Health economic simulation modeling of an AI-enabled clinical decision support system for coronary revascularization
Bibliographic record
Abstract
Abstract Importance Coronary revascularization decision-making can be challenging. While artificial intelligence (AI) models have been developed to support this decision-making, health economic evaluation of such models has been rare. Objective To evaluate the economic value of an AI-enabled coronary revascularization decision support system in terms of cost savings and gains in quality adjusted life years (QALY). Design Retrospective health economic simulation modeling study using real-world patient data and AI-generated patient outcome predictions. Setting 26,605 adult patients with obstructive coronary artery disease who underwent diagnostic coronary angiography between 2009 and 2019 in Alberta, Canada. Exposures Clinicians deciding among medical therapy only, percutaneous coronary intervention, and coronary artery bypass grafting were simulated to be provided with AI-generated decision support information in the form of 3- and 5-year major adverse cardiovascular event and all-cause mortality predictions. Main Outcomes and Measures Average cost savings and gains in QALY, represented as a willingness-to-pay, per patient resulting from treatment decisions altered by the AI-generated decision support. Results Most actual coronary revascularization decisions could have been improved by AI decision support from a health economic perspective. At a willingness-to-pay of $50,000 per QALY, as many as 51% of all actual treatment decisions shifted to another treatment, resulting in an average cost saving of $31,204 and a QALY gain equivalent to up to $2,406 per patient. Even in a conservative scenario where clinicians’ AI adoption was limited by ignoring AI recommendations unless the gain in QALY was substantial, 22.4% of the actual decisions shifted, resulting in an average gain of 0.327 QALY, equivalent to up to $16,371, per patient. Conclusions and Relevance AI can help clinicians to optimize coronary revascularization decisions. The health system level economic value of optimized treatment decisions can be substantial in the form of reduced costs stemming from fewer future complications and improved patient outcomes. Key Points Question How much cost saving and gain in quality adjusted life years (QALY) can be expected from using an AI-enabled clinical decision support system for coronary revascularization decision-making? Findings AI was able to improve the cost-effectiveness of 51% percent of actual treatment decisions. Pursuing AI-based optimal treatments would have resulted in an average cost saving of $31,204 and a QALY gain equivalent to $2,406 per patient. Meaning AI can help optimize coronary revascularization decisions, leading to substantial economic value in the form of cost savings and improved patient outcomes.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.005 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".