Dat Tat Mai, Thai Viet Pham, Thu Nguyen Thi Dang +1eess.IV cs.CV
Objective: Deep learning accelerates brain MRI four- to tenfold, but models can erase lesions or synthesize false tissue - failures pixel-averaged metrics like PSNR and SSIM miss. We review whether current evaluation practices detect this blind spot. Methods: Following PRISMA 2020, we searched seven databases without date limits, including 263 studies (1995-2026), appraised them using QUADAS-2 and matched instruments, and synthesized narratively. Categories were derived from titles, abstracts, and controlled vocabulary; reported prevalence figures represent floors. Duplicate screening achieved high agreement (Fleiss kappa = 0.877), as did appraisal (0.788; 0.390 where observable). Extraction is unaudited. Results: Only 18 of 263 studies (6.8%) recorded both a fidelity metric and reader assessment on identical data, leaving the central surrogate unmeasured. Reader studies mostly measured inter-reader agreement, which was weak: fastMRI 2020 concordance reached 0.457 and 0.386 (Kendall W), improving only where SSIM diverged. Erasing a 100 mm3 lacunar infarct shifts global PSNR by 0.03 dB under the stated error model. As the corpus grew fivefold, reader assessments dropped from 32% to 18%, recovering to 21%. Generative models - most associated with hallucination (39%) - were among the least reader-evaluated (11.3%), while self-supervised models reached 47% with zero reader evaluation. Only 5% released code and ran reader studies; none evaluated a model observer; no named dataset covered acute stroke or hemorrhage. Conclusions: On these floors, current evaluation practices cannot certify diagnostic safety. We derive five requirements safety-oriented evaluations must meet.
Patient-facing medical LLMs and agents increasingly answer symptom questions before clinician contact, where the key safety question is what action the user should take next. We introduce CARE-Bench, a source-grounded benchmark that evaluates sequential patient-facing triage as a four-label per-turn current-action task. CARE-Bench contains 500 cases and 1,059 evaluated patient-disclosure prefixes reconstructed from medical dialogue, consultation, and follow-up-question sources. We evaluate 11 models on 269 held-out rounds under unprompted and minimally prompted open-ended protocols, using a fixed GPT-5.5 mapper to code each response into the four-label action space. Unprompted macro-F1 remains low, ranging from 31.2 to 50.4. Prompting improves 10 of 11 models, with prompted macro-F1 ranging from 46.9 to 63.4, but substantial threshold errors remain. Prompted models often recommend care before needed clarification is obtained; when the correct action was to ask for more information, only 33.5% of prompted outputs preserved the step. The persistence of these errors after prompting suggests that patient-facing triage is not a simple prompting problem and supports explicit evaluation of action timing before deployment.
Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks. We extend it to open-ended clinical conversation under missing information, where safe behavior means recognizing absent information and qualifying, clarifying, or not over-committing - and where the evaluator becomes part of the measurement. We stress-test four models - three flagships (Claude Opus 4.8, GPT-5.5, Grok 4.3) and one mid-tier model (Gemini 3.5 Flash) - by deleting the latter half of the final user turn in HealthBench conversations, grading responses with a four-provider LLM-judge panel and a blinded clinician-anchored reference. Two evaluator-facing results are robust. First, judge choice materially changes apparent safety: inter-judge agreement is only moderate (Fleiss' kappa = 0.65), and after adjusting for each judge's general leniency (vote-level logistic regression), a positive same-provider association remains (exact permutation p = 0.04; GPT-5.5 ~ +0.10 on the probability scale) - large enough to change which model appears to over-commit least once its own-provider judge is excluded. Second, LLM judges are more permissive than clinicians on a blinded 50-item subsample: all four are significantly more lenient than the stricter independent clinician (crediting appropriate uncertainty on 66-84% of items vs 52%), and three of four than the author-influenced consensus (Grok directional only; judge-vs-consensus kappa = 0.20-0.43). On the author-audited clinical-underdetermined subset the permissiveness gap widened and the point-estimate model ordering held. A closed-ended MedQA anchor confirms accuracy is high and option-order effects are within a +/-5-point equivalence region for three of four models, so the safety gap is about calibration, not knowledge. We release the harness, prompts, per-item outputs, judge panel, perturbation audit, and human-annotation protocol.
Background: LLM judges increasingly score whether clinical language models give overconfident answers under incomplete evidence, yet whether a measured "safety gain" reflects real behavior change or the judge's calibration is unresolved. Using a structured evidence-sufficiency prompt as a test case, we asked whether it reduces unsafe overconfident answers, how far that effect depends on the scoring judge, and what it costs in helpfulness. Methods: In a retrospective public-data benchmark (Real-POCQi, HealthBench, MedRBench), four models (GPT-5.5, Claude Opus 4.8, Gemini 3.5 Flash, Grok 4.3) answered a fully paired common panel (1,200 cells) with a standard prompt and the wrapper. The pre-specified endpoint was the paired reduction in unsafe overconfidence scored by the primary judge (GPT-5.4-nano); secondary analyses added a different-family judge (Claude Sonnet 5), a correctness judge, matched scaffold controls, and a blinded three-clinician review. Results: Unsafe overconfidence fell from 49.3% to 24.7%, a paired reduction of 24.7 points (95% CI 21.8-27.7; p<0.001), robust in direction across models and paraphrases. Magnitude was judge-dependent: Sonnet agreed on direction but nearly halved the effect (+13.1 points), with one-directional disagreement. Blinded clinicians characterized the primary judge as a high-sensitivity (1.00), low-specificity (0.55) screen, not a calibrated rate. The gain carried a model-specific helpfulness cost (correct diagnosis 80.3% to 50.3%): near-free for GPT-5.5, near-total for Gemini (-58 points). Matched scaffold controls showed genuine behavior change, not judge circularity. Conclusions: LLM-judged clinical safety effects should be reported as directional and relative, anchored to human review and evaluated jointly with helpfulness, not as calibrated absolute rates. This does not establish clinical deployment readiness.
Digital mental health interventions (DMHIs) offer scalable support, but ensuring they accurately detect users' intent during volatile situations can be challenging. Pure parametric Large Language models (LLMs) do not contain specific safety critical architecture, and can miss critical cues, or hallucinate, undermining reliability. Retrieval Augmented Generation (RAG), which supplements an LLM with retrieved context, could enhance intent detection during volatile situations. Commercially available DMHIs typically combine multiple independent safety layers like rule-based filters, symbolic escalation protocols, and neural classification. The incremental contribution of any single layer, however, remains unquantified. This paper evaluates six LLM models within a DMHI called Wysa, via a controlled comparison of RAG-enabled versus RAG-disabled modes. Anonymized real and synthetic user-chatbot exchanges were annotated by a qualified clinical team against multi-class intent categories (e.g. self-harm, abuse, panic). The study computed classification accuracy, recall, precision and F1 scores against ground truth labels and tested differences for statistical significance. Performance was also examined by risk category and inter-model agreement. While RAG caused a rise in false alarms, the trade-off is consistent with safety-critical design principles that prioritize sensitivity, where flagged cases are routed to additional review rather than acted on directly. Overall, these findings support RAG as a promising approach to improve the accuracy, consistency and safety of LLM-driven DMHIs. Keywords: Digital Mental Health Intervention, Large Language Model, Retrieval Augmented Generation, Accuracy, Recall, Precision
Conversational AI systems have become informal mental health support resources for Generation Alpha (Gen Alpha, born 2010-2024), with 13.1% of U.S. adolescents (5.4 million) using generative AI for mental health advice. While these systems, from therapy apps to general chatbots, rely on large language models trained on extensive psychological literature, their safety for youth communication patterns characterized by hyperbolic language, ironic positivity, rapid semantic drift, and contextual polysemy remains unvalidated. Following multiple adolescent deaths linked to AI chatbot interactions, systematic evaluation is critical. We present two benchmarks: (1) 64 Gen Alpha mental health expressions validated by native speakers (ICC=0.72) and clinicians (kappa=0.78); (2) 75 multi-turn conversations (780 turns) with paired Standard/Gen Alpha versions. Across evaluations of LLM architectures underlying therapy apps and general chatbots - Claude, GPT-4o, Llama-3.1 - models understand 76-82% of vocabulary but correctly calibrate only 64-72% of clinical risk, creating a 10-14 percentage point (pp) vocabulary-comprehension gap (p<.001, d>0.48) absent in human therapists (3pp, p=.22). The gap is architecturally consistent and widens with ambiguity (7pp -> 18pp). We identify six failure patterns: sarcasm masking (29pp), minimization acceptance (43pp), informal style bias (24pp), risk-stratified ambiguity (19pp), semantic drift (19pp), context-dependent violence (7pp). Patterns compound; three or more yield 94% miss rates. Lightweight mitigations fail; only heavy scaffolding achieves human performance (6.4x cost). With 34% baseline miss rate yielding 146,880 estimated annual missed crises, we recommend mandatory human-in-the-loop architectures, quarterly youth-specific validation, transparent performance disclosure, and regulatory frameworks for youth-facing mental health AI.
Large language models (LLMs) are entering clinical practice based on benchmark accuracy that may fail to detect safety-relevant failure modes. Here we present AI-MASLD, a stress-audit framework that adapts the logic of metabolic stress testing from hepatology to the evaluation of clinical LLMs. Using 240 clinical cases across six narrative perturbation probes, we subjected seven models to double-stress testing and quantified performance through three indices: metabolic index (MI), perturbation flip rate (PFR), and counterfactual fairness index (CFI). Under clean baseline conditions, all models performed uniformly well. Under realistic narrative stress, performance diverged sharply, revealing two distinct stress-response phenotypes. Quantized models exhibited pseudonormalization, in which low flip rates hid functional collapse. Medical supervised fine-tuning systematically degraded logical stability, fairness, and information extraction. An open-weight model matched or exceeded proprietary alternatives on every safety dimension. These findings establish narrative stress auditing as a necessary complement to accuracy-based evaluation.
Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated. Existing benchmarks focus on general web or desktop tasks and underrepresent medical software, which requires domain knowledge, exhibits markedly different UI design from mainstream applications, lacks public testing environments, and demands safety validation beyond task completion. We introduce MedCUA-Bench, an interactive benchmark for clinical computer-use agents. It covers 18 clinical scenarios across 10 medical domains, reconstructed from real product manuals and open-source medical systems to capture authentic clinical interfaces while avoiding licensing and privacy constraints. Each task ships with paired intent- and step-level goals to disentangle clinical reasoning from UI execution, and is evaluated by a deterministic checker over task completion and five clinical safety dimensions. Across 23 agents, the best closed-source model reaches 54.2% strict success, while all models remain below 9% on the real OpenEMR. Open-source agents average only 2.5%, with the best reaching 16.2%. MedCUA-Bench exposes the gap between current agents and reliable clinical software use, providing a reproducible testbed for future research.
Sunday Oyinlola Ogundoyin, Muhammad Ikram, Rahat Masoodcs.CL cs.CY
Medical large language models (LLMs), including custom medical GPTs (MedGPTs) and open-source models, are increasingly deployed on web platforms to provide clinical guidance. However, they pose risks of hallucination, policy noncompliance, and unsafe design. We conduct a large-scale assessment of 6,233 MedGPTs, evaluating a stratified sample of 1,500, together with 10 open-source LLMs. We introduce two frameworks: MedGPT-HEval for hallucination detection and an LLM-based pipeline for assessing policy violations and developer intent. Our results show that 25-30% of MedGPTs exhibit low factual accuracy, with bottom- and middle-tier models at highest risk; 33.6-54.3% violate operational thresholds, and 57.06% of Action-enabled models lack adequate privacy disclosures. Compared with open-source models, MedGPTs achieve higher factual accuracy and semantic alignment, though open-source models are more stable. These results reveal systemic gaps in hallucination and compliance, highlighting the need for multi-metric evaluation and stronger safeguards. We release HAA-MedGPT, a structured dataset that supports future research on the safety of web-facing medical LLMs.