NEED
In this industry 4.0 as the quantity and quality of clinical data are rapidly expanding, with the electronic health records (EHRs), and also lot of development happened in technical front in terms of both data handling /processing (Big data) and algorithms (Variety of NLP and computer vision algorithmic – AI) whatever product we are building that should provide the high-quality clinical decision support to achieve the full benefits of electronic health records data.
Here are the four major CDSS functionalities where every HER tool should assist/augment the Doctors with the help of data and insights they are
- At System Function
- Model for giving advice
- Style of Communication
- Human-computer interaction
- Underlying Decision process
System Function needs to provide the 2 basic types of function like what is true? And what to do? What is true is basically applies in CDSS where the advice on fixed set data should readily available when the user enters the data and the nest one What to do is should help in CDSS to advising which test to order with the purpose of further differential diagnosis or which drug to prescribe for the patient’s current condition (On the basis of trained models /data from HER system)
Give advice with this functionality the system should able to provide advice on passive or active nature. Passive advice is completely under the user’s control if he wants he can use whereas the active systems are something where the advice should appear automatically based on the models and relationships with the data. The active devices are like alerts on allergies, Alerts on drugs..etc.
The only problem with this active advice is most of the time it will cause alert fatigue with the user. Hence the system needs to be very careful on what to advise on passive nature and what to advice on active nature
Communication With the better interoperable capability the system should able to communicate the information easily between various departments. And also the communication
Human-computer interaction the product design should be easy to use and apply and it should be more closely to the real-time workflow in terms of design and architecture
Decision process
With the availability of additional statistical models, mathematical techniques, and increasing computing power, much more complex models have been researched and used since, like Bayesian models artificial neural networks, machine learning algorithms. The system should provide the improved prediction of outcome, prioritize treatment or help to choose the best course of action and also it should be able to provide better interpretability capabilities.
Our platform (medeva.io) made all these functionalities made available in our platform which assist/augment the doctors at the point of care. Please check the below for more details
<iframe width=”1280″ height=”720″ src=”https://www.youtube.com/embed/SBD9dVNEp6Y” title=”YouTube video player” frameborder=”0″ allow=”accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture” allowfullscreen></iframe>
