Cost-Effectiveness of Nivolumab Plus Ipilimumab for the First-Line Treatment of Intermediate/Poor-Risk Advanced and/or Metastatic Renal Cell Carcinoma in Switzerland

Scoping Review of Economic Analyses of Rare Kidney Diseases

Introduction

Rare kidney diseases (RKDs) place a substantial economic burden on patients and health systems, the extent of which is unknown and may be systematically underestimated by health economic techniques. We aimed to investigate the economic burden and cost-effectiveness evidence base for RKDs.

Methods

We conducted a systematic scoping review to identify economic evaluations, health technology assessments, and cost-of-illness studies relating to RKDs, published since 2012.

Results

A total of 161 published studies, including 66 cost-of-illness studies and 95 economic evaluations; 72 grey literature reports were also included. Most published literature originated from high-income nations, particularly the USA (81 studies), and focused on a handful of diseases, notably renal cell carcinomas (70) and systemic lupus erythematosus (36). Limited evidence was identified from lower-income settings and there were few studies of genetic conditions, which make up most RKDs. Some studies demonstrated the cost-effectiveness of existing treatments; however, there were limited considerations of broader economic impacts on patients that may be important to those with RKDs. Included health technology assessments highlighted difficulties in obtaining high-quality clinical evidence for treatments in very small patient populations, and often considered equity issues and other patient impacts qualitatively alongside clinical and economic evidence in their recommendations.

Conclusion

We found large gaps in the economic evidence base for RKDs and limited adaptation of methods to account for the uniqueness of these diseases. There may be significant scope for innovation in building an investment case for RKD treatments, as well as in decision-making processes to inform investment decisions.

Artificial Intelligence to Automate Health Economic Modelling: A Case Study to Evaluate the Potential Application of Large Language Models

BACKGROUND

Current generation large language models (LLMs) such as Generative Pre-Trained Transformer 4 (GPT-4) have achieved human-level performance on many tasks including the generation of computer code based on textual input. This study aimed to assess whether GPT-4 could be used to automatically programme two published health economic analyses.

METHODS

The two analyses were partitioned survival models evaluating interventions in non-small cell lung cancer (NSCLC) and renal cell carcinoma (RCC). We developed prompts which instructed GPT-4 to programme the NSCLC and RCC models in R, and which provided descriptions of each model's methods, assumptions and parameter values. The results of the generated scripts were compared to the published values from the original, human-programmed models. The models were replicated 15 times to capture variability in GPT-4's output.

RESULTS

GPT-4 fully replicated the NSCLC model with high accuracy: 100% (15/15) of the artificial intelligence (AI)-generated NSCLC models were error-free or contained a single minor error, and 93% (14/15) were completely error-free. GPT-4 closely replicated the RCC model, although human intervention was required to simplify an element of the model design (one of the model's fifteen input calculations) because it used too many sequential steps to be implemented in a single prompt. With this simplification, 87% (13/15) of the AI-generated RCC models were error-free or contained a single minor error, and 60% (9/15) were completely error-free. Error-free model scripts replicated the published incremental cost-effectiveness ratios to within 1%.

CONCLUSION

This study provides a promising indication that GPT-4 can have practical applications in the automation of health economic model construction. Potential benefits include accelerated model development timelines and reduced costs of development. Further research is necessary to explore the generalisability of LLM-based automation across a larger sample of models.