RESUMO
The historical reliance of biological research on the use of animal models has sometimes made it challenging to address questions that are specific to the understanding of human biology and disease. But with the advent of human organoids - which are stem cell-derived 3D culture systems - it is now possible to re-create the architecture and physiology of human organs in remarkable detail. Human organoids provide unique opportunities for the study of human disease and complement animal models. Human organoids have been used to study infectious diseases, genetic disorders and cancers through the genetic engineering of human stem cells, as well as directly when organoids are generated from patient biopsy samples. This Review discusses the applications, advantages and disadvantages of human organoids as models of development and disease and outlines the challenges that have to be overcome for organoids to be able to substantially reduce the need for animal experiments.
Assuntos
Biologia/métodos , Medicina/métodos , Organoides/fisiologia , Animais , Doenças Transmissíveis/patologia , Doenças Genéticas Inatas/patologia , Engenharia Genética/métodos , Humanos , Neoplasias/patologia , Células-Tronco/fisiologiaRESUMO
Large language models (LLMs) have demonstrated impressive capabilities, but the bar for clinical applications is high. Attempts to assess the clinical knowledge of models typically rely on automated evaluations based on limited benchmarks. Here, to address these limitations, we present MultiMedQA, a benchmark combining six existing medical question answering datasets spanning professional medicine, research and consumer queries and a new dataset of medical questions searched online, HealthSearchQA. We propose a human evaluation framework for model answers along multiple axes including factuality, comprehension, reasoning, possible harm and bias. In addition, we evaluate Pathways Language Model1 (PaLM, a 540-billion parameter LLM) and its instruction-tuned variant, Flan-PaLM2 on MultiMedQA. Using a combination of prompting strategies, Flan-PaLM achieves state-of-the-art accuracy on every MultiMedQA multiple-choice dataset (MedQA3, MedMCQA4, PubMedQA5 and Measuring Massive Multitask Language Understanding (MMLU) clinical topics6), including 67.6% accuracy on MedQA (US Medical Licensing Exam-style questions), surpassing the prior state of the art by more than 17%. However, human evaluation reveals key gaps. To resolve this, we introduce instruction prompt tuning, a parameter-efficient approach for aligning LLMs to new domains using a few exemplars. The resulting model, Med-PaLM, performs encouragingly, but remains inferior to clinicians. We show that comprehension, knowledge recall and reasoning improve with model scale and instruction prompt tuning, suggesting the potential utility of LLMs in medicine. Our human evaluations reveal limitations of today's models, reinforcing the importance of both evaluation frameworks and method development in creating safe, helpful LLMs for clinical applications.
Assuntos
Benchmarking , Simulação por Computador , Conhecimento , Medicina , Processamento de Linguagem Natural , Viés , Competência Clínica , Compreensão , Conjuntos de Dados como Assunto , Licenciamento , Medicina/métodos , Medicina/normas , Segurança do Paciente , MédicosRESUMO
The exceptionally rapid development of highly flexible, reusable artificial intelligence (AI) models is likely to usher in newfound capabilities in medicine. We propose a new paradigm for medical AI, which we refer to as generalist medical AI (GMAI). GMAI models will be capable of carrying out a diverse set of tasks using very little or no task-specific labelled data. Built through self-supervision on large, diverse datasets, GMAI will flexibly interpret different combinations of medical modalities, including data from imaging, electronic health records, laboratory results, genomics, graphs or medical text. Models will in turn produce expressive outputs such as free-text explanations, spoken recommendations or image annotations that demonstrate advanced medical reasoning abilities. Here we identify a set of high-impact potential applications for GMAI and lay out specific technical capabilities and training datasets necessary to enable them. We expect that GMAI-enabled applications will challenge current strategies for regulating and validating AI devices for medicine and will shift practices associated with the collection of large medical datasets.
Assuntos
Inteligência Artificial , Medicina , Diagnóstico por Imagem , Registros Eletrônicos de Saúde , Genômica , Conjuntos de Dados como Assunto , Aprendizado de Máquina não Supervisionado , HumanosRESUMO
Increasing volumes of biomedical data are amassing in databases. Large-scale analyses of these data have wide-ranging applications in biology and medicine. Such analyses require tools to characterize and process entries at scale. However, existing tools, mainly centered on extracting predefined fields, often fail to comprehensively process database entries or correct evident errors-a task humans can easily perform. These tools also lack the ability to reason like domain experts, hindering their robustness and analytical depth. Recent advances with large language models (LLMs) provide a fundamentally new way to query databases. But while a tool such as ChatGPT is adept at answering questions about manually input records, challenges arise when scaling up this process. First, interactions with the LLM need to be automated. Second, limitations on input length may require a record pruning or summarization pre-processing step. Third, to behave reliably as desired, the LLM needs either well-designed, short, 'few-shot' examples, or fine-tuning based on a larger set of well-curated examples. Here, we report ChIP-GPT, based on fine-tuning of the generative pre-trained transformer (GPT) model Llama and on a program prompting the model iteratively and handling its generation of answer text. This model is designed to extract metadata from the Sequence Read Archive, emphasizing the identification of chromatin immunoprecipitation (ChIP) targets and cell lines. When trained with 100 examples, ChIP-GPT demonstrates 90-94% accuracy. Notably, it can seamlessly extract data from records with typos or absent field labels. Our proposed method is easily adaptable to customized questions and different databases.
Assuntos
Medicina , Humanos , Linhagem Celular , Imunoprecipitação da Cromatina , Bases de Dados Factuais , IdiomaRESUMO
Enhancers play an important role in the process of gene expression regulation. In DNA sequence abundance or absence of enhancers and irregularities in the strength of enhancers affects gene expression process that leads to the initiation and propagation of diverse types of genetic diseases such as hemophilia, bladder cancer, diabetes and congenital disorders. Enhancer identification and strength prediction through experimental approaches is expensive, time-consuming and error-prone. To accelerate and expedite the research related to enhancers identification and strength prediction, around 19 computational frameworks have been proposed. These frameworks used machine and deep learning methods that take raw DNA sequences and predict enhancer's presence and strength. However, these frameworks still lack in performance and are not useful in real time analysis. This paper presents a novel deep learning framework that uses language modeling strategies for transforming DNA sequences into statistical feature space. It applies transfer learning by training a language model in an unsupervised fashion by predicting a group of nucleotides also known as k-mers based on the context of existing k-mers in a sequence. At the classification stage, it presents a novel classifier that reaps the benefits of two different architectures: convolutional neural network and attention mechanism. The proposed framework is evaluated over the enhancer identification benchmark dataset where it outperforms the existing best-performing framework by 5%, and 9% in terms of accuracy and MCC. Similarly, when evaluated over the enhancer strength prediction benchmark dataset, it outperforms the existing best-performing framework by 4%, and 7% in terms of accuracy and MCC.
Assuntos
Benchmarking , Medicina , Redes Neurais de Computação , Nucleotídeos , Sequências Reguladoras de Ácido NucleicoRESUMO
Here we describe the LifeTime Initiative, which aims to track, understand and target human cells during the onset and progression of complex diseases, and to analyse their response to therapy at single-cell resolution. This mission will be implemented through the development, integration and application of single-cell multi-omics and imaging, artificial intelligence and patient-derived experimental disease models during the progression from health to disease. The analysis of large molecular and clinical datasets will identify molecular mechanisms, create predictive computational models of disease progression, and reveal new drug targets and therapies. The timely detection and interception of disease embedded in an ethical and patient-centred vision will be achieved through interactions across academia, hospitals, patient associations, health data management systems and industry. The application of this strategy to key medical challenges in cancer, neurological and neuropsychiatric disorders, and infectious, chronic inflammatory and cardiovascular diseases at the single-cell level will usher in cell-based interceptive medicine in Europe over the next decade.
Assuntos
Terapia Baseada em Transplante de Células e Tecidos , Atenção à Saúde/métodos , Atenção à Saúde/tendências , Medicina/métodos , Medicina/tendências , Patologia , Análise de Célula Única , Inteligência Artificial , Atenção à Saúde/ética , Atenção à Saúde/normas , Diagnóstico Precoce , Educação Médica , Europa (Continente) , Feminino , Saúde , Humanos , Legislação Médica , Masculino , Medicina/normasRESUMO
This year's Lasker Basic Science Award recognizes the invention of AlphaFold, a revolutionary advance in the history of protein research which for the first time offers the practical ability to accurately predict the three-dimensional arrangement of amino acids in the vast majority of proteins on a genomic scale on the basis of sequence alone [J. Jumper et al., Nature 596, 583-589 (2021) and K. Tunyasuvunakool et al., Nature 596, 590-596 (2021)]. This extraordinary achievement by Demis Hassabis and John Jumper and their coworkers at Google's DeepMind and other collaborators was built on decades of experimental protein structure determination (structural biology) as well as the gradual development of multiple strategies incorporating biologically inspired statistical approaches. But when Jumper and Hassabis added a brew of innovative neural network-based machine learning approaches to the mix, the results were explosive. Realizing the half-century-old dream of predicting protein structure has already accelerated the pace and creativity of many areas of Chemistry, Biology, and Medicine.
Assuntos
Distinções e Prêmios , Medicina , Aminoácidos , Genômica , Aprendizado de MáquinaRESUMO
These are no ordinary times and Piet Borst is no ordinary scientist. In a world challenged by existential threats such as pandemics, climate change and the consequent upsurge in populism, flagrant disinformation, and the global distrust of science and technology, the statesman scientist is a necessary and rare being. Piet Borst has embraced that role for most of his life while remaining a superb biochemist. Borst is this year's winner of the Lasker-Koshland Special Achievement Award in Medical Science "for research accomplishments and scientific statesmanship that engender the deepest feelings of awe and respect".
Assuntos
Distinções e Prêmios , Medicina , Mudança Climática , Desinformação , EmoçõesRESUMO
Recent advances in mRNA technology and its delivery have enabled mRNA-based therapeutics to enter a new era in medicine. The rapid, potent, and transient nature of mRNA-encoded proteins, without the need to enter the nucleus or the risk of genomic integration, makes them desirable tools for treatment of a range of diseases, from infectious diseases to cancer and monogenic disorders. The rapid pace and ease of mass-scale manufacturability of mRNA-based therapeutics supported the global response to the COVID-19 pandemic. Nonetheless, challenges remain with regards to mRNA stability, duration of expression, delivery efficiency, and targetability, to broaden the applicability of mRNA therapeutics beyond COVID-19 vaccines. By learning from the rapidly expanding preclinical and clinical studies, we can optimise the mRNA platform to meet the clinical needs of each disease. Here, we will summarise the recent advances in mRNA technology; its use in vaccines, immunotherapeutics, protein replacement therapy, and genomic editing; and its delivery to desired specific cell types and organs for development of a new generation of targeted mRNA-based therapeutics.
Assuntos
COVID-19 , Medicina , Humanos , Vacinas contra COVID-19 , COVID-19/prevenção & controle , Pandemias , RNA Mensageiro/uso terapêuticoRESUMO
Prediction of drug-target interactions (DTIs) is essential in medicine field, since it benefits the identification of molecular structures potentially interacting with drugs and facilitates the discovery and reposition of drugs. Recently, much attention has been attracted to network representation learning to learn rich information from heterogeneous data. Although network representation learning algorithms have achieved success in predicting DTI, several manually designed meta-graphs limit the capability of extracting complex semantic information. To address the problem, we introduce an adaptive meta-graph-based method, termed AMGDTI, for DTI prediction. In the proposed AMGDTI, the semantic information is automatically aggregated from a heterogeneous network by training an adaptive meta-graph, thereby achieving efficient information integration without requiring domain knowledge. The effectiveness of the proposed AMGDTI is verified on two benchmark datasets. Experimental results demonstrate that the AMGDTI method overall outperforms eight state-of-the-art methods in predicting DTI and achieves the accurate identification of novel DTIs. It is also verified that the adaptive meta-graph exhibits flexibility and effectively captures complex fine-grained semantic information, enabling the learning of intricate heterogeneous network topology and the inference of potential drug-target relationship.
Assuntos
Algoritmos , Medicina , Benchmarking , Sistemas de Liberação de Medicamentos , SemânticaRESUMO
Large language models (LLMs) are artificial intelligence models trained on vast text data to generate humanlike outputs. They have been applied to various tasks in health care, ranging from answering medical examination questions to generating clinical reports. With increasing institutional partnerships between companies producing LLMs and health systems, the real-world clinical application of these models is nearing realization. As these models gain traction, health care practitioners must understand what LLMs are, their development, their current and potential applications, and the associated pitfalls in a medical setting. This review, coupled with a tutorial, provides a comprehensive yet accessible overview of these areas with the aim of familiarizing health care professionals with the rapidly changing landscape of LLMs in medicine. Furthermore, the authors highlight active research areas in the field that promise to improve LLMs' usability in health care contexts.
Assuntos
Inteligência Artificial , Medicina , Humanos , Pessoal de Saúde , IdiomaRESUMO
The 2023 United States infectious diseases (ID) fellowship match resulted in a large percentage of programs with unfilled positions. A survey was sent to ID program directors nationwide to better understand their perceptions on the match. Program directors perceived geography, a small applicant pool, and low specialty pay as contributing factors to the match results. Developing specialized fellowship tracks, increasing funding for the ID trainee pipeline, and national advocacy for higher compensation were identified as areas to focus on to increase the applicant pool. Areas of controversy, such as decreasing the number or size of fellowship programs, require further discussion.
Assuntos
Bolsas de Estudo , Medicina , Estados Unidos , Inquéritos e QuestionáriosRESUMO
The percentage of infectious diseases (ID) fellowship positions filled has declined in the last years despite a relatively stable number of applicants. The data are concerning since this could impact an already strained workforce. A recent survey of ID fellowship program directors provides insight into the perceptions of program directors about factors that might have affected the match rate in 2023 and could also be applicable to the recent 2024 match. Here, we discuss the results of this survey and discuss the complex factors that might influence the choice of ID as an specialty. Although concerning, recent fellowship match results provide new opportunities to reassess current models of ID training and design innovative strategies for ID fellowship and education.
Assuntos
Internato e Residência , Medicina , Educação de Pós-Graduação em Medicina , Inquéritos e Questionários , Bolsas de EstudoRESUMO
BACKGROUND: Analysis of time-resolved postprandial metabolomics data can improve the understanding of metabolic mechanisms, potentially revealing biomarkers for early diagnosis of metabolic diseases and advancing precision nutrition and medicine. Postprandial metabolomics measurements at several time points from multiple subjects can be arranged as a subjects by metabolites by time points array. Traditional analysis methods are limited in terms of revealing subject groups, related metabolites, and temporal patterns simultaneously from such three-way data. RESULTS: We introduce an unsupervised multiway analysis approach based on the CANDECOMP/PARAFAC (CP) model for improved analysis of postprandial metabolomics data guided by a simulation study. Because of the lack of ground truth in real data, we generate simulated data using a comprehensive human metabolic model. This allows us to assess the performance of CP models in terms of revealing subject groups and underlying metabolic processes. We study three analysis approaches: analysis of fasting-state data using principal component analysis, T0-corrected data (i.e., data corrected by subtracting fasting-state data) using a CP model and full-dynamic (i.e., full postprandial) data using CP. Through extensive simulations, we demonstrate that CP models capture meaningful and stable patterns from simulated meal challenge data, revealing underlying mechanisms and differences between diseased versus healthy groups. CONCLUSIONS: Our experiments show that it is crucial to analyze both fasting-state and T0-corrected data for understanding metabolic differences among subject groups. Depending on the nature of the subject group structure, the best group separation may be achieved by CP models of T0-corrected or full-dynamic data. This study introduces an improved analysis approach for postprandial metabolomics data while also shedding light on the debate about correcting baseline values in longitudinal data analysis.
Assuntos
Medicina , Metabolômica , Humanos , Simulação por Computador , Análise de Dados , Nível de SaúdeRESUMO
Adults with Down syndrome are at an increased risk for developing certain medical conditions, which can be further exacerbated by lower levels of physical activity. Physician counseling can provide a supportive environment to encourage modes of physical activity accessible to patients and caregivers. While some adults with Down syndrome have access to a Down syndrome specialty clinic, most are followed only by a primary care physician. This report includes adult patients with Down syndrome followed at a Down syndrome specialty clinic in Boston and compares physical activity assessment and counseling rates by Down syndrome specialists and primary care physicians. Patients were more likely to have physical activity assessment and counseling performed by a Down syndrome specialist than by a primary care physician. A better understanding of the barriers primary care physicians caring for adults with Down syndrome experience related to physical activity counseling could help improve important health habit counseling in this high-risk population.
Assuntos
Síndrome de Down , Medicina , Adulto , Humanos , Síndrome de Down/complicações , Aconselhamento , Exercício Físico , Fatores de RiscoRESUMO
The Lancet celebrates its 200th anniversary in 2023. In this survey of the journal's history, we explore how it has contributed to shaping medicine both in the UK and internationally, and how it has demonstrated a commitment to "The best science for better lives". For two centuries, the journal has published pioneering articles on key developments in medical science and the organisation of health care. We explore the campaigning and advocacy work of the journal through several indicative areas where science and policy meet, balancing national and global themes over the 19th and 20th centuries. Themes include the raising of professional standards; environmental health in urbanising Britain; the transformation of surgery; the emergence of tropical medicine; the science and politics of vaccination; the advance towards universal health coverage; and the transition from international to global health. In the imperial era, both the journal's research reports and editorial stance were sometimes inflected with colonial attitudes, although it consistently presented medicine as an international endeavour. The Lancet's blend of science and advocacy demonstrates a track record of campaigning for medicine in the cause of social betterment.
Assuntos
Bibliometria , Medicina , Humanos , Aniversários e Eventos Especiais , Políticas , Atenção à SaúdeRESUMO
The emergence of the planetary health approach was highlighted by the report of The Rockefeller Foundation-Lancet Commission on Planetary Health in 2015 and changed how we comprehend human well-being. The report advocates integrating the health of other living beings and Earth's natural systems as intrinsic components of human health. Drawing on over three decades of experience in respiratory epidemiology and environmental health, this article outlines how my perspective on human health underwent a transformative shift upon reading the abovementioned report. The planetary health approach offers a lens through which human health issues and potential solutions can be understood within the context of the Anthropocene. It addresses the pressing existential challenges arising from humanity's transgression of planetary limits. Embracing the planetary health paradigm within the field of health sciences can catalyze transformative changes essential for cultivating a sustainable and equitable future.
Assuntos
Saúde Ambiental , Medicina , Humanos , Planeta Terra , PrevisõesRESUMO
PURPOSE: Combinatorial pharmacogenetic (PGx) panels intended to aid psychiatric prescribing are available to clinicians. Here, we evaluated the documentation of PGx panel results and subsequent prescribing patterns within a tertiary health care system. METHODS: We performed a query of psychiatry service note text in our electronic health record using 71 predefined PGx terms. Patients who underwent combinatorial PGx testing were identified, and documentation of test results was analyzed. Prescription data following testing were examined for the frequency of prescriptions influenced by genes on the panel along with the medical specialties involved. RESULTS: A total of 341 patients received combinatorial PGx testing, and documentation of results was found to be absent or incomplete for 198 patients (58%). The predominant method of documentation was through portable document formats uploaded to the electronic health record's "Media" section. Among patients with at least 1 year of follow-up, a large majority (194/228, 85%) received orders for medications affected by the tested genes, including 132 of 228 (58%) patients receiving at least 1 non-psychiatric medication influenced by the test results. CONCLUSION: Results from combinatorial PGx testing were poorly documented. Medications affected by these results were often prescribed after testing, highlighting the need for discrete results and clinical decision support.
Assuntos
Sistemas de Apoio a Decisões Clínicas , Medicina , Humanos , Farmacogenética/métodos , Prescrições de Medicamentos , Registros Eletrônicos de SaúdeRESUMO
PURPOSE OF REVIEW: The purpose of this review is to highlight the importance of a multidisciplinary thrombotic microangiopathies (TMA) Team. This goal will be accomplished through review of the complement system, discuss various causes of thrombotic microangiopathies (TMA), and aspects of their diagnosis and management. In so doing, readers will gain an appreciation for the complexity of this family of disorders and realize the benefit of a dedicated multidisciplinary TMA Team. RECENT FINDINGS: TMA causes derive from multiple specialty areas, are difficult to timely recognize, pose complex challenges, and require multidisciplinary management. Hematopoietic stem cell transplant-associated TMA (TA-TMA) and TA-TMA related multiorgan dysfunction syndrome (TA-TMA MODS) are areas of burgeoning research; use of complement testing and eculizumab precision-dosing has been found to better suppress complement activity in TA-TMA than standard eculizumab dosing. Newer tests are available to risk-stratify obstetric patients at risk for severe pre-eclampsia, whose features resemble those of TA-TMA MODS. Numerous disorders may produce TMA-like findings, and a systematic approach aids in their identification. TMA Teams elevate institutional awareness of increasingly recognized TMAs, will help expedite diagnostic and therapeutic interventions, and create pathways to future TMA-related research and facilitate access to clinical trials. SUMMARY: Establishment of a TMA-Team is valuable in developing the necessary institutional expertise needed to promptly recognize and appropriately manage patients with TMA.