From Cost Savings to Revenue Boosts: Why Cloud Migration is Critical for Modern Clinical Trials

In a recent analysis from Ken Getz (See page 12 in June 2024 Applied Clinical Trials), it was indicated that a day saved in a clinical trial is worth $0,5 million per day in additional sales. While this figure is lower than the original $0,8 million per day estimate, it still presents a compelling case. When combined with the daily cost savings of running a clinical study (from $7K/day for a phase 1 to $55K/day for a phase 3) and the efficiency gains from new technologies (from 50% to 80% of data managers time), there's a strong business argument for pharmaceutical companies to migrate their Clinical Data Management Systems (CDMS) and Statistical Compute Environment to the cloud, considering that datamanagrement and BioStat represents 20% to 30% of a clinical study cost. This shift, along with investments in solutions to improve site and patient identification and recruitment, is crucial. Add to this the ongoing focus from Pharmaceutical companies on study optimization and clinical trial simulation, and you have the key ingredients driving the latest news in clinical development.

The Move to Cloud

According to an analysis for the Hackett Group, adopting cloud solutions in clinical development offers significant benefits, including a 19% reduction in time spent qualifying and initiating trial sites, and a 20% decrease in time spent analyzing post-trial data. Additionally, cloud migration enhances the use of AI and machine learning by 83%, leading to more efficient and accurate trial processes, ultimately accelerating time to market for new therapies Life sciences firms are increasingly adopting digital technologies like decentralized clinical trials, telemedicine and AI to enhance remote patient interactions, streamline research, and improve data analysis, as highlighted in the ISG Provider Lens? report. These innovations are driving a shift towards more patient-centric and efficient clinical trials, despite ongoing challenges related to data privacy, security, and regulatory compliance.

AI-Driven Protocol Optimization: Enhancing Success Rates and Accelerating Drug Development

Pharmaceutical companies are increasingly investing in protocol optimization as a strategic approach to enhance the Probability of Success (PoS) and streamline the duration and cost of clinical trials. With the average success rate for phase 3 trials standing at around 57.8%, optimizing protocols has never been more crucial. This optimization is achieved through a combination of leveraging historical trial data, conducting what-if scenario planning, and utilizing clinical trial simulations to refine trial design and execution.

Clinical trial simulations have emerged as a powerful tool in improving trial outcomes, and QuantHealth, a leading AI-focused clinical trial design company based in Tel Aviv, is at the forefront of this innovation. With its cutting-edge technology QuantHealth’s AI simulates 100+ clinical trials with 85% accuracy. Their proprietary AI-based Clinical-Simulator integrates over a trillion data points, encompassing clinical and pharmacological information from 350 million patients and more than 700,000 drug entities. For example, in collaboration with AstraZeneca's respiratory disease team, QuantHealth’s simulation technology led to cost reductions exceeding $215 million and significantly improved the likelihood of trial success. Their system simulated over 5,000 protocol variations in minutes, identifying the most promising trial designs which contributed to a reduction in study duration by 11 months and a savings of $200 million.

In addition to QuantHealth's contributions, Insilico Medicine has also made notable advancements in the field of clinical trial optimization. Using their AI platform, inClinico, Insilico Medicine has successfully predicted the outcomes of phase 2 and phase 3 clinical trials with impressive accuracy. Their AI-driven approach focuses on forecasting patient responses to new treatments, thereby optimizing trial design and reducing the risk of failure.

Several companies are using AI to optimize clinical trials such as unlearn.ai (digital twins), trials.ai, Atomwise(predicting trial performance by analyzing molecular structures).

The combination of those technologies will not only enhance the reliability of trial outcomes but also accelerates the drug development process by improving the overall efficiency of bringing new treatments to market.

Revolutionizing Patient Recruitment: How AI and Innovative Platforms are Streamlining Clinical Trials

The life science industry has a general problem of patient recruitment and of matching patients to suitable clinical trials, often due to complex, time-consuming processes and limited access to trial information. Estimates?suggest that over?80%?of clinical trials fail to meet their initial enrollment timelines, and AI can certainly be of help in overcoming the major issues in patient recruitment such as: overestimated eligible population by Pharma, insufficient patient awareness and education, logistical barriers, participant burden and retention, and competition for patients. The concept that describes the gradual attrition of participants from initial screening to trial completion is termed the recruitment funnel:

There are many ways to tackle this problem, and here are some recent examples of announcements:

• UK-based health tech startup has developed Clinical Net, an online platform that streamlines the process of matching and connecting patients to appropriate clinical trials by centralizing and simplifying access to trial information. The platform leverages advanced AI tools to provide both clinicians and patients with easy-to-understand eligibility criteria, enabling quick referrals and direct connections to trial sites, which is especially beneficial for rare cancers and improving recruitment efficiency.
• Walgreens' decentralized model, supported by a $100 million partnership with the U.S. Biomedical Advanced Research and Development Authority (BARDA), enhances patient recruitment by making clinical trials more accessible and representative of the diverse U.S. population. By leveraging its extensive network of community pharmacies and a secure clinical trial platform, Walgreens addresses barriers to participation, reaching over five million patients since 2022 and consistently meeting recruitment targets, including surpassing national averages for diversity. This approach integrates clinical research into patients' everyday healthcare experiences, thus improving recruitment rates and ensuring trials are more inclusive.
• Another way to accelerate clinical trial timelines and enhance patient recruitment across diverse demographics is by leveraging a global site partnership network - a system of strategically aligned research sites across regions such as Australia, Asia, Europe, and the United States that collaborate to streamline clinical trial processes. Avance Clinicalexemplifies the effectiveness of such a network. With its extensive global reach, proven success in accelerating patient recruitment and ensuring high-quality data, it has become a trusted partner for biotech companies seeking efficient and reliable clinical trial solutions.

There is no doubt that many new solutions will be created in this space. AI can help define eligible sites and patients for clinical studies by analyzing the vast amount of existing data.

Clinical Data Management Systems

The clinical trial landscape is increasingly burdened by a fragmented patchwork of systems, leaving data managers scrambling to integrate and standardize a growing flood of data points. However, I’ve seen companies leveraging novel advanced cloud solutions for data management and review, boost efficiency by more than 50%. This innovation allows big pharma to manage many more clinical studies without the need to increase resources. Amidst this shift, as the industry pushes toward greater automation and consolidation data, managers are taking on more specialized roles, making early involvement in protocol design crucial.

As the clinical trial data management market is moving to cloud with SaaS platforms breaking the mold for clinical trials, Medidata Unveils AI-Powered Clinical Data Studio to Enhance Clinical Trial. With the Clinical Studio solution launched at the end of 2023, Medidata joins the club of existing solutions which includes elluminate from eClinical, Saama and EDETEK to enhance clinical trial data management. Medidata's Clinical Data Studio leverages AI to enhance clinical trials by improving data quality and speeding up decision-making. Eisai Inc, the US pharmaceutical subsidiary of Tokyo-based Eisai Co, is one of the first customers to leverage Medidata Clinical Data Studio. Eisai Inc. aims to leverage this innovative data experience to gain control over its clinical data, enable the execution of scalable and complex clinical trials, and enhance patient experience.

Harnessing Generative AI in Clinical Development: Transforming Trial Efficiency and Quality Management

Generative AI (GenAI) is more and more used in clinical development and can significantly enhance clinical trials by improving patient cohort selection, personalizing engagement, streamlining data gathering, and accelerating document creation. It can help optimize trial designs, enhance patient eligibility criteria, and improve recruitment and engagement through personalized content. Additionally, GenAI can automate knowledge processing and document preparation, reducing time and cost. However, challenges include ensuring accuracy, maintaining data privacy, and demonstrating ROI. Despite these concerns, with proper implementation and oversight, GenAI can boost the efficiency and effectiveness of many clinical trial processes. Generative AI is also transforming quality management (QM) and regulatory affairs (RA) by creating new content and automating tasks. It enhances efficiency, compliance, and productivity, helping organizations manage increasing data and regulatory demands. Key benefits include faster content generation, improved training, and better quality control. Generative AI reduces costs and time to market, allowing human experts to focus on critical decisions. Effective implementation requires balancing AI capabilities with data security and financial considerations. The IQVIA blog highlights several specific ways generative AI can improve Quality Management (QM):

Generative AI is also used in clinical development for synthetic data generation. As an example, this paper introduces Persona Hub, a collection of 1 billion diverse personas for AI-driven synthetic data creation. It enables scalable, diverse data synthesis across various domains, potentially shifting the paradigm of AI data creation. The approach promises to improve AI capabilities by eliminating data bottlenecks, facilitate reality simulation for policy testing, and more. The methodology adapts to different scenarios and shows significant performance improvements in tasks such as math reasoning. While promising for advancing AI development, it also raises ethical concerns about data security and misinformation risks.

Additional References:

• Stephen Pyke, chief clinical data and digital officer, Parexel, discusses how AI can be used in clinical trials to streamline operational processes, the importance of collaboration and data sharing in advancing the use of technology, and more.

Upcoming 2024 Conferences

• 82nd FIP World Congress for Pharmacy and Pharmaceutical Sciences, Cape Town September 1st-4th
• BiotechX USA 2024, Philadelphia, PA, September 10-11, 2024
• Intelligent Health AI, Basel, Switzerland, September 11-12, 2024
• BiotechX Europe 2024, Basel, Switzerland, October 9-10, 2024
• Med Tech World, MALTA, November 6th, 8th, 2024
• 6th GCC eHealth Workforce Development Conference, Dubai, November 6th-7th, 2024
• DigiHealthDay 2024, Pfarrkirchen, Germany, November 11th-15th, 2024
• GIANT Health 2024 , London, December 9th-10th, 2024

Other Informational Newsletters on Healthcare and AI

Stay up-to-date with the latest insights and industry trends by subscribing to these informative newsletters from my esteemed colleagues and professionals in the field:

• Healthcare in the Metaverse by Philippe GERWILL
• DigitalhealthReadingList by Wolfgang Schleifer
• Future Tech Trends by Bernard Marr
• All about Blockchain Adoption by Kamlesh Nagware
• AI Frontier by Steve Nouri
• The Atlas by Generative AI
• Last Month in Digital health by Gary Monk

AI Basics

DataCamp:?AI for Beginners

Google’s?AI Video Course

Matt Turck:?The AI/ML Landscape

MIT:?AI Basics

Nvidia: Jensen Huang on AI

SimpliLearn:?AI Bootcamp

WSJ:?AI Predictions and Future of Humanity