Model Medicine: A Clinical Framework for Understanding, Diagnosing, and Treating AI Models

Jihoon Jeong

cs.AIMar 5, 2026

Model Medicine: A Clinical Framework for Understanding, Diagnosing, and Treating AI Models

Authors: Jihoon Jeong

Organizations: Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology (DGIST) · ModuLabs

Abstract

Model Medicine is the science of understanding, diagnosing, treating, and preventing disorders in AI models, grounded in the principle that AI models -- like biological organisms -- have internal structures, dynamic processes, heritable traits, observable symptoms, classifiable conditions, and treatable states. This paper introduces Model Medicine as a research program, bridging the gap between current AI interpretability research (anatomical observation) and the systematic clinical practice that complex AI systems increasingly require. We present five contributions: (1) a discipline taxonomy organizing 15 subdisciplines across four divisions -- Basic Model Sciences, Clinical Model Sciences, Model Public Health, and Model Architectural Medicine; (2) the Four Shell Model (v3.3), a behavioral genetics framework empirically grounded in 720 agents and 24,923 decisions from the Agora-12 program, explaining how model behavior emerges from Core--Shell interaction; (3) Neural MRI (Model Resonance Imaging), a working open-source diagnostic tool mapping five medical neuroimaging modalities to AI interpretability techniques, validated through four clinical cases demonstrating imaging, comparison, localization, and predictive capability; (4) a five-layer diagnostic framework for comprehensive model assessment; and (5) clinical model sciences including the Model Temperament Index for behavioral profiling, Model Semiology for symptom description, and M-CARE for standardized case reporting. We additionally propose the Layered Core Hypothesis -- a biologically-inspired three-layer parameter architecture -- and a therapeutic framework connecting diagnosis to treatment.

Figures & tables

Medical Modality	Neural MRI Mode	Full Name	What It Reveals
T1-weighted MRI	T1	Topology Layer 1	Static architecture—layer structure, attention head organization, parameter count distribution
T2-weighted MRI	T2	Tensor Layer 2	Weight distribution—parameter statistics, norm patterns, potential dead neurons or saturated regions
Functional MRI	fMRI	functional Model Resonance Imaging	Activation patterns during inference—which layers and heads activate for specific inputs
DTI	DTI	Data Tractography Imaging	Information flow pathways—how information propagates through the model from input to output
FLAIR	FLAIR	Feature-Level Anomaly Identification & Reporting	Anomaly detection—representation collapse, entropy spikes, attention pattern irregularities, embedding drift

Table 1: Neural MRI modality mapping between medical neuroimaging and AI model interpretability techniques.

Figure 1: Gemma-2-2B five-modality Neural MRI scan. All modalities show normal findings for a well-trained 2B-parameter model on factual recall.

Figure 2: Comparative anatomy: fMRI activation profiles and DTI circuit maps for three architectures across three task types. Each architecture exhibits a distinctive processing signature.

Figure 3: Self-referential stress testing of Gemma-2-2B. Perturbation sensitivity heatmap and dual causal trace comparison.

Figure 4: Three patterns of instruction tuning effect on perturbation vulnerability across three model families.

Figure 5: Irreducible architectural vulnerabilities persisting across instruction tuning. These represent congenital architectural bottlenecks, not acquired conditions.

Figure 6: Vulnerability–dominance correspondence across three architectures. The components that carry the most information are both the most important and the most dangerous to disrupt—analogous to how coronary arteries are simultaneously the heart’s critical blood supply and its most common point of fatal failure.

Figure 7: Synthesis: the progressive argument from observation to prediction. Four cases build cumulative diagnostic capability, mirroring the historical arc of medical imaging.

Explainable Artificial Intelligence

Explainable artificial intelligence develops ways to make AI decisions understandable, testable, and useful to people.

See all 326 papers

Medical Model Synthesis Architectures: A Case Study
May 10, 2026Katherine M. Collins, Marlene Berke, Ilia Sucholutsky +6Explainable Artificial Intelligence Healthcare
MIT · University of Cambridge · Princeton University +8
M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation
Mar 27, 2026Jihoon JeongAI Agent Evaluation AI Safety Evaluation
Department of Electrical Engineering and Computer Science, Daegu Gyeongbuk Institute of Science and Technology (DGIST) · ModuLabs
Modelpedia: A Catalog of Model Findings for the Meta-Science of AI
Sep 1, 2026Franciszek Bernat, Dawid Płudowski, Michał Jan Włodarczyk +6
Centre for Credible AI · Warsaw University of Technology · University College Cork +9

May 10, 2026J/K move · Enter open · S save

Medical Model Synthesis Architectures: A Case Study

Katherine M. Collins, Marlene Berke, Ilia Sucholutsky, Ayman Ali+5

MIT · University of Cambridge · Princeton University+8

Explainable Artificial Intelligence Healthcare Medical Diagnosis Clinical Reasoning Differential Diagnosis Uncertainty Calibration

Open paper AskPDF arXiv

Medicine is rife with high-stakes uncertainty. Doctors routinely make clinical judgments and decisions that juggle many fundamental unknowns, like predictions about what might be causing a patients' symptoms or decisions about what treatment to try next. Despite increasing interest in developing AI systems that aid or even replace doctors in clinical settings, current systems struggle with calibrated reasoning under uncertainty, and are often deeply opaque about their reasoning. We propose a framework for AI systems that can make practically useful but formally transparent clinical predictions under uncertainty. Given a clinical situation, our framework (MedMSA) uses language models to retrieve relevant prior knowledge, but constructs a formal probabilistic model to support calibrated and verifiable inferences under uncertainty. We show how an initial proof-of-concept of this framework can be used for differential diagnosis, producing an uncertainty-weighted list of potential diagnoses that could explain a patients' symptoms, and discuss future applications and directions for applying this framework more generally for safe clinical collaborations.

Abstract

Explainable Artificial Intelligence

Explore similar work

Medical Model Synthesis Architectures: A Case Study

M-CARE: Standardized Clinical Case Reporting for AI Model Behavioral Disorders, with a 20-Case Atlas and Experimental Validation

Modelpedia: A Catalog of Model Findings for the Meta-Science of AI