Hybrid intelligence decision making: successful human-AI integration in optical diagnosis

preprint OA: closed
Full text JSON View at publisher

Abstract

Artificial Intelligence (AI) systems are precious support for decision-making, with many applications in the medical domain. However, there is little understanding of how human experts interact with AI. Health policy-makers fear flat reliance on AI advice. In this multicentric study, twenty-one endoscopists reviewed 504 videos of lesions from real colonoscopies, with and without the assistance of an AI support system. Endoscopists were influenced by AI (OR = 3.05), but not erratically: they followed the AI advice more when it was correct (OR = 3.48) than incorrect (OR = 1.85). Endoscopists achieved this outcome through a weighted integration of their and the AI opinions, considering the case-by-case estimations of the two reliabilities. This Bayesian-like rational behavior allowed the human-AI hybrid team to outperform both agents taken alone. We discuss the features of the interaction that determined this favorable outcome.
Full text 15,199 characters · extracted from preprint-html · click to expand
Hybrid intelligence decision making: successful human-AI integration in optical diagnosis | 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 Article Hybrid intelligence decision making: successful human-AI integration in optical diagnosis Carlo Reverberi, Tommaso Rigon, Aldo Solari, Cesare Hassan, Paolo Cherubini, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-1439843/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Sep, 2022 Read the published version in Scientific Reports → Version 1 posted 8 You are reading this latest preprint version Abstract Artificial Intelligence (AI) systems are precious support for decision-making, with many applications in the medical domain. However, there is little understanding of how human experts interact with AI. Health policy-makers fear flat reliance on AI advice. In this multicentric study, twenty-one endoscopists reviewed 504 videos of lesions from real colonoscopies, with and without the assistance of an AI support system. Endoscopists were influenced by AI (OR = 3.05), but not erratically: they followed the AI advice more when it was correct (OR = 3.48) than incorrect (OR = 1.85). Endoscopists achieved this outcome through a weighted integration of their and the AI opinions, considering the case-by-case estimations of the two reliabilities. This Bayesian-like rational behavior allowed the human-AI hybrid team to outperform both agents taken alone. We discuss the features of the interaction that determined this favorable outcome. Full Text Additional Declarations Competing interest reported. Andrea Cherubini is an employee of Cosmo AI/Linkverse. Carlo Reverberi is offering paid advice to Linkverse on a different project. The remaining authors have no conflicts of interest to disclose. Funding: this study was sponsored by Cosmo AI/Linkverse. Supplementary Files HAIappendix.pdf exampleadenoma.mp4 examplenonadenoma.mp4 examplenoprediction.mp4 Cite Share Download PDF Status: Published Journal Publication published 01 Sep, 2022 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Major revision 28 Jun, 2022 Reviews received at journal 27 Jun, 2022 Reviewers agreed at journal 17 Jun, 2022 Reviewers agreed at journal 17 Jun, 2022 Reviewers agreed at journal 15 Jun, 2022 Reviewers invited by journal 15 Jun, 2022 Submission checks completed at journal 14 Jun, 2022 First submitted to journal 27 May, 2022 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-1439843","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":109309800,"identity":"34393657-5c4e-4394-bbba-1c1bd2370bdb","order_by":0,"name":"Carlo Reverberi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYHACxgNQBhsQS8gBBRoYEhsYePDpQdFiDNeCTw+yFpBiBrAunNbwt599cOADwz05g+O9zx583GORvuF2c+uGhzsYZOxxaJE4k25wcAZDsbHBmePmhjOeSeRuuHOw7UbiGdwOM2BIYzjMw5CQOHNGGps0zwGglhuJQC1teLTwPwNrqZ85/xmb9J8DEukGBLVIQGxJ4JdgY5NmOCCRQFCLxI1nDAdnGCQY9vOksRv2HJAwnAnWckaCh+cAjhDrT2N88KEiQZ6N/Rjbgx8H6uT5bqQ/u/lzh409ewMOa6CBgGk9PvWjYBSMglEwCggAAACGWXyk1uH4AAAAAElFTkSuQmCC","orcid":"","institution":"University of Milano-Bicocca","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Carlo","middleName":"","lastName":"Reverberi","suffix":""},{"id":109309801,"identity":"e3b051c6-9025-49a7-935b-a0cd24b3cd22","order_by":1,"name":"Tommaso Rigon","email":"","orcid":"","institution":"University of Milano-Bicocca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tommaso","middleName":"","lastName":"Rigon","suffix":""},{"id":109309802,"identity":"38f89c93-cdfd-4b9c-88c5-133d56db50f6","order_by":2,"name":"Aldo Solari","email":"","orcid":"","institution":"University of Milano-Bicocca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Aldo","middleName":"","lastName":"Solari","suffix":""},{"id":109309803,"identity":"c5fbb94f-639e-400c-ac73-31a30a8c86e8","order_by":3,"name":"Cesare Hassan","email":"","orcid":"","institution":"IRCCS Humanitas Research Hospital","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Cesare","middleName":"","lastName":"Hassan","suffix":""},{"id":109309804,"identity":"1226c707-15f6-44a8-bf15-6bd936db3814","order_by":4,"name":"Paolo Cherubini","email":"","orcid":"","institution":"University of Milano-Bicocca","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Paolo","middleName":"","lastName":"Cherubini","suffix":""},{"id":109309805,"identity":"7d9cdc1f-44f3-4aec-bc6e-26ced35bfe79","order_by":5,"name":"Andrea Cherubini","email":"","orcid":"","institution":"Cosmo AI/Linkverse","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Andrea","middleName":"","lastName":"Cherubini","suffix":""}],"badges":[],"createdAt":"2022-03-10 21:29:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-1439843/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-1439843/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-022-18751-2","type":"published","date":"2022-09-02T00:00:00+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":26187830,"identity":"93fe7569-486e-4a8a-aa3f-08fa0f44b2a0","added_by":"auto","created_at":"2022-09-07 16:47:28","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1112132,"visible":true,"origin":"","legend":"","description":"","filename":"HAImanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1439843/v1_covered.pdf"},{"id":22139082,"identity":"be0b11ae-dc98-4bf3-b35a-dc582c2f133b","added_by":"auto","created_at":"2022-06-01 16:26:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1106942,"visible":true,"origin":"","legend":"","description":"","filename":"HAImanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1439843/v1_covered.pdf"},{"id":22139043,"identity":"56c78c59-61d5-49bd-a35b-7e90a59409d1","added_by":"auto","created_at":"2022-06-01 16:26:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":495304,"visible":true,"origin":"","legend":"","description":"","filename":"HAIappendix.pdf","url":"https://assets-eu.researchsquare.com/files/rs-1439843/v1/c1e049b998299df751733a42.pdf"},{"id":22139044,"identity":"ea661cde-c480-4782-a9bc-63f38583015b","added_by":"auto","created_at":"2022-06-01 16:26:18","extension":"mp4","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":17140715,"visible":true,"origin":"","legend":"","description":"","filename":"exampleadenoma.mp4","url":"https://assets-eu.researchsquare.com/files/rs-1439843/v1/d56ca742ef045c733993b773.mp4"},{"id":22139045,"identity":"5f456326-858e-484f-9544-df3cd949587d","added_by":"auto","created_at":"2022-06-01 16:26:18","extension":"mp4","order_by":3,"title":"","display":"","copyAsset":false,"role":"supplement","size":19350125,"visible":true,"origin":"","legend":"","description":"","filename":"examplenonadenoma.mp4","url":"https://assets-eu.researchsquare.com/files/rs-1439843/v1/98364a4bd2e33189a143d1db.mp4"},{"id":22139046,"identity":"150d4fc3-f355-4c0d-a486-315f4930ec98","added_by":"auto","created_at":"2022-06-01 16:26:19","extension":"mp4","order_by":4,"title":"","display":"","copyAsset":false,"role":"supplement","size":20982374,"visible":true,"origin":"","legend":"","description":"","filename":"examplenoprediction.mp4","url":"https://assets-eu.researchsquare.com/files/rs-1439843/v1/34a2a3c6d22816e5ba672125.mp4"}],"financialInterests":"Competing interest reported. Andrea Cherubini is an employee of Cosmo AI/Linkverse. Carlo Reverberi is offering paid advice to Linkverse on a different project. The remaining authors have no conflicts of interest to disclose. Funding: this study was sponsored by Cosmo AI/Linkverse.","formattedTitle":"Hybrid intelligence decision making: successful human-AI integration in optical diagnosis","fulltext":[{"header":"Full Text","content":"This preprint is available for \u003ca href='/article/rs-1439843/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e."}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-1439843/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-1439843/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Artificial Intelligence (AI) systems are precious support for decision-making, with many applications in the medical domain. However, there is little understanding of how human experts interact with AI. Health policy-makers fear flat reliance on AI advice. In this multicentric study, twenty-one endoscopists reviewed 504 videos of lesions from real colonoscopies, with and without the assistance of an AI support system. Endoscopists were influenced by AI (OR = 3.05), but not erratically: they followed the AI advice more when it was correct (OR = 3.48) than incorrect (OR = 1.85). Endoscopists achieved this outcome through a weighted integration of their and the AI opinions, considering the case-by-case estimations of the two reliabilities. This Bayesian-like rational behavior allowed the human-AI hybrid team to outperform both agents taken alone. We discuss the features of the interaction that determined this favorable outcome.","manuscriptTitle":"Hybrid intelligence decision making: successful human-AI integration in optical diagnosis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2022-06-01 16:26:16","doi":"10.21203/rs.3.rs-1439843/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revision","date":"2022-06-28T05:00:54+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2022-06-27T15:17:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"3b29b334-966e-4441-91d1-bd1ff1bb46b6","date":"2022-06-17T21:56:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"b7ea0eb7-ab3e-402a-afa7-ecb39d855f05","date":"2022-06-17T13:50:38+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"fb3f3fc7-8095-4263-868a-156f49c018ef","date":"2022-06-15T17:04:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2022-06-15T14:05:26+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2022-06-14T13:53:11+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2022-05-27T15:34:20+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"cd1f00f3-6b73-43a4-bf6b-8819f78b65b3","owner":[],"postedDate":"June 1st, 2022","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2022-09-07T16:47:15+00:00","versionOfRecord":{"articleIdentity":"rs-1439843","link":"https://doi.org/10.1038/s41598-022-18751-2","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2022-09-02 00:00:00","publishedOnDateReadable":"September 2nd, 2022"},"versionCreatedAt":"2022-06-01 16:26:16","video":"","vorDoi":"10.1038/s41598-022-18751-2","vorDoiUrl":"https://doi.org/10.1038/s41598-022-18751-2","workflowStages":[]},"version":"v1","identity":"rs-1439843","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-1439843","identity":"rs-1439843","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. The paper's references may be in our DB but unresolved to ``paper_id`` (resolution happens at ingest when the cited DOI matches a row we already have). Run the cross-source citation reconcile pass to retry.

Source provenance

europepmc
last seen: 2026-05-19T01:45:01.086888+00:00