Predictive Model for Healthcare StartupHealthcare

Aretove Technologies
The client has unique cloud-based system integrates significant behavioral, clinical and medication adherence data to manage and monitor seniors and people with chronic conditions.

A single platform manages all conditions, providing a unique new source of major health care data. The results are more efficient allocation of resources, improved information sharing, and reduced overall cost of care. There is a need to develop Predictive Model for Healthcare.


With huge amount of data generated from various tablets there was a need to develop Predictive Model for Healthcare. To analyze the data in real-time and apply patterns to predict the next possible actions for patients with similar types of observations and alerts. Timely analysis of current patients data, superimposed with the set of data from other patients with similar health conditions is important to advise care givers.

Challenges included:

  • Develop predictive models to accurately assess when a patient will need to visit doctor or hospital.
  • Develop a predictive model for individual likelihood of memory maintenance and uses, with permission, the data thus entered through care tracker.
  • Provide predictive models using double-blind elements and random assignment, satisfying the continued need for controlled studies.
  • Identify possible personal health risks sooner due to alerts from their observed health conditions, from predictive models relayed by their care givers via the care tracker table.


For predictive modeling, the data mining techniques used included traditional statistics, such as multiple discriminant analysis and logistic regression analysis. They also include non-traditional methods developed in the areas of artificial intelligence and machine learning. The two most important models of these are neural networks and decision trees.

Models were developed to predict surgical risk, helping match patients with the right course of action that will keep them safest during their care. By harnessing EHR data, system can even identify links between previously disparate diseases.  A risk score developed allows clinicians to predict diabetic patients who are likely to develop dementia in the future.


  • Care-management information: trying to predict risks for patients who are likely to get worse, and understand what intervention and what treatments could impact that risk for the patient.
  • Identification of patient’s likelihood to be hospitalized within the next six months, or looking at the likelihood of a patient who might return to the hospital within 30 days.
  • Used geographical data, census data and community data intersected with health observation data to look at where an individual may live and what additional risks there may be.
  • Based on the observation data a lot of lifestyle factors and interests were found to be more predictive of health outcomes than just clinical data alone, particularly in settings of chronic diseases.

Explore various software services and solutions provided by Aretove at the intersection of Business Intelligence, Artificial Intelligence and Machine Learning.

How Can We Help You?

Contact us at to see how we can help you accelerate your data engineering and business intelligence initiatives.

Looking for a Big Data & Predictive Analytics Consultant?