Purpose The integration of Artificial Intelligence into medical practices has recently been advocated for the promise to bring increased efficiency and effectiveness to these practices. Nonetheless, little research has so far been aimed at understanding the best human-AI interaction protocols in collaborative tasks, even in currently more viable settings, like independent double-reading screening tasks. Methods To this aim, we report about a retrospective case-control study, involving 12 board-certified radiologists, in the detection of knee lesions by means of Magnetic Resonance Imaging, in which we simulated the serial combination of two Deep Learning models with humans in eight double-reading protocols. Inspired by the so-called Kasparov's Laws, we investigate whether the combination of humans and AI models could achieve better performance than AI models alone, and whether weak reader, when supported by fit-for-use interaction protocols, could out-perform stronger readers. Results We discuss two main findings: groups of humans who perform significantly worse than a state-of-the-art AI can significantly outperform it if their judgements are aggregated by majority voting (in concordance with the first part of the Kasparov's law); small ensembles of significantly weaker readers can significantly outperform teams of stronger readers, supported by the same computational tool, when the judgments of the former ones are combined within "fit-for-use" protocols (in concordance with the second part of the Kasparov's law). Conclusion Our study shows that good interaction protocols can guarantee improved decision performance that easily surpasses the performance of individual agents, even of realistic super-human AI systems. This finding highlights the importance of focusing on how to guarantee better co-operation within human-AI teams, so to enable safer and more human sustainable care practices.

Studying human-AI collaboration protocols: the case of the Kasparov's law in radiological double reading / F. Cabitza, A. Campagner, L.M. Sconfienza. - In: HEALTH INFORMATION SCIENCE AND SYSTEMS. - ISSN 2047-2501. - 9:1(2021). [10.1007/s13755-021-00138-8]

Studying human-AI collaboration protocols: the case of the Kasparov's law in radiological double reading

L.M. Sconfienza
Ultimo
2021

Abstract

Purpose The integration of Artificial Intelligence into medical practices has recently been advocated for the promise to bring increased efficiency and effectiveness to these practices. Nonetheless, little research has so far been aimed at understanding the best human-AI interaction protocols in collaborative tasks, even in currently more viable settings, like independent double-reading screening tasks. Methods To this aim, we report about a retrospective case-control study, involving 12 board-certified radiologists, in the detection of knee lesions by means of Magnetic Resonance Imaging, in which we simulated the serial combination of two Deep Learning models with humans in eight double-reading protocols. Inspired by the so-called Kasparov's Laws, we investigate whether the combination of humans and AI models could achieve better performance than AI models alone, and whether weak reader, when supported by fit-for-use interaction protocols, could out-perform stronger readers. Results We discuss two main findings: groups of humans who perform significantly worse than a state-of-the-art AI can significantly outperform it if their judgements are aggregated by majority voting (in concordance with the first part of the Kasparov's law); small ensembles of significantly weaker readers can significantly outperform teams of stronger readers, supported by the same computational tool, when the judgments of the former ones are combined within "fit-for-use" protocols (in concordance with the second part of the Kasparov's law). Conclusion Our study shows that good interaction protocols can guarantee improved decision performance that easily surpasses the performance of individual agents, even of realistic super-human AI systems. This finding highlights the importance of focusing on how to guarantee better co-operation within human-AI teams, so to enable safer and more human sustainable care practices.
Collective intelligence; Double reading; Hybrid intelligence; Interaction protocols; Kasparov’s Law
Settore MED/36 - Diagnostica per Immagini e Radioterapia
5-feb-2021
Article (author)
File in questo prodotto:
File Dimensione Formato  
Cabitza2021_Article_StudyingHuman-AICollaborationP.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 3.26 MB
Formato Adobe PDF
3.26 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/815130
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 4
  • ???jsp.display-item.citation.isi??? 5
social impact