new and novel, from improving drug discovery to manufacturing drugs faster to reducing drug development costs.  On average, 9/10 clinical drugs fail to make it trail costing companies around $1.2 billion to develop new drugs. Adoption to AI can elevate pressures from pharma companies, decreasing the amount of money spent on creating drugs and bringing them to market sooner.  There are countless benefits that other industries have experienced using digital technologies like AI and now it is time to establish the right procedures for our industry.
  • Lastly, there was a clear joined effort between pharmaceutical and medical device industries to establish a roadmap on how to implement AI into the health sector.  FDA regulators at the event also provided their strong support to achieve AI implementation to bring the power of AI to the benefit of patients. As we’ve shared previously, the FDA has continued to work towards understanding new digital technologies creating programs like the ETT program.  AI benefits are expanding in various other sectors with industry leaders of tomorrow adapting and embracing new technology which has proven to be as beneficial inside our society today. The path to apply the same outcome in pharmaceutical and the medical device industry only requires to include the same science applied to the processes and products that are being carried in companies today.

As we look to the future of the pharmaceutical and medical device, the power of AI will shape the future of our industry.  Thanks in no small part to the initiatives from the AI Xavier Health University!

July 7, 2019

Bigfinite and NNE Partnership

San Francisco, California, July 9, 2019 — Bigfinite and NNE announced a strategic partner program agreement to collaborate around accelerating digital transformation within manufacturing operations at the world’s leading pharmaceutical and biotech manufacturers.

This collaborative effort is based on Bigfinite’s SaaS platform leveraging Industry 4.0 technologies like artificial intelligence (AI) and machine learning to improve manufacturing operations combined with NNE’s unique pharma domain expertise.  The Bigfinite platform will be able to successfully monitor and optimize NNE’s customer’s operations, identifying and eliminating the root causes of operational issues, enhancing operating performance – all while ensuring GxP compliance and inherent data integrity.  Members from both organizations will work side-by-side to combine NNE’s strong knowledge in pharma operation, automation, and regulations with Bigfinite’s big data, industry, and advanced technological experience.

Pep, CEO of Bigfinite, said, “Partnering with NNE is a tremendous opportunity to accelerate the deployment of our platform and make ‘Pharma 4.0’ a reality.”

While several of these digital technologies have been available for some time, the Pharmaceutical industry has moved slowly and cautiously into the digital world due to heavy regulations.  But as the pressure to reduce cost, raise quality, and the demand for personalized medicine increases, companies must evolve to changing requirements to stay ahead.

Pharma manufacturers in the US alone wastes $50 billion each year and 70% of manufacturing data is never used.  This partnership will help improve those statistics – empowering pharma companies to see their fullest potential with the use of the Bigfinite platform and NNE’s expertise.

According to Mogens Larsson, Vice President (VP), Automation & IT of NNE, “We are excited to partner with Bigfinite Inc., a joined effort to bring market-leading technology that is purpose-built for the industry to our customers, for real and impactful improvements on how to create value from manufacturing and GxP data.”

About NNE: NNE is an international company specialised in pharma engineering. We help pharmaceutical companies bring products to market by providing flexible, compliant and future-proof solutions. We have close to 1,000 professionals delivering global knowledge and best practices, all dedicated to supporting our customers globally and on local sites.

About Bigfinite Inc.: Bigfinite is a cloud-based SaaS platform for the Life Sciences Industry that transforms manufacturing operations with the use of advanced analytics, artificial intelligence, and IoT technologies.  Founded in 2014 by a veteran team that possesses over 30 years of expertise in Pharma and IT, Bigfinite offers an intuitive way to gain process and operational intelligence so you can improve manufacturing operations in a GxP compliant manner.  Our mission is to advance manufacturing operations so pharma and biotech companies can provide patients with the right medicine, at the right time, and at the right price.

June 25, 2019

Where are Pharma Companies in the Age of Artificial Intelligence?

They say good things come to those who wait; we say good things come to those who wait but only the things left by the visionaries before them.  The pharmaceutical industry has long been known to lag in the adoption of new technology due to strong regulations. Even though regulators have recently begun to open up to several new ‘big data’ or pharma 4.0 technologies – the question remains, if pharma companies are doing the same?  In 2016, the European Pharmacopoeia 9.0 in Chapter 5.21announced that neural networks (NN) and support vector machines (SVM) are valid chemometric techniques for processing analytical data sets.  This is a very encouraging announcement from regulators because finally, they are providing guidance for the use of chemometrics (the science of extracting information from chemical systems by data-driven means).  This alone should empower skeptics to start exploring the magnitude of advantages these techniques can provide due to the dramatic advances of new technologies.

In the past, artificial intelligence (AI) was a subject mostly reserved for academics and researchers but with time, industries have evolved and have grown interested in these technologies.  With the democratization of technology, some topics like AI, machine learning (ML), and cloud platforms have become more of a ‘hype topic’ a trendy concept resulting in a lot of people talking about something but only a few actually understanding and implementing it correctly.  Nowadays, AI can be found everywhere – in beer commercials and even commercials for golf clubs.  Did you ever think beer companies would have commercials promoting their use of AI to make their product better?  Beyond these “hype topics”, there is a lack of understanding of these technologies and as a result, there are a lot of people hesitant to use it.  They see AI as a ‘black box’ which stems from the fact that it is extremely complex and not always understood, just like most of us do not understand how our iPhone’s are made or how they work (from a technical standpoint).  However, this misunderstanding, or more precisely the lack of it, does not help in highly regulated environments where everything has to be accounted for, it just adds more fear of regulatory exposure.

After the announcement by the European Pharmacopoeia and the increasingly relevant need to start improving efficiency in the pharma industry, there are no more scientific excuses for not embracing  AI/ML technology. People need to change their mindset and start on a practical approach to incorporate these powerful AI tools and the compelling benefit they represent. And maybe a key for this change in mindset is just a matter of understanding the capabilities of these technologies better and how they work to ultimately be able to verify AI models in agreement with regulators.

A few examples are neural networks and support vector machines.  At first, it seems difficult to track data and understand how it predicts or classifies, but after the pharmacopoeia’s validation, companies should be investing in understanding it better and establishing methodologies to verify AI models. Using these techniques, and the power of cloud computing, we are essentially trading off ‘interpretability’ for increased precision in predictive analytical models.  We believe learning how to verify AI models is the key to solving the ‘chicken vs. egg’ argument – in the cross point between regulators, industry, and vendors. It’s the key nexus point where regulators meet industry and vendors, to get past the chicken vs. egg.

How to verify AI models

The basics of verifying AI models is to prepare a set of experiments with ‘training data’ and ‘verification data’ and keep the data acquisition and the AI model under control at all times or document compliant conditions.

Preparing a design-of-experiment to verify AI models may require huge computational power but running them could require less.  Currently, Bigfinite is working on a scientific paper with procedures to verify AI models.

That flexibility on computational power demand is better managed with cloud server-less technology (or on-demand computing). That it is technically feasible and already used in other industries, the challenge for the pharma industry is to ensure compliance during the whole process.

Connecting the dots

Today, two out of three points are connected, to advance the realization of benefits from state-of-the-art technologies in pharma and biotech:

  • Official regulatory support (European Pharmacopoeia) for use of AI models as valid chemometric techniques for processing analytical data sets
  • Modern, scalable technology to ensure data integrity in cloud
  • people’s mindset, of what is possible today, and how to get started

The last point is a broader topic in itself and warrants an extensive separate post – so stay tuned. At Bigfinite, we work with curious and courageous market leaders who are not satisfied with following in the steps of others. Contact us today, if you are also curious to learn more and innovate your path forward.