AI-Powered Solutions

Evidinno has been pushing the boundaries of technology since day one, always asking how emerging tools can make our work faster, smarter, and more reliable. From our earliest days, we recognized that utilizing artificial intelligence would be the key to eliminating tedious manual tasks and minimizing human error; therefore, we invested deeply in developing and validating our own AI-driven solutions. Today, that vision has become reality: by integrating the very latest large-language and reasoning models into every step of the systematic review process and beyond, we’ve achieved unprecedented speed and precision in screening and data extraction and this journey to perfection continues. Below, you’ll see how each of our digital solutions brings this commitment to life.

AI-Assisted Literature Review

Title/Abstract Screening Module:

Leveraging GPT-4o mini’s deep reasoning capabilities, this module processes thousands of titles and abstracts in minutes, flagging and filtering studies with industry-leading precision. The module has undergone dozens of revisions and testing procedures using previously completed published systematic reviews and is currently under publication in a peer-reviewed journal.

Full-Text Screening Module:

Powered by Claude 3.7 Sonnet, our system dives into full text articles evaluating different sections of the manuscripts for eligibility as per PICO criteria at hand to ensure only the most pertinent papers advance to the next stage. The module has undergone dozens of revisions and testing procedures using previously completed published systematic reviews and is currently under publication in a peer-reviewed journal.

Data Extraction Module:

Utilizing Claude Sonnet 3.7, this component automatically captures all required study details needed for data synthesis including but not limited to study design, interventions, participant demographics, as well as efficacy and safety outcome characteristics from text, tables, and figures ensuring comprehensive, error-free data collection. The module has undergone dozens of revisions and testing procedures using previously completed published systematic reviews and is currently under publication in a peer-reviewed journal.

Risk of Bias Assessor Module:
Currently under development, the module is powered by Claude Sonnet 3.7 and evaluates risk of bias in studies based on the Cochrane risk of bias for randomized trials, as well as Newcastle Ottawa Scale for observational studies.

Centralized Project Repository

All relevant projects from a function or therapeutic area are collected into a central, searchable repository that summarizes key factors of each project. This can be used to streamline new project planning, ensure consistency across multiple projects and allow cross-project analyses or summary of results.  Access to the repository can be tailored to the business needs, with varying levels of read/write permissions available.

Regulatory Dossier Submission Package Analyzer

Continuous surveillance of US and European regulatory approval agencies provides for up-to-date information of packages to inform Clinical Development programs. Our RWE scientists, analysts and CI programmers have created the capability of searching regulatory approvals for submissions that include RWE as a component of the registration packet. This information is tailored to the portfolio considerations of the customer.  The interactive visual user interface allows for inputting of relevant characteristics to assess similarity to historical comparators for strategic tailoring of the registration program. Users can test various scenarios to identify optimal outcomes of use of RWE in their development programs.

Competitive Intelligence Dashboards

Competitive Intelligence services include continuous surveillance of published scientific journals and other gray literature sources including RSS feeds. These sources are populated using AI technology and curated by subject matter experts. The dashboards can be customized to customer needs, and include publication, authors, synthesis and key competitive insight as well as assessment of importance. User access can be tailored to specific department or enterprise wide and allow varying read/write permissions for input/feedback.  Monthly or quarterly reports summarize key findings.  Competitive intelligence from select conferences includes pre-conference screening of abstracts for relevance, on-site attendance for extraction of information from poster and oral presentations and daily curated updates to the dashboard.  Post conference reports are posted to the dashboard within 2 weeks of conference conclusion

Request a Demo of our Digital Solutions