Detecting and treating heart failure using a clinical decision support system
A team from Acando has demonstrated how to detect heart failure in undiagnosed patients by scoring symptoms using SAS Viya, and suggesting the best treatment using patients’ own data and international guidelines.
There are two kinds of heart failure disease – heart failure with reduced ejection fraction and heart failure with preserved ejection fraction. Heart failure with reduced ejection fraction has many treatment options while heart failure with preserved ejection fraction is much harder to diagnose and treat. In addition, new medications are being added as treatment options for patients all the time, further complicating the doctor’s decision-making.
When patients arrive at a busy clinic, general practitioners only have a few moments to fully diagnose and treat a patient. The doctor must examine the medical history thoroughly to ensure the optimal treatment for the patient.
For the 2019 SAS® Viya® Hackathon, Acando created a clinical decision support system that can evaluate diagnosis and treatment.
Much of the needed data exists in the patient’s digital health record, but the doctor needs to read through it before adjusting treatment or diagnosing a new patient. This is time-consuming and leaves room for error. PhD Biljana Stangeland Hackathon Team Lead Acando
Diagnosing and medicating patients with help of algorithms and cardiology guidelines
The diagnostic model called ”H2FPEF”, scores a patient's health based on personal information such as gender, age, weight, current medication, and electrocardiogram results. The model can determine whether a patient is suffering from heart failure and – if necessary - send a warning to the practitioner.
The clinical decision support system takes data from the digital health record and compares it to the European cardiology guidelines. It evaluates if the current treatment options are working, or if a patient needs to be prescribed another medication. The warning will be sent to the practitioner if the treatment does not follow the European cardiology guidelines.
By placing the model into the SAS® Viya® environment, the data can be quickly analysed. The first step is placing all of the patient data into the SAS environment. Next, comparing this data to the model to receive a score identifying whether the patient might have heart failure with preserved ejection fraction. Finally, the data is made into a visual diagram, so the doctor can easily compare similarities between patients.
Due to privacy regulations, Acando needed to use synthetic patient records to run these tests. The data for these patients were created using Synthia generator. This service provides synthetic but realistic patient data and health records to cover every sector of healthcare. It includes a complete medical history including medications, life style, allergies, and injuries.
With the decision support system, we hope to ensure that patients receive the best care and are treated for heart failure before it is too late. Biljana Stangeland Hackathon Team Lead Acando
Challenge:
- It is difficult to diagnose heart failure with preserved ejection fraction.
- Doctors have to manually go through patient history to find symptoms that correlate to this particular diagnosis which is time consuming, and details can be overlooked.
- Medications are constantly changing but prescription routines remain the same. New medications, that are better suited, according to the European cardiology guidelines, are available but are not often enough prescribed by GPs.
Solutions:
- Create a digital system to go through patient journals and automatically pull all relevant information relating to heart failure.
- Send a warning to the doctor so they can assess the symptoms and make a diagnosis.
- Using new and better medications that are approved and recommended by the European guidelines might save many lives.
Benefits:
- Diagnose early - ability to match patient history with the new score for heart failure with preserved ejection fraction quickly and before worsening of the disease
- Doctors can change treatment options if current ones are no longer working
- Doctors will have the most up to date information on medications and treatment options that follow the European Cardiology guidelines.
About Hack In SAS Viya
In association with Intel and SAS Nordic User Group “Fans”. SAS hosted the competition “Smarter Together” for SAS partners. Here, teams of analysts and data scientists demonstrate the value of open data combined with SAS® Viya® in the cloud and open source technologies.
SAS provided the SAS® Viya® platform with a number of SAS tools in the cloud for easy access through saasnow.com. The nine participating teams built showcase based on a number of SAS software products including: Visual Analytics, Visual Statistics, Visual Data Mining & Machine learning, econometrics, and optimization.
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.