Recent advances in Large Language Models (LLMs) and Reinforcement Learning (RL) have led to strong performance in open-domain question answering (QA). However, existing models still struggle with questions that admit multiple valid answers. Standard QA benchmarks, which typically assume a single gold answer, overlook this reality and thus produce inappropriate training signals. Existing attempts to handle ambiguity often rely on costly manual annotation, which is difficult to scale to multi-hop datasets such as HotpotQA and MuSiQue. In this paper, we present A$^2$Search, an annotation-free, end-to-end training framework to recognize and handle ambiguity. At its core is an automated pipeline that detects ambiguous questions and gathers alternative answers via trajectory sampling and evidence verification. The model is then optimized with RL using a carefully designed $\mathrm{AnsF1}$ reward, which naturally accommodates multiple answers. Experiments on eight open-domain QA benchmarks demonstrate that A$^2$Search achieves new state-of-the-art performance. With only a single rollout, A$^2$Search-7B yields an average $\mathrm{AnsF1}@1$ score of $48.4\%$ across four multi-hop benchmarks, outperforming all strong baselines, including the substantially larger ReSearch-32B ($46.2\%$). Extensive analyses further show that A$^2$Search resolves ambiguity and generalizes across benchmarks, highlighting that embracing ambiguity is essential for building more reliable QA systems. Our code, data, and model weights can be found at https://github.com/zfj1998/A2Search

The management of chronic Heart Failure (HF) presents significant challenges in modern healthcare, requiring continuous monitoring, early detection of exacerbations, and personalized treatment strategies. In this paper, we present a predictive model founded on Machine Learning (ML) techniques to identify patients at HF risk. This model is an ensemble learning approach, a modified stacking technique, that uses two specialized models leveraging clinical and echocardiographic features and then a meta-model to combine the predictions of these two models. We initially assess the model on a real dataset and the obtained results suggest that it performs well in the stratification of patients at HR risk. Specifically, we obtained high sensitivity (95\%), ensuring that nearly all high-risk patients are identified. As for accuracy, we obtained 84\%, which can be considered moderate in some ML contexts. However, it is acceptable given our priority of identifying patients at risk of HF because they will be asked to participate in the telemonitoring program of the PrediHealth research project on which some of the authors of this paper are working. The initial findings also suggest that ML-based risk stratification models can serve as valuable decision-support tools not only in the PrediHealth project but also for healthcare professionals, aiding in early intervention and personalized patient management. To have a better understanding of the value and of potentiality of our predictive model, we also contrasted its results with those obtained by using three baseline models. The preliminary results indicate that our predictive model outperforms these baselines that flatly consider features, \ie not grouping them in clinical and echocardiographic features.

Radiomics-based AI models show promise for breast cancer diagnosis but often lack interpretability, limiting clinical adoption. This study addresses the gap between radiomic features (RF) and the standardized BI-RADS lexicon by proposing a dual-dictionary framework. First, a Clinically-Informed Feature Interpretation Dictionary (CIFID) was created by mapping 56 RFs to BI-RADS descriptors (shape, margin, internal enhancement) through literature and expert review. The framework was applied to classify triple-negative breast cancer (TNBC) versus non-TNBC using dynamic contrast-enhanced MRI from a multi-institutional cohort of 1,549 patients. We trained 27 machine learning classifiers with 27 feature selection methods. SHapley Additive exPlanations (SHAP) were used to interpret predictions and generate a complementary Data-Driven Feature Interpretation Dictionary (DDFID) for 52 additional RFs. The best model, combining Variance Inflation Factor (VIF) selection with Extra Trees Classifier, achieved an average cross-validation accuracy of 0.83. Key predictive RFs aligned with clinical knowledge: higher Sphericity (round/oval shape) and lower Busyness (more homogeneous enhancement) were associated with TNBC. The framework confirmed known imaging biomarkers and uncovered novel, interpretable associations. This dual-dictionary approach (BM1.0) enhances AI model transparency and supports the integration of RFs into routine breast cancer diagnosis and personalized care.

The diagnosis of oral diseases presents a problematic clinical challenge, characterized by a wide spectrum of pathologies with overlapping symptomatology. To address this, we developed Clinical Semantic Intelligence (CSI), a novel artificial intelligence framework that diagnoses 118 different oral diseases by computationally modeling the cognitive processes of an expert clinician. Our core hypothesis is that moving beyond simple pattern matching to emulate expert reasoning is critical to building clinically useful diagnostic aids. CSI's architecture integrates a fine-tuned multimodal CLIP model with a specialized ChatGLM-6B language model. This system executes a Hierarchical Diagnostic Reasoning Tree (HDRT), a structured framework that distills the systematic, multi-step logic of differential diagnosis. The framework operates in two modes: a Fast Mode for rapid screening and a Standard Mode that leverages the full HDRT for an interactive and in-depth diagnostic workup. To train and validate our system, we curated a primary dataset of 4,310 images, supplemented by an external hold-out set of 176 images for final validation. A clinically-informed augmentation strategy expanded our training data to over 30,000 image-text pairs. On a 431-image internal test set, CSI's Fast Mode achieved an accuracy of 73.4%, which increased to 89.5% with the HDRT-driven Standard Mode. The performance gain is directly attributable to the hierarchical reasoning process. Herein, we detail the architectural philosophy, development, and rigorous evaluation of the CSI framework.

Background: CT imaging is vital for lung cancer management, offering detailed visualization for AI-based prognosis. However, supervised learning SL models require large labeled datasets, limiting their real-world application in settings with scarce annotations. Methods: We analyzed CT scans from 977 patients across 12 datasets extracting 1218 radiomics features using Laplacian of Gaussian and wavelet filters via PyRadiomics Dimensionality reduction was applied with 56 feature selection and extraction algorithms and 27 classifiers were benchmarked A semi supervised learning SSL framework with pseudo labeling utilized 478 unlabeled and 499 labeled cases Model sensitivity was tested in three scenarios varying labeled data in SL increasing unlabeled data in SSL and scaling both from 10 percent to 100 percent SHAP analysis was used to interpret predictions Cross validation and external testing in two cohorts were performed. Results: SSL outperformed SL, improving overall survival prediction by up to 17 percent. The top SSL model, Random Forest plus XGBoost classifier, achieved 0.90 accuracy in cross-validation and 0.88 externally. SHAP analysis revealed enhanced feature discriminability in both SSL and SL, especially for Class 1 survival greater than 4 years. SSL showed strong performance with only 10 percent labeled data, with more stable results compared to SL and lower variance across external testing, highlighting SSL's robustness and cost effectiveness. Conclusion: We introduced a cost-effective, stable, and interpretable SSL framework for CT-based survival prediction in lung cancer, improving performance, generalizability, and clinical readiness by integrating SHAP explainability and leveraging unlabeled data.

One of the major challenges in the science of maxillofacial radiology imaging is the various artifacts created in images taken by cone beam computed tomography (CBCT) imaging systems. Among these artifacts, motion artifact, which is created by the patient, has adverse effects on image quality. In this paper, according to the conditions and limitations of the CBCT imaging room, the goal is the design and development of a cable-driven parallel robot to create repeatable movements of a dry skull inside a CBCT scanner for studying motion artifacts and building up reference datasets with motion artifacts. The proposed robot allows a dry skull to execute motions, which were selected on the basis of clinical evidence, with 3-degrees of freedom during imaging in synchronous manner with the radiation beam. The kinematic model of the robot is presented to investigate and describe the correlation between the amount of motion and the pulse width applied to DC motors. This robot can be controlled by the user through a smartphone or laptop wirelessly via a Wi-Fi connection. Using wireless communication protects the user from harmful radiation during robot driving and functioning. The results show that the designed robot has a reproducibility above 95% in performing various movements.

The use of automatic short answer grading (ASAG) models may help alleviate the time burden of grading while encouraging educators to frequently incorporate open-ended items in their curriculum. However, current state-of-the-art ASAG models are large neural networks (NN) often described as "black box", providing no explanation for which characteristics of an input are important for the produced output. This inexplicable nature can be frustrating to teachers and students when trying to interpret, or learn from an automatically-generated grade. To create a powerful yet intelligible ASAG model, we experiment with a type of model called a Neural Additive Model that combines the performance of a NN with the explainability of an additive model. We use a Knowledge Integration (KI) framework from the learning sciences to guide feature engineering to create inputs that reflect whether a student includes certain ideas in their response. We hypothesize that indicating the inclusion (or exclusion) of predefined ideas as features will be sufficient for the NAM to have good predictive power and interpretability, as this may guide a human scorer using a KI rubric. We compare the performance of the NAM with another explainable model, logistic regression, using the same features, and to a non-explainable neural model, DeBERTa, that does not require feature engineering.

Understanding how images influence the world, interpreting which effects their semantics have on various quantities and exploring the reasons behind changes in image-based predictions are highly difficult yet extremely interesting problems. By adopting a holistic modeling approach utilizing Neural Additive Models in combination with Diffusion Autoencoders, we can effectively identify the latent hidden semantics of image effects and achieve full intelligibility of additional tabular effects. Our approach offers a high degree of flexibility, empowering us to comprehensively explore the impact of various image characteristics. We demonstrate that the proposed method can precisely identify complex image effects in an ablation study. To further showcase the practical applicability of our proposed model, we conduct a case study in which we investigate how the distinctive features and attributes captured within host images exert influence on the pricing of Airbnb rentals.