Nature Search

A chemical autonomous robotic platform for end-to-end synthesis of nanoparticles

Traditional nanoparticle synthesis faces inefficiency issues. Here, authors developed an AI-driven robotic platform combining GPT models and A algorithm to autonomously optimize metallic nanoparticle synthesis with minimal experiments, achieving high reproducibility.

Fan Gao
Hongqiang Li
Guangxu Chen
ResearchOpen Access14 Aug 2025
Nature Communications

Volume: 16, P: 1-13
Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling

Early detection of clinical deterioration in intensive care unit patients is essential for timely interventions but remains challenging. Here, the authors show that an AI model, APRICOT-M, predicts changes in patient acuity and the need for life-sustaining therapies in real time.

Miguel Contreras
Brandon Silva
Parisa Rashidi
ResearchOpen Access08 Aug 2025
Nature Communications

Volume: 16, P: 1-15
Artificial intelligence-enabled decision support in nephrology

Emerging evidence suggests that artificial intelligence (AI)-enabled decision support systems may have an important role in the diagnosis, prognosis and treatment of kidney diseases. This Review provides an overview of AI fundamentals and the state of the art of AI-enabled decision support systems in nephrology.

Tyler J. Loftus
Benjamin Shickel
Azra Bihorac
Reviews22 Apr 2022
Nature Reviews Nephrology

Volume: 18, P: 452-465
Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge

Solveig K. Sieberts
Jennifer Schaff
Larsson Omberg
ResearchOpen Access19 Mar 2021
npj Digital Medicine

Volume: 4, P: 1-12
A large language model for delirium prediction in the intensive care unit using structured electronic health records

Miguel Contreras
Sumit Kapoor
Parisa Rashidi
ResearchOpen Access06 Nov 2025
Scientific Reports

Volume: 15, P: 1-13
Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling

The response of the body to drugs follows complex dynamical processes that can be difficult to predict. Lu and colleagues combine a neural network approach with pharmacokinetic/pharmacodynamic modelling to learn these complex dynamics.

James Lu
Brendan Bender
Yuanfang Guan
Research21 Jun 2021
Nature Machine Intelligence

Volume: 3, P: 696-704
Crowd-sourced benchmarking of single-sample tumor subclonal reconstruction

Benchmarking of tumor subclonal reconstruction algorithms finds that interalgorithm variability overwhelms intertumor variability and identifies key quality metrics.

Adriana Salcedo
Maxime Tarabichi
Paul C. Boutros
ResearchOpen Access11 Jun 2024
Nature Biotechnology

Volume: 43, P: 581-592
Emergent constraints indicate slower increases in future global evapotranspiration

Yuanfang Chai
Yao Yue
Chiyuan Miao
ResearchOpen Access12 Feb 2025
npj Climate and Atmospheric Science

Volume: 8, P: 1-9
Hybrid DWT NLM method with NOA optimization for ECG signal denoising

Wen Chen
Yuanfang Zhang
Jianzhong Hao
ResearchOpen Access07 Jul 2025
Scientific Reports

Volume: 15, P: 1-12
A community effort to create standards for evaluating tumor subclonal reconstruction

Methods for reconstructing tumor evolution are benchmarked in the DREAM Somatic Mutation Calling Tumour Heterogeneity Challenge.

Adriana Salcedo
Maxime Tarabichi
Paul C. Boutros
Research09 Jan 2020
Nature Biotechnology

Volume: 38, P: 97-107
Gelatin-based spray for forest fire prevention and fertilization

Forest fire prevention methods are often not environmentally friendly and are limited in remote areas. Here, a gelatin-based fire spray extends ignition time and reduces the heat release of fires while also acting as leaf and soil fertilizers to aid plant growth.

Yuanfang Ai
Na Zheng
Kun Cao
ResearchOpen Access19 Dec 2024
Communications Materials

Volume: 5, P: 1-8
Harmonizing across datasets to improve the transferability of drug combination prediction

A machine learning-based method improves the transferability of drug combination predictions across datasets from studies with variable experimental settings, such as the number of doses and dose ranges tested.

Hanrui Zhang
Ziyan Wang
Yuanfang Guan
ResearchOpen Access11 Apr 2023
Communications Biology

Volume: 6, P: 1-10
Hierarchical machine learning models can identify stimuli of climate change misinformation on social media

An analysis of five million climate-themed social-media posts identified four distinct spikes in climate change misinformation, using a two-step hierarchical model in machine learning.

Cristian Rojas
Frank Algra-Maschio
Yuan-Fang Li
ResearchOpen Access16 Aug 2024
Communications Earth & Environment

Volume: 5, P: 1-8

Search

A chemical autonomous robotic platform for end-to-end synthesis of nanoparticles

Real-time prediction of intensive care unit patient acuity and therapy requirements using state-space modelling

Artificial intelligence-enabled decision support in nephrology

Crowdsourcing digital health measures to predict Parkinson’s disease severity: the Parkinson’s Disease Digital Biomarker DREAM Challenge

A large language model for delirium prediction in the intensive care unit using structured electronic health records

Deep learning prediction of patient response time course from early data via neural-pharmacokinetic/pharmacodynamic modelling

Crowd-sourced benchmarking of single-sample tumor subclonal reconstruction

Emergent constraints indicate slower increases in future global evapotranspiration

Hybrid DWT NLM method with NOA optimization for ECG signal denoising

A community effort to create standards for evaluating tumor subclonal reconstruction

Gelatin-based spray for forest fire prevention and fertilization

Harmonizing across datasets to improve the transferability of drug combination prediction

Hierarchical machine learning models can identify stimuli of climate change misinformation on social media

Search

Quick links

Search

Filter By:

Search

Quick links