Carlos Garcia Fernandez

arXiv2026

Clinical Reasoning AI for Oncology Treatment Planning: A Multi-Specialty Case-Based Evaluation

Background: More than 80% of U.S. cancer care is delivered in community settings, where survival remains worse than at academic centers. Clinicians must integrate genomics, staging, radiology, pathology, and changing guidelines, creating cognitive burden. We evaluated OncoBrain, an AI clinical reasoning platform for oncology treatment-plan generation, as an early step toward OGI. Methods: OncoBrain combines general-purpose LLMs with a cancer-specific graph retrieval-augmented generation layer, a gold-standard treatment-plan corpus as long-term memory, and a model-agnostic safety layer (CHECK) for hallucination detection and suppression. We evaluated clinician-enriched case summaries across gynecologic, genitourinary, neuro-oncology, gastrointestinal/hepatobiliary, and hematologic malignancies. Three clinician groups completed structured evaluations of 173 cases using a common 16-item instrument: subspecialist oncologists reviewed 50 cases, physician reviewers 78, and advanced practice providers 45. Results: Ratings were highest for scientific accuracy, evidence support, and safety, with lower but favorable scores for workflow integration and time savings. On a 5-point scale, mean alignment with evidence and guidelines was 4.60, 4.56, and 4.70 across subspecialists, physician reviewers, and advanced practice providers. Mean scores for absence of safety or misinformation concerns were 4.80, 4.40, and 4.60. Workflow integration averaged 4.50, 3.94, and 4.00; perceived time savings averaged 5.00, 3.89, and 3.60. Conclusions: In this multi-specialty vignette-based evaluation, OncoBrain generated oncology treatment plans judged guideline-concordant, clinically acceptable, and easy to supervise. These findings support the potential of a carefully engineered AI reasoning platform to assist oncology treatment planning and justify prospective real-world evaluation in community settings.

cs.CY↗

arXiv2025

From Solution to Surface: Persistence of the Diradical Character of a Diindenoanthracene Derivative on a Metallic Substrate

Organic diradicals are envisioned as elementary building blocks for designing a new generation of spintronic devices and have been used in constructing prototypical field effect transistors and non-linear optical devices. Open-shell systems, however, are also reactive, thus requiring design strategies to protect their radical character from the environment, especially when they are embedded into solid-state devices. Here, we report the persistence on a metallic surface of the diradical character of a diindeno[b,i]anthracene (DIAn) core protected by bulky end-groups. Our scanning tunneling spectroscopy measurements on single-molecules detected singlet-triplet excitations that were absent for DIAn species packed in assembled structures. Density functional theory simulations unravel that molecular geometry on the metal substrate can crucially modify the value of the single-triplet gap via the delocalization of the radical sites. The persistence of the diradical character over metallic substrates is a promising finding for integrating radical-based materials in functional devices.

cond-mat.mtrl-sci↗