Clinical Decision Support System 

Project Domain / Category

 Decision Support System 

Abstract/Introduction

Clinical Decision Support System (CDSS) is a system that provides clinicians, staff, patients and other individuals with knowledge and person-specific information, intelligently filtered and presented at appropriate times to enhance health and health care. Over the past few decades there has been a significant shift towards developing intelligent systems to help humans in decision making in different domains of life. CDSS is one of them. These kinds of software use relevant knowledge, rules within a knowledge base and relevant patient and clinical data to improve clinical decision making on topics like preventive, acute and chronic care, diagnostics, specific test ordering, prescribing practices etc. A CDSS correlates data about patient traits with a trustworthy knowledge base to guide a clinician with patient-specific advice, assessments or recommendations. Clinicians, health-care staff or patients can manually enter patient characteristics into the computer systems; alternatively, electronic medical records (EMR) can be queried for retrieval of patient characteristics. These kinds of decision-support systems allow the clinicians to spot and choose the most appropriate treatment.

The value that CDSS brings to clinicians, patients, medical staffs and health organizations is immense and proven. Hence, health organizations around the globe always pursue to implement CDSS to improve quality of care and thereby improve patient satisfaction, to reduce costs and finally to attract and maintain medical staff. The purpose of this project is to develop an indigenous state-of-the-art CDSS to help practitioners, at any level, in their daily life clinical decision making and thus improve the health care in developing countries like Pakistan where health conditions are already alarming. This simply means that clinicians will interact with a CDSS to analyze and reach a diagnosis based on patient data.

Functional Requirements: The proposed CDSS will be complete application providing state-of-the-art decision support services to practitioners at various levels. The main services provided by the proposed application will be:

1) Diagnostic assistance: Based on the patient’s data and the system’s knowledge base, the CDSS will provide likely diagnoses. This is beneficial when the clinician is not confident with his or her knowledge on a certain condition or when the patient’s symptoms are complex or seemingly unrelated.

2)  Drug dosing or prescribing: Overall prescription of medication is one of the commonest tasks of a physician. CDSS will have the power to reduce toxic drug levels, reduce medical errors and change prescribing in accordance to guideline recommendations. Such systems have been widely accepted, since they are well integrated into a routine part of the clinician’s workflow.

3) Test selection: Based on the patient data/history, the system will be able to suggest relevant medical tests. Test will be selected on the basis of pre-defined protocols and guidelines already present in the system.

4) Alerts and reminders:  A CDSS will alert the doctor or physician when certain input data is alarming or a potential risk to the patient. For example, if a patient has a history of cardiac issues and the system reads that their blood pressure is abnormally high it can alert the doctor of the abnormality.

5) Logical Reasoning:  One of the problems faced by many practitioners is to provide logical reason in case if any of the standards or recommendation is deviated. System will provide complete reason or root followed to reach a decision.

High Level Architecture: Architecture will comprise of three main components.

Working memory: Working memory will contain the current facts and figures taken from the patient. This will be a temporary memory to store current patient data.

Knowledge Base: Knowledge base will be the actual data store for the CDSS containing the rules and protocols for actual diagnostics. Rules will permanently be saved here. This will be dynamically updated i.e.; knowledge base will be updated every time new facts are discovered.

Inference engine: This is the actual processing unit that will perform diagnostics using the facts from working memory and rules from knowledge base. User will interact inference engine to perform different tasks.  Note: Same architecture (described above) will be followed for all modules. Figure below shows the architectural diagram of the system.

 

Release details: As the project is very broad in scope, so keeping time duration of semesters in mind, project may be developed in release where each release will comprise of a single module described in functional requirements section.

Tools:

Microsoft.Net, SQL Server

Leave a Comment