Automating Scientific Innovation
Turning your ideas into tangible results
Smoothing the flow between research & clinical practice
Why choose Us
We combine clinical and Data Science expertise to deliver high-quality clinical research designs and the best experience while conducting your project.
Our Mission
Our mission is to automate scientific discovery, creating novel clinical research designs delivered in an Agile workflow.
What we Do
We design and conduct novel clinical research and healthcare policy studies using advanced Data Science models and deliver these results using an Agile workflow.
Agile workflow
In an Agile Data Science workflow, you get results on a continuous, weekly basis, so that you can provide constant feedback. Our goal is to align your goals and expectations with the final analysis report of your data.
We provide amazing Data Science methods!
Machine Learning
Machine learning models deliver highly accurate, personalized outcome predictions, as well as the modifiable factors contributing to those risks.
Image Recognition
Specialized crafted neural networks can automatically detect features such as radiological signs from medical images, including radiographs, CT, MRI, ultrasound, among other modalities.
Natural Language Processing
NLP allows the extraction of data from free text. Some examples include admission and discharge summaries, radiology and pathology reports, among others.
Clinical Trial Analysis
Clinical trials require a very unique and detailed analysis. We support a wide range of designs, such as parallel, cluster (including stepped wedge), non-inferiority, n-of-1, factorial, preference, and sequential adaptive trials.
Patient Reported Measures
Patient-reported measures are scales designed to evaluate a specific trait. It includes the development of new scales, crosswalk algorithms to compare scores across different scales measuring the same concept, and the construction of Computerized Adaptive Tests to reduce the number of questions as well as increase the assessment precision, ultimately reducing sample size requirements.
Data Enrichment
Novel methods based on machine learning to link clinical data to external data sources, enriching datasets with patient-level information on social determinants of health, quality of life, diet, cognitive levels, among others.
Causal Models based on Observational Data
Causal models are an approximation of clinical trials, but using 'real-world' data. Methods include propensity scores, the difference in differences, interrupted time series, regression discontinuity, instrumental variables, and Bayesian Networks.
Longitudinal Analysis
The longitudinal analysis includes any analytical methods involved when you follow patients over time, including multiple outcome assessments over time for one individual. Methods include survival analysis, mixed-effects models, among others.
Spatial Analysis
Some health issues are very location dependent. Spatial analysis Involves the representation of conditions, outcomes, and other clinical variables through maps. Risks are then calculated taking into account patients' proximity to a variety of environmental exposures and social determinants of health.
Let's Get In Touch!
Ready to start your next project with us? Give us a call or send us an email and we will get back to you as soon as possible!