Related Experiment Video

Updated: Feb 10, 2026

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

2.6K

Deep learning model for identification of metabolic bone disease of prematurity using wrist radiographs

Seul Gi Park1,2,3, Seoi Jeong4,5,6, Minwoo Cho5,6,7

  • 1Department of Pediatrics , SMG-SNU Boramae Medical Center , Seoul, Republic of Korea.

Scientific Reports
|February 8, 2026
PubMed

Insights

A new deep learning model accurately identifies metabolic bone disease (MBD) of prematurity using wrist X-rays. This AI tool aids clinicians, especially non-radiologists, in early MBD diagnosis and treatment.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Neonatology

Background:

  • Metabolic bone disease (MBD) of prematurity is a common complication in preterm infants.
  • Early identification of MBD is crucial for timely intervention and preventing long-term complications.
  • Radiographic assessment of MBD is essential but can be challenging, particularly for non-specialists.

Purpose of the Study:

  • To develop and validate a deep learning model for identifying radiographic features of MBD of prematurity.
  • To evaluate the impact of this AI-powered decision support on clinical diagnosis.
  • To assess the model's performance in a broad clinical setting.

Main Methods:

  • Retrospective study of preterm infants (<1500g birth weight) with wrist radiographs.
  • Development and training of a DenseNet-based deep learning model on an internal dataset.
  • Validation of the model on an external dataset and through a reader study.
  • Performance evaluation using AUROC, sensitivity, specificity, and accuracy.

Main Results:

  • The DenseNet model achieved high performance (AUROC: 0.961, accuracy: 92.0%) on the internal dataset.
  • External validation demonstrated strong generalizability (AUROC: 0.927).
  • The AI model significantly improved diagnostic accuracy for non-radiologists (65.4% to 78.7%).

Conclusions:

  • A wrist radiography-based deep learning model effectively identifies MBD of prematurity.
  • The model shows potential for broad clinical application, aiding in timely diagnosis.
  • This AI tool can enhance diagnostic capabilities, particularly for non-radiologists, leading to improved patient outcomes.

Keywords:
Artificial intelligenceDeep learning, prematurityMetabolic bone disease of prematurityWrist radiography

More Related Videos

Author Spotlight: Advancing Alzheimer's Research &#8211; Exploring Early Detection and Multi-Omics Approaches09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.9K
Models of Bone Metastasis08:49

Models of Bone Metastasis

Published on: September 4, 2012

43.2K

Related Concept Videos

What is Metabolism?00:52

What is Metabolism?

Overview
132.1K
Effect of Hepatic Disease on Pharmacokinetics: Active Drug, Metabolite and Fraction of Metabolized Drug01:14

Effect of Hepatic Disease on Pharmacokinetics: Active Drug, Metabolite and Fraction of Metabolized Drug

In pharmacotherapy, monitoring drug concentrations is paramount, especially for drugs whose therapeutic effects hinge on both the active compound and its metabolite. Hepatic impairment profoundly influences drug potency by altering liver function. If the drug is more potent than its metabolite, impaired liver function amplifies drug activity due to elevated drug concentration levels. Conversely, if the metabolite holds greater potency, diminished liver function diminishes drug activity by...
234
Avoidance Learning and Learned Helplessness01:14

Avoidance Learning and Learned Helplessness

Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
2.6K
Associative Learning01:27

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
1.4K
Purposive Learning01:22

Purposive Learning

E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
515
Observational Learning01:12

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...
1.0K