MIMIC-IV v2.2
English
United States, Cambridge
the Beth Israel Deaconess Medical Center
数据描述
No dataset description found.
physionet.org
IP: 18.18.42.54
加载中...
相关论文
21NutriSighT: Interpretable Transformer Model for Dynamic Prediction of Underfeeding Enteral Nutrition in Mechanically Ventilated Patients
Mateen Jangda•Jayshil Patel•Akhil Vaid•Jaskirat Gill•Paul McCarthy等 20 人
Nature Communications
2025
•2025/12/17
•Vol.16 No.1 p.111890
Achieving adequate enteral nutrition among mechanically ventilated patients is challenging, yet critical. We develop NutriSighT, a transformer model using learnable positional encodings to predict which patients would be underfed (receive less than 70% daily caloric requirements) between days 3-7 of...
Computational modelsTranslational research
10.1038/S41467-025-66200-1
ISSN:2041-1723
Unlocking the potential of real-time ICU mortality prediction: redefining risk assessment with continuous data recovery
Puguang Xie•Yu Hu•Jiao Li•Yu Ma•Jingjing Xiao
Npj Digital Medicine
2025
•2025/11/28
•Vol.8 No.1 p.7330
Real-time prediction of short-term mortality risk in the intensive care unit (ICU) is often hampered by missing medical data. To address this, we developed RealMIP, an end-to-end framework leveraging generative model for the dynamic imputation of missing values and continuous mortality risk assessme...
Computational biology and bioinformaticsDiseasesHealth careMedical researchRisk factors
10.1038/S41746-025-02114-Y
ISSN:2398-6352
Zero shot health trajectory prediction using transformer
Pawel Renc•Yugang Jia•Anthony E. Samir•Jaroslaw Was•Quanzheng Li等 7 人
Npj Digital Medicine
2024
•2024/9/19
•Vol.7 No.1 p.1-10
Integrating modern machine learning and clinical decision-making has great promise for mitigating healthcare’s increasing cost and complexity. We introduce the Enhanced Transformer for Health Outcome Simulation (ETHOS), a novel application of the transformer deep-learning architecture for analyzing ...
DiseasesHealth care
10.1038/S41746-024-01235-0
ISSN:2398-6352
An optimal antibiotic selection framework for Sepsis patients using Artificial Intelligence
Philipp Wendland•Christof Schenkel-Häger•Ingobert Wenningmann•Maik Kschischo
Npj Digital Medicine
2024
•2024/11/29
•Vol.7 No.1 p.1-13
In this work we present OptAB, the first completely data-driven online-updateable antibiotic selection model based on Artificial Intelligence for Sepsis patients accounting for side-effects. OptAB performs an iterative optimal antibiotic selection for real-world Sepsis patients focussing on minimizi...
Adverse effectsAntimicrobial therapyBacterial infectionComputational sciencePredictive medicine
10.1038/S41746-024-01350-Y
ISSN:2398-6352
The obesity paradox in younger adult patients with sepsis: analysis of the MIMIC-IV database
Yongseop Lee•Sangmin Ahn•Min Han•Jung Ah Lee•Jin Young Ahn等 11 人
International Journal Of Obesity
2024
•2024/4/26
•00 p.1-8
The obesity paradox suggests that individuals with obesity may have a survival advantage against specific critical illnesses, including sepsis. However, whether this paradox occurs at younger ages remains unclear. Therefore, we aimed to investigate whether obesity could improve survival in younger a...
EpidemiologyRisk factors
10.1038/S41366-024-01523-5
ISSN:0307-0565
Towards autonomous medical artificial intelligence agents
Dyke Ferber•Lars Hilgers•Christiane Höper•Benedict Kinny-Köster•Jan-Niklas Eckardt等 20 人
Nature
2026
•2026/6/17
•00 p.1-10
Large language models (LLMs) show great potential for clinical decision-making, yet most applications remain narrow, task-specific chat tools rather than systems integrated into clinical workflows1,2. However, building physician copilots will require models that operate within the electronic health ...
Computational scienceHealth servicesTranslational research
10.1038/S41586-026-10675-5
ISSN:0028-0836
Acquisition parameters influence AI recognition of race in chest x-rays and mitigating these factors reduces underdiagnosis bias
William Lotter
Nature Communications
2024
•2024/8/29
•Vol.15 No.1 p.1-11
A core motivation for the use of artificial intelligence (AI) in medicine is to reduce existing healthcare disparities. Yet, recent studies have demonstrated two distinct findings: (1) AI models can show performance biases in underserved populations, and (2) these same models can be directly trained...
Computational scienceComputer scienceMedical ethicsMedical imaging
10.1038/S41467-024-52003-3
ISSN:2041-1723
Weakly supervised language models for automated extraction of critical findings from radiology reports
Avisha Das•Ish A. Talati•Juan Manuel Zambrano Chaves•Daniel Rubin•Imon Banerjee
Npj Digital Medicine
2025
•2025/5/8
•Vol.8 No.1 p.1-9
Critical findings in radiology reports are life threatening conditions that need to be communicated promptly to physicians for timely management of patients. Although challenging, advancements in natural language processing (NLP), particularly large language models (LLMs), now enable the automated i...
Computational modelsMachine learning
10.1038/S41746-025-01522-4
ISSN:2398-6352
Shareable artificial intelligence to extract cancer outcomes from electronic health records for precision oncology research
Kenneth L. Kehl•Justin Jee•Karl Pichotta•Morgan A. Paul•Pavel Trukhanov等 13 人
Nature Communications
2024
•2024/11/12
•Vol.15 No.1 p.1-11
Databases that link molecular data to clinical outcomes can inform precision cancer research into novel prognostic and predictive biomarkers. However, outside of clinical trials, cancer outcomes are typically recorded only in text form within electronic health records (EHRs). Artificial intelligence...
CancerCancer epidemiologyMachine learningOutcomes research
10.1038/S41467-024-54071-X
ISSN:2041-1723
TransformEHR: transformer-based encoder-decoder generative model to enhance prediction of disease outcomes using electronic health records
Zhichao Yang•Avijit Mitra•Weisong Liu•Dan Berlowitz•Hong Yu
Nature Communications
2023
•2023/11/29
•Vol.14 No.1 p.1-10
Deep learning transformer-based models using longitudinal electronic health records (EHRs) have shown a great success in prediction of clinical diseases or outcomes. Pretraining on a large dataset can help such models map the input space better and boost their performance on relevant tasks through f...
Computer scienceDisease preventionExperimental models of disease
10.1038/S41467-023-43715-Z
ISSN:2041-1723
Quantifying disparities in intimate partner violence: a machine learning method to correct for underreporting
Divya Shanmugam•Kaihua Hou•Emma Pierson
Npj Women's Health
2024
•2024/5/15
•Vol.2 No.1 p.1-13
The first step towards reducing the pervasive disparities in women’s health is to quantify them. Accurate estimates of the relative prevalence across groups—capturing, for example, that a condition affects Black women more frequently than white women—facilitate effective and equitable health policy ...
DiagnosisHealth services
10.1038/S44294-024-00011-5
ISSN:2948-1716
Generating unseen diseases patient data using ontology enhanced generative adversarial networks
Chang Sun•Michel Dumontier
Npj Digital Medicine
2025
•2025/1/3
•Vol.8 No.1 p.1-14
Generating realistic synthetic health data (e.g., electronic health records), holds promise for fundamental research, AI model development, and enhancing data privacy safeguards. Generative Adversarial Networks (GANs) have been employed for this purpose, but their performance is largely constrained ...
Computational biology and bioinformaticsDiseasesMachine learning
10.1038/S41746-024-01421-0
ISSN:2398-6352
Algorithmic antibiotic decision-making in urinary tract infection using prescriber-informed prediction of treatment utility
Alex Howard•Peter L. Green•Yinzheng Zhong•David M. Hughes•Alessandro Gerada等 9 人
Npj Digital Medicine
2026
•2026/1/26
•Vol.9 No.1 p.1360
Predicting antibiotic treatment outcomes could help tackle antibiotic resistance by guiding prescribing decisions. Existing approaches do not quantitatively incorporate the judgment of clinician users. Our antibiotic decision-making algorithm predicted treatment outcomes for 13 antibiotics using cli...
AntibioticsAntimicrobial resistanceClinical microbiologyMachine learning
10.1038/S41746-026-02369-Z
ISSN:2398-6352
Personalised antimicrobial susceptibility testing with clinical prediction modelling informs appropriate antibiotic use
Alex Howard•David M. Hughes•Peter L. Green•Anoop Velluva•Alessandro Gerada等 8 人
Nature Communications
2024
•2024/11/21
•Vol.15 No.1 p.1-13
Antimicrobial susceptibility testing is a key weapon against antimicrobial resistance. Diagnostic microbiology laboratories use one-size-fits-all testing approaches that are often imprecise, inefficient, and inequitable. Here, we report a personalised approach that adapts laboratory testing for urin...
Antimicrobial resistanceClinical microbiologyComputer scienceInfectious-disease diagnosticsPolicy and public health in microbiology
10.1038/S41467-024-54192-3
ISSN:2041-1723
Explainable AI unravels sepsis heterogeneity via coagulation-inflammation profiles for prognosis and stratification
Li Zhu•Zengtian Chen•Hong Zhang•Hongjun Chen•Lanqi Liu等 21 人
Nature Communications
2025
•2025/11/24
•Vol.16 No.1 p.103960
Sepsis is a leading cause of hospital mortality, and its significant heterogeneity complicates prognosis and stratification. To address this challenge, we developed an explainable artificial intelligence prognostic model (SepsisFormer, a transformer-based neural network) and an automated risk-strati...
Infectious diseasesOutcomes researchTranslational research
10.1038/S41467-025-65365-Z
ISSN:2041-1723
GRACE-ICU: A multimodal nomogram-based approach for illness severity assessment of older adults in the ICU
Xiaoli Liu•Wesley Yeung•Ziyue Chen•Sicheng Hao•Zhicheng Yang等 15 人
Npj Digital Medicine
2025
•2025/8/13
•Vol.8 No.1 p.1-12
Clinical notes are crucial for patient assessment in the ICU but can be challenging to accurately and objectively analyze in time-constrained situations. We developed the GRACE-ICU model which integrates clinical notes and structured data to rapidly assess critical illness severity in older adults. ...
Experimental models of diseaseGeriatricsHealth careMedical researchRisk factors
10.1038/S41746-025-01875-W
ISSN:2398-6352
Evaluation and mitigation of the limitations of large language models in clinical decision-making
Paul Hager•Friederike Jungmann•Robbie Holland•Kunal Bhagat•Inga Hubrecht等 11 人
Nature Medicine
2024
•2024/7/4
•00 p.1-10
Clinical decision-making is one of the most impactful parts of a physician’s responsibilities and stands to benefit greatly from artificial intelligence solutions and large language models (LLMs) in particular. However, while LLMs have achieved excellent performance on medical licensing exams, these...
DiagnosisHealth care economicsTranslational research
10.1038/S41591-024-03097-1
ISSN:1078-8956
The HM-TARGET personalised real-time haemodynamic targets in critical care
Yanhua Sun•Jiangqiong Li•Xiang Liu•Genevieve A. Mortensen•Xiaoping Gu等 11 人
Nature Communications
2025
•2025/8/7
•Vol.16 No.1 p.1-16
Haemodynamic management in critical care typically relies on static, population-based targets that overlook patient-specific physiology and the evolving nature of illness. We develop and validate a framework for real-time, personalised haemodynamic management using a time-dependent Cox model that in...
Predictive markersPredictive medicine
10.1038/S41467-025-62527-X
ISSN:2041-1723
Unbiased clustering of acute-on-chronic liver failure patients using machine learning in a real-world ICU cohort
Mengyi Zhang•Fanpu Ji•Jian Zu•Yingli He•Tao Chen等 15 人
Nature Communications
2026
•2026/1/20
•Vol.17 No.1 p.16700
Acute-on-chronic liver failure is a complex condition with varied definitions, complicating risk stratification and targeted management. We apply unsupervised clustering to data from 1,256 patients with acute-on-chronic liver failure as defined by the North American Association for the Study of End-...
Functional clusteringLiver fibrosisPrognostic markers
10.1038/S41467-026-68368-6
ISSN:2041-1723
A distributional reinforcement learning model for optimal glucose control after cardiac surgery
Jacob M. Desman•Zhang-Wei Hong•Moein Sabounchi•Ashwin S. Sawant•Jaskirat Gill等 32 人
Npj Digital Medicine
2025
•2025/5/27
•Vol.8 No.1 p.1-12
This study introduces Glucose Level Understanding and Control Optimized for Safety and Efficacy (GLUCOSE), a distributional offline reinforcement learning algorithm for optimizing insulin dosing after cardiac surgery. Trained on 5228 patients, tested on 920, and externally validated on 649, GLUCOSE ...
Machine learningTherapeutics
10.1038/S41746-025-01709-9
ISSN:2398-6352
Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling
Miguel Contreras•Brandon Silva•Benjamin Shickel•Andrea Davidson•Tezcan Ozrazgat-Baslanti等 17 人
Nature Communications
2025
•2025/8/8
•Vol.16 No.1 p.1-15
Intensive care unit (ICU) patients often experience rapid changes in clinical status, requiring timely identification of deterioration to guide life-sustaining interventions. Current artificial intelligence (AI) models for acuity assessment rely on mortality as a proxy and lack direct prediction of ...
Machine learningPreclinical researchPredictive medicine
10.1038/S41467-025-62121-1
ISSN:2041-1723