What question did this study set out to answer?

To evaluate the cost-effectiveness of an artificial intelligence medical device (DERM) for pre-referral triage of suspected skin cancer in primary care compared with standard general practitioner care.

August 20, 2026PharmacoEconomics - OpenOpen Access

Cost-Effectiveness of an Artificial Intelligence as a Medical Device (AIaMD) for Triaging Patients Presenting to Primary Care with Concerns that They Have a Skin Cancer: A Modelling Study

View Full Paper

Ask AI

Bookmark

Authors

JJJavad Javan‐Noughabi ZZZhivko Zhelev BGBogdan Grigore

Discussion

Member takes

Overview

Economic modelling study demonstrates variable cost-effectiveness of AI skin cancer triage in primary care depending on physician diagnostic accuracy, suggesting potential value with targeted...

Key Points

To evaluate the cost-effectiveness of an artificial intelligence medical device (DERM) for pre-referral triage of suspected skin cancer in primary care compared with standard general practitioner care.
Decision-analytic model adapted to the community setting using a UK NHS and personal social services perspective over a lifetime horizon up to 100 years.
Compared standard care with two AI-assisted strategies: autonomous AI discharge (DERM_autonomous) and AI with human second reading upon discharge recommendation (DERM_2R).
Assessed costs, healthcare utilization, and quality-adjusted life-years (QALYs) across three base-case scenarios reflecting different GP diagnostic sensitivity and specificity assumptions.
Under maximum GP sensitivity, standard care was the most cost-effective option, dominating DERM_autonomous, while DERM_2R produced an ICER of £30,370 per QALY gained.
Under maximum GP specificity, DERM_autonomous dominated standard care, and DERM_2R yielded an ICER of £397 per QALY relative to standard care.
When GP diagnostic accuracy was back-calculated from routine NHS data, both DERM_autonomous and DERM_2R dominated standard care.

Cite This Study

Javan‐Noughabi et al. (2026) studied this question.

synapsesocial.com/papers/6a86b56c8a91293e6a1ccc5d https://doi.org/10.1007/s41669-026-00675-6

View Full Paper

Ask AI

Bookmark

August 20, 2026PharmacoEconomics - OpenOpen Access

Cost-Effectiveness of an Artificial Intelligence as a Medical Device (AIaMD) for Triaging Patients Presenting to Primary Care with Concerns that They Have a Skin Cancer: A Modelling Study

View Full Paper

Ask AI

Bookmark

Authors

JJJavad Javan‐Noughabi ZZZhivko Zhelev BGBogdan Grigore

Discussion

Member takes

Overview

Economic modelling study demonstrates variable cost-effectiveness of AI skin cancer triage in primary care depending on physician diagnostic accuracy, suggesting potential value with targeted...

Key Points

To evaluate the cost-effectiveness of an artificial intelligence medical device (DERM) for pre-referral triage of suspected skin cancer in primary care compared with standard general practitioner care.
Decision-analytic model adapted to the community setting using a UK NHS and personal social services perspective over a lifetime horizon up to 100 years.
Compared standard care with two AI-assisted strategies: autonomous AI discharge (DERM_autonomous) and AI with human second reading upon discharge recommendation (DERM_2R).
Assessed costs, healthcare utilization, and quality-adjusted life-years (QALYs) across three base-case scenarios reflecting different GP diagnostic sensitivity and specificity assumptions.
Under maximum GP sensitivity, standard care was the most cost-effective option, dominating DERM_autonomous, while DERM_2R produced an ICER of £30,370 per QALY gained.
Under maximum GP specificity, DERM_autonomous dominated standard care, and DERM_2R yielded an ICER of £397 per QALY relative to standard care.
When GP diagnostic accuracy was back-calculated from routine NHS data, both DERM_autonomous and DERM_2R dominated standard care.

Cite This Study

Javan‐Noughabi et al. (2026) studied this question.

synapsesocial.com/papers/6a86b56c8a91293e6a1ccc5d https://doi.org/10.1007/s41669-026-00675-6

View Full Paper

Ask AI

Bookmark