The Three Ghosts of Medical AI: Can the Black-Box Present Deliver?
Not on the map. Why?
Abstract (arXiv)
Our title alludes to the three Christmas ghosts encountered by Ebenezer Scrooge in textitA Christmas Carol, who guide Ebenezer through the past, present, and future of Christmas holiday events. Similarly, our article will take readers through a journey of the past, present, and future of medical AI. In doing so, we focus on the crux of modern machine learning: the reliance on powerful but intrinsically opaque models. When applied to the healthcare domain, these models fail to meet the needs for transparency that their clinician and patient end-users require. We review the implications of this failure, and argue that opaque models (1) lack quality assurance, (2) fail to elicit trust, and (3) restrict physician-patient dialogue. We then discuss how upholding transparency in all aspects of model design and model validation can help ensure the reliability of medical AI.
Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 1; 2023: 2; 2024: 3; 2025: 6; 2026: 2.
16 papers.
Sort:
By area:
- 2021Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyondcited by 75
- 2023A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?cited by 24
- 2024Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnosticscited by 11
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Recordscited by 6
- 2021CapillaryNet: An Automated System to Quantify Skin Capillary Density and Red Blood Cell Velocity from Handheld Vital Microscopycited by 2
- 2023A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactualscited by 1
- 2022Learning Generative Factors of EEG Data with Variational auto-encoderscited by 0
- 2024Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imagingcited by 0
- 2025Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundariescited by 0
- 2025Uncertainty-Aware Learning Policy for Reliable Pulmonary Nodule Detection on Chest X-Raycited by 0
- 2025CLMN: Concept based Language Models via Neural Symbolic Reasoningcited by 0
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networkscited by 0
4 more
- 2025UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Datacited by 0
- 2025Medication counseling with large language models: balancing flexibility and rigiditycited by 0
- 2026Interpretable and backpropagation-free Green Learning for efficient multi-task echocardiographic segmentation and classificationcited by 0
- 2026Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessmentcited by 0
- 2026Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment11 Sep 2026
- 2026Interpretable and backpropagation-free Green Learning for efficient multi-task echocardiographic segmentation and classification27 Jan 2026
- 2025UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data18 Dec 2025
- 2025Medication counseling with large language models: balancing flexibility and rigidity2 Dec 2025
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks21 Nov 2025
- 2025CLMN: Concept based Language Models via Neural Symbolic Reasoning11 Oct 2025
- 2025Uncertainty-Aware Learning Policy for Reliable Pulmonary Nodule Detection on Chest X-Ray18 Aug 2025
- 2025Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundaries16 Jul 2025
- 2024Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics2 Oct 2024
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records13 Sep 2024
- 2024Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imaging8 Jul 2024
- 2023A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactuals5 Oct 2023
4 more
- 2023A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?10 Apr 2023
- 2022Learning Generative Factors of EEG Data with Variational auto-encoders4 Jun 2022
- 2021CapillaryNet: An Automated System to Quantify Skin Capillary Density and Red Blood Cell Velocity from Handheld Vital Microscopy23 Apr 2021
- 2021Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond3 Feb 2021
- 2021Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyondcited by 75
- 2023A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?cited by 24
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Recordscited by 6
- 2021CapillaryNet: An Automated System to Quantify Skin Capillary Density and Red Blood Cell Velocity from Handheld Vital Microscopycited by 2
- 2023A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactualscited by 1
- 2022Learning Generative Factors of EEG Data with Variational auto-encoderscited by 0
- 2024Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imagingcited by 0
- 2025Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundariescited by 0
- 2025Uncertainty-Aware Learning Policy for Reliable Pulmonary Nodule Detection on Chest X-Raycited by 0
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networkscited by 0
- 2025UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Datacited by 0
- 2025Medication counseling with large language models: balancing flexibility and rigiditycited by 0
12 most cited of 14 All 14 (JSON)
- 2026Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment11 Sep 2026
- 2026Interpretable and backpropagation-free Green Learning for efficient multi-task echocardiographic segmentation and classification27 Jan 2026
- 2025UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data18 Dec 2025
- 2025Medication counseling with large language models: balancing flexibility and rigidity2 Dec 2025
- 2025Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks21 Nov 2025
- 2025Uncertainty-Aware Learning Policy for Reliable Pulmonary Nodule Detection on Chest X-Ray18 Aug 2025
- 2025Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundaries16 Jul 2025
- 2024SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records13 Sep 2024
- 2024Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imaging8 Jul 2024
- 2023A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactuals5 Oct 2023
- 2023A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?10 Apr 2023
- 2022Learning Generative Factors of EEG Data with Variational auto-encoders4 Jun 2022
12 newest of 14 All 14 (JSON)