Overview: Our client is a European MedTech start-up focused on the detection of cardiovascular anomalies. The start-up’s objective is to challenge the market for ECG signal-based detection of heart pathologies, such as, but not limited to, atrial fibrillation, premature beats, subventricular tachycardia, etc, obtained from affordable wearable devices such as the Polar H10. The company required an ML-based model development and preparation for the Class 2A medical device certification, in order to ensure that their system is safe and effective for patients to use at home. 

Team: Our team of experts included a Data Engineer, Data Scientists, ML Engineers and a Project Manager

Approach: 
Discovery phase

Our Data Scientists collaborated with the client in order to understand their existing ECG signal processing system, as well as their computation-based algorithms. We created an automated testing tool that assessed the performance of the current solution against a range of internal and external medical data sets. Based on this analysis, we provided recommendations to improve the scope of detectable medical conditions and identified areas for improvement. 
We advised the client on the certification process and prepared an action plan for the  ML-related work and documentation needed for the Class 2A certification. We also provided improvement recommendations and execution support, which helped the client enhance their ECG signal processing system and algorithms. Our team completed the analysis and recommendations in less than 8 weeks, providing actionable advice, which helped the client reduce the application processing time. 

ML-based signal processing model development phase

The client provided the raw ECG signal data, including labelled data with annotations of R-peaks, pathologies, as well as ‘soft’ and ‘hard’ noise segments. This labelled data was used as inputs for the models and deemed as their training set. The quality and accuracy of pathology predictions (detection) heavily depend on the cleaness of the ECG signal. This is why it is important to have robust, well-performing models in terms of accuracy and precision, which can distinguish between the clean and noisy parts of the ECG signals. Our Data Scientists developed ML-based models for ‘soft’  and ‘hard’ noise detection. Upon successfully passing the strict model performance acceptance criteria of the client, our ML Engineers created the production pipelines for training and inference and integrated it into the client’s platform and business processes. Our collaboration continues with the development of further pathology detection ML-based algorithms. 

Overview: Our client, a financial services company, approached us with a challenge to improve their data analysis tools and provide automation to their team's daily work. They wanted a solution that would help their surveillance organization gain more insights into potential scenarios. Our approach was to create a solution that would enable them to predict MTD/YTD prices.

Approach: We worked in close collaboration with the client to analyze multiple numerical methods and compose different types of feature vectors to improve the prediction model's accuracy. We developed a script that extracts information and an algorithm that calculates the analysis of historical price changes.
We integrated multiple data sources into the solution, including the Bloomberg service terminal, to ensure we had the most accurate and up-to-date data. We developed an API and a user-friendly interface for filtering and searching the information we extracted and analyzed. We used Keras to predict MTD / YTD prices developing a stock prediction model with a neural network to predict the returns on stocks. 

Tech stack: Python, Django,Vue.js, AWS, Keras. 

Challenge: Creating a fully functioning solution from scratch

Team: Data Engineers, Data Scientists, ML Engineers, DevOps

Solution: The project started with the investigation phase to analyse the existing data and test multiple solutions which meet the needs of both client and cloud providers. AWS was selected as a core service provider for data storage combined with ElasticSearch. Our team built the full ETL process to start operations. Once the data structure and pipelines were set, we introduced two teams of Data Scientists - one specialized in semantic analysis (NLP) and the other with experience in image recognition. The ML part was further taken care of by our engineers. The output was a dashboard of data visualisations made in Kibana to present the results.

Status: Successful completion of the data engineering phase with ongoing data science stages.

Challenge: The client`s request involved road and traffic analysis. The task included building a vehicle counting system based on vehicle type and classification, as well as differentiating between various types of vehicles and conducting a total count.

Approach: We started by developing a custom video surveillance software which made it possible to remotely watch the traffic situation and collect data. Utilizing image recognition and data analytics techniques we developed a POC model analysing the traffic data, which was further extended to a fully functioning tool for road and safety as the traffic analysis.

Through advanced deep learning our team created a solution which was able to detect and alert for potential accidents, predict congestion, or plan efficient roads and parking spaces. The solution is currently growing into autonomously monitoring traffic cameras and systems and generating real-time alerts when certain events of interest occur.

Tech stack: Python, React.JS, Yolo, SSD and OpenCV

Overview: Our client needed a tool to analyze electricity consumption based on the data from sensors integrated into electrical sockets, in real-time and historically, with the ability to track any critical moments. The client also required the tool to be scalable and applicable to other sensors in the market.

Solution: To ensure that the tool met the requirements, our team collaborated with the client's team to understand their needs and preferences. We analyzed the data collected by the sensors to develop algorithms to accurately track the electricity consumption of each socket. We then integrated the algorithms into a user-friendly interface that allowed users to easily track their electricity usage over time. We used Python, Django and Angular to develop the backend and front end of the tool, respectively, ensuring a scalable solution that could be easily extended to support other sensors in the market.

Our team also implemented various features to enhance the user experience. We included notifications and snapshots for critical moments, such as extreme power consumption, electrical fault or a sudden surge in electricity usage. We also generated heat maps for each socket, providing users with visual information about their electricity usage over time. We ensured that the tool was responsive and could be used on mobile devices, enabling users to monitor their electricity usage on the go.

Tech stack: Python, Django, Angular, AWS.

Research led by Georgi Nalbantov PhD, Head of Data Science @ Childish.AI, to examine the impact of pre-existing cardiac conditions on radiation-induced lung toxicity (RILT) after high-dose radio(chemo)therapy for lung cancer.

Overview:

• Traditionally, radiation effect on the heart and lungs were studied separately
• Recent studies reveal a short-term interaction between heart irradiation and lung dysfunction
• This study bridges the gap by investigating how cardiac issues affect RILT in the short term 

Observations:

• 28.9% of patients had cardiac comorbidity before radiotherapy
• 44% of patients had cardiac comorbidity before radiotherapy
• Patients with cardiac comorbidity had 2.58 times higher odds of developing RILT

Predictive model for RILT:

• A model was built which helps identify patients at higher risk of RILT
• This model incorporates cardiac comorbidity, tumour location, lung function, chemotherapy, and pretreatment dyspnea score
• The model demonstrated an Area Under the Curve (AUC) of 0.72 in the training set and 0.67 in the validation set, signifying its predictive performance