Applied machine learning to predict patients’ status based on their lab test/genetics variations

Company Information

A downtown Toronto hospital sought to harness the power of machine learning to predict patients’ health outcomes based on lab test and genetic variation data. In an innovative step forward, ProCogia was enlisted to apply advanced data science and bioinformatics methodologies to improve clinical decision-making and operational efficiency within the hospital.

The Challenge

The project faced significant challenges, including the handling of vast datasets with missing or low-quality data, managing the complexity of human genetics variants, and the need for accurate classification of patient statuses. Moreover, the hospital required a solution that could seamlessly integrate into their existing systems to enhance predictive analytics capabilities without disrupting ongoing clinical operations.

Procogia’s Approach

Our team applied data cleaning/wrangling to handle missing value, and low-quality data using pandas, PySpark and Dask.

We applied data management of a large dataset of human genetics variants using PySpark and Hadoop cluster.

Machine Learning (ML) techniques were used for different classification tasks such as SVM, Random Forest, and logistic regression.

We used data visualization tools such as Tableau to visualize the data in a compelling and easy-to-digest way.

The Results

This architectural redevelopment has had positive effects across the organization, from optimizing where the products are sold, to how sizes are displayed on the client’s e-commerce site. Improved capabilities include:

Clinicians and scientists received more insights to assist them in making better decisions about medical treatments and underlying conditions.

Improved predictions about patient’s disease status with encouraging accuracies (80%), precision and recall (F1 score).

Improved operation efficiency of the hospital by predicting a patient’s length of stay. Hospitals can identify patients with a high length of stay risk at the time of admission. As a result, these patients can have their treatment plan optimized to minimize the length of stay, and it can aid logistics such as room and bed allocation planning.

Services Used

Data Science

We use open source technology to leverage the full potential of your data. Predictive and prescriptive results are actioned using AI and Machine Learning (ML).

BI & Analytics

We transform complex and high-volume data into BI reports using dashboards and visualizations, allowing you to make smarter decisions.


We deliver scientific results that drive clinical and translational research decisions. Our Bioinformatics team has extensive experience designing, optimizing, executing and analyzing pre-clinical and clinical research projects using next-generation sequencing technologies.


ProCogia’s collaboration with the downtown Toronto hospital exemplifies the transformative potential of applying machine learning and bioinformatics to healthcare. By providing clinicians and hospital administrators with advanced tools for predictive analytics, ProCogia has not only improved patient outcomes but also enhanced the efficiency and effectiveness of hospital operations. This case study highlights ProCogia’s ability to navigate complex data challenges and deliver innovative solutions that have a tangible impact on healthcare delivery and patient care.

Explore more stories

Dig deeper into data development by browsing our blogs…

Get in Touch

Let us leverage your data so that you can make smarter decisions. Talk to our team of data experts today or fill in this form and we’ll be in touch.