Who We Are
Investor RelationsNews

Applying automation effectively on pharmacovigilance ICSR processing​

Pharmacovigilance (PV) organizations today are facing intense pressure to modernize themselves and become more efficient; the reasons being increasing patient data volumes, multiple data sources, dynamic global regulations, and the need to monitor and track geography-based nuances at a global level. The pressure to make drugs and therapies available to patients in a faster manner has led to fast- track approvals of multiple lifesaving drugs. Faster product approvals have led to limited exposure of drug therapies to clinical trials, making it more crucial for PV programs to continuously monitor Adverse Events (AEs) post approval and observe drug safety profiles for a prolonged period on a broader patient population to assess the risks, along with the effectiveness of medications.1
Enhancing efficiencies in PV can be expedited with automation and by streamlining the case handling process. Although the management of patient safety is crucial, companies tend to allocate budgets toward staff-based traditional data processing rather than exploring opportunities in digital, automation, analytics, and artificial intelligence.
To introduce automation and accelerate this change, PV organizations need to establish benchmarks on case processing efforts to identify bottlenecks and areas of opportunity where automation could deliver value. Once the relevant PV steps are identified and mapped, it is easier to measure effort and impact, and therefore identify specific points in the value chain that can benefit most from technology. Various technology approaches such as conversion to digital, automation of business processes, and analytical insights for decision-making can improve case processing.
Figure 1: Value creation and change readiness

Technology-based ICSR processing is a good starting point for PV modernization

With Individual Case Safety Report (ICSR) automation, the process of handling AEs is highly structured and value stream mapping is easier to perform as it is a high-volume activity. Moreover, the challenges in PV compliance faced by organizations with ICSR processing:
The increasing number of products under development and in the market has resulted in a spike in the number of reported AEs
The increasing public and media awareness plus patient-centric focus has increased the challenges of tracing reportable AEs. The sources of AEs have now expanded to journals, articles, social media, and non-standardized data sources
The increasing regulatory requirements on ICSRs, around global marketing authorization, have resulted in high costs of PV operations in pharmaceutical companies
Case management requires diligence in data point review, medical assessment, coding, and relevant reconciliation. Many products with multiple labels require correct referencing of labels, which is a time-consuming effort
The monitoring and maintenance of patients under the Expanded Access Programs/Compassionate Use Programs with relevant labels and post-approval labels increase the complexity in PV monitoring

Digital, analytics, and AI technologies can be applied across multiple points in the ICSR life cycle

Thousands of AEs are processed every month either by ICSR processing teams at pharmaceutical companies, or by their outsourcing partners. This involves case intake, triage, booking, data entry, quality review, and medical review of ICSRs in the safety database. Some of these cases are reported to regulatory authorities on an expedited basis by submission teams. Most pharmaceuticals and medical devices organizations spend an overwhelming part of their PV budgets on this task. Naturally, driving costs out of case processing is often the primary goal for leaders in the life sciences industry. Automation can take advantage of scale and generate cost savings per ICSR. This includes native automation and standalone technologies that reduce the manual effort required to carry out duplicate checks, speed up coding functions, and streamline case writing.
While technology alone cannot perform the complete activities of ICSR case management, there are specific steps in this high volume and rapid throughput activity that can be accelerated using technology. Technology enables PV organizations to effectively complete ICSR processing, and generate consistent and complete cases that are correctly classified for signal detection.

Testing cycles can be accelerated with automation

Automation in PV testing cycles brings forth a significant opportunity to formulate faster hypothesis. A 2018 pilot study conducted by the American Society for Clinical Pharmacology and Therapeutics (ASCPT)2 takes cognizance of the same. The said study tested the feasibility of using Robotic Process Automation and Artificial Intelligence (AI), among other new-age technologies, to automate the processing of AE reports. Solutions proposed by 3 commercial vendors participating in this pilot study were simultaneously tallied against Pfizer. The outcomes confirmed that AI-enabled automotive tools expedite the deduction of AEs from source documents.
Further advancement of technology in this domain, including leveraging Natural Language Processing (NLP) technology, Big Data Analytics, and data extracted from social media, could pave the way for complete migration of manually-intensive methods of source document annotation, which could effectively be replaced by total reliance on data fields of safety databases. While the benefits of such an overhaul can only be studied in the long term, it has been accepted universally by PV professionals that the ability to differentiate between vendor capabilities and identify the best candidate in a testing cycle for the discovery phase analysis is an assured benefit of process automation.
AI methods such as NLP, Machine Learning (ML), and Neural Networks have proven to improve the current workflow and provide support in the medical judgment and decision-making process.
Following are some of the categories where automation technologies can be applied in ICSR processing:
Ingestion of structured and unstructured content Early introduction of technology to convert case information into a structured and digital format can eliminate the cumbersome task of case data relevance and data capture. Before data entry, cases need to be verified for validity and routed appropriately. A technology-driven approach to convert a case to digital includes reading incoming case intake information in the form of text, images, and text embedded in forms/tables from XML, Docx, and PDF files. Optical Character Recognition (OCR) can be used to extract relevant information from the files. Medical ontology-enabled NLP/ML maps relevant ICSR information to International Conference on Harmonisation (ICH) E2B data fields in a regulatory compliant manner, therefore eliminating a large portion of data capture efforts.
Case management and processing With 40% to 80% of allocated PV budgets spent on case processing and case volumes growing at a rate of 10% to 15% per year, driving costs out of case processing is the primary goal of 90% of the ASCPT survey respondents.2 Low-cost leaders are outsourcing, taking advantage of scale, and moving aggressively to automate case processing. Gaining cost control over this process while maintaining compliance and enhancing patient safety is entirely dependent on companies' ability to automate most of these activities.

Figure 2: PV automation focus areas (Data source: Deloitte survey)

Reducing the cost burden through simplification

%90 Average case cost
90% Focused on reducing case processing cost through automation
~35% Expected cost reduction due to automation
>80% Utilization of managed services for case processing

Investing in signaling

>70% Identified maturity gap in signal processing
>90% Focused on expanding capabilities in product benefit and risk management
100% Investing in advanced visualization technologies
The highest impact opportunities in case processing come from effective triaging, duplicate checking, data entry, medical assessment, medical coding, narrative creation, and in-line quality control (QC) activities. Case content can be ingested and structured using OCR and NLP, following which business rules and AI classifiers can help identify correct case types for triaging to corresponding functions. More complex algorithms can additionally determine the case type, ensure data handling, identify duplication, route cases for additional information required, and also create follow-up mechanisms till resolution.
The inclusion of AI to automatically identify case type from a highly structured and known case profile can reduce manual review efforts and streamline the medical review process. AE case processing can be made more efficient for common low-risk cases by creating profiles of highly common non-serious and on-label case types. Approaches to automate narrative creation, ability to determine the listing of an AE against labels, medical coding, and detection of discrepant data through complex algorithms and business rules can reduce medical review efforts effectively. Lastly, ML can be applied to determine the machine generated confidence in classification to ensure intervention when necessary. Periodically using this confidence data as training sets helps the AI algorithms to achieve 100% confidence ultimately eliminating the overall requirement for QC.
Signal detection Most pharmaceutical companies continue to use traditional signal detection and investigation methods (e.g., medical assessment of individual spontaneous reports of AEs, interventional clinical trials, and database mining), a few are leveraging real-world evidence, and almost none are progressing using social media channels. This is consistent with current PV system capabilities. As pharma companies continue to drive toward true safety management, short-term signalling investments are likely to focus on visualization and long-term efforts on data integration tools and process investments. Using safety information to feed knowledge back into the discovery process in real-time remains a gap due to limitations with existing signal detection and management systems. The additional opportunity to make use of real-time signal intelligence integrate into the case processing information that can prompt detailed review on specific case types also remains an opportunity where AI can play an effective role. The ultimate goal is predictive signalling that applies knowledge of existing signals to strengthen the ICSR process to flag case types that need further investigations for signal management.
Decision-making Sometimes, the quality of information available in ICSR is poor. In such scenarios, semi-supervised or unsupervised learning plays a major role in devising hypotheses. For example, while building unlisted events and drugs correlation, and causality classifiers, specific types of Neural Networks are built and improvised with training over a period of time to enhance the medical assessment of specific patient data parameters, lab analytes, AEs, and corresponding medications. In some cases, technology can pull insights from precedent information that allows decisions on the case based on relevant reference information. This AI-based predictive capability provides reference precedent data for the relevant ICSR presented, enabling teams to evaluate the case and determine if it classifies as a known corresponding signal or as a potentially new signal.

Few enablers are crucial for a successful AI implementation on ICSR processing

Build a model with a high degree of configurability and adaptability to different data source formats, in order to reduce the incremental system validation efforts for each change. The accuracy of resulting automation needs to achieve acceptable limits, so that safety teams basing their judgment on automatically sourced and populated information do not have to duplicate the activity, rendering automation useless.
While adopting the ML model, ensure an awareness of the man versus machine responsibilities in case processing post automation. Preparing the organization and respective teams with a structured deployment approach across specific steps in the ICSR process can ensure faster adoption and adaptation to new ways of working with high confidence.
Create an intuitive user interface that demonstrates the AI fields and is easy to customize, to ensure the ability to readily stay on top of changes over time.

Benefits of Automation in Pharmacovigilance ICSR Processing

Most organizations venture into technology endeavors in PV to ensure they are effectively able to scale over time. AI can continue to provide multiple benefits. Some of these include:

Figure 3: Benefits of automation in PV

Enhanced data quality and accuracy with standardized inputs for automated case processing
Improved productivity with minimized time and effort on low-value data entry and manual process steps
Reduced cycle time enabling faster case intake and processing through automation
An expedited path to the market with no compromise on patient safety
Scalability and future readiness with the ability to handle case volume growth and diverse types of incoming data formats effectively
Better compliance with improved accuracy and consistency of AE reporting
Positive return on investment with tangible cost reduction with investments in technology that augments existing processes and tools

Automation in PV will be an incremental process, though with change comes growth

The end goal for AI and ML in PV will occur when automation and analytics enable complete case identification and classification using relevant reference intelligence to properly classify the case and route it for further medical review. The opportunity for case segmentation, routing, alignment to existing labels, data capture, processing, and advanced insights from known signals can streamline the process, accelerate decision-making, improve compliance toward patient care, and increase the focus on medical relevance of cases for the pharma company. Applying technology to relevant high-impact processes can allow for early adoption of technology, improved efficiencies, and higher value realization from the automation for pharma enterprises.


Benefit risk balance for Marketed drugs: evaluating safety signals. No. 762.2. Report of CIOMS Working Group IV. Geneva: CIOMS. Council for International Organisations of Medical Sciences; 1998
Schmider J, Kumar K, LaForest C, Swankoski B, Naim K, Caubel PM. Innovation in Pharmacovigilance: Use of Artificial Intelligence in Adverse Event Case Processing. ResearchGate; 2018
Murali K, Kaur S, Prakash A, Medhi B. AI in pharmacovigilance – re-imagining the ICSR processing. Pharmafield. Last accessed date 02 January 2022
Dorota Owczarek. Augmenting drug safety and pharmacovigilance services with artificial intelligence (AI). nexocode. Last accessed date 02 January 2022
Nicole G. What is pharmacovigilance. Technology Networks. Last accessed date 02 January 2022
Ghosh R, Kempf D, Pufko A, et al. Automation opportunities in pharmacovigilance: an industry survey. Springer Link. Last accessed date 02 January 2022


Vladimir Penkrat
Vladimir Penkrat
Dr. Shubha Rao
Dr. Shubha Rao
Naveen Kumar Pawar
Naveen Kumar Pawar
Imran Khan
Imran Khan

Insights to build #FutureReadyHealthcare