# The Three Ghosts of Medical AI: Can the Black-Box Present Deliver?

arXiv: https://arxiv.org/abs/2012.06000 · HTML: https://mlsanity.com/paper/2012.06000/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 16 of 16)

- [Unbox the Black-box for the Medical Explainable AI via Multi-modal and Multi-centre Data Fusion: A Mini-Review, Two Showcases and Beyond](https://mlsanity.com/paper/2102.01998/) (2021)
- [A Review on Explainable Artificial Intelligence for Healthcare: Why, How, and When?](https://mlsanity.com/paper/2304.04780/) (2023)
- [Zodiac: A Cardiologist-Level LLM Framework for Multi-Agent Diagnostics](https://mlsanity.com/paper/2410.02026/) (2024)
- [SimSUM: Simulated Benchmark with Structured and Unstructured Medical Records](https://mlsanity.com/paper/2409.08936/) (2024)
- [CapillaryNet: An Automated System to Quantify Skin Capillary Density and Red Blood Cell Velocity from Handheld Vital Microscopy](https://mlsanity.com/paper/2104.11574/) (2021)
- [A Quantitatively Interpretable Model for Alzheimer's Disease Prediction Using Deep Counterfactuals](https://mlsanity.com/paper/2310.03457/) (2023)
- [Learning Generative Factors of EEG Data with Variational auto-encoders](https://mlsanity.com/paper/2206.01939/) (2022)
- [Transfer or Self-Supervised? Bridging the Performance Gap in Medical Imaging](https://mlsanity.com/paper/2407.05592/) (2024)
- [Trustworthy Tree-based Machine Learning by MoS2 Flash-based Analog CAM with Inherent Soft Boundaries](https://mlsanity.com/paper/2507.12384/) (2025)
- [Uncertainty-Aware Learning Policy for Reliable Pulmonary Nodule Detection on Chest X-Ray](https://mlsanity.com/paper/2508.13236/) (2025)
- [CLMN: Concept based Language Models via Neural Symbolic Reasoning](https://mlsanity.com/paper/2510.10063/) (2025)
- [Patient-level Information Extraction by Consistent Integration of Textual and Tabular Evidence with Bayesian Networks](https://mlsanity.com/paper/2511.17056/) (2025)
- [UniCoMTE: A Universal Counterfactual Framework for Explaining Time-Series Classifiers on ECG Data](https://mlsanity.com/paper/2512.17100/) (2025)
- [Medication counseling with large language models: balancing flexibility and rigidity](https://mlsanity.com/paper/2601.11544/) (2025)
- [Interpretable and backpropagation-free Green Learning for efficient multi-task echocardiographic segmentation and classification](https://mlsanity.com/paper/2601.19743/) (2026)
- [Prism-SQA: An Interpretable and Adaptable Neural Framework for Surface Electromyography Quality Assessment](https://mlsanity.com/paper/2609.12724/) (2026)

## 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.