Cry Detection AI

Analyse babies’ cries with our state-of-the-art technology AI. Our real-time analysis of their stress levels guides clinicians to provide timely care, and aid parents in recognizing signs of true distress in their baby.

Assess baby’s needs

There are four identifiable needs when a baby cries: hunger, sleep, colic and pain. Recognition of pain alerts the clinician and parent to search for any stressors affecting the baby, allowing faster identification of any underlying health conditions they may have. 

Respond to cry alerts when away

Nurses can stay updated on a baby’s stress level and receive updates on their phone when the baby cries. This allows them to respond to babies who are in single rooms or in covered incubators.

Works in loud environments

Cry Detection filters out background noise to identify babies’ cries even in a busy and noisy environment with alarm sounds, breathing machines or people talking.

"If we can't hear the babies, our brand new single room department simply operates with the doors open."



Cry Detection is an artificial intelligence software that can be used to detect babies’ crying in the incubator. This information can be used by the healthcare team to respond to babies in need.

It can be used separately or in parallel. Our S2S package offers live streaming, so this software can record audio along with visual data. Alternatively, it can be used alone and thus record audio only. 

No. This service runs as a digital service of Neolook or on premise within the hospital server system. It can be accessed on any device that can use the internet. This includes mobile phones, tablets, laptops and desktop computers.

No. The service can be easily switched on or off per bed as needed, using our Control Panel. 

No. Just like humans, AI is not always right. By training the AI on department data the Accuracy, False Positive and False Negative rate is optimized.

Our systems has controls  to increase or decrease sensitivity. This is done by setting the pre processing Algorithm before the AI and the post processing algorithm after the AI.