Menu ≡ ╳
Clinical trials demand time and money from drug sponsors and patience from participants. From start to finish, they average a time window of 9 years and cost of $1.3 B. The real challenge is that 12% of clinical trials succeed while the rest leave dashed hopes behind, begging the question as to what can make clinical trials succeed? In other words, what makes them fail? How do we derive actionable insights from clinical trials, even as we ensure adherence to FDA guidelines, follow good manufacturing protocols, and continually tackle issues with patient recruitment, enrollment, and retention? How do we ensure that, when results are reviewed at the end of each stage in a clinical trial, they justify moving to the next stage? In short, how do we ensure the success of a trial?
Technology is the only recourse we have to advance clinical research, while staying compliant with FDA’s guidance in-home visits, direct-to-patient trial supply, telehealth, ePRO/eCOA, eConsent, and remote patient monitoring. As more drug sponsors adopt decentralized trials, we need to track all in-clinic and remote data endpoints. Factors like poor study design, inappropriate endpoints or eligibility criteria or omission of appropriate ones, inappropriate analysis, too large or too small a sample size, inconsistencies in protocol, suboptimal site selections, issues with recruitment are all reasons why a clinical trial would fail. Most of these would lead us to collect ineffective data.
Since our focus is on data, let’s also check if we are working hard enough to derive reliable insights from the data we collect so assiduously. Do we understand data quality issues, and analyze outliers sufficiently without cutting corners? Are we killing our projects due to a negligent approach to ensuring clean data? These days, huge amounts of data are collected using clinical findings/observations, patient health records, scanned images, wearable devices, and genomic studies. We bring together large amounts of data to throw a light a patient’s health in myriad ways, enabling a precision health approach and advancing health care itself. While we ensure that there’s quantity, we may find that quality is missing. Data sources should be verified before collected and integrated into the trial data.
Collecting patient medical data presents many challenges. It could be unstructured or taken from independent sources which operate in silos. Many times, data loses its structure during transmission. It may also have been inefficient to begin with, as the methods were ineffective, faulty due to the patients’ lack of adherence, or because they have been misplaced or lost. Patients may also drop out because they are not willing to travel or pay for the additional tests needed. All these issues as well as duplication, overlapping, inadequacy, incompleteness could adversely affect the data collected and thereby the accuracy of the study and its outcomes.
Clinical trials need accurate, consistent, high-quality data with high response and low attrition for reliable results. While bringing cost effective care to people, quality data could find a cure for orphan diseases or reduce medical errors, measure the effectiveness of a given drug against a specific ailment or drive the delivery of optimal treatment based on data-driven diagnostics and analytics. The continuing issue is ensuring the quality of data. We are all aware of the fact that data is everywhere and that it is being collected every step of the way. Gaining deep and valuable insights from data is possible only when high quality data from disparate sources is combined and allowed to present a broader picture.
AI works best with bigger data sets, but we need to exercise the required care to ensure that data lakes do not turn into data swamps, offering little or no actionable insights. By applying AI at the point of care, clinical trial teams can work on making the insights more efficient for patients, manufacturers, and physicians. AI could also help resolve the challenges with enrollment and ensure that the participants adhere to the medication protocol.
Collecting high-quality data and deriving meaningful insights from it is the key to success. As we look to the future of clinical trial data processes, we can see that technology will continue to have a significant impact on the data lifecycle and how we manage it to achieve the best outcomes.
At MaxisIT, we clearly understand strategic priorities within clinical R&D, as we implement solutions for improving Clinical Development Portfolios via an integrated platform-based approach. For over 17 years, MaxisIT’s Clinical Trial Oversight System (CTOS) has been synonymous with timely access to study-specific, standardized and aggregated operational, trial, and patient data, enabling efficient trial oversight. MaxisIT’s platform is a purpose-built solution, which helps the Life Sciences industry by empowering business stakeholders. Our solution optimizes the clinical ecosystem; and enables in-time decision support, continuous monitoring over regulatory compliance, and greater operational efficiency at a measurable rate.