CoChat
Sign Up
Cited by 18Artificial Intelligence in Healthcare and EducationExplainable Artificial Intelligence (XAI)Radiology practices and education

Invisible to Machines: Designing AI that Supports Vision Work in Radiology

Open access
Anichini, Giulia, Natali, Chiara, Cabitza, Federico·2024·Computer Supported Cooperative Work (CSCW)
DOI 10.1007/s10606-024-09491-0
Open this paper in CoChat — free accountOpen PDF

Abstract

In this article we provide an analysis focusing on clinical use of two deep learning-based automatic detection tools in the field of radiology. The value of these technologies conceived to assist the physicians in the reading of imaging data (like X-rays) is generally assessed by the human-machine performance comparison, which does not take into account the complexity of the interpretation process of radiologists in its social, tacit and emotional dimensions. In this radiological vision work, data which informs the physician about the context surrounding a visible anomaly are essential to the definition of its pathological nature. Likewise, experiential data resulting from the contextual tacit knowledge that regulates professional conduct allows for the assessment of an anomaly according to the radiologist’s, and patient’s, experience. These data, which remain excluded from artificial intelligence processing, question the gap between the norms incorporated by the machine and those leveraged in the daily work of radiologists. The possibility that automated detection may modify the incorporation or the exercise of tacit knowledge raises questions about the impact of AI technologies on medical work. This article aims to highlight how the standards that emerge from the observation practices of radiologists challenge the automation of their vision work, but also under what conditions AI technologies are considered “objective” and trustworthy by professionals.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s10606-024-09491-0

Cites

9 of 9 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • Radiological diagnosis is a distributed, collaborative process embedded in a professional infrastructure of routines, norms, and tacit expectations that shape both vision work and how expertise is recognised.

    “Radiological diagnosis is a distributed, collaborative process embedded in a professional infrastructure of routines, norms, and tacit expectations that shape both vision work (Anichini, Natali, and Cabitza 2024) and how expertise is recognised.”

    From From Oracles to Productive Friction: Designing for Meaningful Human Oversight in Clinical AI (2026) · cites this paper as Anichini, Natali, and Cabitza 2024

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 90

  1. Aanestad, M., B. Edwin, and R. Mårvik. 2003. Medical image quality as a socio-technical phenomenon. Methods of Information in Medicine 42 (04): 302-306.
  2. Alac, Morana. 2011. Handling digital brains: A laboratory study of multimodal semiotic interaction in the age of computers. MIT Press.
  3. Alby, Francesca, Cristina Zucchermaglio, and Mattia Baruzzo. 2015. Diagnostic decision making in oncology: Creating shared knowledge and managing complexity. Mind, Cul- ture, and Activity 22 (1): 4-22.
  4. Anichini, Giulia, and Bénédicte Geffroy. 2021. L'intelligence artificielle á l'épreuve des savoirs tacites. analyse des pratiques d'utilisation d'un outil d'aide à la détection en radiologie. Sciences Sociales et Santé 39 (2): 43-69.
  5. Assale, Michela, Silvia Bordogna, and Cabitza Federico. 2020. Vague visualizations to reduce quantification bias in shared medical decision making. In: VISIGRAPP 2020 - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 3: 209-216.
  6. Bardram, Jakob E., and Claus Bossen. 2005. A web of coordinative artifacts: collaborative work at a hospital ward. In: GROUP'05, 168-176. ACM.
  7. Bawden, David, and Lyn Robinson. 2020. Information overload: An overview. Oxford University Press.
  8. Beaulieu, Anne. 2001. Voxels in the brain: Neuroscience, informatics and changing notions of objectivity. Social Studies of Science 31 (5): 635-680.
  9. Berg, Marc. 1999. Accumulating and coordinating: Occasions for information technologies in medical work. Computer Supported Cooperative Work 8 (4): 373-401.
  10. Berg, Marc, and Els Goorman. 1999. The contextual nature of medical information. Inter- national Journal of Medical Informatics 56 (1-3): 51-60.
  11. Berlin, Leonard. 2014. Radiologic errors, past, present and future. Diagnosis 1 (1): 79-84.
  12. Blois, Marsden S. 1980. Clinical judgment and computers. New England Journal of Medicine 303 (4): 192-197.
  13. Bourret, Pascale. 2005. Brca patients and clinical collectives: New configurations of action in cancer genetics practices. Social Studies of Science 35 (1): 41-68.
  14. Bourret, Pascale, and Vololona Rabeharisoa. 2008. Décision et jugement médicaux en situation de forte incertitude: l'exemple de deux pratiques cliniques à l'épreuve de la génétique. Sciences Sociales et Santé 26 (1): 33-66.
  15. Bratteteig, Tone, and Ina Wagner. 2016. Unpacking the notion of participation in partici- patory design. Computer Supported Cooperative Work (CSCW) 25: 425-475.
  16. Cabitza, Federico, and Carla Simone. 2015. Building socially embedded technologies: Implications about design. In: Designing socially embedded technologies in the real- world, Wulf V., K. Schmidt, D. Randall (eds.). Springer, London. https://doi.org/10. 1007/978-1-4471-6720-4_11 · DOI
  17. Cabitza, Federico, and Jean-David Zeitoun. 2019. The proof of the pudding: In praise of a culture of real-world validation for medical artificial intelligence. Annals of Translational Medicine 7 (8): 161.
  18. Cabitza, Federico, Raffaele Rasoini, and Gian Franco Gensini. 2017. Unintended conse- quences of machine learning in medicine. Jama 318 (6): 517-518.
  19. Cabitza, Federico, Andrea Campagner, Davide Ciucci, and Andrea Seveso. 2019a. Pro- grammed inefficiencies in DSS-supported human decision making. In: Modeling Deci- sions for Artificial Intelligence: 16th International Conference, MDAI 2019, Milan, Italy, 4-6, September 2019, Proceedings 16, 201-212. Springer.
  20. Cabitza, Federico, Angela Locoro, Camilla Alderighi, Raffaele Rasoini, Domenico Com- pagnone, and Pedro Berjano. 2019b. The elephant in the record: On the multiplicity of data recording work. Health Informatics Journal 25 (3): 475-490.
  21. Cabitza F., A. Campagner, F. Del Zotti, A. Ravizza, and F. Sternini. 2020. All you need is higher accuracy? On the quest for minimum acceptable accuracy for medical artifi- cial intelligence. In: Proceedings of the e-Health Procedings of the 12th International Conference on e-Health, Online, 21-23.
  22. Cabitza, Federico, Andrea Campagner, Riccardo Angius, Chiara Natali, and Carlo Rever- beri. 2023a. Ai shall have no dominion: on how to measure technology dominance in ai-supported human decision-making. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems.
  23. Cabitza, Federico, Andrea Campagner, Lorenzo Famiglini, Chiara Natali, Valerio Cac- cavella, and Enrico Gallazzi. 2023b. Let me think! Investigating the effect of explana- tions feeding doubts about the ai advice. In: International Cross-Domain Conference for Machine Learning and Knowledge Extraction, 155-169. Springer.
  24. Cabitza, Federico, Chiara Natali, Lorenzo Famiglini, Andrea Campagner, Valerio Cac- cavella, and Enrico Gallazzi. (2024). Never tell me the odds: Investigating pro-hoc explanations in medical decision making. Artificial Intelligence in Medicine 150 (3): 102819. https://doi.org/10.1016/j.artmed.2024.102819 · DOI
  25. Cai, Carrie J., Samantha Winter, David Steiner, Lauren Wilcox, and Michael Terry. 2019. "Hello AI": uncovering the onboarding needs of medical practitioners for human-ai collaborative decision-making. Proceedings of the ACM on Human-computer Interaction 3 (CSCW): 1-24.
  26. Carlin, Leslie, Helen Smith, Flis Henwood, Steve Flowers, Andrea Jones, Rebecca Prentice, and Ken Miles. 2010. Double vision: an exploration of radiologists' and general prac- titioners' views on using picture archiving and communication systems (pacs). Health Informatics Journal 16 (2): 75-86.
  27. Christin, Angèle. 2020. The ethnographer and the algorithm: Beyond the black box. Theory and Society 49 (5-6): 897-918.
  28. Collins, Harry M. 1974. The tea set: Tacit knowledge and scientific networks. Science Studies 4 (2): 165-185.
  29. Collins, Harry M. 2001. Tacit knowledge, trust and the Q of sapphire. Social Studies of Science 31 (1): 71-85.
  30. Cooper, Alan. 1999. The Inmates are Running the Asylum. In: Arend, U.,E. Eberleh, and K. Pitschke (eds) Software-Ergonomie'99. Berichte des German Chapter of the ACM, 53. Vieweg+Teubner Verlag. https://doi.org/10.1007/978-3-322-99786-9_1 · DOI · Paper page
  31. Coopmans, Catelijne, Janet Vertesi, Michael E. Lynch, and Steve Woolgar. 2014. Repre- sentation in scientific practice revisited. MIT Press.
  32. Debono, Deborah S., David Greenfield, Joanne F. Travaglia, Janet C. Long, Deborah Black, Julie Johnson, and Jeffrey Braithwaite. 2013. Nurses' workarounds in acute healthcare settings: A scoping review. BMC Health Services Research 13 (1): 1-16.
  33. Dix, Alan. 2007. Designing for appropriation. In: Proceedings of HCI 2007 The 21st British HCI Group Annual Conference University of Lancaster, UK, 1-4. https://doi.org/10. 14236/ewic/HCI2007.53 · DOI · Paper page
  34. Dodier, Nicolas, and Janine Barbot. 2016. La force des dispositifs. In: Annales. Histoire, sciences sociales, 71: 421-448. Cambridge University Press.
  35. Frischmann, Brett, and Evan Selinger. 2018. Re-engineering humanity. Cambridge Uni- versity Press.
  36. Goodwin, Charles. 1994. Professional vision. American Anthropologist 96 (3): 606-633.
  37. Grasseni, Cristina. 2004. Skilled vision. An apprenticeship in breeding aesthetics. Social Anthropology 12 (1): 41-55.
  38. Hanseth, Ole, and Nina Lundberg. 2001. Designing work oriented infrastructures. Computer Supported Cooperative Work 10 (3-4): 347-372.
  39. Hartswood, Mark, Rob Procter, and Linda J. Williams. 1998. Prompting in practice: How can we ensure radiologists make best use of computer-aided detection systems in screening mammography? Digital Mammography: Nijmegen, 13: 363-370. Dordrecht: Springer.
  40. Hartswood, Mark, Rob Procter, Mark Rouncefield, and Roger Slack. 2003a. Making a case in medical work: Implications for the electronic medical record. Computer Supported Cooperative Work (CSCW) 12: 241-266.
  41. Hartswood, Mark, Rob Procter, Mark Rouncefield, Roger Slack, James Soutter, and Alex Voss. 2003b. 'repairing' the machine: A case study of the evaluation of computer-aided detection tools in breast screening. In: ECSCW 2003: Proceedings of the Eighth European Conference on Computer Supported Cooperative Work 14-18 2003, 375-394. Helsinki, Finland: Springer.
  42. Henderson, Kathryn. 1998. On line and on paper: Visual representations, visual culture, and computer graphics in design engineering. MIT press.
  43. Hullman, Jessica. 2019. Why authors don't visualize uncertainty. IEEE Transactions on Visualization and Computer Graphics 26 (1): 130-139.
  44. Joshi, Suhas Govind, and Tone Bratteteig. 2015. Assembling fragments into continuous design: On participatory design with old people. In: Scandinavian Conference on Infor- mation Systems, 13-29. Springer.
  45. Kitchin, Rob, and Alistair Fraser. 2020. Slow computing: Why we need balanced digital lives. Bristol University Press.
  46. Kohli-Laven, Nina, Pascale Bourret, Peter Keating, and Alberto Cambrosio. 2011. Cancer clinical trials in the era of genomic signatures: Biomedical innovation, clinical utility, and regulatory-scientific hybrids. Social Studies of Science 41 (4): 487-513.
  47. Latour, Bruno. 1986. Visualization and cognition. Knowledge and Society 6 (6): 1-40.
  48. Lincoln, Christie M, Ritodhi Chatterjee, and Marc H. Willis. 2019. Augmented radiology: Looking over the horizon, 1 (1): e180039 .
  49. Lu, Danni, Chenyang Tao, Junya Chen, Fan Li, Feng Guo, and Lawrence Carin. 2020. Reconsidering generative objectives for counterfactual reasoning. Advances in Neural Information Processing Systems 33: 21539-21553.
  50. Luff, Paul, Christian Heath, and David Greatbatch. 1992. Tasks-in-interaction: Paper and screen based documentation in collaborative activity. In: Proceedings of the 1992 ACM conference on Computer-supported cooperative work, 163-170.
  51. Lynch, Michael. 1985. Discipline and the material form of images: An analysis of scientific visibility. Social Studies of Science 15 (1): 37-66.
  52. Miller, R. A., and F. E. Masarie Jr. 1990. The demise of the greek oracle model for medical diagnostic systems. Methods of Information in Medicine 29 (01): 1-2.
  53. Natali, Chiara, Lorenzo Famiglini, Andrea Campagner, Giovanni Andrea, La Maida Enrico, Gallazzi and Federico Cabitza. 2023. Color shadows 2: Assessing the impact of xai on diagnostic decision-making. In: World Conference on Explainable Artificial Intelligence, 618-629. Springer.
  54. Nonaka, lkujiro, Takeuchi Hirotaka, and Umemoto Katsuhiro. 1996. A theory of organiza- tional knowledge creation. International Journal of Technology Management 11 (7-8): 833-845.
  55. Parmiggiani, Elena, Thomas Østerlie, and Petter Grytten Almklov. 2022. In the backrooms of data science. Journal of the Association for Information Systems 23 (1): 139-164.
  56. Perrotta, Manuela. 2013. The study of technoscientific imaging in sts. TECNOSCIENZA: Italian Journal of Science & Technology Studies 3(2): 163-176.
  57. Piras, Enrico Maria, and Alberto Zanutto. 2010. Prescriptions, x-rays and grocery lists. designing a personal health record to support (the invisible work of) health information management in the household. Computer Supported Cooperative Work (CSCW) 19: 585- 613.
  58. Prasad, Amit. 2005. Making images/making bodies: Visibilizing and disciplining through magnetic resonance imaging (mri). Science, Technology, & Human Values 30 (2): 291- 316.
  59. Putha, Preetham, Manoj Tadepalli, Bhargava Reddy, Tarun Raj, Justy Antony Chiramal, Shalini Govil, Namita Sinha, Manjunath KS, Sundeep Reddivari, Ammar Jagirdar, Pooja Rao, and Prashant Warier. 2018. Can artificial intelligence reliably report chest x-rays?: Radiologist validation of an algorithm trained on 2.3 million x-rays. arXiv:1807.07455 · arXiv
  60. Raymond, Jean, and Isabelle Trop. 2007. The practice of ethics in the era of evidence-based radiology. Radiology 244 (3): 643-649.
  61. Reyna, Matthew A., Elaine O. Nsoesie, and Gari D. Clifford. 2022. Rethinking algorithm performance metrics for artificial intelligence in diagnostic medicine. JAMA 328 (4): 329-330.
  62. Rodríguez-Ruiz, Alejandro, Elizabeth Krupinski, Jan Jurre Mordang, Kathy Schilling, Sylvia H. Heywang-Köbrunner, Ioannis Sechopoulos, and Ritse M. Mann. 2019. Detec- tion of breast cancer with mammography: Effect of an artificial intelligence support system. Radiology 290 (2): 305-314.
  63. Rouncefield M., M. Hartswood, R. Procter, R. Slack, and A. Voss. 2003. "Reparing" the machine: A case study of evaluating computer aided detection tools in breast screening. In: European Conference on Computer Supported Cooperative Work.
  64. Sambasivan, Nithya, and Rajesh Veeraraghavan. 2022. The deskilling of domain expertise in ai development. In: Proceedings of the 2022 CHI Conference on Human Factors in Computing Systems, 1-14.
  65. Sardanelli, Francesco, and Giovanni Di Leo. 2009. Biostatistics for radiologists: Planning, performing, and writing a radiologic study. Springer Science & Business Media.
  66. Saunders, Barry F. 2008. CT suite: The work of diagnosis in the age of noninvasive cutting. Duke University Press.
  67. Schmidt, Kjeld. 1991. Riding a tiger, or computer supported cooperative work. In: Pro- ceedings of the Second European Conference on Computer-Supported Cooperative Work ECSCW'91, 1-16. Springer.
  68. Schmidt, Kjeld. 2000. The critical role of workplace studies in CSCW. Cambridge Univer- sity Press Cambridge.
  69. Seaver, Nick. 2015. The nice thing about context is that everyone has it. Media, Culture & Society 37 (7): 1101-1109.
  70. Sendelbach, Sue, and Marjorie Funk. 2013. Alarm fatigue: a patient safety concern. AACN Advanced Critical Care 24 (4): 378-386.
  71. Shneiderman, Ben. 2021. Human-centered ai: A new synthesis. In: Human-Computer Interaction-INTERACT 2021: 18th IFIP TC 13 International Conference, Bari, Italy, August 30-September 3, 2021, Proceedings, Part I 18, Springer, 3-8.
  72. Shneiderman, Ben. 2022. Human-centered AI. Oxford University Press.
  73. Simone, Carla, and Kjeld Schmidt. 1993. Computational Mechanisms of Interaction for CSCW. Lancaster University.
  74. Simone, Carla, Angela Locoro, and Federico Cabitza. 2019. Drift of a corporate social media: The design and outcomes of a longitudinal study. In: Organizing for the Digital World, 189-201. Springer.
  75. Skitka, Linda J., Kathleen Mosier, and Mark D. Burdick. 2000. Accountability and automa- tion bias. International Journal of Human-Computer Studies 52 (4): 701-717.
  76. Slack, Roger, Mark Hartswood, Rob Procter, and Mark Rouncefield. 2016. Cultures of reading: On professional vision and the lived work of mammography. In: Orders of ordinary action, 175-193. Routledge.
  77. Star, Susan Leigh, and Anselm Strauss. 1999. Layers of silence, arenas of voice: The ecology of visible and invisible work. Computer Supported Cooperative Work (CSCW) 8: 9-30.
  78. Steen, Marc. 2013. Co-design as a process of joint inquiry and imagination. Design Issues 29 (2): 16-28.
  79. Sterponi, Laura, Cristina Zucchermaglio, Francesca Alby, and Marilena Fatigante. 2017. Endangered literacies? affordances of paper-based literacy in medical practice and its persistence in the transition to digital technology. Written Communication 34 (4): 359- 386.
  80. Suchman, Lucille Alice. 2007.Human-machine reconfigurations: Plans and situated actions. Cambridge University Press.
  81. Tellioglu, Hilda, and Wagner Ina. 2001. Work practices surrounding pacs: the politics of space in hospitals. Computer Supported Cooperative Work (CSCW) 10: 163-188.
  82. Turrini, Mauro, and Catherine Bourgain. 2021. Appraising screening, making risk in/visible. the medical debate over non-rare thrombophilia (nrt) testing before prescribing the pill. Sociology of Health & Illness 43(7): 1627-1642.
  83. van Leeuwen, Bart, Richard Gasaway, Gerke Spaling, and B.V. Netage. 2022. Adopting ai to support situational awareness in emergency response: a reflection by profession- als. In: Proceedings of the First International Conference on Hybrid Human-Artificial Intelligence. Frontiers in Artificial Intelligence and Applications, IOS Press.
  84. van Berkel, Niels, Mikael B. Skov, and Jesper Kjeldskov. 2021. Human-ai interaction: intermittent, continuous, and proactive. Interactions 28 (6): 67-71.
  85. Van den Broek, Elmira, Anastasia Sergeeva, and Marleen Huysman. 2021. When the machine meets the expert: An ethnography of developing ai for hiring. MIS Quarterly 45(3).
  86. Vodrahalli, Kailas, Tobias Gerstenberg, and James Zou. 2022. Uncalibrated models can improve human-ai collaboration. arXiv:2202.05983 · arXiv
  87. Weiser, Mark, and John Seely Brown. 1996. Designing calm technology. PowerGrid Jour- nal 1 (1): 75-85.
  88. Wenger, Etienne. 2009. Communities of practice: The key to knowledge strategy. In: Knowl- edge and communities, 3-20. Routledge.
  89. Winthereik, BritRoss, and Signe Vikkelsø. 2005. Ict and integrated care: some dilemmas of standardising inter-organisational communication. CSCW 14 (1): 43-67.
  90. Zenisek, Jan, Florian Holzinger, and Michael Affenzeller. 2019. Machine learning based concept drift detection for predictive maintenance. Computers & Industrial Engineering 137 (106): 031.

Cited by

Sorted by citations

Authors
Anichini, G., Natali, C., & Cabitza, F.
Affiliations
  • Centre National de la Recherche Scientifique (FR)
  • University of Milano-Bicocca (IT)
  • IRCCS Ospedale Galeazzi - Sant'Ambrogio (IT)
Corresponding author
Natali, Chiara
ORCID
Venue
Computer Supported Cooperative Work (CSCW)
Publisher
Springer Science and Business Media LLC
Published
2024-05-28
Volume
33
Issue
4
Pages
993-1036
ISSN
  • 0925-9724 (ISSN-L)
  • 1573-7551
DOI
10.1007/s10606-024-09491-0
OpenAlex
W4399092230
Cited by
18
References
9
Citations by year
2026: 9 · 2025: 8 · 2024: 1
FWCI
1.53
Type
journal article
Language
en
Open access
Licence
Locations
  • Computer Supported Cooperative Work (CSCW) (publishedVersion, cc-by)
  • BOA (University of Milano-Bicocca) (submittedVersion, cc-by)
Funders
Università degli Studi di Milano - Bicocca
Topics
  • Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Health Sciences › Medicine › Radiology, Nuclear Medicine and Imaging › Radiology practices and education
Keywords
artificial intelligence in radiology, deep learning, tacit knowledge, medical image interpretation, human-machine comparison, trust in AI, professional norms

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review