How Continuous Data Oversight Improves Outcomes
AUTHOR: MOULIK SHAH, FOUNDER AND CEO, MAXISIT
Get more clinical trials across the finish line with continuous data oversight. Here’s how real-time oversight supports risk-based monitoring.
AUTHOR: MOULIK SHAH, FOUNDER AND CEO, MAXISIT
Get more clinical trials across the finish line with continuous data oversight. Here’s how real-time oversight supports risk-based monitoring.
Far too many promising drug candidates don’t make it through clinical trials. While most trials fail to prove safety and efficacy, many more fail due to low enrollment, supply chain issues, or business-related motivations.
Almost every trial experiences both anticipated and unanticipated challenges. Some of these — such as protocol noncompliance, data fraud, and high dropout rates—can derail a trial if not addressed early and quickly.
To promptly address and drop the odds of unanticipated risk, many clinical trial sponsors and CROs have adopted the risk-based approach to monitoring, encouraged by the FDA. They’re also adopting clinical technology powered by artificial intelligence and machine learning (AI/ML) at an increasing rate.
In 2021, over 130 drug and biologic applications submitted to the FDA used AI/ML. In 2017, there was only one. The most common uses include outcome prediction, covariate selection and confounding adjustment, pharmacometrics modeling, and anomaly detection.
By leveraging AI/ML for continuous trial oversight, sponsors and CROs proactively identify risks and optimize trial operations, thereby raising the odds of success.
Our Clinical Trial Oversight System (CTOS) de-risks clinical trials, producing more successful outcomes.
Traditional clinical trial oversight relies on manual monitoring and retrospective analysis. This approach not only delays risk identification, but also introduces more risk by way of error.
An automated approach de-risks data monitoring by reducing or eliminating manual data entry. The FDA encourages sponsors to monitor “important and likely risks” identified during assessment, as well as “additional risks detected during the conduct of the clinical investigation…”. Advanced technology enables sponsors to meet these demands.
AI/ML-based tools continuously analyze vast amounts of data, including patient demographics, medical records, adverse event reports, and real-time monitoring data. By applying advanced analytic techniques, AI/ML can identify patterns, anomalies, and early warning signs, enabling proactive risk detection. By identifying risks in real-time, researchers can intervene on the spot to develop mitigating strategies. Putting out fires as they happen ensures the trial keeps moving according to protocol, with fewer delays.
AI/ML is transforming clinical trial conduct by way of more efficient, collaborative operations. For instance, AI-based tools can streamline patient recruitment by identifying suitable participants based on specific inclusion and exclusion criteria.
A literature review that assessed the use of AI/ML in clinical trials found about half the papers reviewed used these tools for patient recruitment. AI/ML-based tools performed automated eligibility analysis, matched potential participants to trials, and simplified trial searching capabilities. Other uses mentioned in the review include AI-based sensors for patient monitoring, identifying missing data and missing visits, as well as statistical analysis.
ML models can forecast enrollment rates and patient retention, enabling better resource allocation and timeline management. Furthermore, AI-powered virtual assistants and remote monitoring technology enhance communication between trial participants and investigators, facilitating real-time data collection and reducing the burden of manual data entry.
AI/ML can provide invaluable insights and recommendations to support evidence-based decision-making throughout the clinical trial lifecycle. For example, with the help of AI, data managers can identify sites that are behind enrollment targets or are experiencing high dropout rates. By matching real-time data with historical benchmarks, AI-based tools flag these issues almost immediately so sponsors can investigate problems before they impact the timeline.
AI can also help study teams monitor study drug and/or protocol adherence in real-time, particularly when patients are participating remotely. If the data suggest a patient is not taking the study drug as required, or if the patient is not completing ePRO assessments, the study team could contact the patient right away to come up with a solution.
AI/ML technologies enable real-time data monitoring and analysis for more effective risk-based monitoring and faster time from data review to regulatory submission. AI/ML-based tools equip study teams to identify data anomalies and inconsistencies throughout the trial, as well as protocol deviations.
With the ability to detect these risks in real-time, study teams can take steps to correct them. These steps could be as simple as accommodating patients who are having trouble completing ePRO assessments or as complex as investigating potential data fraud.
Later in the study, predictive analytics help improve the quality and speed of data analysis and reporting, reducing the odds of a flagged or rejected submission. Built-in AI-enabled data quality and statistical programs provide traceability. They also flag issues ahead of time, both of which support timely submission.
AI/ML algorithms learn over time based on the data that’s fed into the models. The more clinical data they capture and analyze, the better the performance. The models’ learning ability enables sponsors to refine protocols to include more effective methods and analyses. It also helps teams continually improve operational strategies and ultimately improve trial success rates.
Drug development is more scientifically complex and data-intensive than ever. To continue producing life-changing therapies, life sciences organizations must leverage advanced technology to proactively monitor, manage, and mitigate risk.
CTOS leverages AI/ML and other advanced capabilities to identify risks before and after they happen so that study teams can respond quickly. Clinical operations and data management teams benefit from collaborative workflows and full data visibility in real time. This allows them to make more informed decisions while meeting critical milestones sooner. All these operational outcomes translate to better patient outcomes by way of more therapies crossing the finish line.
MaxisIT’s purpose-fit and intelligent clinical data analytics platform helps improve clinical trial performance, mitigate risk, and optimize clinical outcomes. We provide a centralized and reliable source of truth for diverse data types from various sources, giving life sciences companies real-time insight to shorten cycle time and increase return on investment.
Incorporating an end-to-end clinical data pipeline from intake to visualization, MaxisIT's solutions are powered by AI/ML and metadata-centric approaches. Our impressive portfolio of over 3,300 clinical trials and an unparalleled 100% customer retention rate affirm the quality and reliability of our services.
Moulik Shah Founder & CEO, MaxisIT
Moulik Shah is a passionate healthcare technology entrepreneur and the visionary CEO of MaxisIT, where he has been at the forefront of leveraging technology to transform pharmaceutical and life sciences clinical trials.
His dedication to improving patient outcomes and his leadership in directing patient-centricity, patient diversity, interoperability, and real-world-data-led collaborations have been at the core of his vision of an integrated healthcare ecosystem based on effective use of data and analytics platforms.
He has been instrumental in driving innovation and progress in the industry. Under Moulik’s leadership, MaxisIT has become a leading provider of clinical data and analytics which is driving real-world impact in the pharmaceutical and life sciences clinical trials.
https://www.maxisit.com/