ClearMed
AI in MedicineReal-World Cohort5 min read

Functional Connectivity at Birth and Longitudinal Neurocognitive Development in Very Preterm Infants

Maternal, pregnancy, delivery, and infant clinical data were collected from birth through discharge from the neonatal intensive care unit.

Published in JAMA Network OpenObservational cohort study
4/5 Strong Trial
Evidence Meter · 4/5

Strong Clinical Evidence

Tested directly in patients through a prospective clinical trial or large multicenter human cohort.

Source

Follow-Up Window

3 years

In this study of infants born VPT, neonatal functional network organization was associated with cognitive performance at corrected age 2 and 3 years.

What Changes?

AI in Medicine · Real-World Cohort

Current Standard

Conventional ai in medicine practice relies on standard-of-care monitoring and existing regimens prior to this study.

New Finding

The findings highlight the relevance of distributed connectivity involving the DMN and SMN to later cognitive outcomes and support further investigation of neonatal functional connectivity as an early marker of neurodevelopment.

3 Key Takeaways

Plain English Summary
  1. 01Core Finding

    Participants underwent magnetic resonance imaging at full-term-equivalent age at Cincinnati Children's Hospital using the same scanner.

  2. 02Study Evidence

    Tested in a study at the real-world stage.

  3. 03Practical Meaning

    findings reveal real-world links, though lifestyle or unmeasured factors cannot be fully ruled out without an RCT.

What This Means for You

In this study of infants born VPT, neonatal functional network organization was associated with cognitive performance at corrected age 2 and 3 years. The findings highlight the relevance of distributed connectivity involving the DMN and SMN to later cognitive outcomes and support further investigation of neonatal functional connectivity as an early marker of neurodevelopment.

The Discovery

This study included infants born VPT (gestational age ≤32 weeks) from 5 level III and IV neonatal intensive care units in the greater Cincinnati, Ohio, area between September 16, 2016, and November 19, 2019. Maternal, pregnancy, delivery, and infant clinical data were collected from birth through discharge from the neonatal intensive care unit. Participants underwent magnetic resonance imaging at full-term-equivalent age at Cincinnati Children's Hospital using the same scanner. Image preprocessing and statistical analyses for this study were conducted between January 25, 2025, and July 30, 2026. Cognitive outcomes were assessed at corrected age 2 and 3 years using the Bayley Scales of Infant and Toddler Development, Third Edition and the Differential Ability Scales, Second Edition, respectively. Functional connectivity was measured within and between the default mode network (DMN), somatomotor network (SMN), dorsal attention network (DAN), frontoparietal control network, visual network (VIS), and cingulo-opercular network (CO). Associations between neonatal functional connectivity and cognitive outcomes were examined using a bayesian hierarchical linear mixed-effects model. A total of 257 infants born VPT (mean [SD] gestational age, 29.2 [2.5] weeks; 132 male [51.4%]) were included in the final analysis. Stronger neonatal connectivity involving the DMN was positively associated with cognitive performance, including intra-DMN (0.23; 95% credible interval [CrI], 0.06-0.39) and DMN connections with the frontoparietal control network (0.24; 95% CrI, 0.07-0.40), SMN (0.20; 95% CrI, 0.02-0.37), VIS (0.32; 95% CrI, 0.13-0.51), and CO (0.39; 95% CrI, 0.21-0.56). Positive associations were also observed for SMN-VIS (0.27; 95% CrI, 0.12-0.43) and SMN-CO (0.26; 95% CrI, 0.09-0.44) connectivity. The SMN-VIS was the only connection showing a difference between assessments, with a less pronounced association at 3 years than at 2 years (interaction, -0.09; 95% CrI, -0.20 to <0.01).

How It Works, Simply

This ai in medicine research focuses on deep neural network feature extraction & risk stratification. Researchers evaluated it using an observational cohort study at the real-world cohort stage of medical research.

3 Key Takeaways

Clinical Takeaways
  1. 01Core Finding

    Participants underwent magnetic resonance imaging at full-term-equivalent age at Cincinnati Children's Hospital using the same scanner.

  2. 02Study Evidence

    Tested in a study at the real-world stage.

  3. 03Practical Meaning

    findings reveal real-world links, though lifestyle or unmeasured factors cannot be fully ruled out without an RCT.

Key Numbers

Quantitative Study Readout
2 years
Follow-Up Window
01

Biological Mechanism & Study Design

Study Design & Cohort

Observational cohort study

Observational cohort study · Real-World Cohort

Biological Pathway & Modality

Deep neural network feature extraction & risk stratification

Intervention: Functional Connectivity at Birth and Neurocognitive Development in Very

02

Experimental Findings & Endpoints

This study included infants born VPT (gestational age ≤32 weeks) from 5 level III and IV neonatal intensive care units in the greater Cincinnati, Ohio, area between September 16, 2016, and November 19, 2019.

Maternal, pregnancy, delivery, and infant clinical data were collected from birth through discharge from the neonatal intensive care unit. Participants underwent magnetic resonance imaging at full-term-equivalent age at Cincinnati Children's Hospital using the same scanner.

Image preprocessing and statistical analyses for this study were conducted between January 25, 2025, and July 30, 2026. Cognitive outcomes were assessed at corrected age 2 and 3 years using the Bayley Scales of Infant and Toddler Development, Third Edition and the Differential Ability Scales, Second Edition, respectively.

Functional connectivity was measured within and between the default mode network (DMN), somatomotor network (SMN), dorsal attention network (DAN), frontoparietal control network, visual network (VIS), and cingulo-opercular network (CO). Associations between neonatal functional connectivity and cognitive outcomes were examined using a bayesian hierarchical linear mixed-effects model.

A total of 257 infants born VPT (mean [SD] gestational age, 29.2 [2.5] weeks; 132 male [51.4%]) were included in the final analysis. Stronger neonatal connectivity involving the DMN was positively associated with cognitive performance, including intra-DMN (0.23; 95% credible interval [CrI], 0.06-0.39) and DMN connections with the frontoparietal control network (0.24; 95% CrI, 0.07-0.40), SMN (0.20; 95% CrI, 0.02-0.37), VIS (0.32; 95% CrI, 0.13-0.51), and CO (0.39; 95% CrI, 0.21-0.56).

Positive associations were also observed for SMN-VIS (0.27; 95% CrI, 0.12-0.43) and SMN-CO (0.26; 95% CrI, 0.09-0.44) connectivity. The SMN-VIS was the only connection showing a difference between assessments, with a less pronounced association at 3 years than at 2 years (interaction, -0.09; 95% CrI, -0.20 to <0.01).

03

Clinical Translation & Practice Context

In this study of infants born VPT, neonatal functional network organization was associated with cognitive performance at corrected age 2 and 3 years.

The findings highlight the relevance of distributed connectivity involving the DMN and SMN to later cognitive outcomes and support further investigation of neonatal functional connectivity as an early marker of neurodevelopment.

03

The Bottom Line · Clinical Pearl

“In this cohort study of infants born VPT, neonatal functional network organization was associated with cognitive performance at corrected age 2 and 3 years.”

Published in JAMA Network Open · Current Stage: Real-World Cohort

Practical Next Step

Questions for Your Next Doctor Visit

  1. 1Based on my health history, do these ai in medicine findings (observational cohort study in ai in medicine care) apply to my situation?
  2. 2How do the potential benefits of this approach compare with the standard care I'm currently using?
  3. 3Given the study's key limitation (observational cohort findings reveal real-world links, though lifestyle or unmeasured factors cannot be fully ruled out without an RCT.), what risks or follow-up steps should we watch for?
AI in Medicine · Real-World Cohort
Study Type
Observational cohort study

Observational cohort study

Evidence Score
4/5 · Strong Clinical Evidence
Evidence Meter · 4/5

Strong Clinical Evidence

Tested directly in patients through a prospective clinical trial or large multicenter human cohort.

Tested directly in patients through a prospective clinical trial or large multicenter human cohort.

Who It Applies To
Observational cohort study in ai in medicine care
Intervention & Mechanism
Functional Connectivity at Birth and Longitudinal Neurocognitive Development in Very

Deep neural network feature extraction & risk stratification

Key Limitation
Observational cohort findings reveal real-world links, though lifestyle or unmeasured factors cannot be fully ruled out without an RCT.

Translational Stage

LEVEL 2 · Real-World Cohort

Classified as Observational cohort study along the clinical evidence continuum

  1. Lab & Discovery
  2. Early Trials
  3. Human Evidence
  4. 4Real-World CohortActive

Indexed Clinical Entities

Original Publication & AMA Citation

Functional Connectivity at Birth and Longitudinal Neurocognitive Development in Very Preterm Infants. JAMA Network Open. Published 2026;Nov 2. Accessed November 15, 2026. https://pubmed.ncbi.nlm.nih.gov/42970289/

JAMA Network Open

https://pubmed.ncbi.nlm.nih.gov/42970289/

Read Original Paper

Continue Reading

Related in AI in Medicine

View all AI in Medicine briefings →
AI in Medicine editorial photograph for ClinicalAge, a framework for modelling ageing trajectories from longitudinal electronic health records in the UK: a model development and validation study
AI IN MEDICINE · CLINICAL PRACTICE

ClinicalAge, a framework for modelling ageing trajectories from longitudinal electronic health records in the UK: a model development and validation study

Your Medical Records Could Reveal Your True 'Biological Age' — And Predict Your Health Future. A new AI tool, ClinicalAge, uses your existing health records to calculate your biological age, offering a powerful predictor of future health risks and lifespan.

3/5 Observational
Evidence Meter · 3/5

Real-World Observation

Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.

1 min readThe Lancet Digital Health
AI IN MEDICINE · CLINICAL PRACTICE

AI Enhances Bionic Vision Precision in Brain Implant Patient

An AI-powered system can precisely predict and generate personalized visual percepts in a blind individual with a brain implant by learning their unique cortical responses to electrical stimulation. Current bionic eye technologies, while offering some degree of visual perception, often struggle with precision, consistency, and the intuitive generation of meaningful visual information for the patient.

3/5 Observational
Evidence Meter · 3/5

Real-World Observation

Finds meaningful patterns in human health records or cohorts, though observational data cannot prove direct cause.

1 min readScienceDaily
AI IN MEDICINE · PRECLINICAL

AI Discovers Natural Molecule for Obesity with Promising Side Effect Profile

AI-guided discovery of the natural molecule BRP offers a novel, potentially better-tolerated approach to obesity treatment than existing medications. BRP represents a potential 'Ozempic-like' treatment for obesity that may circumvent common digestive side effects and muscle loss often associated with current GLP-1 agonists.

2/5 Preclinical
Evidence Meter · 2/5

Animal & Preclinical Data

Demonstrated in living animal models before large-scale human safety and dosing trials begin.

1 min readScienceDaily