Nature Search

The diversity and consistency of what and when people eat

An exploratory, observational analysis involving 2.5 million food logs from over 20,000 adults across 2 weeks highlights both consistent and divergent patterns in food habits that may, in turn, influence human health.

Tyler Tran
Emily N. C. Manoogian
Satchidananda Panda
ResearchOpen Access23 Apr 2026
Nature Metabolism

Volume: 8, P: 981-997
Reproducibility and robustness of economics and political science research

Robustness checks and reproduction of analyses with existing and updated data based on 110 articles in economics and political science journals with data and code-sharing requirements found high levels of robustness and reproducibility and determined that robustness was not dependent on author characteristics or data availability.

Abel Brodeur
Derek Mikola
Yaolang Zhong
Research01 Apr 2026
Nature

Volume: 652, P: 151-156
Geographic and dietary differences of urinary uranium levels in the Strong Heart Family Study

Kevin P. Patterson
Anne E. Nigra
Ana Navas-Acien
Research03 Jul 2024
Journal of Exposure Science & Environmental Epidemiology

Volume: 35, P: 393-402
Merlin: a computed tomography vision–language foundation model and dataset

Merlin, a vision–language foundation model trained on a large dataset of paired CT scans, patient record data and radiology reports, demonstrates strong performance across model architectures, diagnostic and prognostic tasks, and external sites.

Louis Blankemeier
Ashwin Kumar
Akshay S. Chaudhari
Research04 Mar 2026
Nature

Volume: 652, P: 1318-1328
Holistic evaluation of large language models for medical tasks with MedHELM

MedHELM, an extensible evaluation framework including a new taxonomy for classifying medical tasks and a benchmark of many datasets across these categories, enables the evaluation of large language models on real-world clinical tasks.

Suhana Bedi
Hejie Cui
Nigam H. Shah
Research20 Jan 2026
Nature Medicine

Volume: 32, P: 943-951
Publisher Correction: Reproducibility and robustness of economics and political science research

Abel Brodeur
Derek Mikola
Yaolang Zhong
Amendments and Corrections23 Apr 2026
Nature

Volume: 653, P: E7
Typical food portion sizes consumed by Australian adults: results from the 2011–12 Australian National Nutrition and Physical Activity Survey

Miaobing Zheng
Jason H Y Wu
Anna Rangan
ResearchOpen Access20 Jan 2016
Scientific Reports

Volume: 6, P: 1-9
Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences

The availability of labelled training data is one of the practical obstacles towards wide application of machine learning models in medicine. Here the authors develop a weakly supervised deep learning model for the classification of aortic malformations using unlabelled cardiac MRI sequences from the UK biobank.

Jason A. Fries
Paroma Varma
James R. Priest
ResearchOpen Access15 Jul 2019
Nature Communications

Volume: 10, P: 1-10
Ontology-driven weak supervision for clinical entity classification in electronic health records

In the electronic health record, using clinical notes to identify entities such as disorders and their temporality can inform many important analyses. Here, the authors present a framework for weakly supervised entity classification using medical ontologies and expert-generated rules.

Jason A. Fries
Ethan Steinberg
Nigam H. Shah
ResearchOpen Access01 Apr 2021
Nature Communications

Volume: 12, P: 1-11
Infant gut microbiome composition is associated with non-social fear behavior in a pilot study

Experimental manipulation of the gut microbiome in animal models impacts fear behaviours. Here, the authors show in a pilot study that features of the human infant gut microbiome are associated with non-social fear behaviours during a laboratory based assessment.

Alexander L. Carlson
Kai Xia
Rebecca C. Knickmeyer
ResearchOpen Access02 Jun 2021
Nature Communications

Volume: 12, P: 1-16
How to interpret ‘zero-shot’ results from generative EHR models

Generative models trained on electronic health records are viewed as ‘zero-shot predictors’ for clinical outcomes — but this interpretation is misleading.

Suhana Bedi
Jason Alan Fries
Nigam H. Shah
Comments & Opinion07 Jan 2026
Nature Medicine

Volume: 32, P: 404-406
Social epidemiology of early adolescent nutrition

Jason M. Nagata
Christiane K. Helmer
Andrea K. Garber
ResearchOpen Access27 Jan 2025
Pediatric Research

Volume: 98, P: 885-894
Automatic engagement of limbic and prefrontal networks in response to food images reflects distinct information about food hedonics and inhibitory control

Representational similarity analysis reveals distinct networks of prefrontal and limbic brain regions that automatically encode healthfulness and hedonic value, guiding food consumption.

Jason A. Avery
Madeline Carrington
Alex Martin
ResearchOpen Access20 Feb 2025
Communications Biology

Volume: 8, P: 1-12
Rethinking ratio-based normalization towards model-based approaches in heart weight analysis

Manuela A. Oestereicher
Patricia da Silva-Buttkus
Nadine Spielmann
ResearchOpen Access17 Mar 2026
Scientific Reports

Volume: 16, P: 1-14
SARS-CoV-2 spike glycoprotein vaccine candidate NVX-CoV2373 immunogenicity in baboons and protection in mice

Here, the authors characterize a SARS-CoV-2 subunit vaccine candidate that contains full-length spike protein stabilized in its prefusion conformation, and show immunogenicity in baboons and protection in mice with Matrix-M adjuvanted vaccine.

Jing-Hui Tian
Nita Patel
Gale Smith
ResearchOpen Access14 Jan 2021
Nature Communications

Volume: 12, P: 1-14
Associations of dietary patterns with kidney cancer risk, kidney cancer-specific mortality and all-cause mortality among postmenopausal women

Qi Jin
Jinesh Gheeya
Fred K. Tabung
Research28 Oct 2023
British Journal of Cancer

Volume: 129, P: 1978-1987
Estimating the efficacy of symptom-based screening for COVID-19

Alison Callahan
Ethan Steinberg
Nigam H. Shah
ResearchOpen Access13 Jul 2020
npj Digital Medicine

Volume: 3, P: 1-3
A multi-center study on the adaptability of a shared foundation model for electronic health records

Lin Lawrence Guo
Jason Fries
Lillian Sung
ResearchOpen Access27 Jun 2024
npj Digital Medicine

Volume: 7, P: 1-9
TIMER: temporal instruction modeling and evaluation for longitudinal clinical records

Hejie Cui
Alyssa Unell
Nigam H. Shah
ResearchOpen Access26 Sept 2025
npj Digital Medicine

Volume: 8, P: 1-9
EHR foundation models improve robustness in the presence of temporal distribution shift

Lin Lawrence Guo
Ethan Steinberg
Lillian Sung
ResearchOpen Access07 Mar 2023
Scientific Reports

Volume: 13, P: 1-11
Medical device surveillance with electronic health records

Alison Callahan
Jason A. Fries
Nigam H. Shah
ResearchOpen Access25 Sept 2019
npj Digital Medicine

Volume: 2, P: 1-10
Red teaming ChatGPT in medicine to yield real-world insights on model behavior

Crystal T. Chang
Hodan Farah
Roxana Daneshjou
ResearchOpen Access07 Mar 2025
npj Digital Medicine

Volume: 8, P: 1-10
Analysis of genome-wide knockout mouse database identifies candidate ciliopathy genes

Kendall Higgins
Bret A. Moore
Ala Moshiri
ResearchOpen Access01 Dec 2022
Scientific Reports

Volume: 12, P: 1-17
Hospitalization prediction from the emergency department using computer vision AI with short patient video clips

Wui Ip
Maria Xenochristou
Lawrence V. Hofmann
ResearchOpen Access19 Dec 2024
npj Digital Medicine

Volume: 7, P: 1-8
Identification of genes required for eye development by high-throughput screening of mouse knockouts

Bret Moore et al. from the International Mouse Phenotyping Consortium report the identification of 347 mouse genes that influence ocular phenotypes when knocked out. 75% of the identified genes have not previously been associated with any ocular pathology.

Bret A. Moore
Brian C. Leonard
Ala Moshiri
ResearchOpen Access21 Dec 2018
Communications Biology

Volume: 1, P: 1-12
A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency

Adam S. Miner
Scott L. Fleming
Nigam H. Shah
ResearchOpen Access02 Dec 2022
npj Mental Health Research

Volume: 1, P: 1-12
Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine

Lin Lawrence Guo
Stephen R. Pfohl
Lillian Sung
ResearchOpen Access17 Feb 2022
Scientific Reports

Volume: 12, P: 1-10
Assessing the accuracy of automatic speech recognition for psychotherapy

Adam S. Miner
Albert Haque
Nigam H. Shah
ResearchOpen Access03 Jun 2020
npj Digital Medicine

Volume: 3, P: 1-8
Author Correction: Identification of genes required for eye development by high-throughput screening of mouse knockouts

Bret A. Moore
Brian C. Leonard
Ala Moshiri
Amendments and CorrectionsOpen Access07 Mar 2019
Communications Biology

Volume: 2, P: 1-2
AI is a viable alternative to high throughput screening: a 318-target study

Izhar Wallach
Denzil Bernard
Abraham Heifets
ResearchOpen Access02 Apr 2024
Scientific Reports

Volume: 14, P: 1-16
The shaky foundations of large language models and foundation models for electronic health records

Michael Wornow
Yizhe Xu
Nigam H. Shah
ReviewsOpen Access29 Jul 2023
npj Digital Medicine

Volume: 6, P: 1-10
Author Correction: AI is a viable alternative to high throughput screening: a 318-target study

Izhar Wallach
Denzil Bernard
Ellie Giles
Amendments and CorrectionsOpen Access16 Sept 2024
Scientific Reports

Volume: 14, P: 1-2

Search

The diversity and consistency of what and when people eat

Reproducibility and robustness of economics and political science research

Geographic and dietary differences of urinary uranium levels in the Strong Heart Family Study

Merlin: a computed tomography vision–language foundation model and dataset

Holistic evaluation of large language models for medical tasks with MedHELM

Publisher Correction: Reproducibility and robustness of economics and political science research

Typical food portion sizes consumed by Australian adults: results from the 2011–12 Australian National Nutrition and Physical Activity Survey

Weakly supervised classification of aortic valve malformations using unlabeled cardiac MRI sequences

Ontology-driven weak supervision for clinical entity classification in electronic health records

Infant gut microbiome composition is associated with non-social fear behavior in a pilot study

How to interpret ‘zero-shot’ results from generative EHR models

Social epidemiology of early adolescent nutrition

Automatic engagement of limbic and prefrontal networks in response to food images reflects distinct information about food hedonics and inhibitory control

Rethinking ratio-based normalization towards model-based approaches in heart weight analysis

SARS-CoV-2 spike glycoprotein vaccine candidate NVX-CoV2373 immunogenicity in baboons and protection in mice

Associations of dietary patterns with kidney cancer risk, kidney cancer-specific mortality and all-cause mortality among postmenopausal women

Estimating the efficacy of symptom-based screening for COVID-19

A multi-center study on the adaptability of a shared foundation model for electronic health records

TIMER: temporal instruction modeling and evaluation for longitudinal clinical records

EHR foundation models improve robustness in the presence of temporal distribution shift

Medical device surveillance with electronic health records

Red teaming ChatGPT in medicine to yield real-world insights on model behavior

Analysis of genome-wide knockout mouse database identifies candidate ciliopathy genes

Hospitalization prediction from the emergency department using computer vision AI with short patient video clips

Identification of genes required for eye development by high-throughput screening of mouse knockouts

A computational approach to measure the linguistic characteristics of psychotherapy timing, responsiveness, and consistency

Evaluation of domain generalization and adaptation on improving model robustness to temporal dataset shift in clinical medicine

Assessing the accuracy of automatic speech recognition for psychotherapy

Author Correction: Identification of genes required for eye development by high-throughput screening of mouse knockouts

AI is a viable alternative to high throughput screening: a 318-target study

The shaky foundations of large language models and foundation models for electronic health records

Author Correction: AI is a viable alternative to high throughput screening: a 318-target study

Search

Quick links

Search

Filter By:

Search

Quick links