We demonstrate the capabilities of ValueGen.AI in navigating, extracting, synthesizing, and summarizing common critiques raised by multiple HTA agencies, a time and labor-intensive task for humans.
We utilize 13 HTA reports from three major agencies: the National Institute for Health and Care Excellence (NICE) in the United Kingdom, the Haute Autorité de Santé (HAS) in France, and the Gemeinsamer Bundesausschuss (G-BA) in Germany. ValueGen.AI uses language-agnostic capabilities, enabling the processing of documents written in English and native languages (French and German). This functionality was vital for ensuring that the AI accurately extracted critiques in different languages without requiring translations that might lose nuances. This cross-comparison enabled a clearer understanding of shared concerns as well as agency-specific perspectives.
Table 1.Summary of Shared and Unique Critiques by HTA Agency
The review of HTA reports revealed several recurring critiques across agencies regarding tofacitinib's assessment for ulcerative colitis:
Trial Design: A predominant critique noted by all three agencies pertained to the design and methodology of clinical trials. Concerns were raised about data collection methods and reliability, suggesting a need for more robust trial frameworks.
Comparator Arm: All three agencies pointed out limitations related to insufficient details on the comparator arm used in clinical studies, which undermined the robustness of comparative analyses.
Safety: NICE uniquely raised issues around safety and adverse events, while HAS focused on public health impact.
Economic Analysis: Only NICE raised concerns about the economic analysis conducted.
The majority of the critiques were related to trial design, which was followed by the current management, including lack of details on the comparator arm or analysis of adverse events
