From Prediction to Action: A Structured Scoping Review and Framework Synthesis of Integrative AI Decision Systems

From Prediction to Action: A Structured Scoping Review and Framework Synthesis of Integrative AI Decision Systems | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article From Prediction to Action: A Structured Scoping Review and Framework Synthesis of Integrative AI Decision Systems Dominika Zak This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9684818/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Artificial intelligence, machine learning, and big data analytics are increasingly used in settings where predictions influence clinical, financial, operational, and public decisions. In these settings, the central issue is not whether a model can produce a score, but whether the score can be translated into reliable action under real-world constraints. A structured scoping technical review and framework synthesis was conducted in 2026. Searches covered PubMed/MEDLINE, PubMed Central, IEEE Xplore, ACM Digital Library, Google Scholar, and targeted publisher websites for literature published from 2018 through 2026. Search terms combined artificial intelligence, machine learning, clinical decision support, model validation, calibration, dataset shift, fairness, explainability, MLOps, workflow integration, value-based care, fraud detection, traffic prediction, smart infrastructure, predictive maintenance, and operational decision support. Records were screened for deployment relevance, methodological detail, and applicability to high-stakes decision systems. The search and citation process identified 112 candidate records. After duplicate removal, 78 records were screened by title and abstract, 34 full texts were assessed, and 23 studies or guidance documents were included in the final synthesis. The evidence mapped consistently to six linked components of AI deployment: data integration, engineering pipelines, learning, validation, serving and workflow, and value capture. Governance was identified as a cross-cutting requirement because privacy, interpretability, fairness, accountability, documentation, monitoring, and human oversight affected every stage of the system. The review develops the Integrative AI Decision Systems (IADS) framework as the main research output. Healthcare is used as the primary application domain because AI outputs may affect diagnosis, triage, utilization management, care coordination, patient safety, and value-based care performance. Finance, smart infrastructure, and industry are used as comparative sectors because they reveal similar deployment problems involving drift, class imbalance, adversarial behavior, real-time reliability, transferability, and cost-sensitive decisions. AI creates durable value only when predictive performance is connected to validated workflows, monitoring, and accountable decision processes. Health Economics and Outcomes Research Decision Sciences Artificial Intelligence and Machine Learning Health Policy artificial intelligence machine learning big data analytics decision systems healthcare analytics value-based care model validation MLOps dataset shift high-stakes AI Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9684818","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":638607286,"identity":"e8a4b02d-96ba-433a-a4be-ba98c8346ccb","order_by":0,"name":"Dominika Zak","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvElEQVRIiWNgGAWjYDCCAwzMDB9sgIwbYC4zcVoYZ6SRqoWZhyQtfOcPPza2SbDJ57vd/HQDQ4V1YgMhLZIHjhkn5ySkWc68c8zsBsOZdMJaDA42GB/O/XHYwOBGgtkNxrbDRGg5zP75sEUCSEv6txuM/4jRcozHOJkBrCUHaEsDEVokz/AUG/YkpBlI3sgpu5FwLN2YoBa+88c3S/xIsDHgu5G+7caHGmtZglpQQQJpykfBKBgFo2AU4AIAwa5Fy8YP4iIAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0008-2224-0730","institution":"Fordham University","correspondingAuthor":true,"prefix":"","firstName":"Dominika","middleName":"","lastName":"Zak","suffix":""}],"badges":[],"createdAt":"2026-05-12 00:50:33","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9684818/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9684818/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109139983,"identity":"b491ef6d-de77-4d38-ad50-29d1ec40a627","added_by":"auto","created_at":"2026-05-13 02:19:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":822143,"visible":true,"origin":"","legend":"","description":"","filename":"integrativeaidecisionsystemsFinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9684818/v1_covered_3c589fc6-8e36-413d-811b-fe16cfab5112.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eFrom Prediction to Action: A Structured Scoping Review and Framework Synthesis of Integrative AI Decision Systems\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Fordham University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"artificial intelligence, machine learning, big data analytics, decision systems, healthcare analytics, value-based care, model validation, MLOps, dataset shift, high-stakes AI","lastPublishedDoi":"10.21203/rs.3.rs-9684818/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9684818/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eArtificial intelligence, machine learning, and big data analytics are increasingly used in settings where predictions influence clinical, financial, operational, and public decisions. In these settings, the central issue is not whether a model can produce a score, but whether the score can be translated into reliable action under real-world constraints. A structured scoping technical review and framework synthesis was conducted in 2026. Searches covered PubMed/MEDLINE, PubMed Central, IEEE Xplore, ACM Digital Library, Google Scholar, and targeted publisher websites for literature published from 2018 through 2026. Search terms combined artificial intelligence, machine learning, clinical decision support, model validation, calibration, dataset shift, fairness, explainability, MLOps, workflow integration, value-based care, fraud detection, traffic prediction, smart infrastructure, predictive maintenance, and operational decision support. Records were screened for deployment relevance, methodological detail, and applicability to high-stakes decision systems. The search and citation process identified 112 candidate records. After duplicate removal, 78 records were screened by title and abstract, 34 full texts were assessed, and 23 studies or guidance documents were included in the final synthesis. The evidence mapped consistently to six linked components of AI deployment: data integration, engineering pipelines, learning, validation, serving and workflow, and value capture. Governance was identified as a cross-cutting requirement because privacy, interpretability, fairness, accountability, documentation, monitoring, and human oversight affected every stage of the system. The review develops the Integrative AI Decision Systems (IADS) framework as the main research output. Healthcare is used as the primary application domain because AI outputs may affect diagnosis, triage, utilization management, care coordination, patient safety, and value-based care performance. Finance, smart infrastructure, and industry are used as comparative sectors because they reveal similar deployment problems involving drift, class imbalance, adversarial behavior, real-time reliability, transferability, and cost-sensitive decisions. AI creates durable value only when predictive performance is connected to validated workflows, monitoring, and accountable decision processes.\u003c/p\u003e","manuscriptTitle":"From Prediction to Action: A Structured Scoping Review and Framework Synthesis of Integrative AI Decision Systems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-13 02:19:19","doi":"10.21203/rs.3.rs-9684818/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8b01fed8-1281-4120-b225-c8d533a6e055","owner":[],"postedDate":"May 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":67965506,"name":"Health Economics and Outcomes Research"},{"id":67965507,"name":"Decision Sciences"},{"id":67965508,"name":"Artificial Intelligence and Machine Learning"},{"id":67965509,"name":"Health Policy"}],"tags":[],"updatedAt":"2026-05-13T02:19:19+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-13 02:19:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9684818","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9684818","identity":"rs-9684818","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}