1
|
Newman-Toker DE, Sharfstein JM. The Role for Policy in AI-Assisted Medical Diagnosis. JAMA HEALTH FORUM 2024; 5:e241339. [PMID: 38635262 DOI: 10.1001/jamahealthforum.2024.1339] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/19/2024] Open
Abstract
This JAMA Forum discusses the promise and pitfalls of using large language models and artificial intelligence (AI) in the diagnosis of patients.
Collapse
Affiliation(s)
- David E Newman-Toker
- Armstrong Institute Center for Diagnostic Excellence, School of Medicine, Johns Hopkins University, Baltimore, Maryland
| | - Joshua M Sharfstein
- Bloomberg School of Public Health, Johns Hopkins University, Baltimore, Maryland
| |
Collapse
|
2
|
Foltz EA, Witkowski A, Becker AL, Latour E, Lim JY, Hamilton A, Ludzik J. Artificial Intelligence Applied to Non-Invasive Imaging Modalities in Identification of Nonmelanoma Skin Cancer: A Systematic Review. Cancers (Basel) 2024; 16:629. [PMID: 38339380 PMCID: PMC10854803 DOI: 10.3390/cancers16030629] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Revised: 01/28/2024] [Accepted: 01/29/2024] [Indexed: 02/12/2024] Open
Abstract
BACKGROUND The objective of this study is to systematically analyze the current state of the literature regarding novel artificial intelligence (AI) machine learning models utilized in non-invasive imaging for the early detection of nonmelanoma skin cancers. Furthermore, we aimed to assess their potential clinical relevance by evaluating the accuracy, sensitivity, and specificity of each algorithm and assessing for the risk of bias. METHODS Two reviewers screened the MEDLINE, Cochrane, PubMed, and Embase databases for peer-reviewed studies that focused on AI-based skin cancer classification involving nonmelanoma skin cancers and were published between 2018 and 2023. The search terms included skin neoplasms, nonmelanoma, basal-cell carcinoma, squamous-cell carcinoma, diagnostic techniques and procedures, artificial intelligence, algorithms, computer systems, dermoscopy, reflectance confocal microscopy, and optical coherence tomography. Based on the search results, only studies that directly answered the review objectives were included and the efficacy measures for each were recorded. A QUADAS-2 risk assessment for bias in included studies was then conducted. RESULTS A total of 44 studies were included in our review; 40 utilizing dermoscopy, 3 using reflectance confocal microscopy (RCM), and 1 for hyperspectral epidermal imaging (HEI). The average accuracy of AI algorithms applied to all imaging modalities combined was 86.80%, with the same average for dermoscopy. Only one of the three studies applying AI to RCM measured accuracy, with a result of 87%. Accuracy was not measured in regard to AI based HEI interpretation. CONCLUSION AI algorithms exhibited an overall favorable performance in the diagnosis of nonmelanoma skin cancer via noninvasive imaging techniques. Ultimately, further research is needed to isolate pooled diagnostic accuracy for nonmelanoma skin cancers as many testing datasets also include melanoma and other pigmented lesions.
Collapse
Affiliation(s)
- Emilie A. Foltz
- Department of Dermatology, Oregon Health & Science University, Portland, OR 97201, USA
- Elson S. Floyd College of Medicine, Washington State University, Spokane, WA 99202, USA
| | - Alexander Witkowski
- Department of Dermatology, Oregon Health & Science University, Portland, OR 97201, USA
| | - Alyssa L. Becker
- Department of Dermatology, Oregon Health & Science University, Portland, OR 97201, USA
- John A. Burns School of Medicine, University of Hawai’i at Manoa, Honolulu, HI 96813, USA
| | - Emile Latour
- Biostatistics Shared Resource, Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97201, USA
| | - Jeong Youn Lim
- Biostatistics Shared Resource, Knight Cancer Institute, Oregon Health & Science University, Portland, OR 97201, USA
| | - Andrew Hamilton
- Department of Dermatology, Oregon Health & Science University, Portland, OR 97201, USA
| | - Joanna Ludzik
- Department of Dermatology, Oregon Health & Science University, Portland, OR 97201, USA
| |
Collapse
|
3
|
Ongaro L, Rossin G, Biasatti A, Pacini M, Rizzo M, Traunero F, Piasentin A, Perotti A, Trombetta C, Bartoletti R, Zucchi A, Simonato A, Pavan N, Liguori G, Claps F. Fluorescence Confocal Microscopy in Urological Malignancies: Current Applications and Future Perspectives. Life (Basel) 2023; 13:2301. [PMID: 38137902 PMCID: PMC10744992 DOI: 10.3390/life13122301] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2023] [Revised: 11/29/2023] [Accepted: 12/03/2023] [Indexed: 12/24/2023] Open
Abstract
Fluorescence confocal microscopy (FCM) represents a novel diagnostic technique able to provide real-time histological images from non-fixed specimens. As a consequence of its recent developments, FCM is gaining growing popularity in urological practice. Nevertheless, evidence is still sparse, and, at the moment, its applications are heterogeneous. We performed a narrative review of the current literature on this topic. Papers were selected from the Pubmed, Embase, and Medline archives. We focused on FCM applications in prostate cancer (PCa), urothelial carcinoma (UC), and renal cell carcinoma (RCC). Articles investigating both office and intraoperative settings were included. The review of the literature showed that FCM displays promising accuracy as compared to conventional histopathology. These results represent significant steps along the path of FCM's formal validation as an innovative ready-to-use diagnostic support in urological practice. Instant access to a reliable histological evaluation may indeed significantly influence physicians' decision-making process. In this regard, FCM addresses this still unmet clinical need and introduces intriguing perspectives into future diagnostic pathways. Further studies are required to thoroughly assess the whole potential of this technique.
Collapse
Affiliation(s)
- Luca Ongaro
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Giulio Rossin
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Arianna Biasatti
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Matteo Pacini
- Urology Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (A.P.); (R.B.); (A.Z.)
| | - Michele Rizzo
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Fabio Traunero
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Andrea Piasentin
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Alessandro Perotti
- Urology Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (A.P.); (R.B.); (A.Z.)
| | - Carlo Trombetta
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Riccardo Bartoletti
- Urology Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (A.P.); (R.B.); (A.Z.)
| | - Alessandro Zucchi
- Urology Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (A.P.); (R.B.); (A.Z.)
| | - Alchiede Simonato
- Urology Clinic, Department of Surgical, Oncological and Stomatological Sciences, University of Palermo, 90127 Palermo, Italy; (A.S.); (N.P.)
| | - Nicola Pavan
- Urology Clinic, Department of Surgical, Oncological and Stomatological Sciences, University of Palermo, 90127 Palermo, Italy; (A.S.); (N.P.)
| | - Giovanni Liguori
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
| | - Francesco Claps
- Urological Clinic, Department of Medicine, Surgery and Health Sciences, University of Trieste, 34149 Trieste, Italy; (L.O.); (G.R.); (A.B.); (M.R.); (F.T.); (A.P.); (C.T.); (G.L.)
- Urology Unit, Department of Translational Research and New Technologies in Medicine and Surgery, University of Pisa, 56126 Pisa, Italy; (M.P.); (A.P.); (R.B.); (A.Z.)
| |
Collapse
|