Evaluating Explainable Machine Learning Models for Clinicians
Uloženo v:
| Vydáno v: | Cognitive Computation vol. 16, no. 4 (Jul 2024), p. 1436 |
|---|---|
| Hlavní autor: | |
| Další autoři: | , , , , , , , |
| Vydáno: |
Springer Nature B.V.
|
| Témata: | |
| On-line přístup: | Citation/Abstract Full Text Full Text - PDF |
| Tagy: |
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
MARC
| LEADER | 00000nab a2200000uu 4500 | ||
|---|---|---|---|
| 001 | 3076132393 | ||
| 003 | UK-CbPIL | ||
| 022 | |a 1866-9956 | ||
| 022 | |a 1866-9964 | ||
| 024 | 7 | |a 10.1007/s12559-024-10297-x |2 doi | |
| 035 | |a 3076132393 | ||
| 045 | 2 | |b d20240701 |b d20240731 | |
| 100 | 1 | |a Scarpato, Noemi |u San Raffaele Roma Open University, Rome, Italy (GRID:grid.466134.2) (ISNI:0000 0004 4912 5648); Interinstitutional Multidisciplinary Biobank (BioBIM), IRCCS San Raffaele Roma, Rome, Italy (GRID:grid.18887.3e) (ISNI:0000000417581884) | |
| 245 | 1 | |a Evaluating Explainable Machine Learning Models for Clinicians | |
| 260 | |b Springer Nature B.V. |c Jul 2024 | ||
| 513 | |a Journal Article | ||
| 520 | 3 | |a Gaining clinicians’ trust will unleash the full potential of artificial intelligence (AI) in medicine, and explaining AI decisions is seen as the way to build trustworthy systems. However, explainable artificial intelligence (XAI) methods in medicine often lack a proper evaluation. In this paper, we present our evaluation methodology for XAI methods using forward simulatability. We define the Forward Simulatability Score (FSS) and analyze its limitations in the context of clinical predictors. Then, we applied FSS to our XAI approach defined over an ML-RO, a machine learning clinical predictor based on random optimization over a multiple kernel support vector machine (SVM) algorithm. To Compare FSS values before and after the explanation phase, we test our evaluation methodology for XAI methods on three clinical datasets, namely breast cancer, VTE, and migraine. The ML-RO system is a good model on which to test our XAI evaluation strategy based on the FSS. Indeed, ML-RO outperforms two other base models—a decision tree (DT) and a plain SVM—in the three datasets and gives the possibility of defining different XAI models: TOPK, MIGF, and F4G. The FSS evaluation score suggests that the explanation method F4G for the ML-RO is the most effective in two datasets out of the three tested, and it shows the limits of the learned model for one dataset. Our study aims to introduce a standard practice for evaluating XAI methods in medicine. By establishing a rigorous evaluation framework, we seek to provide healthcare professionals with reliable tools for assessing the performance of XAI methods to enhance the adoption of AI systems in clinical practice. | |
| 653 | |a Machine learning | ||
| 653 | |a Simulation | ||
| 653 | |a Datasets | ||
| 653 | |a Artificial intelligence | ||
| 653 | |a Clinical medicine | ||
| 653 | |a Support vector machines | ||
| 653 | |a Decision making | ||
| 653 | |a Effectiveness | ||
| 653 | |a Causality | ||
| 653 | |a Algorithms | ||
| 653 | |a Migraine | ||
| 653 | |a Performance evaluation | ||
| 653 | |a Kernel functions | ||
| 653 | |a Explainable artificial intelligence | ||
| 653 | |a Decision trees | ||
| 700 | 1 | |a Nourbakhsh, Aria |u University of Rome Tor Vergata, Department of Enterprise Engineering, Rome, Italy (GRID:grid.6530.0) (ISNI:0000 0001 2300 0941) | |
| 700 | 1 | |a Ferroni, Patrizia |u San Raffaele Roma Open University, Rome, Italy (GRID:grid.466134.2) (ISNI:0000 0004 4912 5648); Interinstitutional Multidisciplinary Biobank (BioBIM), IRCCS San Raffaele Roma, Rome, Italy (GRID:grid.18887.3e) (ISNI:0000000417581884) | |
| 700 | 1 | |a Riondino, Silvia |u University of Rome Tor Vergata, Department of Systems Medicine, Rome, Italy (GRID:grid.6530.0) (ISNI:0000 0001 2300 0941) | |
| 700 | 1 | |a Roselli, Mario |u University of Rome Tor Vergata, Department of Systems Medicine, Rome, Italy (GRID:grid.6530.0) (ISNI:0000 0001 2300 0941) | |
| 700 | 1 | |a Fallucchi, Francesca |u Guglielmo Marconi University, Rome, Italy (GRID:grid.440899.8) (ISNI:0000 0004 1780 761X) | |
| 700 | 1 | |a Barbanti, Piero |u San Raffaele Roma Open University, Rome, Italy (GRID:grid.466134.2) (ISNI:0000 0004 4912 5648); IRCCS San Raffaele Roma, Headache and Pain Unit, Rome, Italy (GRID:grid.18887.3e) (ISNI:0000000417581884) | |
| 700 | 1 | |a Guadagni, Fiorella |u San Raffaele Roma Open University, Rome, Italy (GRID:grid.466134.2) (ISNI:0000 0004 4912 5648); Interinstitutional Multidisciplinary Biobank (BioBIM), IRCCS San Raffaele Roma, Rome, Italy (GRID:grid.18887.3e) (ISNI:0000000417581884) | |
| 700 | 1 | |a Zanzotto, Fabio Massimo |u University of Rome Tor Vergata, Department of Enterprise Engineering, Rome, Italy (GRID:grid.6530.0) (ISNI:0000 0001 2300 0941) | |
| 773 | 0 | |t Cognitive Computation |g vol. 16, no. 4 (Jul 2024), p. 1436 | |
| 786 | 0 | |d ProQuest |t Computer Science Database | |
| 856 | 4 | 1 | |3 Citation/Abstract |u https://www.proquest.com/docview/3076132393/abstract/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text |u https://www.proquest.com/docview/3076132393/fulltext/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |
| 856 | 4 | 0 | |3 Full Text - PDF |u https://www.proquest.com/docview/3076132393/fulltextPDF/embedded/7BTGNMKEMPT1V9Z2?source=fedsrch |