Back

Replicating Health-Economic Simulation Models for Alzheimer's Disease Using Artificial Intelligence

Gilson, F.; Osstyn, S.; Handels, R.

2025-10-13 health economics
10.1101/2025.10.08.25337408 medRxiv
Show abstract

BACKGROUNDTransparency and credibility of health-economic simulation models is essential to inform reimbursement decisions. Model replication can support model transparency and credibility. Artificial intelligence (AI), particularly large language models, offers new opportunities to accelerate model replication. This led to the research question: "To what extent can the results of existing health-economic Markov models be replicated by models developed using generative AI for eliciting input parameters and code generation?" METHODSReplication was performed in three steps. First, a chain-of-thought prompting strategy in ChatGPT-4 was developed to replicate in R an open-source model co-developed by one of the authors and with publicly available code. Second, it was applied to replicate a model co-developed by one of the authors but without publicly available code. Third, it was applied to a model without the involvement of the authors and without publicly available code. A mixed- methods approach was employed in terms of qualitatively addressing the face validity of the prompt development and refinement and quantitatively assessing deviations between AI- generated and original model predictions. RESULTSThe first model required approximately one month to replicate, while adaptations to the second and third models took approximately two weeks each. Across the three models and 45 replications (15 per model), the average absolute relative deviations between ChatGPT-4 generated model predictions and published results were: [≤]14% for quality-adjusted life years and costs in the first model, [≤]7% in the second model, and [≤]28% in the third model. CONCLUSIONSOur approach could support more time-efficient model replication for reimbursement decision-makers, researchers or pharmaceutical companies. This could contribute to transparency and credibility of health-economic models.

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

1
PLOS ONE
4510 papers in training set
Top 6%
23.2%
2
BMJ Open
554 papers in training set
Top 1%
13.1%
3
Journal of the American Medical Informatics Association
61 papers in training set
Top 0.2%
10.4%
4
Medical Decision Making
10 papers in training set
Top 0.1%
10.4%
50% of probability mass above
5
American Journal of Preventive Medicine
11 papers in training set
Top 0.1%
5.0%
6
npj Digital Medicine
97 papers in training set
Top 2%
2.1%
7
BMC Medical Research Methodology
43 papers in training set
Top 0.4%
2.1%
8
BMC Medicine
163 papers in training set
Top 3%
1.9%
9
Research Synthesis Methods
20 papers in training set
Top 0.1%
1.9%
10
Journal of Medical Internet Research
85 papers in training set
Top 2%
1.7%
11
BJGP Open
12 papers in training set
Top 0.3%
1.7%
12
BMC Public Health
147 papers in training set
Top 4%
1.3%
13
Journal of Medical Economics
10 papers in training set
Top 0.1%
1.3%
14
Frontiers in Artificial Intelligence
18 papers in training set
Top 0.6%
0.8%
15
Clinical and Translational Science
21 papers in training set
Top 0.9%
0.8%
16
European Radiology
14 papers in training set
Top 0.6%
0.8%
17
PLOS Biology
408 papers in training set
Top 18%
0.8%
18
Frontiers in Public Health
140 papers in training set
Top 7%
0.8%
19
Systematic Reviews
11 papers in training set
Top 0.4%
0.8%
20
Scientific Reports
3102 papers in training set
Top 72%
0.8%
21
Epilepsy Research
12 papers in training set
Top 0.3%
0.8%
22
PLOS Computational Biology
1633 papers in training set
Top 24%
0.8%
23
Scientific Data
174 papers in training set
Top 2%
0.8%
24
Journal of Alzheimer’s Disease
39 papers in training set
Top 1%
0.8%
25
JAMA Network Open
127 papers in training set
Top 4%
0.8%
26
Nature Human Behaviour
85 papers in training set
Top 5%
0.5%
27
PLOS Medicine
98 papers in training set
Top 6%
0.5%