1
|
Salihu A, Meier D, Noirclerc N, Skalidis I, Mauler-Wittwer S, Recordon F, Kirsch M, Roguelov C, Berger A, Sun X, Abbe E, Marcucci C, Rancati V, Rosner L, Scala E, Rotzinger DC, Humbert M, Muller O, Lu H, Fournier S. A study of ChatGPT in facilitating Heart Team decisions on severe aortic stenosis. EUROINTERVENTION 2024; 20:e496-e503. [PMID: 38629422 PMCID: PMC11017225 DOI: 10.4244/eij-d-23-00643] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Accepted: 02/01/2024] [Indexed: 04/19/2024]
Abstract
BACKGROUND Multidisciplinary Heart Teams (HTs) play a central role in the management of valvular heart diseases. However, the comprehensive evaluation of patients' data can be hindered by logistical challenges, which in turn may affect the care they receive. AIMS This study aimed to explore the ability of artificial intelligence (AI), particularly large language models (LLMs), to improve clinical decision-making and enhance the efficiency of HTs. METHODS Data from patients with severe aortic stenosis presented at HT meetings were retrospectively analysed. A standardised multiple-choice questionnaire, with 14 key variables, was processed by the OpenAI Chat Generative Pre-trained Transformer (GPT)-4. AI-generated decisions were then compared to those made by the HT. RESULTS This study included 150 patients, with ChatGPT agreeing with the HT's decisions 77% of the time. The agreement rate varied depending on treatment modality: 90% for transcatheter valve implantation, 65% for surgical valve replacement, and 65% for medical treatment. CONCLUSIONS The use of LLMs offers promising opportunities to improve the HT decision-making process. This study showed that ChatGPT's decisions were consistent with those of the HT in a large proportion of cases. This technology could serve as a failsafe, highlighting potential areas of discrepancy when its decisions diverge from those of the HT. Further research is necessary to solidify our understanding of how AI can be integrated to enhance the decision-making processes of HTs.
Collapse
Affiliation(s)
- Adil Salihu
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - David Meier
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Nathalie Noirclerc
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Ioannis Skalidis
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Sarah Mauler-Wittwer
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Frederique Recordon
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Matthias Kirsch
- Department of Cardiovascular Surgery, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Christan Roguelov
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Alexandre Berger
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Xiaowu Sun
- Institute of Mathematics and School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland
| | - Emmanuel Abbe
- Institute of Mathematics and School of Computer and Communication Sciences, EPFL, Lausanne, Switzerland
| | - Carlo Marcucci
- Department of Anesthesiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Valentina Rancati
- Department of Anesthesiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Lorenzo Rosner
- Department of Anesthesiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Emanuelle Scala
- Department of Anesthesiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - David C Rotzinger
- Department of Radiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Marc Humbert
- Department of Geriatrics, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Olivier Muller
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| | - Henri Lu
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
- Division of Cardiovascular Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA
| | - Stephane Fournier
- Department of Cardiology, Lausanne University Hospital, University of Lausanne, Lausanne, Switzerland
| |
Collapse
|
2
|
Maurizi N, Skalidis I, Auberson D, Mahendiran T, Fournier S, Abbe E, Muller O. [Can smart devices and AI in cardiology improve clinical practice?]. Rev Med Suisse 2023; 19:1041-1046. [PMID: 37222645 DOI: 10.53738/revmed.2023.19.828.1041] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Subscribe] [Scholar Register] [Indexed: 05/25/2023]
Abstract
Remote monitoring is becoming increasingly popular among healthcare professionals and patients for diagnosing and treating heart disease. Several smart devices connected to smartphones have been developed and validated in recent years, but their clinical use is still limited. Significant advances in the field of artificial intelligence (AI) are also revolutionizing several fields, yet the impact that these innovations could have on routine clinical practice is still unknown. We review the evidence and uses of the main smart devices currently available as well as the latest applications of AI in the field of cardiology, with the aim to ultimately evaluate the potential of this technology to transform modern clinical practice.
Collapse
Affiliation(s)
- Niccolo Maurizi
- Service de cardiologie, Centre hospitalier universitaire vaudois, 1011 Lausanne
| | - Ioannis Skalidis
- Service de cardiologie, Centre hospitalier universitaire vaudois, 1011 Lausanne
| | - Denise Auberson
- Service de cardiologie, Centre hospitalier universitaire vaudois, 1011 Lausanne
| | - Thabo Mahendiran
- Service de cardiologie, Centre hospitalier universitaire vaudois, 1011 Lausanne
- Laboratoire Mathematical Data Science, École polytechnique fédérale de Lausanne, 1015 Lausanne
| | - Stephane Fournier
- Service de cardiologie, Centre hospitalier universitaire vaudois, 1011 Lausanne
| | - Emmanuel Abbe
- Laboratoire Mathematical Data Science et LTS4, École polytechnique fédérale de Lausanne, 1015 Lausanne
| | - Olivier Muller
- Service de cardiologie, Centre hospitalier universitaire vaudois, 1011 Lausanne
| |
Collapse
|
3
|
Skalidis I, Cagnina A, Luangphiphat W, Mahendiran T, Muller O, Abbe E, Fournier S. ChatGPT takes on the European Exam in Core Cardiology: an artificial intelligence success story? Eur Heart J Digit Health 2023; 4:279-281. [PMID: 37265864 PMCID: PMC10232281 DOI: 10.1093/ehjdh/ztad029] [Citation(s) in RCA: 20] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/18/2023] [Revised: 04/12/2023] [Accepted: 04/21/2023] [Indexed: 06/03/2023]
Abstract
Chat Generative Pre-trained Transformer (ChatGPT) is currently a trending topic worldwide triggering extensive debate about its predictive power, its potential uses, and its wider implications. Recent publications have demonstrated that ChatGPT can correctly answer questions from undergraduate exams such as the United States Medical Licensing Examination. We challenged it to answer questions from a more demanding, post-graduate exam-the European Exam in Core Cardiology (EECC), the final exam for the completion of specialty training in Cardiology in many countries. Our results demonstrate that ChatGPT succeeds in the EECC.
Collapse
Affiliation(s)
- Ioannis Skalidis
- Cardiology Department, University Hospital of Lausanne, Rue du Bugnon 46, 1011 Lausanne, Switzerland
| | - Aurelien Cagnina
- Cardiology Department, University Hospital of Lausanne, Rue du Bugnon 46, 1011 Lausanne, Switzerland
| | - Wongsakorn Luangphiphat
- Cardiology Department, University Hospital of Lausanne, Rue du Bugnon 46, 1011 Lausanne, Switzerland
| | - Thabo Mahendiran
- Cardiology Department, University Hospital of Lausanne, Rue du Bugnon 46, 1011 Lausanne, Switzerland
- Institute of Mathematics and School of Computer and Communication Sciences, EPFL, EPFL FSB SMA, Station 8,1015 Lausanne, Switzerland
| | - Olivier Muller
- Cardiology Department, University Hospital of Lausanne, Rue du Bugnon 46, 1011 Lausanne, Switzerland
| | - Emmanuel Abbe
- Institute of Mathematics and School of Computer and Communication Sciences, EPFL, EPFL FSB SMA, Station 8,1015 Lausanne, Switzerland
| | | |
Collapse
|
6
|
Abstract
Recovering low-rank structures via eigenvector perturbation analysis is a common problem in statistical machine learning, such as in factor analysis, community detection, ranking, matrix completion, among others. While a large variety of bounds are available for average errors between empirical and population statistics of eigenvectors, few results are tight for entrywise analyses, which are critical for a number of problems such as community detection. This paper investigates entrywise behaviors of eigenvectors for a large class of random matrices whose expectations are low-rank, which helps settle the conjecture in Abbe et al. (2014b) that the spectral algorithm achieves exact recovery in the stochastic block model without any trimming or cleaning steps. The key is a first-order approximation of eigenvectors under the ℓ ∞ norm:u k ≈ A u k * λ k * , where {u k } and{ u k * } are eigenvectors of a random matrix A and its expectation E A , respectively. The fact that the approximation is both tight and linear in A facilitates sharp comparisons between u k andu k * . In particular, it allows for comparing the signs of u k andu k * even if‖ u k - u k * ‖ ∞ is large. The results are further extended to perturbations of eigenspaces, yielding new ℓ ∞-type bounds for synchronization (ℤ 2 -spiked Wigner model) and noisy matrix completion.
Collapse
Affiliation(s)
- Emmanuel Abbe
- PACM and Department of EE, Princeton University, Princeton, NJ 08544, USA
| | - Jianqing Fan
- Department of ORFE, Princeton University, Princeton, NJ 08544, USA
| | - Kaizheng Wang
- Department of ORFE, Princeton University, Princeton, NJ 08544, USA
| | - Yiqiao Zhong
- Department of ORFE, Princeton University, Princeton, NJ 08544, USA
| |
Collapse
|
8
|
Abbe E, Pereira JM, Singer A. Sample Complexity of the Boolean Multireference Alignment Problem. Proc IEEE Int Symp Info Theory 2018; 2017:1316-1320. [PMID: 29755834 DOI: 10.1109/isit.2017.8006742] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
The Boolean multireference alignment problem consists in recovering a Boolean signal from multiple shifted and noisy observations. In this paper we obtain an expression for the error exponent of the maximum A posteriori decoder. This expression is used to characterize the number of measurements needed for signal recovery in the low SNR regime, in terms of higher order autocorrelations of the signal. The characterization is explicit for various signal dimensions, such as prime and even dimensions.
Collapse
|