The application of large language models (LLMs) in the medical field has garnered significant attention, yet their reasoning capabilities in more specialized domains like anesthesiology remain underexplored. To bridge this gap, we introduce AnesSuite, the first comprehensive dataset suite specifically designed for anesthesiology reasoning in LLMs. The suite features AnesBench, an evaluation benchmark tailored to assess anesthesiology-related reasoning across three levels: factual retrieval (System 1), hybrid reasoning (System 1.x), and complex decision-making (System 2). Alongside this benchmark, the suite includes three training datasets that provide an infrastructure for continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning with verifiable rewards (RLVR). Leveraging this suite, we develop Morpheus, the first baseline model collection for anesthesiology reasoning. Despite undergoing limited training with SFT and group relative policy optimization (GRPO), Morpheus not only achieves substantial improvements in anesthesiology that rival larger-scale models, but also demonstrates enhanced reasoning capabilities across general medical and broad-domain b
Medical large language models (LLMs) have gained popularity recently due to their significant practical utility. However, most existing research focuses on general medicine, and there is a need for in-depth study of LLMs in specific fields like anesthesiology. To fill the gap, we introduce Hypnos, a Chinese Anesthesia model built upon existing LLMs, e.g., Llama. Hypnos' contributions have three aspects: 1) The data, such as utilizing Self-Instruct, acquired from current LLMs likely includes inaccuracies. Hypnos implements a cross-filtering strategy to improve the data quality. This strategy involves using one LLM to assess the quality of the generated data from another LLM and filtering out the data with low quality. 2) Hypnos employs a general-to-specific training strategy that starts by fine-tuning LLMs using the general medicine data and subsequently improving the fine-tuned LLMs using data specifically from Anesthesiology. The general medical data supplement the medical expertise in Anesthesiology and enhance the effectiveness of Hypnos' generation. 3) We introduce a standardized benchmark for evaluating medical LLM in Anesthesiology. Our benchmark includes both publicly availa
Increasing the efficiency and effectiveness of the healthcare system is a challenge faced worldwide. Many outpatient clinics have implemented two-stage service systems, with both a physician and physician assistant, to enhance capacity and reduce costs. Some patients only visit a physician assistant while some patients visit both providers depending on their patient type. However, minimizing provider idle time and overtime while reducing patient waiting time is challenging in two-stage service systems. Thus, our objective is to find daily appointment templates, based on block scheduling, that minimize a weighted sum of these metrics. A block schedule divides the overall schedule into several time blocks and assigns patients of different types into each block in proportion to their daily demand to balance the workload throughout the day. Since the problem is shown to be strongly $\mathcal{NP}$-Hard, we develop a heuristic algorithm that provides a no-idle time appointment template that is easily implementable. We expand our study to include stochastic service times and show that our algorithm yields an efficient block schedule under practically relevant conditions. The algorithm is
As an important means of providing medical services in developing countries and remote areas, Mobile Health Clinics (MHCs) focus on distributing medical supplies and providing basic health needs to underserved communities. In this paper, we propose a new model for the mobile health clinics with resupply from a truck and heterogeneous demand. In addition to the traditional routing decisions, our model also establishes en-route resupply plan. Adding the en-route resupply plan adds complexities to this problem as more constraints need to be added to accommodate for the synchronization between a fleet of MHCs and a resupply truck. We model this problem as a vehicle routing problem with multiple synchronization constraints and heterogeneous demand (VRPMSC-HD) and formulate a mixed integer linear programming (MILP). We propose a metaheuristic based on adaptive large neighborhood search (ALNS) with new operators to solve large-scale instances of the model. To demonstrate the value of the synchronization approach, we compare the total distance traveled by the mobile health clinics and the resupply truck and the arrival of the last mobile health clinic to the depot against a model where mob
Background and Objective: In neurosurgery, fusing clinical images and depth images that can improve the information and details is beneficial to surgery. We found that the registration of face depth images was invalid frequently using existing methods. To abundant traditional image methods with depth information, a method in registering with depth images and traditional clinical images was investigated. Methods: We used the dlib library, a C++ library that could be used in face recognition, and recognized the key points on faces from the structure light camera and CT image. The two key point clouds were registered for coarse registration by the ICP method. Fine registration was finished after coarse registration by the ICP method. Results: RMSE after coarse and fine registration is as low as 0.995913 mm. Compared with traditional methods, it also takes less time. Conclusions: The new method successfully registered the facial depth image from structure light images and CT with a low error, and that would be promising and efficient in clinical application of neurosurgery.
Clinic testing plays a critical role in containing infectious diseases such as COVID-19. However, one of the key research questions in fighting such pandemics is how to optimize testing capacities across clinics. In particular, domain experts expect to know exactly how to adjust the features that may affect testing capacities, given that dynamics and uncertainty make this a highly challenging problem. Hence, as a tool to support both policymakers and clinicians, we collaborated with domain experts to build ClinicLens, an interactive visual analytics system for exploring and optimizing the testing capacities of clinics. ClinicLens houses a range of features based on an aggregated set of COVID-19 data. It comprises Back-end Engine and Front-end Visualization that take users through an iterative exploration chain of extracting, training, and predicting testing-sensitive features and visual representations. It also combines AI4VIS and visual analytics to demonstrate how a clinic might optimize its testing capacity given the impacts of a range of features. Three qualitative case studies along with feedback from subject-matter experts validate that ClinicLens is both a useful and effecti
Data deprivation, or the lack of easily available and actionable information on the well-being of individuals, is a significant challenge for the developing world and an impediment to the design and operationalization of policies intended to alleviate poverty. In this paper we explore the suitability of data derived from OpenStreetMap to proxy for the location of two crucial public services: schools and health clinics. Thanks to the efforts of thousands of digital humanitarians, online mapping repositories such as OpenStreetMap contain millions of records on buildings and other structures, delineating both their location and often their use. Unfortunately much of this data is locked in complex, unstructured text rendering it seemingly unsuitable for classifying schools or clinics. We apply a scalable, unsupervised learning method to unlabeled OpenStreetMap building data to extract the location of schools and health clinics in ten countries in Africa. We find the topic modeling approach greatly improves performance versus reliance on structured keys alone. We validate our results by comparing schools and clinics identified by our OSM method versus those identified by the WHO, and de
The medical adoption of NLP tools requires interpretability by end users, yet traditional explainable AI (XAI) methods are misaligned with clinical reasoning and lack clinician input. We introduce CHiRPE (Clinical High-Risk Prediction with Explainability), an NLP pipeline that takes transcribed semi-structured clinical interviews to: (i) predict psychosis risk; and (ii) generate novel SHAP explanation formats co-developed with clinicians. Trained on 944 semi-structured interview transcripts across 24 international clinics of the AMP-SCZ study, the CHiRPE pipeline integrates symptom-domain mapping, LLM summarisation, and BERT classification. CHiRPE achieved over 90% accuracy across three BERT variants and outperformed baseline models. Explanation formats were evaluated by 28 clinical experts who indicated a strong preference for our novel concept-guided explanations, especially hybrid graph-and-text summary formats. CHiRPE demonstrates that clinically-guided model development produces both accurate and interpretable results. Our next step is focused on real-world testing across our 24 international sites.
Clinical text classification requires choosing between specialized fine-tuned models (BERT variants) and general-purpose large language models (LLMs), yet neither dominates across all instances. We introduce Learning to Defer for clinical text (L2D-Clinical), a framework that learns when a BERT classifier should defer to an LLM based on uncertainty signals and text characteristics. Unlike prior L2D work that defers to human experts assumed universally superior, our approach enables adaptive deferral-improving accuracy when the LLM complements BERT. We evaluate on two English clinical tasks: (1) ADE detection (ADE Corpus V2), where BioBERT (F1=0.911) outperforms the LLM (F1=0.765), and (2) treatment outcome classification (MIMIC-IV with multi-LLM consensus ground truth), where GPT-5-nano (F1=0.967) outperforms ClinicalBERT (F1=0.887). On ADE, L2D-Clinical achieves F1=0.928 (+1.7 points over BERT) by selectively deferring 7% of instances where the LLM's high recall compensates for BERT's misses. On MIMIC, L2D-Clinical achieves F1=0.980 (+9.3 points over BERT) by deferring only 16.8\% of cases to the LLM. The key insight is that L2D-Clinical learns to selectively leverage LLM strength
Urgent care clinics and emergency departments around the world periodically suffer from extended wait times beyond patient expectations due to inadequate staffing levels. These delays have been linked with adverse clinical outcomes. Previous research into forecasting demand this domain has mostly used a collection of statistical techniques, with machine learning approaches only now beginning to emerge in recent literature. The forecasting problem for this domain is difficult and has also been complicated by the COVID-19 pandemic which has introduced an additional complexity to this estimation due to typical demand patterns being disrupted. This study explores the ability of machine learning methods to generate accurate patient presentations at two large urgent care clinics located in Auckland, New Zealand. A number of machine learning algorithms were explored in order to determine the most effective technique for this problem domain, with the task of making forecasts of daily patient demand three months in advance. The study also performed an in-depth analysis into the model behaviour in respect to the exploration of which features are most effective at predicting demand and which
A key task in ML is to optimize models at various stages, e.g. by choosing hyperparameters or picking a stopping point. A traditional ML approach is to use validation loss, i.e. to apply the training loss function on a validation set to guide these optimizations. However, ML for healthcare has a distinct goal from traditional ML: Models must perform well relative to specific clinical requirements, vs. relative to the loss function used for training. These clinical requirements can be captured more precisely by tailored metrics. Since many optimization tasks do not require the driving metric to be differentiable, they allow a wider range of options, including the use of metrics tailored to be clinically-relevant. In this paper we describe two controlled experiments which show how the use of clinically-tailored metrics provide superior model optimization compared to validation loss, in the sense of better performance on the clinical task. The use of clinically-relevant metrics for optimization entails some extra effort, to define the metrics and to code them into the pipeline. But it can yield models that better meet the central goal of ML for healthcare: strong performance in the cl
We evaluate the impact of large language model-based clinical decision support in live care. In partnership with Penda Health, a network of primary care clinics in Nairobi, Kenya, we studied AI Consult, a tool that serves as a safety net for clinicians by identifying potential documentation and clinical decision-making errors. AI Consult integrates into clinician workflows, activating only when needed and preserving clinician autonomy. We conducted a quality improvement study, comparing outcomes for 39,849 patient visits performed by clinicians with or without access to AI Consult across 15 clinics. Visits were rated by independent physicians to identify clinical errors. Clinicians with access to AI Consult made relatively fewer errors: 16% fewer diagnostic errors and 13% fewer treatment errors. In absolute terms, the introduction of AI Consult would avert diagnostic errors in 22,000 visits and treatment errors in 29,000 visits annually at Penda alone. In a survey of clinicians with AI Consult, all clinicians said that AI Consult improved the quality of care they delivered, with 75% saying the effect was "substantial". These results required a clinical workflow-aligned AI Consult i
Movement directly reflects neurological and musculoskeletal health, yet objective biomechanical assessment is rarely available in routine care. We introduce Portable Biomechanics Laboratory (PBL), a secure platform for fitting biomechanical models to video collected with a handheld, moving, smartphone. We validate this approach on over 15 hours of data synchronized to ground truth motion capture, finding mean joint-angle errors < 3$°$ and pelvis-translation errors of a few centimeters across patients with neurological-injury, lower-limb prosthesis users, pediatric in-patients, and controls. In > 5 hours of prospective deployments to neurosurgery and sports-medicine clinics, PBL was easy to setup, yielded highly reliable gait metrics (ICC > 0.9), and detected clinically relevant differences. For cervical-myelopathy patients, its measurement of gait quality correlated with modified Japanese Orthopedic Association (mJOA) scores and were responsive to clinical intervention. Handheld smartphone video can therefore deliver accurate, scalable, and low-burden biomechanical measurement, enabling greatly increased monitoring of movement impairments. We release the first clinically-v
This paper introduces Artificial Intelligence Clinics on Mobile (AICOM), an open-source project devoted to answering the United Nations Sustainable Development Goal 3 (SDG3) on health, which represents a universal recognition that health is fundamental to human capital and social and economic development. The core motivation for the AICOM project is the fact that over 80% of the people in the least developed countries (LDCs) own a mobile phone, even though less than 40% of these people have internet access. Hence, through enabling AI-based disease diagnostics and screening capability on affordable mobile phones without connectivity will be a critical first step to addressing healthcare access problems. The technologies developed in the AICOM project achieve exactly this goal, and we have demonstrated the effectiveness of AICOM on monkeypox screening tasks. We plan to continue expanding and open-sourcing the AICOM platform, aiming for it to evolve into an universal AI doctor for the Underserved and Hard-to-Reach.
Diffusion-weighted magnetic resonance imaging (DW-MRI) derived scalar maps are effective for assessing neurodegenerative diseases and microstructural properties of white matter in large number of brain conditions. However, DW-MRI inherently limits the combination of data from multiple acquisition sites without harmonization to mitigate scanner-specific biases. While the widely used ComBAT method reduces site effects in research, its reliance on linear covariate relationships, homogeneous populations, fixed site numbers, and well populated sites constrains its clinical use. To overcome these limitations, we propose Clinical-ComBAT, a method designed for real-world clinical scenarios. Clinical-ComBAT harmonizes each site independently, enabling flexibility as new data and clinics are introduced. It incorporates a non-linear polynomial data model, site-specific harmonization referenced to a normative site, and variance priors adaptable to small cohorts. It further includes hyperparameter tuning and a goodness-of-fit metric for harmonization assessment. We demonstrate its effectiveness on simulated and real data, showing improved alignment of diffusion metrics and enhanced applicabilit
Artificial intelligence is poised to augment dermatological care by enabling scalable image-based diagnostics. Yet, the development of robust and equitable models remains hindered by datasets that fail to capture the clinical and demographic complexity of real-world practice. This complexity stems from region-specific disease distributions, wide variation in skin tones, and the underrepresentation of outpatient scenarios from non-Western populations. We introduce DermaCon-IN, a prospectively curated dermatology dataset comprising 5,450 clinical images from 3,002 patients across outpatient clinics in South India. Each image is annotated by board-certified dermatologists with 245 distinct diagnoses, structured under a hierarchical, aetiology-based taxonomy adapted from Rook's classification. The dataset captures a wide spectrum of dermatologic conditions and tonal variation commonly seen in Indian outpatient care. We benchmark a range of architectures, including convolutional models (ResNet, DenseNet, EfficientNet), transformer-based models (ViT, MaxViT, Swin), and Concept Bottleneck Models to establish baseline performance and explore how anatomical and concept-level cues may be int
Dynamic treatment regimes have been proposed to personalize treatment decisions by utilizing historical patient data, but they may not always improve on the current standard of care. It is thus meaningful to integrate the standard of care into the evaluation of treatment strategies, and previous works have suggested doing so through the concept of clinical utility. Here we will focus on the comparative component of clinical utility as the average outcome had the full population received treatment based on the proposed dynamic treatment regime in comparison to the full population receiving the ``standard" treatment assignment mechanism, such as a physician's choice. Clinical trials to evaluate clinical utility are rarely conducted, and thus, previous works have proposed an emulated clinical trial framework using observational data. However, only one simple estimator was previously suggested, and the practical details of how one would conduct this emulated trial were not detailed. Here, we illuminate these details and propose several estimators of clinical utility based on estimators proposed in the dynamic treatment regime literature. We illustrate the considerations and the estimat
We present a novel contribution to Spanish clinical natural language processing by introducing the largest publicly available clinical corpus, ClinText-SP, along with a state-of-the-art clinical encoder language model, RigoBERTa Clinical. Our corpus was meticulously curated from diverse open sources, including clinical cases from medical journals and annotated corpora from shared tasks, providing a rich and diverse dataset that was previously difficult to access. RigoBERTa Clinical, developed through domain-adaptive pretraining on this comprehensive dataset, significantly outperforms existing models on multiple clinical NLP benchmarks. By publicly releasing both the dataset and the model, we aim to empower the research community with robust resources that can drive further advancements in clinical NLP and ultimately contribute to improved healthcare applications.
Clinical decision-making is inherently complex and fast-paced, particularly in emergency departments (EDs) where critical, rapid and high-stakes decisions are made. Clinical Decision Rules (CDRs) are standardized evidence-based tools that combine signs, symptoms, and clinical variables into decision trees to make consistent and accurate diagnoses. CDR usage is often hindered by the clinician's cognitive load, limiting their ability to quickly recall and apply the appropriate rules. We introduce CDR-Agent, a novel LLM-based system designed to enhance ED decision-making by autonomously identifying and applying the most appropriate CDRs based on unstructured clinical notes. To validate CDR-Agent, we curated two novel ED datasets: synthetic and CDR-Bench, although CDR-Agent is applicable to non ED clinics. CDR-Agent achieves a 56.3\% (synthetic) and 8.7\% (CDR-Bench) accuracy gain relative to the standalone LLM baseline in CDR selection. Moreover, CDR-Agent significantly reduces computational overhead. Using these datasets, we demonstrated that CDR-Agent not only selects relevant CDRs efficiently, but makes cautious yet effective imaging decisions by minimizing unnecessary intervention
MTV is increasingly recognized as an accurate estimate of disease burden, which has prognostic value, but its implementation has been hindered by the time-consuming need for manual segmentation of images. Automated quantitation using AI-driven approaches is promising. AI-driven automated quantification significantly reduces labor-intensive manual segmentation, improving consistency, reproducibility, and feasibility for routine clinical practice. AI-enhanced radiomics provides comprehensive characterization of tumor biology, capturing intratumoral and intertumoral heterogeneity beyond what conventional volumetric metrics alone offer, supporting improved patient stratification and therapy planning. AI-driven segmentation of normal organs improves radioligand therapy planning by enabling accurate dose predictions and comprehensive organ-based radiomics analysis, further refining personalized patient management.