De Innovatiefste Student van Nederland

We are proud to announce that we have reached the finals of “De Innovatiefste Student van Nederland”! Together with our colleague Livia Popper and Roel Montree we have developed Neolook Cry Detection, designed to detect neonatal crying in a hospital environment.

From 5-9 september our team (Livia Popper, Miguel Boekhold and Roel Montree) will go through the intensive bootcamp week with various training courses from leading experts and organizations. They work on their business plan, receive pitch training and learn about marketing and branding. All of this in order to be maximum prepared for the great final on October 13th!

Want to know more about the project? Visit the website.

Neolook Solutions expands

We are looking for an Office/Backoffice Manager to join our team in Utrecht. Are you interested in working for a meaningful company helping babies and children in #NICU and #PICU? Look at the job opening via this link! You can apply directly on our LinkedIn job posting! 

Interview with MindTitan; an organization helping to transform organizations to become AI-driven!

As Neolook Solutions we are always aiming to expand our impact and to inspire other people and organizations. Therefore, Neolook Solutions Managing Director Marco D’Agata spoke with MindTitan for their article about computer vision applications. MindTitan is an organization that acts as a bridge between science and the industry, making value-generating solutions. MindTitan beliefs that AI is going to play a large role in the future. Their mission is to solve business problems using AI and machine learning. A perfect match between our mision and theirs! In this article MindTitan features three business leaders who use computer vision technologies in their products. Curious to what Marco had to say? Read the full article via: https://mindtitan.com/resources/blog/computer-vision-application-3-startup-founders-describe-their-experience/#neolook-solutions-saving-lives-with-computer-vision-techniques

Support for nurses as AI detects prematures crying in a NICU with single rooms 


One in ten babies are born premature. Prematures have an increased risk to develop diseases. Critical neonates are often admitted to a Neonatal Intensive Care Unit (NICU) and held in an incubator under supervision of phycisians and nurses. Nurses need to watch over the child and be ready to care for the baby at any time. With the increase in amount of admitted babies and pressure on staff availability, this can be hard to manage. 

Just like normal babies, prematures cry to tell something is wrong. And human as we are, we respond to that. As do the nurses at the intensive care. But sometimes human nature gets hindered unexpectedly by new developments that have the best intentions: Meet ‘single room care’, where babies are cared for in a dedicated private room. With better controls and less stress for the child, and more comfortable for parents. Many hospitals are stepping over to single rooms. But that gives peculiar problems for monitoring and watching over the child. For example: “how to hear when a baby is crying?” 

AI Crying detection

Detecting a cry in a NICU room is not as easy as it seems. While humans are very perceptive to babies crying (by design through evolution), for an algorithm, it would just be another recorded sound just like any other. Additionally, the room holding the incubator has a constant background noise of up to 50 dB, with medical equipment giving alarm beeps and other sound signals, as well as people in the room that might be talking. On top of that, a microphone is preferably located outside of the incubator, making the baby crying often much lower in volume than the background sounds. 

Therefore, a simple noise level detector would not cut it for this application. Nor do filtering techniques with banding. Instead, Neolook designed a machine learning algorithm, to analyse the data stream live, and raise an alert whenever crying was detected. 

For this approach, live audio is first converted into a spectrogram. It is a type of image that can show you how the frequencies in an audio signal behave over time. An example can be seen below:


And then it is the task of the machine learning algorithm to use this low-resolution image, and determine if it represents a baby crying or not. To do this on scale for a fully operational NICU, an advanced convolutional neural network (CNN) has been set up, and trained using 10.753 examples of no crying, and 3.092 examples of baby crying. These samples were all recorded within the live situation, as to mimic the final environment as close as possible. Obtaining examples of a baby crying is harder than it might seem, because the recorded data will mostly consist of other sounds, while the baby is sleeping in the incubator. 

After training the algorithm, it achieved an accuracy of 94.72%. This is lower than the optimal value, but special care was taken with preprocessing and post processing to make the algorithm more selective; that is to say, the algorithm needs to sure it is a baby crying, before it actually sends an alert. This extra design is to prevent ‘alarm fatigue’. Alarm fatigue is a problem where the nurses start to ignore the alarms raised because too many of them happen. This can happen when the algorithm sends too many false alerts: it will say a baby is crying, while there is no crying happening. Therefore, it is better to have an optimally balanced trade off performance to favour reliability.

We’re hiring a Full Stack Developer and a Data Science Engineer

Good news. After a good Q2 with 3 hospital contracts. We are happy to announce another 4 hospital contracts. Two Starter Packages and more striking: two department scale-ups. One for NICU and one for ICU due to Corona/Covid-19. 

When the work in the field doubles up. We double up on the backbone. Therefore we are hiring a Full Stack Developer and a Data Scientist EngineerHave look at the job postings page.

Cessation of Breathing study with S2S Academic

The Dutch national neonatal landscape is clear and well organized. Each center has it’s specialty research topic. And all specialties needed are divided among the different centers. Building on the Screen2Screen Family platform, the Technical University Eindhoven (TUE) mounted a research project on top of it with Screen2Screen Academic. The study, Cessation of Breathing (COB) develops and test a novel algorithm during a PhD project. The algorithm will be used in Alarm Management. 

First Q2 results

Early results are in since our start in March. 

We welcomed our first three hospital contracts. Our first three countries The Netherlands, United Kingdom and Japan. And we we secured an unexpected three PhD research projects. Innovate and serve people, clinical practice and science: all at once.

See below the first Dutch journalism coverage. 

Article in AD Journal (Dutch)


Soft launch of Neolook Solutions

Supporting Family ties and bonding for vulnerable children in intensive care.

How to do that in modern work/life balance? In the digital age? We soft launched new company Neolook Solutions and Screen2Screen Family to do just that. 

Screen2Screen offers video augmented services, made to fit special use cases in the NICU, neonatal and pediatric space. Screen2Screen makes it easy to configure and adjust video services. With a strong privacy-by-design fundament, and simplicity as the key to make it work for healthcare professionals in a complex environment. On top of it, Screen2Screen allows scalability, enables academic research, and integrates with existing infrastructure.   

Neolook Solutions was a corporate venture of Royal Philips in 2018 and 2019. It originated from Philips customer and market driven innovation. Screen2Screen technologies were applied straight from research labs into commercial long term strategic partnerships. After successful commercial implementation, the venture was created. Considering the best routing for the venture, it was decided to place the venture back outside Philips ‘in the market’ to better serve the highly specialized and small niche. 

Since march 2020, Neolook Solutions is live as an independent, privately held company.