The decision-making process for health technology assessment (HTA) in ultra-rare diseases faces a significant challenge for agencies worldwide. This study sought to offer an analytical overview of the clinical evidence outlined in the recommendations of the Brazilian National Committee for Health Technology Incorporation (Conitec) in ultra-rare diseases.

Data were extracted from recommendation reports for the ultra-rare diseases evaluated between 2012 and 2022. To classify a disease as ultra-rare, the epidemiological criterion or a consultation with the Orphanet platform was used (prevalence of ≤1/50,000 inhabitants). The extracted variables included the type of evidence synthesis, type of studies, instrument, the result of the assessment of the methodological quality of the studies, the format of evidence synthesis presentation, whether the evidence was graded, and the result.

Among 53 analyzed reports, 70 percent relied on randomized controlled trials, followed by systematic reviews (SR), and observational studies. Reports with positive recommendations based on SR comprised 63 percent. GRADE applied to 27 reports and indicated low or very low results for the first two outcomes (62% and 65%). No clear link between evidence quality and final recommendations was observed. Meta-analysis-based reports had 83 percent positive recommendation rate, compared to 55 percent without meta-analysis. Surrogate outcomes were predominant. Clinical characteristics significantly influenced final decisions, especially when new data emerged in public consultation or had the potential to alter disease progression, reduce severe events, or enhance survival.

Ultra-rare diseases pose challenges in evidence quantity and quality. Traditional HTA frameworks seem inadequate, lacking robust evidence for these conditions. The difficulties in ultra-rare disease HTA underscore the need for specialized frameworks. This analysis acknowledges limitations, notably the heterogeneity in older report structures compared to recent ones, reflecting evolving HTA methodologies in Brazil.

The decision-making process for incorporating technologies for ultrarare diseases (URD) has been a challenge for health technology assessment agencies worldwide. These challenges have been presented in debates about the budget impact of incorporating technologies for URD. This is an important issue because there are other dimensions of the economic and social impact of URD that require consideration.

Data were extracted from National Committee for Health Technology Incorporation (CONITEC) reports (2012 to 2022) on technologies for the treatment of URD in Brazil. Diseases were classified using an epidemiological criterion or Orphanet consultation (prevalence ≤1 per 50,000 inhabitants). Variables included eligible patient count, population estimation method, incremental impact values for one and five years, and diffusion rate in the first and fifth year. Univariate logistic regression was used to adjust the relationship between the budget impact analysis and the final recommendation, considering factors associated with incorporation in univariate regression and p-values less than 0.10 in a multivariate regression.

Among 53 reports, 48 percent exclusively employed the epidemiological approach for incremental impact assessment population estimation, rising to 69.5 percent when combined with measured demand. Population data were nearly evenly sourced from national and international platforms, with the UK, the USA, and multicenter studies being the most cited internationally. Notable differences were found between favorable and unfavorable CONITEC recommendations, with lower values being associated with incorporation. Market share diffusion rates favored the option of 100 percent diffusion in both the first year and the cumulative five years. The analysis highlighted the influence of demand characteristics and technology type on the budget impact value over one and five years.

The study found that budget impact data significantly influenced the final recommendation for technology incorporation, indicating a criterion favoring technologies with a lower budget impact. However, requester characteristics and technology type also played a role in the decision-making process, suggesting that additional factors influence recommendations.

Incorporating technologies for ultrarare diseases (URD) poses challenges for global health technology assessment (HTA) agencies. Difficulties include defining an analytical framework and establishing differentiated cost-effectiveness thresholds. The rise of technological innovations intensifies demands from healthcare professionals, media, and the general population, placing pressure on healthcare systems in developing countries.

To analyze ultrarare medicine costs in submissions to the Brazilian National Committee for Health Technology Incorporation (CONITEC), data from HTA reports on URD (from 2012 to 2022) were extracted. Diseases were classified as URD based on an epidemiological criterion or Orphanet consultation (prevalence ≤1 per 50,000 inhabitants). Extracted variables included initial and final prices, annual patient cost, incremental cost-effectiveness ratio (ICER), and initial and final CONITEC recommendations. Price differences were calculated by the Brazilian Medicines Market Regulation Chamber.

Among 53 reports, 30 featured economic evaluations, with only 13.3 percent initially receiving positive recommendations. However, eight gained favor, including post-consultation, price-conditioned, and risk sharing-based approvals. Annual medication costs ranged from USD17,439.20 to USD1,108,237.00 per patient, with discounts of between 25 and 64 percent. Despite some technologies having ICERs that were significantly higher than the national threshold, no statistical relationship was found between ICERs and recommendations. Monthly and annual costs varied, with higher costs for heterogeneous diseases and lower costs for metabolic conditions. Sensitivity analyses, using both deterministic and probabilistic analyses, were conducted in 58 percent of the reports.

Incorporation of technologies for URD does not correlate with lower annual costs or increased discounts because costs are not considered in isolation by CONITEC’s decision-making process. Recognizing URD as a subgroup with distinct criteria may enhance the implementation of HTA processes tailored to the unique challenges of these conditions.

Health technology assessment (HTA) plays a vital role in healthcare decision-making globally, necessitating the identification of key factors impacting evaluation outcomes due to the significant workload faced by HTA agencies.

The aim of this study was to predict the approval status of evaluations conducted by the Brazilian Committee for Health Technology Incorporation (CONITEC) using natural language processing (NLP).

Data encompassing CONITEC’s official report summaries from 2012 to 2022. Textual data was tokenized for NLP analysis. Least Absolute Shrinkage and Selection Operator, logistic regression, support vector machine, random forest, neural network, and extreme gradient boosting (XGBoost), were evaluated for accuracy, area under the receiver operating characteristic curve (ROC AUC) score, precision, and recall. Cluster analysis using the k-modes algorithm categorized entries into two clusters (approved, rejected).

The neural network model exhibited the highest accuracy metrics (precision at 0.815, accuracy at 0.769, ROC AUC at 0.871, and recall at 0.746), followed by XGBoost model. The lexical analysis uncovered linguistic markers, like references to international HTA agencies’ experiences and government as demandant, potentially influencing CONITEC’s decisions. Cluster and XGBoost analyses emphasized that approved evaluations mainly concerned drug assessments, often government-initiated, while non-approved ones frequently evaluated drugs, with the industry as the requester.

NLP model can predict health technology incorporation outcomes, opening avenues for future research using HTA reports from other agencies. This model has the potential to enhance HTA system efficiency by offering initial insights and decision-making criteria, thereby benefiting healthcare experts.