Legal teams often face the daunting task of reviewing large volumes of claimant documents to identify disease mentions and link them to mass tort settlement evidence. This manual process not only consumed a cumbersome load of time but also faced inconsistencies, which impacted the fairness and efficiency of claim evaluation. With increasing case volumes, the law firm needed a way to reduce the time spent on manual review while maintaining accuracy and reliability.
To address this, Rannsolve’s AI-powered Named Entity Recognition (NER) model was introduced to the law firm to automate legal document review and extract structured information from unstructured text and represent it in a machine-readable format. The AI entity detection model was used to scan claimant documents and flag medical keywords and conditions related to the tort. NER automated the identification of required evidence-related data within claimant submissions, and evidence linking was performed using co-reference resolution. Also, the scoring models were used to evaluate and rank the strength of connections between pieces of evidence.
The implementation of this AI solution made the legal document automation process to a much more sophisticated level. Accuracy in identifying evidence increased to 91%, while the review speed increased fivefold. The system could process over 200,000 pages each month. As a result, the firm saved more than 10,000 hours annually, allowing legal teams to utilize their time more strategically.
Share this case study
Comprehensive Solutions – Driven by AI Innovation – Transforming Business