{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T12:18:34Z","timestamp":1793276314442,"version":"4.5.0"},"reference-count":27,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Ministry of Health & Welfare, Republic of Korea","award":["RS-2022-KH129902"],"award-info":[{"award-number":["RS-2022-KH129902"]}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early and accurate diagnosis of Parkinson\u2019s disease (PD) remains a major clinical and economic challenge, particularly in settings where dopaminergic imaging, such as positron emission tomography (PET) scans, is limited by cost, availability, and patient access. Artificial intelligence (AI) has emerged as a promising tool to support magnetic resonance imaging (MRI)-based diagnosis of PD, but its economic value has yet to be fully evaluated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The AI model used in this study analyzes susceptibility map-weighted MRI to detect nigrosome-1 signal loss (the \u201cswallow-tail sign\u201d), providing objective support for early PD identification. We conducted a patient-level cost\u2013benefit analysis (CBA) comparing current PET-based diagnostic pathways with an MRI-based AI triage strategy for PD. A total of 24 mutually exclusive diagnostic scenarios were modeled to capture variation in disease presence, AI accuracy, and PET access. The analysis was conducted from a societal perspective in South Korea and a healthcare system perspective in the United States, covering both short-term (1-year) and long-term (2025\u20132050) horizons. Sensitivity analyses and AI adoption rate scenarios (30, 65, 100%) were included.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In short-term analysis, AI-assisted diagnosis yielded net benefits of 9.3 million US dollars (USD) (South Korea) and 76.0 million USD (United States) under 30% adoption, which increased to 31.0 million USD and 253.2 million USD, respectively, under full AI adoption. Benefit\u2013cost (B\/C) ratios exceeded 1.4 in Korea and 1.3 in the U. S., and net benefit remained positive up to an AI unit cost of 226 USD in Korea and 1,506 USD in the U. S. The AI model also reduced PET use by over 31% through effective triage and enabled over 13,000 Korean PD patients to access PET who might otherwise have forgone it due to cost. Long-term projection (Korea only) indicated cumulative net savings of 2.5 billion USD by 2050 with gradually increasing AI adoption.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>MRI-based AI triage for PD diagnosis is a cost-beneficial strategy with the potential to reduce unnecessary imaging and expand access among underserved populations. Particularly in health systems with limited PET availability, this approach may offer scalable economic and clinical advantages over time.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2025.1723829","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:42:17Z","timestamp":1766040137000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Economic value of AI-based MRI triage for Parkinson\u2019s disease: a cost-benefit study in South Korea and the United States"],"prefix":"10.3389","volume":"13","author":[{"given":"KyungYi","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soohwa","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sung Sik","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong Hoon","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A-Leum","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1130","DOI":"10.1056\/NEJM199810153391607","article-title":"Parkinson's disease","volume":"339","author":"Lang","year":"1998","journal-title":"N Engl J Med"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s42466-024-00325-4","article-title":"Diagnosis and treatment of Parkinson\u00b4 s disease (guideline of the German Society for Neurology)","volume":"6","author":"H\u00f6glinger","year":"2024","journal-title":"Neurol Res Pract"},{"key":"ref3","volume-title":"Global atlas of medical devices 2022","year":"2022"},{"key":"ref4","first-page":"769","article-title":"Imaging of substantia nigra in Parkinson\u2019s disease: a narrative review","volume-title":"Brain Sci","author":"Feraco","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1425095","DOI":"10.3389\/fnagi.2024.1425095","article-title":"Classification of Parkinson\u2019s disease by deep learning on midbrain MRI","volume":"16","author":"Welton","year":"2024","journal-title":"Front Aging Neurosci"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"999","DOI":"10.3174\/ajnr.A8585","article-title":"Deep learning\u2013based algorithm for automatic quantification of Nigrosome-1 and parkinsonism classification using susceptibility map\u2013weighted MRI","volume":"46","author":"Suh","year":"2025","journal-title":"Am J Neuroradiol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1002\/jmri.25553","article-title":"Imaging of nigrosome 1 in substantia nigra at 3T using multiecho susceptibility map-weighted imaging (SMWI)","volume":"46","author":"Nam","year":"2017","journal-title":"J Magn Reson Imaging"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"3597","DOI":"10.1007\/s00330-021-08454-z","article-title":"A prospective multi-Centre study of susceptibility map-weighted MRI for the diagnosis of neurodegenerative parkinsonism","volume":"32","author":"Sung","year":"2022","journal-title":"Eur Radiol"},{"key":"ref9","volume-title":"FacialPulse: An efficient RNN-based depression detection via temporal facial landmarks. Proceedings of the 32nd ACM international conference on multimedia","author":"Wang","year":"2024"},{"key":"ref10","volume-title":"Learning from heterogeneity: Generalizing dynamic facial expression recognition via distributionally robust optimization. Proceedings of the 33rd ACM international conference on multimedia","author":"Cui","year":"2025"},{"key":"ref11","volume-title":"Consumer Price index by expenditure purpose","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1186\/s13244-021-01077-4","article-title":"Cost-effectiveness of artificial intelligence aided vessel occlusion detection in acute stroke: an early health technology assessment","volume":"12","author":"Van Leeuwen","year":"2021","journal-title":"Insights Imaging"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1570","DOI":"10.3390\/brainsci11121570","article-title":"Health economic impact of software-assisted brain MRI on therapeutic decision-making and outcomes of relapsing-remitting multiple sclerosis patients\u2014a microsimulation study","volume":"11","author":"Sima","year":"2021","journal-title":"Brain Sci"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3310\/RDPA1487","article-title":"Software with artificial intelligence-derived algorithms for analysing CT brain scans in people with a suspected acute stroke: a systematic review and cost-effectiveness analysis","volume":"28","author":"Westwood","year":"2024","journal-title":"Health Technol Assess"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1080\/0013791X.2017.1294718","article-title":"Evaluating the cost-effectiveness of an early detection of Parkinson's disease through innovative technology","volume":"62","author":"Munoz","year":"2017","journal-title":"Eng Econ"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"191","DOI":"10.17340\/jkna.2017.4.1","article-title":"The prevalence and incidence of Parkinson\u2032s disease in South Korea: a 10-year nationwide population\u2013based study","volume":"35","author":"Lee","year":"2017","journal-title":"J Korean Neurol Assoc"},{"key":"ref17","volume-title":"Future population projections key population indicators (sex ratio, population growth rate, population structure, dependency ratio, etc.) \/ Nationwide","year":"2023"},{"key":"ref18","year":"2025"},{"key":"ref19","article-title":"An open label, Multicenter, retrospective, pivotal trial to evaluate the efficacy of clinical decision support system-mPDia for neurodegenerative parkinsonism using MRI images","year":"2020"},{"key":"ref20","volume-title":"Evaluation of the clinical utility of 18F FP-CIT PET\/CT in patients with suspected Parkinson's disease and a comparative study of its effectiveness with existing diagnostic methods","author":"Park","year":"2016"},{"key":"ref21","article-title":"How much does a PET scan cost?","year":""},{"key":"ref22","volume-title":"Parkinson's disease patients increase by 15% in five years, with medical costs rising by 25.3%","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1038\/s41531-020-0117-1","article-title":"Current and projected future economic burden of Parkinson\u2019s disease in the US","volume":"6","author":"Yang","year":"2020","journal-title":"NPJ Parkinsons Dis"},{"key":"ref24","article-title":"The economic burden of Parkinson\u2019s disease: chart of the day","year":""},{"key":"ref25","volume-title":"Wages and working hours by age","year":"2025"},{"key":"ref26","volume-title":"2023 senior citizen statistics","year":"2023"},{"key":"ref27","volume-title":"The third Korea National Health and nutrition examination survey (KNHANES 3)","year":"2006"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1723829\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:42:26Z","timestamp":1766040146000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1723829\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":27,"alternative-id":["10.3389\/fpubh.2025.1723829"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1723829","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]},"article-number":"1723829"}}