Data Science
Our data scientists can help you extract further knowledge from your health data by applying the latest data science techniques and tools. Discover correlations in your data, create and utilize prediction models and in general extract knowledge from your health data.
Data Visualizations
We can design data visualizations for your health data and data analysis results that allows you to get a clearer view of what the data represents, spot and highlight trends uncovered by data analysis, and present your data and outcomes clearly to others.
For example, by visualizing the estimated gender distribution of diagnosed and un-diagnosed diabetes, you can get a better understanding of any potential gender bias in the diagnosis of diabetes.
Numbers represented in millions-of-patients and taken from https://www.cdc.gov/diabetes/pdfs/data/statistics/national-diabetes-statistics-report.pdf
Data analytics
We help you gain further insight into your health data by designing data analysis protocols tailored to your health data sources and domain.
By developing and implementing data analytics that are relevant for your data, you can spot trends, generate forecasts, predict outcomes, and in general get better understanding of how patient care can be improved.
Machine learning
At edenceHealth we believe that data can save lives, but only if we turn them into insights. Therefore, we create and implement custom statistical models that unlock a whole range of new opportunities, not only in optimization of business processes, but most importantly, also in improvement of patient care. More specific, we do both patient-level prediction and population-level estimation.
At the patient-level causal effect contrasts what happened to the exposed patient, with what would have happened had the exposure not occurred or had a different exposure occurred. Such models give the opportunity to the integration of a much more personalized medical care, moving beyond the status quo in healthcare.
At the population level, the objective is to produce a high-quality estimate of a causal effect. Use-cases for population-level effect estimation include treatment selection, safety surveillance, and comparative effectiveness.