
All iLive content is medically reviewed or fact checked to ensure as much factual accuracy as possible.
We have strict sourcing guidelines and only link to reputable media sites, academic research institutions and, whenever possible, medically peer reviewed studies. Note that the numbers in parentheses ([1], [2], etc.) are clickable links to these studies.
If you feel that any of our content is inaccurate, out-of-date, or otherwise questionable, please select it and press Ctrl + Enter.
Ultrasound Instead of Spinal Tap: New Device Detects Meningitis in Babies with High Accuracy
Last reviewed: 03.08.2025

An international study led by the Barcelona Institute for Global Health (ISGlobal) has demonstrated that a new high-definition ultrasound device can accurately diagnose meningitis in newborns and infants without the need for a spinal tap, a traditional and invasive method. The results are published in the journal Pediatric Research.
Meningitis: a threat to life and health
Meningitis is an inflammation of the membranes that cover the brain and spinal cord. Bacterial and fungal forms of the disease can be fatal if diagnosed late, and can have serious consequences, including neurological damage, cognitive impairment, and disability. Children in low- and middle-income countries, where access to early diagnosis is limited, are particularly vulnerable.
The problem of current diagnostics
Today, diagnosis of meningitis is based on a lumbar puncture, in which a sample of cerebrospinal fluid (CSF) is taken and analyzed for signs of inflammation. However, this procedure:
- invasive and associated with risks;
- difficult to access in low resource conditions;
- in developed countries it is often performed even with low suspicion, but with low efficiency;
- In poor regions, on the contrary, it is almost never carried out, which leads to underdiagnosis and erroneous prescriptions.
Alternative - NEOSONICS
The developed device NEOSONICS uses high-frequency ultrasound directed through the fontanelle (the unossified area between the baby’s skull bones) to visualize CSF.
A special algorithm with elements of deep learning (AI) analyzes the resulting images, recognizes cells and determines the presence of signs of inflammation.
The study was conducted between 2020 and 2023 and included more than 200 infants aged up to 24 months from clinics in Spain (Sant Joan de Déu, La Paz, Quironsalud), Mozambique and Morocco.
High precision
- The device correctly identified 17 out of 18 cases of meningitis and 55 out of 58 healthy patients.
- Performance: 94% sensitivity and 95% specificity in detecting high levels of leukocytes in CSF.
"This inexpensive, portable, and easy-to-use device could reduce the need for punctures and be useful even in situations where puncture is contraindicated," explains Sarah Ajanovic, lead author of the study.
Opportunities and Prospects
NEOSONICS can:
- reduce the number of unnecessary antibiotic prescriptions;
- avoid complications from punctures;
- improve early diagnosis;
- used for non-invasive monitoring of treatment.
"This is a step towards introducing non-invasive diagnostics into clinical practice. We are also exploring the possibilities of further integrating artificial intelligence into the interpretation of ultrasound data," adds Professor Quique Bassat, Director of ISGlobal and co-author of the paper.
AI improves interpretation
AI algorithms analyze the texture and characteristics of images to highlight inflammatory patterns, improving diagnostic accuracy. In the future, this technology could become an important tool for rapid, safe, and accurate diagnosis of meningitis in infants, especially in settings with limited access to labs and specialists.