: We investigated whether human preferences hold the potential to improve diagnostic artificial intelligence (AI)-based decision support using skin cancer diagnosis as a use case. We utilized nonuniform rewards and penalties based on expert-generated tables, balancing the benefits and harms of various diagnostic errors, which were applied using reinforcement learning. Compared with supervised learning, the reinforcement learning model improved the sensitivity for melanoma from 61.4% to 79.5% (95% confidence interval (CI): 73.5-85.6%) and for basal cell carcinoma from 79.4% to 87.1% (95% CI: 80.3-93.9%). AI overconfidence was also reduced while simultaneously maintaining accuracy. Reinforcement learning increased the rate of correct diagnoses made by dermatologists by 12.0% (95% CI: 8.8-15.1%) and improved the rate of optimal management decisions from 57.4% to 65.3% (95% CI: 61.7-68.9%). We further demonstrated that the reward-adjusted reinforcement learning model and a threshold-based model outperformed naïve supervised learning in various clinical scenarios. Our findings suggest the potential for incorporating human preferences into image-based diagnostic algorithms.

A reinforcement learning model for AI-based decision support in skin cancer / Barata, Catarina; Rotemberg, Veronica; Codella, Noel C F; Tschandl, Philipp; Rinner, Christoph; Akay, Bengu Nisa; Apalla, Zoe; Argenziano, Giuseppe; Halpern, Allan; Lallas, Aimilios; Longo, Caterina; Malvehy, Josep; Puig, Susana; Rosendahl, Cliff; Soyer, H Peter; Zalaudek, Iris; Kittler, Harald. - In: NATURE MEDICINE. - ISSN 1078-8956. - 29:8(2023), pp. 1941-1946. [10.1038/s41591-023-02475-5]

A reinforcement learning model for AI-based decision support in skin cancer

Longo, Caterina;
2023

Abstract

: We investigated whether human preferences hold the potential to improve diagnostic artificial intelligence (AI)-based decision support using skin cancer diagnosis as a use case. We utilized nonuniform rewards and penalties based on expert-generated tables, balancing the benefits and harms of various diagnostic errors, which were applied using reinforcement learning. Compared with supervised learning, the reinforcement learning model improved the sensitivity for melanoma from 61.4% to 79.5% (95% confidence interval (CI): 73.5-85.6%) and for basal cell carcinoma from 79.4% to 87.1% (95% CI: 80.3-93.9%). AI overconfidence was also reduced while simultaneously maintaining accuracy. Reinforcement learning increased the rate of correct diagnoses made by dermatologists by 12.0% (95% CI: 8.8-15.1%) and improved the rate of optimal management decisions from 57.4% to 65.3% (95% CI: 61.7-68.9%). We further demonstrated that the reward-adjusted reinforcement learning model and a threshold-based model outperformed naïve supervised learning in various clinical scenarios. Our findings suggest the potential for incorporating human preferences into image-based diagnostic algorithms.
2023
29
8
1941
1946
A reinforcement learning model for AI-based decision support in skin cancer / Barata, Catarina; Rotemberg, Veronica; Codella, Noel C F; Tschandl, Philipp; Rinner, Christoph; Akay, Bengu Nisa; Apalla, Zoe; Argenziano, Giuseppe; Halpern, Allan; Lallas, Aimilios; Longo, Caterina; Malvehy, Josep; Puig, Susana; Rosendahl, Cliff; Soyer, H Peter; Zalaudek, Iris; Kittler, Harald. - In: NATURE MEDICINE. - ISSN 1078-8956. - 29:8(2023), pp. 1941-1946. [10.1038/s41591-023-02475-5]
Barata, Catarina; Rotemberg, Veronica; Codella, Noel C F; Tschandl, Philipp; Rinner, Christoph; Akay, Bengu Nisa; Apalla, Zoe; Argenziano, Giuseppe; Halpern, Allan; Lallas, Aimilios; Longo, Caterina; Malvehy, Josep; Puig, Susana; Rosendahl, Cliff; Soyer, H Peter; Zalaudek, Iris; Kittler, Harald
File in questo prodotto:
File Dimensione Formato  
s41591-023-02475-5.pdf

Open access

Tipologia: Versione pubblicata dall'editore
Dimensione 8.55 MB
Formato Adobe PDF
8.55 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Licenza Creative Commons
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11380/1312655
Citazioni
  • ???jsp.display-item.citation.pmc??? 1
  • Scopus 15
  • ???jsp.display-item.citation.isi??? 12
social impact