Work

From Benchmark to Bedside: Mapping the Translational Gaps of Artificial Intelligence in Clinical Medicine

Year: 2026
Type: article
Abstract: Artificial intelligence (AI) has reached specialist-level performance across a widening range of clinical tasks, yet celebrated benchmark results have repeatedly failed to translate into patient benefit. This survey reviews 29 core sources (2016–2024) through an original framework of three translational gaps—validation, utility, and governance—that jointly explain the distance between benchmark scores and bedside value; reported figures are quoted only from peer-reviewed studies, pivotal trials, or first-party regulatory documents. Capability measurement has matured across three generations—specialist image classifiers, examination-scale language models exceeding 86% on USMLE-style questions, and workflow-level deployments such as autonomous diabetic-retinopathy screening and ambient clinical documentation. Each gap independently severs the link between performance and benefit: deployed models degrade under dataset shift, an externally audited sepsis model fell far below its reported accuracy, nearly half of the citations in generated medical content can be fabricated, and human–AI collaboration can underperform either party alone. Governance responses—risk-tiered regulation, equity audits, and post-market surveillance—are converging on medicine's established logic: grading AI claims with the same evidence hierarchy that evidence-based medicine applies to therapies.
Language: English
Field: Medicine
Open Access status: diamond
OpenAlex ID: W7220057123
FWCI:
Cites: 24
Cited by:
Related to: 10