Trially and Margo: Aligning AI Technology with Altasciences' Accelerated Drug Development Goals

Introduction to Altasciences’ Case Study

Altasciences, who provides flexible services for preclinical and clinical studies, including formulation, manufacturing, and analysis, published a case study titled, “Streamlining Clinical Trial Start-up for Accelerated Drug Development.” This study highlights the successful strategies Altasciences employed in a Phase I study to drastically reduce the clinical trial start-up period. Altasciences noted that to meet a sponsor’s immediate need for a regulatory filing, the standard start-up time (defined as time from study award to first dose) of 12 weeks needed to be shortened to less than four weeks. Through strong project management, collaborative alignment, and parallel processing, Altasciences achieved a remarkably fast start-up timeframe of 3.5 weeks from study award to first subject first dose (FSFD). The successful acceleration relied on the expedited completion of critical start-up tasks, notably subject recruitment and screening.

Trially’s AI platform and the Margo AI agent are engineered to solve the core inefficiencies that delay these critical start-up milestones—specifically, manual screening, trial-site mismatch, and poor lead conversion. Trially is proven to deliver superior results 4x faster than competitor solutions. By eliminating major bottlenecks in the patient identification and enrollment process, Trially and Margo are fundamentally consistent with the objectives detailed in Altasciences' case study, enabling sites to accelerate their timeline toward First Subject First Dose (FSFD).

Focused Timeline Management and Parallel Task Execution

Altasciences’ Case Study Objective: Altasciences implemented focused timeline management, meticulously guiding the team to prioritize the start-up phase through the first subject first visit (FSFV) to meet the sponsor’s key performance indicator (KPI) of “first dose”. The case study highlights the importance of parallel task execution, where regulatory document preparation and IRB approval run concurrently with other necessities like study document generation and database building. Subject recruitment and screening were among the essential tasks required to be completed during this extremely shortened timeframe.

Trially’s Consistency: Trially directly addresses the speed required for tasks that must run in parallel during an accelerated start-up. One major bottleneck traditionally is the manual interpretation and preparation of protocol criteria, which contributes to staff time wastage. Trially’s Protocol NLP Parser automatically parses complex protocols into Inclusion/Exclusion (I/E) criteria cards, taking only 5–10 minutes. This immediate protocol preparation means that criteria are instantly available for feasibility counts and patient identification. By instantly setting up the criteria (seconds, not hours or days), Trially allows patient identification and matching—using EHR data—to occur concurrently with other required initial tasks like regulatory documentation or IRB preparation, thereby supporting the parallel task strategy outlined in the Altasciences’ case study. Furthermore, Trially offers Immediate Value Delivery using appointment-based patient recruitment via CSV uploads, allowing sites to start identifying patients even before full EHR integration is complete (which takes 1-2 weeks for EHR API).

Expediting Subject Recruitment and Reducing Manual Labor

Altasciences’ Case Study Objective: The successful achievement of the 3.5-week start-up timeframe was predicated on the efficient completion of all necessary tasks, including subject recruitment and screening. Delays in identifying and qualifying patients threaten the goal of accelerated drug development.

Trially’s Consistency: Trially’s core function is to unlock faster qualified patient enrollment. The platform uses its proprietary AI matching engine to instantly match patients to trials. Trially rapidly prioritizes and stack-ranks up to 10x candidates. Since manual screening often wastes over 250 hours per month per site amid increasingly complex protocols, Trially offers a transformative solution. Trially dramatically reduces this manual effort, delivering a 90% reduction in manual EHR chart review hours for Clinical Research Coordinators (CRCs). This significant efficiency gain—transforming 36 hours of review down to 2.5 hours per month in one case study—ensures that the critical task of subject screening can be executed rapidly and efficiently enough to meet the extremely tight, sub-four-week timeline required by Altasciences’ sponsor.

Achieving Precision to Minimize Start-Up Screen Failures

Altasciences’ Case Study Objective: While Altasciences’ case study emphasizes speed and parallel processing, sustained acceleration requires high quality and minimal re-work. Inefficient recruitment leads to high screen failure (SF) rates, costing sites time and money, and jeopardizing the ability to predictably hit enrollment goals. Historically, 80% of sites fail to meet their enrollment target.

Trially’s Consistency: Trially ensures that the high-speed identification required for an accelerated start-up does not compromise quality, which would cause subsequent delays. Trially guarantees 95% accuracy in matching patients against criteria using its LLM-assisted prescreening technology. This high precision results in a notable reduction in screen failure rates; Trially has demonstrated a 73% reduction in screen failure rates. Additionally, LLM-assisted prescreening increases eligibility rates (20.4%) compared to the traditional methods (12.7%). By ensuring that the patients identified on Day 1 are of high quality, Trially minimizes wasted time and screen failures, which is vital when operating under the severe time constraints outlined in the Altasciences’ case study.

Automated Patient Engagement via Margo

Altasciences’ Case Study Objective: The success demonstrated in the Altasciences’ case study required swift execution through effective communication and strong collaboration  However, fast enrollment goals are often thwarted in the 'Patient-Physician engagement stage’, a manual and time-intensive process where qualified candidates often fall through the cracks due to insufficient follow-up, staffing shortages and [a flawed] physician handoff."

Trially/Margo’s Consistency: Trially Connect, featuring the Margo AI Agent, is the automated layer that converts the high-quality patient matches identified by Trially Match into enrolled participants. Margo addresses the "last mile" recruitment challenge. Margo automates the engagement process—prescreening, qualifying, scheduling appointments, and sending reminders (SMS, Voice). Margo focuses on leveraging "warmest leads" by rapidly prescreening patients based on upcoming visits and generating real-time patient qualification summaries for the CRC. By automating this crucial follow-up and engagement phase, Margo ensures that highly qualified candidates are quickly converted, preventing the workflow gaps and poor follow-up that could derail the rapid FSFD goal achieved in Altasciences’ successful accelerated drug development case study.