Sepsis Prediction via Machine Learning

Sepsis is a disease associated with pathogenic microorganisms in the bloodstream and the body's response to it. It can move quickly in the body stream and is one of the leading causes of mortality in hospitalized patients (around 38%). Existing detection methods suffer from low performance and often require time-consuming laboratory test results. Early and accurate sepsis onset predictions could allow more aggressive and targeted treatment giving the doctors an advantage in handling the dire consequences and keeping the medical costs of treatment low.

This is some text inside of a div block.
This is some text inside of a div block.

Predera Health Engine

Predictive analytics can help physicians make more accurate diagnoses. For example, when patients come to the ER with chest pain, it is often difficult to know whether the patient should be hospitalized or sent home. Imagine if your electronic health record system (EHR) has access to a solution that utilizes demographic information, past conditions of the patient, prescriptions, historical clinical notes, procedural information and learns from the data a personalized score of riskiness of the patient. This accurate predictive system that would assess the likelihood that the patient could be sent home safely, could be used in conjunction with the physician’s judgment to have a much better outcome for the patient, in turn makes the physician job slightly easier with a high quality outcome for the hospital.

We have built such a predictive healthcare engine that can plug into your electronic health record system (Epic, Cerner, Meditech, AllScripts among others) to learn patient diagnosis models and score patients in real-time for their riskiness. We have built and tested a highly accurate model with low false positives for  Sepsis, All-cause Readmission models and Length-of-Stay at hospitals.

Are you ready for predictive analytics?

If your answers to any of the following questions is YES, you can benefit from our solution

- Do you use an EHR to capture all the historical information of your patients in a warehouse?

- Do you currently use the data to compute quality metrics for your hospital?

- Do you support access to the data source via any exchange protocol like FHIR/HL7?