搜索医学 AI 论文与资源

ICLR 2026 Poster accepted paper at ICLR 2026. Real-world temporal data often consists of multiple signal types recorded at irregular, asynchronous intervals. For instance, in the medical domain, different types of blood tests can be measured at different times and frequencies, resulting in fragmented and unevenly scattered temporal data. Similar issues of irregular sampling occur in other domains, such as the monitoring of large systems using event log files. Effectively learning from such data requires handling sets of temporal sparse and heterogeneous signals. In this work, we propose Super Mixing Additive Networks (SuperMAN), a novel and interpretable-by-design framework for learning directly from such heterogeneous signals, by modeling them as sets of implicit graphs.

ICLR 2026 Poster accepted paper at ICLR 2026. Hybrid neural ordinary differential equations (neural ODEs) integrate mechanistic models with neural ODEs, offering strong inductive bias and flexibility, and are particularly advantageous in data-scarce healthcare settings. However, excessive latent states and interactions from mechanistic models can lead to training inefficiency and over-fitting, limiting practical effectiveness of hybrid neural ODEs. In response, we propose a new hybrid pipeline for automatic state selection and structure optimization in mechanistic neural ODEs, combining domain-informed graph modifications with data-driven regularization to sparsify the model for improving predictive performance and stability while retaining mechanistic plausibility. Experiments on synthetic and real-world data show improved predictive performance and robustness with desired sparsity, establishing an effective solution for hybrid model reduction in healthcare applications.

ICLR 2026 Poster accepted paper at ICLR 2026. Estimating heterogeneous treatment effects (HTEs) in time-varying settings is particularly challenging, as the probability of observing certain treatment sequences decreases exponentially with longer prediction horizons. Thus, the observed data contain little support for many plausible treatment sequences, which creates severe overlap problems. Existing meta-learners for the time-varying setting typically assume adequate treatment overlap, and thus suffer from exploding estimation variance when the overlap is low. To address this problem, we introduce a novel overlap-weighted orthogonal WO meta-learner for estimating HTEs that targets regions in the observed data with high probability of receiving the interventional treatment sequences.

ICLR 2026 Poster accepted paper at ICLR 2026. Estimating potential outcomes for treatments over time based on observational data is important for personalized decision-making in medicine. However, many existing methods for this task fail to properly adjust for time-varying confounding and thus yield biased estimates. There are only a few neural methods with proper adjustments, but these have inherent limitations (e.g., division by propensity scores that are often close to zero), which result in poor performance. As a remedy, we introduce the iterative G-computation network (IGC-Net). Our IGC-Net is a novel, neural end-to-end model which adjusts for time-varying confounding in order to estimate conditional average potential outcomes (CAPOs) over time.

ICLR 2026 Poster accepted paper at ICLR 2026. Healthcare insurance fraud detection presents unique machine learning challenges: labeled data are scarce due to delayed verification processes, and fraudulent behaviors evolve rapidly, often manifesting in complex, graph-structured interactions. Existing methods struggle in such settings. Pretraining routines typically overlook structural anomalies under limited supervision, while online models often fail to adapt to changing fraud patterns without labeled updates. To address these issues, we propose the Continual Fiedler Vector Graph model (ConFVG), a fraud detection framework designed for label-scarce and non-stationary environments.

ICLR 2026 Poster accepted paper at ICLR 2026. Accurate detection of clinically meaningful events in healthcare time-series data is crucial for reliable downstream analysis and decision support. However, most existing methods struggle to jointly localize event boundaries and classify event types; even detection transformer (DETR)-based approaches show limited performance when confronted with extremely sparse events typical of clinical recordings. To address these challenges, we propose a coarse-to-fine detection framework combining a global context explorer, a local detail inspector, and an adaptive gating module (AGM) that fuses multiple label perspectives. The AGM uses transformed labels—encoding event presence and temporal position—to improve learning on sparse events.

ICLR 2026 Poster accepted paper at ICLR 2026. Learning to Defer (L2D) improves AI reliability in decision-critical environments by training AI to either make its own prediction or defer the decision to a human expert. A key challenge is adapting to unseen experts at test time, whose competence can differ from the training population. Current methods for this task, however, can falter when unseen experts are out-of-distribution (OOD) relative to the training population. We identify a core architectural flaw as the cause: they learn identity-conditioned policies by processing class-indexed signals in fixed coordinates, creating shortcuts that violate the problem's inherent permutation symmetry.

ICLR 2026 Poster accepted paper at ICLR 2026. Healthcare data, such as Intensive Care Unit (ICU) records, comprise heterogeneous multivariate time series sampled at irregular intervals with pervasive missingness. However, clinical applications demand predictive models that are both accurate and interpretable. We present our Graph Attention-based Relational Learning for Intensive Care (GARLIC) model, a novel neural network architecture that imputes missing data through a learnable exponential-decay encoder, captures inter-sensor dependencies via time-lagged summary graphs, and fuses global patterns with cross-dimensional sequential attention. All attention weights and graph edges are learned end-to-end to serve as built-in observation-, signal-, and edge-level explanations.

ICLR 2026 Poster accepted paper at ICLR 2026. Electronic medical records (EMRs) are vital for healthcare research, but their use is limited by privacy concerns. Synthetic EMR generation offers a promising alternative, yet most existing methods merely imitate real records without adhering to rigorous clinical quality principles. To address this, we introduce LLM-CARe, a stage-wise cyclic refinement framework that progressively improves EMR quality through three stages, each targeting a specific granularity: corpus, section and document. At each stage, a Critic, an Adviser, and a Reviser collaborate iteratively to evaluate, provide feedback, and refine the drafts.

ICLR 2026 Oral accepted paper at ICLR 2026. Biosignals offer valuable insights into the physiological states of the human body. Although biosignal modalities differ in functionality, signal fidelity, sensor comfort, and cost, they are often intercorrelated, reflecting the holistic and interconnected nature of human physiology. This opens up the possibility of performing the same tasks using alternative biosignal modalities, thereby improving the accessibility, usability, and adaptability of health monitoring systems. However, the limited availability of large labeled datasets presents challenges for training models tailored to specific tasks and modalities of interest.

ICLR 2026 Poster accepted paper at ICLR 2026. Medical time series (MedTS) classification suffers from poor generalizability in real-world deployment due to inter- and intra-dataset heterogeneity, such as varying numbers of channels, signal lengths, task definitions, and patient characteristics. % implicit patient characteristics, variable channel configurations, time series lengths, and diagnostic tasks. To address this, we propose FORMED, a novel framework for repurposing a backbone foundation model, pre-trained on generic time series, to enable highly generalizable MedTS classification on unseen datasets. FORMED combines the backbone with a novel classifier comprising two components: (1) task-specific channel embeddings and label queries, dynamically sized to match any number of channels and target classes, and (2) a shared decoding attention layer, jointly trained across datasets to capture medical domain knowledge through task-agnostic feature-query interactions.

ICLR 2026 Poster accepted paper at ICLR 2026. Pan-cancer screening in large-scale CT scans remains challenging for existing AI methods, primarily due to the difficulty of localizing diverse types of tiny lesions in large CT volumes. The extreme foreground-background imbalance significantly hinders models from focusing on diseased regions, while redundant focus on healthy regions not only decreases the efficiency but also increases false positives. Inspired by radiologists' glance and focus diagnostic strategy, we introduce GF-Screen, a Glance and Focus reinforcement learning framework for pan-cancer screening. GF-Screen employs a Glance model to localize the diseased regions and a Focus model to precisely segment the lesions, where segmentation results of the Focus model are leveraged to reward the Glance model via Reinforcement Learning (RL). Code/project link: https://github.com/Luffy03/GF-Screen

ICLR 2026 Poster accepted paper at ICLR 2026. Federated learning (FL) is increasingly adopted in domains like healthcare, where data privacy is paramount. A fundamental challenge in these systems is statistical heterogeneity—the fact that data distributions vary significantly across clients (e.g., different hospitals may treat distinct patient demographics). While current FL algorithms focus on aggregating model updates from these heterogeneous clients, the potential of the central server remains under-explored. This paper is motivated by a healthcare scenario: could a central server not only coordinate model training but also guide a new patient to the hospital best equipped for their specific condition?

ICLR 2026 Poster accepted paper at ICLR 2026. Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, and recent advances have extended this paradigm to Multimodal Large Language Models (MLLMs). In the medical domain, where diagnostic decisions depend on nuanced visual cues and sequential reasoning, CoT aligns naturally with clinical thinking processes. However, current benchmarks for medical image understanding generally focus on the final answer while ignoring the reasoning path. An opaque process lacks reliable bases for judgment, making it difficult to assist doctors in diagnosis.

ICLR 2026 Poster accepted paper at ICLR 2026. LLMs are increasingly being used in healthcare. This promises to free physicians from drudgery, enabling better care to be delivered at scale. But the use of LLMs in this space also brings risks; for example, such models may worsen existing biases. How can we spot when LLMs are (spuriously) relying on patient race to inform predictions? In this work we assess the degree to which Sparse Autoencoders (SAEs) can reveal (and control) associations the model has made between race and stigmatizing concepts. We first identify SAE latents in gemma-2 models which appear to correlate with Black individuals.

ICLR 2026 Poster accepted paper at ICLR 2026. We present a systematic study of medical-domain interpretability in Large Language Models (LLMs). We study how the LLMs both represent and process medical knowledge through four different interpretability techniques: (1) UMAP projections of intermediate activations, (2) gradient-based saliency with respect to the model weights, (3) layer lesioning/removal and (4) activation patching. We present knowledge maps of five LLMs which show, at a coarse-resolution, where knowledge about patient's ages, medical symptoms, diseases and drugs is stored in the models. In particular for Llama3.3-70B, we find that most medical knowledge is processed in the first half of the model's layers.

ICLR 2026 Poster accepted paper at ICLR 2026. While LLMs have demonstrated medical knowledge and conversational ability, their deployment in clinical practice raises new risks: patients may place greater trust in LLM-generated responses than in nurses' professional judgments, potentially intensifying nurse–patient conflicts. Such risks highlight the urgent need of evaluating whether LLMs align with the core nursing values upheld by human nurses. This work introduces the first benchmark for nursing value alignment, consisting of five core value dimensions distilled from international nursing codes: _Altruism_, _Human Dignity_, _Integrity_, _Justice_, and _Professionalism_. We define two-level tasks on the benchmark, considering the two characteristics of emerging nurse–patient conflicts.

ICLR 2026 Poster accepted paper at ICLR 2026. The growing demand for prenatal ultrasound imaging has intensified a global shortage of trained sonographers, creating barriers to essential fetal health monitoring. Deep learning has the potential to enhance sonographers' efficiency and support the training of new practitioners. Vision-Language Models (VLMs) are particularly promising for ultrasound interpretation, as they can jointly process images and text to perform multiple clinical tasks within a single framework. However, despite the expansion of VLMs, no standardized benchmark exists to evaluate their performance in fetal ultrasound imaging. Code/project link: https://github.com/BioMedIA-MBZUAI/FETAL-GAUGE

ICLR 2026 Oral accepted paper at ICLR 2026. Accurate analysis of Medical time series (MedTS) data, such as Electroencephalography (EEG) and Electrocardiography (ECG), plays a pivotal role in healthcare applications, including the diagnosis of brain and heart diseases. MedTS data typically exhibits two critical patterns: **temporal dependencies** within individual channels and **channel dependencies** across multiple channels. While recent advances in deep learning have leveraged Transformer-based models to effectively capture temporal dependencies, they often struggle to model channel dependencies. This limitation stems from a structural mismatch: ***MedTS signals are inherently centralized, whereas the Transformer's attention is decentralized***, making it less effective at capturing global synchronization and unified waveform patterns. Code/project link: https://github.com/Levi-Ackman/TeCh

ICLR 2026 Poster accepted paper at ICLR 2026. Deploying clinical ML is slow and brittle: models that work at one hospital often degrade under distribution shifts at the next. In this work, we study a simple question -- can large language models (LLMs) create portable patient embeddings i.e. representations of patients enable a downstream predictor built on one hospital to be used elsewhere with minimal-to-no retraining and fine-tuning. To do so, we map from irregular ICU time series onto concise natural language summaries using a frozen LLM, then embed each summary with a frozen text embedding model to obtain a fixed length vector capable of serving as input to a variety of downstream predictors.

ICLR 2026 Poster accepted paper at ICLR 2026. Current medical language model (LM) benchmarks often over-simplify the complexities of day-to-day clinical practice tasks and instead rely on evaluating LMs on multiple-choice board exam questions. In psychiatry especially, these challenges are worsened by fairness and bias issues, since models can be swayed by patient demographics even when those factors should not influence clinical decisions. Thus, we present an expert-created and annotated dataset spanning five critical domains of decision-making in mental healthcare: treatment, diagnosis, documentation, monitoring, and triage. This U.S. centric dataset — created without any LM assistance — is designed to capture the nuanced clinical reasoning and daily ambiguities mental health practitioners encounter, reflecting the inherent complexities of care delivery that are missing from existing datasets.

ICLR 2026 Poster accepted paper at ICLR 2026. Body composition analysis through CT and MRI imaging provides critical insights for cardio-metabolic health assessment but remains limited by accessibility barriers including radiation exposure, high costs, and infrastructure requirements. We present AbdCTBench, a large-scale dataset containing 23,506 CT-derived abdominal surface meshes from 18,719 patients, paired with 87 comorbidity labels, 31 specific diagnosis codes, and 16 CT-derived biomarkers. Our key insight is that external surface geometry is predictive of internal tissue composition, enabling accessible health screening through consumer devices. We establish comprehensive benchmarks across seven computer vision architectures (ResNet-18/34/50, DenseNet-121, EfficientNet-B0, ViT-Small, Swin Transformer-Base), demonstrating that models can learn robust surface-to-biomarker representations directly from 2D mesh projections. Code/project link: https://abdctbenchrepo.github.io/AbdCTBench/

ICLR 2026 Poster 论文提出 MENTAT：一个由临床专家创建和标注、面向心理健康真实任务与模糊性的公平性评测数据集，用于评估语言模型在临床决策任务中的表现与偏差。

MIMIC-IV is a large deidentified electronic health record dataset from Beth Israel Deaconess Medical Center, covering hospital and ICU data for critical care research. It is a core benchmark source for clinical prediction, temporal EHR modeling, phenotyping, and healthcare AI method development.

国家医疗保障局公告的 2026 全国医学模拟人和健康传感器智能感知大赛，由国家医保局与湖南省人民政府联合举办，赛道覆盖 AI 虚拟病人、虚拟病人对话模拟、虚拟手术/诊疗系统、护理具身机器人和多类健康传感器智能感知设备。公告要求 2026-05-31 前报名、2026-06-10 前上传参赛项目信息。

HL7 healthcare AI challenge focused on AI applications around health data interoperability and standards-based workflows.

This Nature Portfolio / npj Health Systems collection is open for submissions until 2026-06-15. It focuses on software-powered healthcare, including clinical decision-making and AI integration, EHR and health-data infrastructures, telemedicine, remote care, multimodal agentic AI, trustworthiness, responsibility, alignment, and health-system workflows.

This SAGE / Design for Augmented Humanity special issue calls for papers on human-centred and augmented healthcare AI, including theories, applications, and methodologies. The CFP lists a paper submission deadline of 2026-05-30 and is relevant to clinical translation, trustworthy and explainable medical AI, human-AI collaboration, and clinical workflow AI.

This Technologies special issue calls for work on AI-enabled smart healthcare systems. It is relevant to medical AI submissions on intelligent monitoring, anomaly detection, assistive technologies, smart sensing, clinical decision support, and AI-assisted healthcare workflows. The page lists a manuscript submission deadline of 2026-08-30.

This Healthcare special issue focuses on artificial intelligence in public health, healthcare services, and management, including disease surveillance, outbreak prediction, GenAI in diagnostics, imaging and EHRs, patient engagement, and AI ethics and equity. The MDPI flyer lists a manuscript submission deadline of 2026-07-31.

This Applied Sciences special issue calls for novel approaches for machine learning in healthcare applications, with keywords including machine learning, deep learning, explainable AI, generative AI, BERT, GPT, and reinforcement learning. The page lists a manuscript submission deadline of 2026-06-30.

This Applied Sciences special issue calls for AI-driven healthcare work, including explainable and trustworthy AI, EHR and clinical text, bias and fairness, public health and epidemiology, translational AI, real-world clinical deployment, benchmarks, and reproducibility. The page lists a manuscript submission deadline of 2026-08-30.

This MDPI AI special issue calls for work on adversarial learning and its applications in healthcare, including robustness, privacy attacks and defenses, federated learning, generative AI for healthcare, and medical image analysis. The page lists a manuscript submission deadline of 2026-10-27.

The INFORMS Journal on Data Science CFP focuses on artificial intelligence and data science for healthcare. It is relevant to medical AI work on clinical prediction, decision support, operations, fairness, reliability, and deployment of data-driven healthcare systems. The CFP page lists a 2026 special issue call and submission timeline.

This Taylor & Francis / Risk Management and Healthcare Policy article collection focuses on artificial intelligence in healthcare risk management, including AI applications for early disease detection, personalized treatment optimization, real-time risk prediction, patient safety, and health-system risk management. The CFP listing gives a 2026-05-31 submission deadline.

CCF-Deadlines lists PRICAI 2026 with papers due 2026-06-13 UTC-12 and conference dates 2026-11-17 to 2026-11-20 in Guangzhou. PRICAI is a general AI venue relevant to medical AI methods, clinical decision support, medical agents, and trustworthy healthcare AI.

CCF-Deadlines lists NLPCC 2026 with papers due 2026-05-26 UTC+8 and conference dates 2026-11-03 to 2026-11-05 in Macau. NLPCC is relevant to Chinese clinical NLP, Chinese biomedical language resources, medical text mining, and healthcare question answering.

CCF-Deadlines lists ICTAI 2026 with papers due 2026-06-30 AoE and conference dates 2026-11-02 to 2026-11-04 in Boca Raton. ICTAI is relevant to medical AI tools, clinical decision-support systems, medical LLM agents, and deployable AI techniques for healthcare workflows.

CCF-Deadlines lists IEEE BigData 2026 with papers due 2026-08-21 AoE and conference dates 2026-12-14 to 2026-12-17 in Phoenix. IEEE BigData is relevant to healthcare big data, clinical data integration, EHR-scale prediction, biomedical multimodal analytics, and privacy-aware health data mining.

IEEE BIBM 2026 covers bioinformatics, biomedicine, and health informatics, including machine learning and AI, biomedical image analysis, biomedical signal analysis, clinical decision support, EHR standards, healthcare knowledge representation, NLP and text mining, and precision medicine. The official CFP lists electronic submission of full papers due 2026-07-05, notification on 2026-09-25, camera-ready on 2026-10-25, and the conference on 2026-12-01 to 2026-12-04 in Dallas.

Stanford MED277 / CS337 AI-Assisted Health Care examines how to move technical advances into clinical settings, choose the right healthcare problems, and improve outcomes that matter. It is geared toward learners who want to use AI and machine learning for real-world human health impact.

Stanford AI in Healthcare Leadership and Strategy is a four-week hybrid program for healthcare leaders. It covers AI strategy, governance, model performance and safety, clinical and operational value, implementation, change management, and responsible scaling of AI solutions in healthcare.

MIT OCW 6.S897 Machine Learning for Healthcare introduces clinical data and machine learning for risk stratification, disease progression modeling, precision medicine, diagnosis, subtype discovery, medical imaging, public health, and clinical workflow improvement.

MIT OCW HST.953 focuses on practical considerations for operationalizing machine learning in healthcare settings. It is relevant for learners moving from clinical data modeling into visualization, deployment, workflow, and real-world healthcare AI implementation.

This Microsoft Learn module helps healthcare professionals adopt Microsoft AI solutions. It covers goals and challenges in life sciences, pharmacology, and healthcare; opportunities for AI; healthcare provider use cases; and business value from AI in patient recovery and health operations.

FutureLearn's Artificial Intelligence for Healthcare course covers AI concepts, tools, ethics, diagnostics, patient care, operational efficiency, personalized medicine, and robotic surgery. The page lists 8 weeks at 2 hours per week and introductory level.

This University of Manchester and Health Education England FutureLearn course introduces AI for healthcare professionals, including how AI could support the workforce, real-world examples in radiology, pathology, nursing, ethical issues, logistics, and financial challenges. The page lists 5 weeks at 2 hours per week.

This University of Colorado System course introduces how AI shapes modern health systems, including key applications, adoption trends, digital transformation, health equity, and opportunities for addressing grand healthcare challenges. Coursera lists it as beginner level and 8 hours.

MIT course materials for machine learning methods in healthcare and clinical data.