Successful Digital Interventions in Recent Clinical Trials
Mahesh possesses 33+ years of global experience in the pharmaceutical and biotechnology industries, encompassing drug discovery and development, contract research, and manufacturing organizations. He possesses deep expertise in various key operational areas, including clinical and commercial operations, quality assurance, regulatory compliance, process development, project management, operational excellence, and capital projects.
Before joining Veeda as Group CEO, Mahesh held senior leadership positions at notable companies such as Syngene International (part of the Biocon Group), Sanofi, and Biological E Limited. He also spent over 20 years in the United States, where he completed his PhD and worked with multinational pharmaceutical giants like Amgen and Monsanto. Mahesh earned his doctorate in Medicinal Chemistry from the University of Utah.
In an exclusive interview with Mandvi Singh, Managing Editor, siliconindia, Dr. Mahesh Bhalgat, Group CEO & Managing Director, Veeda Lifesciences, shared his insights on ‘Successful Digital Interventions in Recent Clinical Trials’.
In recent years, the integration of digital technologies has revolutionized the landscape of clinical trials. These advancements have not only streamlined the process but also enhanced the accuracy, inclusivity, and overall efficiency of trials. The use of technology-oriented solutions that aim to improve health include a wide range of tools, including mobile health applications, telemedicine, portable devices, and clinically integrated platforms that take advantage of electronic health files. There have been some very critical and most successful digital interventions in recent clinical trials that have significantly impacted and boosted potential for future research.
The use of technology and digital tools is one of the most significant advancements in digital clinical trials is the use of wearable technologies and remote sensors. These devices have transformed data collection by providing continuous, real-time monitoring of participants' health metrics that measure a range of parameters, including heart rate, respiratory rate, and physical activity levels. The use of this technology enables researchers to gather comprehensive data without requiring participants to visit clinical sites, thus increasing convenience and participation rates. In May 2024, the FDA approved the use of the Apple Watch’s as a heart monitoring tool in a cardiovascular study. This approval allows researchers to use the Apple Watch to detect arrhythmias and monitor participants' AFib burden, providing a non-invasive way to evaluate the effectiveness of cardiac ablation devices. This landmark decision allowed historical heartbeat data to be used as a secondary endpoint in studies.
Amongst CROs, the adoption of technologies accelerated after the COVID-19 pandemic, where Artificial Intelligence (AI) and Machine Learning (ML) technology has played a pivotal role in enhancing the efficiency and accuracy of clinical trials. AI algorithms can analyse vast amounts of data quickly, identifying patterns and predicting outcomes with high precision. AI and ML are increasingly used in drug discovery, process optimization, and predictive maintenance.
Use of AI in clinical trials by Stanford University: In the area of personalized cancer care research, a clinical trial was conducted at the Stanford University to evaluate the effectiveness of AI in predicting treatment responses and personalizing cancer treatment plans. The trial included patients with various types of cancer, such as lung, breast, and prostate cancer. AI algorithms were used to analyse medical images (e.g., MRI, CT scans) and genomic data to identify tumour characteristics and predict treatment responses. The AI system collected and analysed data from medical images, pathology reports, and patient histories to create personalized treatment plans.
AI algorithms accurately identified tumour characteristics, such as size, shape, and growth patterns, from medical images. The AI system predicted treatment responses with high accuracy, helping oncologists tailor therapies to individual patients. AI-driven analysis enabled the creation of personalized treatment plans, improving the likelihood of successful outcomes. Patients receiving AI-guided treatments showed a higher response rate and longer progression-free survival compared to those receiving standard treatments. AI-driven data analysis accelerated the identification of potential drug candidates by analysing genomic and clinical data. The time required for drug development was significantly shortened, with AI identifying promising compounds faster than traditional methods.
CROs are increasingly using AI and digital technology tools that are beneficial not only in enhancing the planning, tracking, and management of clinical trials but provides a centralized platform for real-time tracking of trial progress, key milestones, and timelines, ensuring that clients including all stakeholders have access to critical information. The Clinical Trial Management System (CTMS) at Veeda Lifesciences streamlines site selection, onboarding, and performance monitoring, ensuring high-quality data and reliable trial outcomes. The CTMS facilitates efficient budget planning, grant management, and invoicing, reducing administrative burdens and ensuring timely payments. With comprehensive monitoring and reporting capabilities, the CTMS helps identify and mitigate risks early, improving overall trial efficiency. By integrating investigational product supply management and quality assurance audits, the CTMS ensures compliance with regulatory standards and enhances data integrity. Overall, the CTMS platform at Veeda Lifesciences leads to more efficient, accurate, and compliant clinical trials, ultimately benefiting clients with faster and more reliable research outcomes.
During the COVID 19 pandemic, the concept of decentralized clinical trials (DCTs) gained momentum wherein digital technology is extensively used to conduct trials remotely. Unlike traditional clinical trials, which require participants to visit centralized locations, DCTs enable various trial activities to occur at locations convenient for participants, such as their homes. This model utilizes telemedicine, mobile health technologies, electronic data capture (EDC), and other digital tools to facilitate remote participation, data collection, and monitoring.
One notable example of a successful decentralized clinical trial is the ADAPTABLE (Aspirin Dosing: A Patient-centric Trial Assessing Benefits and Long-term Effectiveness) study, conducted by the Duke Clinical Research Institute (DCRI), aimed to determine the optimal aspirin dosage for preventing heart attacks and strokes. The convenience of remote participation led to high retention rates and improved compliance with study protocols. Participants reported positive experiences, citing the convenience and reduced burden of travel. The use of digital tools streamlined trial operations, reducing costs and administrative workload and the decentralized approach minimized the environmental impact by reducing the need for travel and associated carbon emissions.
Additionally, the Electronic Data Capture (EDC) platforms used for conducting pharmaceutical research studies in CROs is an exceptional technology platform to enhance the efficiency of clinical trials by streamlining data collection, management, and analysis processes. At Veeda Lifesciences, the EDC platform enables real-time data access and monitoring, allowing for immediate identification of discrepancies and faster decision-making. The system has built-in validation checks that ensures high data integrity, reducing errors and improving the overall quality of trial data. By automating routine tasks and facilitating global collaboration, we believe in optimizing efficiency by minimizing manual intervention and accelerate trial timelines. Additionally, these digital platforms ensure compliance with regulatory standards, enhancing data security and reliability. Overall, the integration of EDC tools leads to more efficient, accurate, and cost-effective clinical trials, ultimately benefiting clients with faster and more reliable research outcomes. As the industry continues to embrace these innovations, DCTs and related digital tools are poised to play a crucial role in the future of clinical research.
As digital interventions become more prevalent in pharmaceutical research operations in CROs, it is essential to address the ethical and regulatory challenges they present. Ensuring data privacy and security is paramount, as is maintaining the scientific rigor of trials conducted outside traditional clinical settings. Researchers must also navigate the complexities of obtaining informed consent in a digital environment, ensuring that participants fully understand the nature and risks of the trial. Regulatory bodies are increasingly recognizing the importance of digital interventions and are developing guidelines to ensure their safe and effective use in clinical trials. The European Medicines Agency (EMA) has established guidelines to regulate the use of AI in drug development. Here are some key aspects:
AI Workplan 2023-2028: The EMA, along with the Heads of Medicines Agencies (HMAs), has published a workplan to guide the use of AI in medicines regulation until 2028. This plan aims to maximize the benefits of AI while managing associated risks.
Scientific Guidelines: The EMA provides scientific guidelines to help medicine developers prepare marketing authorization applications for human medicines. These guidelines cover the use of AI throughout the medicinal product lifecycle.
Reflection Paper on AI/ML: The EMA has adopted a reflection paper on the use of AI and machine learning (ML) in drug development. This paper outlines the considerations and best practices for integrating AI/ML technologies in the development process.
The rapid advancement of AI and ML technologies has revolutionized the healthcare industry, particularly in the development of Software as a Medical Device (SaMD). Recognizing the potential and challenges of these innovations, the USFDA has established a comprehensive framework to ensure the safety, effectiveness, and continuous improvement of AI/ML-based SaMD.
1. Total Product Lifecycle (TPLC) Approach: The FDA's framework adopts a Total Product Lifecycle (TPLC) approach, emphasizing continuous oversight throughout the entire lifecycle of AI/ML-based SaMD. This approach includes:
o Pre-Market Development: Ensuring that AI/ML algorithms are rigorously tested and validated before they are introduced to the market.
o Post-Market Performance Monitoring: Continuously evaluating the device's performance in real-world settings to ensure ongoing safety and effectiveness.
o Continuous Learning and Improvement: Allowing for the iterative improvement of AI/ML algorithms based on new data and insights.
2. Good Machine Learning Practices (GMLP): To support the development of safe and effective AI/ML-based SaMD, the FDA advocates for the adoption of GMLP, which include:
o Data Quality and Integrity: Ensuring that the data used to train and validate AI/ML algorithms is of high quality and representative of the intended patient population.
o Algorithm Transparency: Providing clear documentation of the algorithm's design, development, and validation processes.
o Robustness and Reliability: Demonstrating that the AI/ML algorithm performs consistently and reliably across different clinical settings.
3. Predetermined Change Control Plan (PCCP): This plan allows manufacturers to make certain modifications to AI/ML algorithms without requiring a new pre-market submission. The PCCP outlines:
o Types of Changes: Specifying the types of algorithm changes that can be made under the plan.
o Implementation Methods: Detailing the methods for implementing and validating these changes to ensure they do not compromise the device's safety and effectiveness.
4. Transparency and Real-World Performance Monitoring: is a cornerstone of the FDA's framework. The agency encourages manufacturers to provide clear and comprehensive information about their AI/ML-based SaMD, including:
o Clearly communicating what the device can and cannot do.
o Performance Metrics: Sharing real-world performance data to demonstrate the device's effectiveness in diverse clinical settings.
o Updates and Changes: Informing users about any updates or changes to the AI/ML algorithm and their potential impact on device performance.
Conclusion: AI and digital transformation have revolutionized CROs by enhancing data analysis, predictive modelling, and process automation. These technologies streamline drug discovery, development, leading to faster and more cost-effective operations. As we continue to embrace these advancements, the future of clinical trials is undoubtedly digital, and the potential for further innovation is immense.
Before joining Veeda as Group CEO, Mahesh held senior leadership positions at notable companies such as Syngene International (part of the Biocon Group), Sanofi, and Biological E Limited. He also spent over 20 years in the United States, where he completed his PhD and worked with multinational pharmaceutical giants like Amgen and Monsanto. Mahesh earned his doctorate in Medicinal Chemistry from the University of Utah.
In an exclusive interview with Mandvi Singh, Managing Editor, siliconindia, Dr. Mahesh Bhalgat, Group CEO & Managing Director, Veeda Lifesciences, shared his insights on ‘Successful Digital Interventions in Recent Clinical Trials’.
In recent years, the integration of digital technologies has revolutionized the landscape of clinical trials. These advancements have not only streamlined the process but also enhanced the accuracy, inclusivity, and overall efficiency of trials. The use of technology-oriented solutions that aim to improve health include a wide range of tools, including mobile health applications, telemedicine, portable devices, and clinically integrated platforms that take advantage of electronic health files. There have been some very critical and most successful digital interventions in recent clinical trials that have significantly impacted and boosted potential for future research.
The use of technology and digital tools is one of the most significant advancements in digital clinical trials is the use of wearable technologies and remote sensors. These devices have transformed data collection by providing continuous, real-time monitoring of participants' health metrics that measure a range of parameters, including heart rate, respiratory rate, and physical activity levels. The use of this technology enables researchers to gather comprehensive data without requiring participants to visit clinical sites, thus increasing convenience and participation rates. In May 2024, the FDA approved the use of the Apple Watch’s as a heart monitoring tool in a cardiovascular study. This approval allows researchers to use the Apple Watch to detect arrhythmias and monitor participants' AFib burden, providing a non-invasive way to evaluate the effectiveness of cardiac ablation devices. This landmark decision allowed historical heartbeat data to be used as a secondary endpoint in studies.
Amongst CROs, the adoption of technologies accelerated after the COVID-19 pandemic, where Artificial Intelligence (AI) and Machine Learning (ML) technology has played a pivotal role in enhancing the efficiency and accuracy of clinical trials. AI algorithms can analyse vast amounts of data quickly, identifying patterns and predicting outcomes with high precision. AI and ML are increasingly used in drug discovery, process optimization, and predictive maintenance.
Use of AI in clinical trials by Stanford University: In the area of personalized cancer care research, a clinical trial was conducted at the Stanford University to evaluate the effectiveness of AI in predicting treatment responses and personalizing cancer treatment plans. The trial included patients with various types of cancer, such as lung, breast, and prostate cancer. AI algorithms were used to analyse medical images (e.g., MRI, CT scans) and genomic data to identify tumour characteristics and predict treatment responses. The AI system collected and analysed data from medical images, pathology reports, and patient histories to create personalized treatment plans.
AI algorithms accurately identified tumour characteristics, such as size, shape, and growth patterns, from medical images. The AI system predicted treatment responses with high accuracy, helping oncologists tailor therapies to individual patients. AI-driven analysis enabled the creation of personalized treatment plans, improving the likelihood of successful outcomes. Patients receiving AI-guided treatments showed a higher response rate and longer progression-free survival compared to those receiving standard treatments. AI-driven data analysis accelerated the identification of potential drug candidates by analysing genomic and clinical data. The time required for drug development was significantly shortened, with AI identifying promising compounds faster than traditional methods.
CROs are increasingly using AI and digital technology tools that are beneficial not only in enhancing the planning, tracking, and management of clinical trials but provides a centralized platform for real-time tracking of trial progress, key milestones, and timelines, ensuring that clients including all stakeholders have access to critical information. The Clinical Trial Management System (CTMS) at Veeda Lifesciences streamlines site selection, onboarding, and performance monitoring, ensuring high-quality data and reliable trial outcomes. The CTMS facilitates efficient budget planning, grant management, and invoicing, reducing administrative burdens and ensuring timely payments. With comprehensive monitoring and reporting capabilities, the CTMS helps identify and mitigate risks early, improving overall trial efficiency. By integrating investigational product supply management and quality assurance audits, the CTMS ensures compliance with regulatory standards and enhances data integrity. Overall, the CTMS platform at Veeda Lifesciences leads to more efficient, accurate, and compliant clinical trials, ultimately benefiting clients with faster and more reliable research outcomes.
During the COVID 19 pandemic, the concept of decentralized clinical trials (DCTs) gained momentum wherein digital technology is extensively used to conduct trials remotely. Unlike traditional clinical trials, which require participants to visit centralized locations, DCTs enable various trial activities to occur at locations convenient for participants, such as their homes. This model utilizes telemedicine, mobile health technologies, electronic data capture (EDC), and other digital tools to facilitate remote participation, data collection, and monitoring.
One notable example of a successful decentralized clinical trial is the ADAPTABLE (Aspirin Dosing: A Patient-centric Trial Assessing Benefits and Long-term Effectiveness) study, conducted by the Duke Clinical Research Institute (DCRI), aimed to determine the optimal aspirin dosage for preventing heart attacks and strokes. The convenience of remote participation led to high retention rates and improved compliance with study protocols. Participants reported positive experiences, citing the convenience and reduced burden of travel. The use of digital tools streamlined trial operations, reducing costs and administrative workload and the decentralized approach minimized the environmental impact by reducing the need for travel and associated carbon emissions.
Additionally, the Electronic Data Capture (EDC) platforms used for conducting pharmaceutical research studies in CROs is an exceptional technology platform to enhance the efficiency of clinical trials by streamlining data collection, management, and analysis processes. At Veeda Lifesciences, the EDC platform enables real-time data access and monitoring, allowing for immediate identification of discrepancies and faster decision-making. The system has built-in validation checks that ensures high data integrity, reducing errors and improving the overall quality of trial data. By automating routine tasks and facilitating global collaboration, we believe in optimizing efficiency by minimizing manual intervention and accelerate trial timelines. Additionally, these digital platforms ensure compliance with regulatory standards, enhancing data security and reliability. Overall, the integration of EDC tools leads to more efficient, accurate, and cost-effective clinical trials, ultimately benefiting clients with faster and more reliable research outcomes. As the industry continues to embrace these innovations, DCTs and related digital tools are poised to play a crucial role in the future of clinical research.
As digital interventions become more prevalent in pharmaceutical research operations in CROs, it is essential to address the ethical and regulatory challenges they present. Ensuring data privacy and security is paramount, as is maintaining the scientific rigor of trials conducted outside traditional clinical settings. Researchers must also navigate the complexities of obtaining informed consent in a digital environment, ensuring that participants fully understand the nature and risks of the trial. Regulatory bodies are increasingly recognizing the importance of digital interventions and are developing guidelines to ensure their safe and effective use in clinical trials. The European Medicines Agency (EMA) has established guidelines to regulate the use of AI in drug development. Here are some key aspects:
AI Workplan 2023-2028: The EMA, along with the Heads of Medicines Agencies (HMAs), has published a workplan to guide the use of AI in medicines regulation until 2028. This plan aims to maximize the benefits of AI while managing associated risks.
Scientific Guidelines: The EMA provides scientific guidelines to help medicine developers prepare marketing authorization applications for human medicines. These guidelines cover the use of AI throughout the medicinal product lifecycle.
Reflection Paper on AI/ML: The EMA has adopted a reflection paper on the use of AI and machine learning (ML) in drug development. This paper outlines the considerations and best practices for integrating AI/ML technologies in the development process.
The rapid advancement of AI and ML technologies has revolutionized the healthcare industry, particularly in the development of Software as a Medical Device (SaMD). Recognizing the potential and challenges of these innovations, the USFDA has established a comprehensive framework to ensure the safety, effectiveness, and continuous improvement of AI/ML-based SaMD.
1. Total Product Lifecycle (TPLC) Approach: The FDA's framework adopts a Total Product Lifecycle (TPLC) approach, emphasizing continuous oversight throughout the entire lifecycle of AI/ML-based SaMD. This approach includes:
o Pre-Market Development: Ensuring that AI/ML algorithms are rigorously tested and validated before they are introduced to the market.
o Post-Market Performance Monitoring: Continuously evaluating the device's performance in real-world settings to ensure ongoing safety and effectiveness.
o Continuous Learning and Improvement: Allowing for the iterative improvement of AI/ML algorithms based on new data and insights.
2. Good Machine Learning Practices (GMLP): To support the development of safe and effective AI/ML-based SaMD, the FDA advocates for the adoption of GMLP, which include:
o Data Quality and Integrity: Ensuring that the data used to train and validate AI/ML algorithms is of high quality and representative of the intended patient population.
o Algorithm Transparency: Providing clear documentation of the algorithm's design, development, and validation processes.
o Robustness and Reliability: Demonstrating that the AI/ML algorithm performs consistently and reliably across different clinical settings.
3. Predetermined Change Control Plan (PCCP): This plan allows manufacturers to make certain modifications to AI/ML algorithms without requiring a new pre-market submission. The PCCP outlines:
o Types of Changes: Specifying the types of algorithm changes that can be made under the plan.
o Implementation Methods: Detailing the methods for implementing and validating these changes to ensure they do not compromise the device's safety and effectiveness.
4. Transparency and Real-World Performance Monitoring: is a cornerstone of the FDA's framework. The agency encourages manufacturers to provide clear and comprehensive information about their AI/ML-based SaMD, including:
o
o Performance Metrics: Sharing real-world performance data to demonstrate the device's effectiveness in diverse clinical settings.
o Updates and Changes: Informing users about any updates or changes to the AI/ML algorithm and their potential impact on device performance.
Conclusion: AI and digital transformation have revolutionized CROs by enhancing data analysis, predictive modelling, and process automation. These technologies streamline drug discovery, development, leading to faster and more cost-effective operations. As we continue to embrace these advancements, the future of clinical trials is undoubtedly digital, and the potential for further innovation is immense.
.jpg "5K Car Care : Driving The Auto Franchise Space With A Comprehensive Approach To Car Detailing")
