AgentScore: Autoformulation of Deployable Clinical Scoring Systems

Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable decision rules. While machine-learning models achieve strong performance, many fail to translate into routine clinical use due to misalignment with workflow constraints such as memorability, auditability, and bedside execution. We argue that this gap arises not from insufficient predictive power, but from optimizing over model classes that are incompatible with guideline deployment. Deployable guidelines often take the form of unit-weighted clinical checklists, formed by thresholding the sum of binary rules, but learning such scores requires searching an exponentially large discrete space of possible rule sets. We introduce AgentScore, which performs semantically guided optimization in this space by using LLMs to propose candidate rules and a deterministic, data-grounded verification-and-selection loop to enforce statistical validity and deployability constraints. Across eight clinical prediction tasks, AgentScore outperforms existing score-generation methods and achieves AUC comparable to more flexible interpretable models despite operating under stronger structural constraints. On two additional externally validated tasks, AgentScore achieves higher discrimination than established guideline-based scores.

Knowledge-Informed Kernel State Reconstruction for Interpretable Dynamical System Discovery

Recovering governing equations from data is central to scientific discovery, yet existing methods often break down under noisy, partial observations, or rely on black-box latent dynamics that obscure mechanism. We introduce MAAT (Model Aware Approximation of Trajectories), a framework for symbolic discovery built on knowledge-informed Kernel State Reconstruction. MAAT formulates state reconstruction in a reproducing kernel Hilbert space and directly incorporates structural and semantic priors such as non-negativity, conservation laws, and domain-specific observation models into the reconstruction objective, while accommodating heterogeneous sampling and measurement granularity. This yields smooth, physically consistent state estimates with analytic time derivatives, providing a principled interface between fragmented sensor data and symbolic regression. Across twelve diverse scientific benchmarks and multiple noise regimes, MAAT substantially reduces state-estimation MSE for trajectories and derivatives used by downstream symbolic regression relative to strong baselines.

Timely Clinical Diagnosis through Active Test Selection

There is growing interest in using machine learning (ML) to support clinical diag- nosis, but most approaches rely on static, fully observed datasets and fail to reflect the sequential, resource-aware reasoning clinicians use in practice. Diagnosis remains complex and error prone, especially in high-pressure or resource-limited settings, underscoring the need for frameworks that help clinicians make timely and cost-effective decisions. We propose ACTMED (Adaptive Clinical Test selection via Model-based Experimental Design), a diagnostic framework that integrates Bayesian Experimental Design (BED) with large language models (LLMs) to better emulate real-world diagnostic reasoning. At each step, ACTMED selects the test expected to yield the greatest reduction in diagnostic uncertainty for a given patient. LLMs act as flexible simulators, generating plausible patient state distributions and supporting belief updates without requiring structured, task-specific training data. Clinicians can remain in the loop; reviewing test suggestions, interpreting intermediate outputs, and applying clinical judgment throughout. We evaluate ACTMED on real-world datasets and show it can optimize test selection to improve diagnostic accuracy, interpretability, and resource use. This represents a step to- ward transparent, adaptive, and clinician-aligned diagnostic systems that generalize across settings with reduced reliance on domain-specific data.

Continuous non-contact vital sign monitoring of neonates in intensive care units using RGB-D cameras

Neonates in intensive care require continuous monitoring. Current measurement devices are limited for long-term use due to the fragility of newborn skin and the interference of wires with medical care and parental interactions. Camera-based vital sign monitoring has the potential to address these limitations and has become of considerable interest in recent years due to the absence of physical contact between the recording equipment and the neonates, as well as the introduction of low-cost devices. We present a novel system to capture vital signs while offering clinical insights beyond current technologies using a single RGB-D camera. Heart rate and oxygen saturation were measured using colour and infrared signals with mean average errors (MAE) of 7.69 bpm and 3.37%, respectively. Using the depth signals, an MAE of 4.83 breaths per minute was achieved for respiratory rate. Tidal volume measurements were obtained with a MAE of 0.61 mL. Flow-volume loops can also be calculated from camera data, which have applications in respiratory disease diagnosis. Our system demonstrates promising capabilities for neonatal monitoring, augmenting current clinical recording techniques to potentially improve outcomes for neonates.

Deep Learning for Motion Classification in Ankle Exoskeletons Using Surface EMG and IMU Signals

Ankle exoskeletons have garnered considerable interest for their potential to enhance mobility and reduce fall risks, particularly among the aging population. The efficacy of these devices relies on accurate real-time prediction of the user's intended movements through sensor-based inputs. This paper presents a novel motion prediction framework that integrates three Inertial Measurement Units (IMUs) and eight surface Electromyography (sEMG) sensors to capture both kinematic and muscular activity data. A comprehensive set of activities, representative of everyday movements in barrier-free environments, was recorded for the purpose. Our findings reveal that Convolutional Neural Networks (CNNs) slightly outperform Long Short-Term Memory (LSTM) networks on a dataset of five motion tasks, achieving classification accuracies of $96.5 \pm 0.8 \%$ and $87.5 \pm 2.9 \%$, respectively. Furthermore, we demonstrate the system's proficiency in transfer learning, enabling accurate motion classification for new subjects using just ten samples per class for finetuning. The robustness of the model is demonstrated by its resilience to sensor failures resulting in absent signals, maintaining reliable performance in real-world scenarios. These results underscore the potential of deep learning algorithms to enhance the functionality and safety of ankle exoskeletons, ultimately improving their usability in daily life.