search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
Company insight


A GxP data fabric: the foundation of AI in pharma manufacturing


Everyone recognises the value of artificial intelligence (AI) but the ‘intelligence’ that can be derived is only as good as the data foundation, and the journey to implementation can be harrowing. Andy Alasso, senior vice-president of product management at Aizon, explains how enterprises can transform manufacturing from the foundational elements of process data to a GxP data fabric to an industrialised AI platform.


How far has the pharmaceutical industry progressed in its adoption of AI in manufacturing? Andy Alasso: Primarily due to regulatory considerations, the pharma industry has traditionally been slow to adopt new technology. However, recently with an increased demand for manufacturing capacity and efficiency, many pharma companies are investing in technology adoption and taking advantage of many technological advances like IIOT, cloud computing and AI.


While these technologies offer great promise, adoption requires a foundational approach to data integrity and GxP compliance. Ultimately, what manufacturers need to get to is to have real-time data available in a compliant manner, qualified algorithms and validated models to detect and predict outcomes.


Has Covid-19 had an impact on the speed of that adoption? Covid has absolutely accelerated the digitalisation and AI adoption by the biopharma industry. The need to manufacture and deliver billions of product doses to many sites, geographically distributed around the globe, while many folks work remotely, has demanded many improvements in technology. Now is the time to harness the analytical power to increase efficiency and expediency while reducing risk. The regulatory bodies have often been cited as one hindrance to progress; however, these organisations are now encouraging the use of advanced


technologies to help speed manufacturing and improve the quality of drug products. This global challenge is a great opportunity to drive this change.


What are some of the challenges that pharma companies face when looking to implement AI? The first important challenge is understanding the data. There must be an appreciation for data management, quality, volume, source, structure, accuracy and accessibility. Sometimes the hardest part of using AI is aggregating (or wrangling) the data necessary to feed the models.


batch quality and yield efficiency. This is why Aizon exists. We meet manufacturers where they are in their digital maturity and help them work from the early stages of building a data fabric through the industrialisation of AI across their organisations.


Can you share with us some of the use cases for GxP AI that have shown an ROI? One example is from a top plasma company, where Aizon engineers used raw material source analysis to identify clusters that had higher likelihood to produce filter clogging and low harvest yields. AI was


“Ultimately, what manufacturers need to get to is to have real-time data available in a compliant manner, qualified algorithms and validated models to detect and predict outcomes.”


The first operational challenge is the ability to gather the data from the different systems and have it ready to apply these technologies. Different manufacturing sites have different systems, different formats, different environments. The ability to create a GxP-compliant data fabric allowing for real-time data ingestions is an important first step.


The second challenge is then to qualify and scale AI in a compliant manner across the organisation. It is one thing to crunch data with a Python script, but it’s a whole different story to have validated models to make real-time decisions that can affect


World Pharmaceutical Frontiers / www.worldpharmaceuticals.net


used to identify which parameters to optimise in the extraction processes depending on the characteristics of the supply. As a result, it has seen an over 4% increase of process performance. Another example is a leading biotech manufacturing monoclonal antibodies for oncology with an already impressive and highly optimised yield. Using AI to analyse years of historical batch data, the company discovered a correlation that helped it further optimise, resulting in huge expense savings. ●


www.aizon.ai 41


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65