Missed and delayed diagnosis remains a major challenge in rare disease care. At the initial clinical encounters, physicians assess rare disease risk using only limited information under high uncertainty. When high-risk patients are not recognised at this stage, targeted diagnostic testing is often not initiated, resulting in missed diagnosis. Existing primary care triage processes are structurally insufficient to reliably identify patients with rare diseases at initial clinical presentation and universal screening is needed to reduce diagnostic delay. Here we present RareAlert, an early screening system which predict patient-level rare disease risk from routinely available primary-visit information. RareAlert integrates reasoning generated by ten LLMs, calibrates and weights these signals using machine learning, and distils the aligned reasoning into a single locally deployable model. To develop and evaluate RareAlert, we curated RareBench, a real-world dataset of 158,666 cases covering 33 Orphanet disease categories and more than 7,000 rare conditions, including both rare and non-rare presentations. The results showed that rare disease identification can be reconceptualised as a u
Over the past 50 years, the advancements in medical and health research have radically changed the epidemiology of health conditions in neonates, children, and adolescents; and clinical research has on the whole, moved forward. However, large sections of the pediatric community remain vulnerable and underserved, by clinical research. One reason for this is the fact that most pediatric diseases are also rare diseases (i.e., they fit the EU definition of a rare condition, by affecting no more than 5 in 10,000 individuals), and indeed the majority of conditions under this umbrella heading are in fact much rarer, affecting fewer than 1 in 100,000. Rare pediatric diseases incur particular challenges, both in terms of actually conducting clinical trials but also planning trials (and indeed, stimulating the preclinical research and knowledge generation necessary to embark on clinical trials in the first place). The pediatric regulation and orphan regulation (covering rare diseases) were introduced to address the complexities in research and development of medicines specifically for children and for people living with a rare disease, respectively. The regulations have been reasonably effec
Despite the impressive capabilities of Large Language Models (LLMs) in general medical domains, questions remain about their performance in diagnosing rare diseases. To answer this question, we aim to assess the diagnostic performance of LLMs in rare diseases, and explore methods to enhance their effectiveness in this area. In this work, we introduce a rare disease question-answering (ReDis-QA) dataset to evaluate the performance of LLMs in diagnosing rare diseases. Specifically, we collected 1360 high-quality question-answer pairs within the ReDis-QA dataset, covering 205 rare diseases. Additionally, we annotated meta-data for each question, facilitating the extraction of subsets specific to any given disease and its property. Based on the ReDis-QA dataset, we benchmarked several open-source LLMs, revealing that diagnosing rare diseases remains a significant challenge for these models. To facilitate retrieval augmentation generation for rare disease diagnosis, we collect the first rare diseases corpus (ReCOP), sourced from the National Organization for Rare Disorders (NORD) database. Specifically, we split the report of each rare disease into multiple chunks, each representing a d
Despite rare diseases affecting 1 in 10 Americans, their differential diagnosis remains challenging. Due to their impressive recall abilities, large language models (LLMs) have been recently explored for differential diagnosis. Existing approaches to evaluating LLM-based rare disease diagnosis suffer from two critical limitations: they rely on idealized clinical case studies that fail to capture real-world clinical complexity, or they use ICD codes as disease labels, which significantly undercounts rare diseases since many lack direct mappings to comprehensive rare disease databases like Orphanet. To address these limitations, we explore MIMIC-RD, a rare disease differential diagnosis benchmark constructed by directly mapping clinical text entities to Orphanet. Our methodology involved an initial LLM-based mining process followed by validation from four medical annotators to confirm identified entities were genuine rare diseases. We evaluated various models on our dataset of 145 patients and found that current state-of-the-art LLMs perform poorly on rare disease differential diagnosis, highlighting the substantial gap between existing capabilities and clinical needs. From our findi
Large language models (LLMs) have demonstrated impressive capabilities in disease diagnosis. However, their effectiveness in identifying rarer diseases, which are inherently more challenging to diagnose, remains an open question. Rare disease performance is critical with the increasing use of LLMs in healthcare settings. This is especially true if a primary care physician needs to make a rarer prognosis from only a patient conversation so that they can take the appropriate next step. To that end, several clinical decision support systems are designed to support providers in rare disease identification. Yet their utility is limited due to their lack of knowledge of common disorders and difficulty of use. In this paper, we propose RareScale to combine the knowledge LLMs with expert systems. We use jointly use an expert system and LLM to simulate rare disease chats. This data is used to train a rare disease candidate predictor model. Candidates from this smaller model are then used as additional inputs to black-box LLM to make the final differential diagnosis. Thus, RareScale allows for a balance between rare and common diagnoses. We present results on over 575 rare diseases, beginnin
Rare diseases, despite their low individual incidence, collectively impact around 300 million people worldwide due to the vast number of diseases. The involvement of multiple organs and systems, and the shortage of specialized doctors with relevant experience, make diagnosing and treating rare diseases more challenging than common diseases. Recently, agents powered by large language models (LLMs) have demonstrated notable applications across various domains. In the medical field, some agent methods have outperformed direct prompts in question-answering tasks from medical examinations. However, current agent frameworks are not well-adapted to real-world clinical scenarios, especially those involving the complex demands of rare diseases. To bridge this gap, we introduce RareAgents, the first LLM-driven multi-disciplinary team decision-support tool designed specifically for the complex clinical context of rare diseases. RareAgents integrates advanced Multidisciplinary Team (MDT) coordination, memory mechanisms, and medical tools utilization, leveraging Llama-3.1-8B/70B as the base model. Experimental results show that RareAgents outperforms state-of-the-art domain-specific models, GPT
Domain-specific intelligence demands specialized knowledge and sophisticated reasoning for problem-solving, posing significant challenges for large language models (LLMs) that struggle with knowledge hallucination and inadequate reasoning capabilities under constrained parameter budgets. Inspired by Bloom's Taxonomy in educational theory, we propose Retrieval-Augmented Reasoning Modeling (RARE), a novel paradigm that decouples knowledge storage from reasoning optimization. RARE externalizes domain knowledge to retrievable sources and internalizes domain-specific reasoning patterns during training. Specifically, by injecting retrieved knowledge into training prompts with masked losses, RARE transforms learning objectives from rote memorization to contextualized reasoning. It enables models to bypass parameter-intensive memorization and prioritize the development of higher-order cognitive processes. Extensive experiments demonstrate that lightweight RARE-trained models (e.g., Llama-3.1-8B) could achieve state-of-the-art performance, surpassing retrieval-augmented GPT-4 and DeepSeek-R1 up to approximately 20\% accuracy. RARE establishes a paradigm shift where maintainable external kno
In this work, we develop first near-complete 3D models for NTD-hXPB - the N-terminal protein domain of the human transcription factor XPB. The results are very significant as NTD-hXPB plays a critical role in the synthesis of proteins (specifically transcription) and DNA damage repair (specifically nucleotide excision repair). NTD-hXPB is directly implicated in rare diseases XP-B, XP-CS, and TTD2, whose symptoms include neurodegenerative disorders, premature aging, and decreased fertility. NTDhXPB is also linked to anti-cancer therapies. As a bi-product we derived 3D models of NTD-mXPB - homologue of NTD-hXPB in mycobacterium tuberculosis aka MTB (causative agent of most cases of tuberculosis, which surpassed HIV as #1 infectious disease killer in 2014). These could be potential target for TB therapeutics. Our ab-initio modelling protocol takes advantage of recent powerful advances (prediction of contact residues) in protein structure modeling. Our protocol also includes human in the loop, inspired by the prevailing theory that computational abilities of human minds can be powerfully harnessed in engineering/problem-solving. Using the developed models in this paper, we are able to
Rare diseases are collectively common, affecting approximately one in twenty individuals worldwide. In recent years, rapid progress has been made in rare disease diagnostics due to advances in DNA sequencing, development of new computational and experimental approaches to prioritize genes and genetic variants, and increased global exchange of clinical and genetic data. However, more than half of individuals suspected to have a rare disease lack a genetic diagnosis. The Genomics Research to Elucidate the Genetics of Rare Diseases (GREGoR) Consortium was initiated to study thousands of challenging rare disease cases and families and apply, standardize, and evaluate emerging genomics technologies and analytics to accelerate their adoption in clinical practice. Further, all data generated, currently representing ~7500 individuals from ~3000 families, is rapidly made available to researchers worldwide via the Genomic Data Science Analysis, Visualization, and Informatics Lab-space (AnVIL) to catalyze global efforts to develop approaches for genetic diagnoses in rare diseases (https://gregorconsortium.org/data). The majority of these families have undergone prior clinical genetic testing
The emergence of generative Large Language Models (LLMs) emphasizes the need for accurate and efficient prompting approaches. LLMs are often applied in Few-Shot Learning (FSL) contexts, where tasks are executed with minimal training data. FSL has become popular in many Artificial Intelligence (AI) subdomains, including AI for health. Rare diseases affect a small fraction of the population. Rare disease identification from clinical notes inherently requires FSL techniques due to limited data availability. Manual data collection and annotation is both expensive and time-consuming. In this paper, we propose Models-Vote Prompting (MVP), a flexible prompting approach for improving the performance of LLM queries in FSL settings. MVP works by prompting numerous LLMs to perform the same tasks and then conducting a majority vote on the resulting outputs. This method achieves improved results to any one model in the ensemble on one-shot rare disease identification and classification tasks. We also release a novel rare disease dataset for FSL, available to those who signed the MIMIC-IV Data Use Agreement (DUA). Furthermore, in using MVP, each model is prompted multiple times, substantially in
Generalist Large Language Models (LLMs), such as GPT-4, have shown considerable promise in various domains, including medical diagnosis. Rare diseases, affecting approximately 300 million people worldwide, often have unsatisfactory clinical diagnosis rates primarily due to a lack of experienced physicians and the complexity of differentiating among many rare diseases. In this context, recent news such as "ChatGPT correctly diagnosed a 4-year-old's rare disease after 17 doctors failed" underscore LLMs' potential, yet underexplored, role in clinically diagnosing rare diseases. To bridge this research gap, we introduce RareBench, a pioneering benchmark designed to systematically evaluate the capabilities of LLMs on 4 critical dimensions within the realm of rare diseases. Meanwhile, we have compiled the largest open-source dataset on rare disease patients, establishing a benchmark for future studies in this domain. To facilitate differential diagnosis of rare diseases, we develop a dynamic few-shot prompt methodology, leveraging a comprehensive rare disease knowledge graph synthesized from multiple knowledge bases, significantly enhancing LLMs' diagnostic performance. Moreover, we pres
Rare diseases affect over 300 million individuals worldwide, yet timely and accurate diagnosis remains an urgent challenge. Patients often endure a prolonged diagnostic odyssey exceeding five years, marked by repeated referrals, misdiagnoses, and unnecessary interventions, leading to delayed treatment and substantial emotional and economic burdens. Here we present DeepRare, a multi-agent system for rare disease differential diagnosis decision support powered by large language models, integrating over 40 specialized tools and up-to-date knowledge sources. DeepRare processes heterogeneous clinical inputs, including free-text descriptions, structured Human Phenotype Ontology terms, and genetic testing results, to generate ranked diagnostic hypotheses with transparent reasoning linked to verifiable medical evidence. Evaluated across nine datasets from literature, case reports and clinical centres across Asia, North America and Europe spanning 14 medical specialties, DeepRare demonstrates exceptional performance on 3,134 diseases. In human-phenotype-ontology-based tasks, it achieves an average Recall@1 of 57.18%, outperforming the next-best method by 23.79%; in multi-modal tests, it rea
Background: The web has become a primary information resource about illnesses and treatments for both medical and non-medical users. Standard web search is by far the most common interface for such information. It is therefore of interest to find out how well web search engines work for diagnostic queries and what factors contribute to successes and failures. Among diseases, rare (or orphan) diseases represent an especially challenging and thus interesting class to diagnose as each is rare, diverse in symptoms and usually has scattered resources associated with it. Methods: We use an evaluation approach for web search engines for rare disease diagnosis which includes 56 real life diagnostic cases, state-of-the-art evaluation measures, and curated information resources. In addition, we introduce FindZebra, a specialized (vertical) rare disease search engine. FindZebra is powered by open source search technology and uses curated freely available online medical information. Results: FindZebra outperforms Google Search in both default setup and customised to the resources used by FindZebra. We extend FindZebra with specialized functionalities exploiting medical ontological information
Effective public health decisions require early reliable inference of infectious disease properties. In this paper we assess the ability to infer infectious disease attributes from population-level stochastic epidemic trajectories. In particular, we construct stochastic Kermack-McKendrick model trajectories, sample them with and without observational error, and evaluate inversions for the population mean infectiousness as a function of time since infection, the infection duration distribution, and its complementary cumulative distribution, the infection survival distribution. Based on an integro-differential equation formulation we employ a natural regression approach to fit the corresponding integral kernels and show that these disease attributes are recoverable from both multi-trajectory inversions and regularized single trajectory inversions. Moreover, we demonstrate that the infection duration distribution (or alternatively the infection survival distribution) and population mean infectiousness kernel recovered can be used to solve for the individual infectiousness profile, the infectiousness of an individual over the duration of their infection, assuming that individual infect
The use of nanoparticles for targeted drug delivery, especially in diseased arteries, is a novel procedure. We are incorporating nanoparticles into blood vessels using a catheter, which could potentially deliver drugs precisely to affected areas, reducing side effects and increasing treatment efficiency. Considering non-Newtonian fluid modeling because blood is a complex fluid with non-linear behavior. In this paper, we are using mathematical modeling to understand blood flow dynamics, temperature, and concentration dispersion, which can provide valuable insights into the behavior of therapeutic nanoparticles in the bloodstream. The perturbation method is used to solve the complex mathematical model with permeable flow boundary conditions. We are investigating flow field characteristics including wall shear stress, pressure, and impedance to understand how nanoparticles disperse and interact with different physiological aspects. In conclusion, the proposed study focuses on the use of nanotechnology and mathematical modeling to understand the effects of therapeutic nanoparticles in diseased arteries, which is an important and valuable contribution to the medical field.
Developing drugs for rare diseases presents unique challenges from a statistical perspective. These challenges may include slowly progressive diseases with unmet medical needs, poorly understood natural history, small population size, diversified phenotypes and geneotypes within a disorder, and lack of appropriate surrogate endpoints to measure clinical benefits. The Real-World Evidence (RWE) Scientific Working Group of the American Statistical Association Biopharmaceutical Section has assembled a research team to assess the landscape including challenges and possible strategies to address these challenges and the role of real-world data (RWD) and RWE in rare disease drug development. This paper first reviews the current regulations by regulatory agencies worldwide and then discusses in more details the challenges from a statistical perspective in the design, conduct, and analysis of rare disease clinical trials. After outlining an overall development pathway for rare disease drugs, corresponding strategies to address the aforementioned challenges are presented. Other considerations are also discussed for generating relevant evidence for regulatory decision-making on drugs for rare
Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports. We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients.
Due to the aging of the world population and westernization of lifestyles, the prevalence of neurodegenerative diseases such as Alzheimer's disease (AD) and Parkinson's disease (PD) is rapidly rising and is expected to put a strong socioeconomic burden on health systems worldwide. Due to the limited success of clinical trials of therapies against neurodegenerative diseases, research has extended its scope to a systems medicine point of view, with a particular focus on the gastrointestinal-brain axis as a potential main actor in disease development and progression. Microbiome as well as metabolome studies along the gastrointestinal-brain axis have already revealed important insights into disease pathomechanisms. Both the microbiome and metabolome can be easily manipulated by dietary and lifestyle interventions, and might thus offer novel, readily available therapeutic options to prevent the onset as well as the progression of PD and AD. This review summarizes our current knowledge on the association between microbiota, metabolites, and neurodegeneration in light of the gastrointestinal-brain axis. In this context, we also illustrate state-of-the art methods of microbiome and metabol
The rising prevalence of vision-threatening retinal diseases poses a significant burden on the global healthcare systems. Deep learning (DL) offers a promising solution for automatic disease screening but demands substantial data. Collecting and labeling large volumes of ophthalmic images across various modalities encounters several real-world challenges, especially for rare diseases. Here, we introduce EyeDiff, a text-to-image model designed to generate multimodal ophthalmic images from natural language prompts and evaluate its applicability in diagnosing common and rare diseases. EyeDiff is trained on eight large-scale datasets using the advanced latent diffusion model, covering 14 ophthalmic image modalities and over 80 ocular diseases, and is adapted to ten multi-country external datasets. The generated images accurately capture essential lesional characteristics, achieving high alignment with text prompts as evaluated by objective metrics and human experts. Furthermore, integrating generated images significantly enhances the accuracy of detecting minority classes and rare eye diseases, surpassing traditional oversampling methods in addressing data imbalance. EyeDiff effectivel
In rare disease physician targeting, a major challenge is how to identify physicians who are treating diagnosed or underdiagnosed rare diseases patients. Rare diseases have extremely low incidence rate. For a specified rare disease, only a small number of patients are affected and a fractional of physicians are involved. The existing targeting methodologies, such as segmentation and profiling, are developed under mass market assumption. They are not suitable for rare disease market where the target classes are extremely imbalanced. The authors propose a graphical model approach to predict targets by jointly modeling physician and patient features from different data spaces and utilizing the extra relational information. Through an empirical example with medical claim and prescription data, the proposed approach demonstrates better accuracy in finding target physicians. The graph representation also provides visual interpretability of relationship among physicians and patients. The model can be extended to incorporate more complex dependency structures. This article contributes to the literature of exploring the benefit of utilizing relational dependencies among entities in healthca