1
|
Kassem K, Sperti M, Cavallo A, Vergani AM, Fassino D, Moz M, Liscio A, Banali R, Dahlweid M, Benetti L, Bruno F, Gallone G, De Filippo O, Iannaccone M, D'Ascenzo F, De Ferrari GM, Morbiducci U, Della Valle E, Deriu MA. An innovative artificial intelligence-based method to compress complex models into explainable, model-agnostic and reduced decision support systems with application to healthcare (NEAR). Artif Intell Med 2024; 151:102841. [PMID: 38658130 DOI: 10.1016/j.artmed.2024.102841] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2023] [Revised: 02/29/2024] [Accepted: 03/11/2024] [Indexed: 04/26/2024]
Abstract
BACKGROUND AND OBJECTIVE In everyday clinical practice, medical decision is currently based on clinical guidelines which are often static and rigid, and do not account for population variability, while individualized, patient-oriented decision and/or treatment are the paradigm change necessary to enter into the era of precision medicine. Most of the limitations of a guideline-based system could be overcome through the adoption of Clinical Decision Support Systems (CDSSs) based on Artificial Intelligence (AI) algorithms. However, the black-box nature of AI algorithms has hampered a large adoption of AI-based CDSSs in clinical practice. In this study, an innovative AI-based method to compress AI-based prediction models into explainable, model-agnostic, and reduced decision support systems (NEAR) with application to healthcare is presented and validated. METHODS NEAR is based on the Shapley Additive Explanations framework and can be applied to complex input models to obtain the contributions of each input feature to the output. Technically, the simplified NEAR models approximate contributions from input features using a custom library and merge them to determine the final output. Finally, NEAR estimates the confidence error associated with the single input feature contributing to the final score, making the result more interpretable. Here, NEAR is evaluated on a clinical real-world use case, the mortality prediction in patients who experienced Acute Coronary Syndrome (ACS), applying three different Machine Learning/Deep Learning models as implementation examples. RESULTS NEAR, when applied to the ACS use case, exhibits performances like the ones of the AI-based model from which it is derived, as in the case of the Adaptive Boosting classifier, whose Area Under the Curve is not statistically different from the NEAR one, even the model's simplification. Moreover, NEAR comes with intrinsic explainability and modularity, as it can be tested on the developed web application platform (https://neardashboard.pythonanywhere.com/). CONCLUSIONS An explainable and reliable CDSS tailored to single-patient analysis has been developed. The proposed AI-based system has the potential to be used alongside the clinical guidelines currently employed in the medical setting making them more personalized and dynamic and assisting doctors in taking their everyday clinical decisions.
Collapse
Affiliation(s)
- Karim Kassem
- Polito(BIO)Med Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Turin, Italy
| | - Michela Sperti
- Polito(BIO)Med Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Turin, Italy
| | - Andrea Cavallo
- SmartData@PoliTO Center for Big Data Technologies, Politecnico di Torino, Turin, Italy
| | - Andrea Mario Vergani
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Via Ponzio 34/5, 20133 Milan, Italy; Department of Mathematics, Politecnico di Milano, Via Bonardi 9, 20133 Milan, Italy; Health Data Science Centre, Human Technopole, Viale Rita Levi-Montalcini 1, 20157 Milan, Italy
| | - Davide Fassino
- Department of Mathematical Sciences, Politecnico di Torino, Turin, Italy
| | | | | | | | | | | | - Francesco Bruno
- Division of Cardiology, Cardiovascular and Thoracic Department, Città della Salute e della Scienza, Turin, Italy; Cardiology, Department of Medical Sciences, University of Turin, Turin, Italy
| | - Guglielmo Gallone
- Division of Cardiology, Cardiovascular and Thoracic Department, Città della Salute e della Scienza, Turin, Italy; Cardiology, Department of Medical Sciences, University of Turin, Turin, Italy
| | - Ovidio De Filippo
- Division of Cardiology, Cardiovascular and Thoracic Department, Città della Salute e della Scienza, Turin, Italy; Cardiology, Department of Medical Sciences, University of Turin, Turin, Italy
| | | | - Fabrizio D'Ascenzo
- Division of Cardiology, Cardiovascular and Thoracic Department, Città della Salute e della Scienza, Turin, Italy; Cardiology, Department of Medical Sciences, University of Turin, Turin, Italy
| | - Gaetano Maria De Ferrari
- Division of Cardiology, Cardiovascular and Thoracic Department, Città della Salute e della Scienza, Turin, Italy; Cardiology, Department of Medical Sciences, University of Turin, Turin, Italy
| | - Umberto Morbiducci
- Polito(BIO)Med Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Turin, Italy
| | - Emanuele Della Valle
- Department of Electronics, Information and Bioengineering (DEIB), Politecnico di Milano, Via Ponzio 34/5, 20133 Milan, Italy
| | - Marco Agostino Deriu
- Polito(BIO)Med Lab, Department of Mechanical and Aerospace Engineering, Politecnico di Torino, Turin, Italy.
| |
Collapse
|