Life Sciences

From Pharmaceuticals to Medical Devices to Diagnostics, Mareana solves the toughest data challenges in Life Sciences. We help some of the largest global companies speed project delivery, reduce regulatory complexity and improve product development cycle time.

pharma batch.jpeg

Continued Process Verification (qSync)

qSync™ is an AI and machine learning software that digitizes end-to-end paper batch records for Continued Process Verification (CPV) without changing your existing qualified process...and without making expensive and risky system changes.

Mareana combines handwriting recognition, AI text analytics, a flexible, repeatable query engine, and a deep understanding of CPV and associated processes and technology to digitize your process and allow your team to focus on value-added analytics, not data wrangling.


Veeva Vault Document Migration (qSync)

Mareana qSync™ automates metadata enrichment for all document types across multiple systems. Eliminating the need for manual visual document inspection or data entry, qSync™ proposes a metadata taxonomy and enrichment values that subject matter experts or users verify and approve. qSync™ eliminates months of tedious manual data enrichment and can accelerate data document migration by up to 90%

pile of shit.jpg

Improve Visibility of Regulatory Data (qFind)

The increasing scope, complexity, and integration needs of Global Regulatory requirements (MDSAP, for example) are placing new demands on Regulatory leaders and organizations. Regulatory data has always been highly complex and processes and systems are straining under these new demands. Yet the Digital Transformation occurring in other areas has been relatively slow to take hold in Regulatory. Companies that are able to initiate and advance Regulatory Data Digital Strategies will enjoy significant advantages not only in compliance, but also in efficiency and growth.


Clinical Supply Optimization (qSync)

Mareana’s qSync™ solution helps clinical study supply professionals manage Investigational Product (IP) kit supply and logistics across multiple studies with numerous CRO’s even when IRT systems or other data sources (like excel, pdf) are not integrated.  Study supply professionals can now ensure that patients are provided the right dosage and strength at the right time.

Dilithium Crystal Schematic.jpeg

Unstructured Data Migration for PLM (qFind)

Mareana assists companies with complex Product Lifecycle Management (PLM) data migration by expeditiously digitizing data from structured and unstructured sources such as bill of materials (BOM), regulated ingredient lists, regulated labels, engineering drawings, analytical test standards, and printed sales and marketing materials. Companies experience faster innovation time via improved product portfolio management, data governance, and product lifecycle costing.


Discard Reduction (qSci)

Mareana qSci helped a global Pharma manufacturer improve its P&L by over $30MM year by reducing the incidence of product requiring discard near their expiry data. Across a complex global supply chain with complex transactional buy/sell relationships among regions, API and fill/finish plants, we used machine learning, and industrial-scale mathematical modeling to identify, quantify, and remediate key factors driving the discards. qSci excels in aggregating and virtualizing millions of data points and transaction lines from ERP, MES, LIMS and other systems to pinpoint—at the product level—the hidden variables driving waste and discard. Transparent, intuitive data visualizations make it easy for finance and operations leaders to understand and fix the root causes.

waste reduction.jpg


Expiry management is a challenge in all industries, but if you have shelf life limits to components as pharmaceutical companies do, the complexity and urgency escalate. With an increasingly complex supply chain, a global pharmaceutical giant was mystified by a sizable number of product discards, even with a mature procurement and planning process.

Mareana used qSci to analyze the problem and quantify the root causes. Machine learning and multiple simultaneous mathematical modeling revealed the key factors in materials and batches that drove component discards. After addressing factors like batch sizes, delivery windows, and lead times specific to each individual component and plant, this client has saved $30MM/year in reduced product discards.