Question

Clinical Pathways: multidisciplinary plans of best clinical practice.

• What are some computational tools designed to support health care decision making and benefit patient care? Why do we need them? Are they important?

• What are knowledge versus non-knowledge based resources. Why do we need them? Are they important?

• What are some safeguards needed for proper use of such a system? Why do we need them? Are they important?

Answer 1

Emergence of IT has revolutionized the healthcare data acquisition, management, analysis and dissemination of information and knowledge. Most computers programs in health care are intended to have a direct effect on the quality of healthcare decisions.

CDSS – Clinical Decision Support System

These are computer programs that help physicians to make diagnoses and support health-care workers by providing a vast collection of possible diseases and symptoms to make better clinical decision making. The programs must have:

• Access to good data
• Extensive background knowledge encoded for the clinical domain in question
• An intelligent approach to problem-solving
• Appropriate cost–benefit trade-offs
• Efficiency

Tools for Information Management

Health-care information systems and information-retrieval systems are tools that manage information. Specialized knowledge-management workstations are under development in research settings; these workstations provide sophisticated environments for storing and retrieving clinical knowledge. These tools provide the data and knowledge needed by the clinician, but they generally do not help them to apply that information to a particular decision task. Interpretation is left to the clinician.

Tools for Focusing Attention

These tools are designed to remind the user of diagnoses that might otherwise have been overlooked. These tools flag abnormal values that alert providers to possible drug interactions.

Tools for Providing Patient-Specific Recommendations

These programs provide advice based on sets of patient-specific data. They may follow simple algorithms that may be based on decision theory and cost-benefit analysis. Diagnostic assistants such as DXplain or QMR suggest differential diagnoses or indicate additional information that would help to narrow the range of etiologic possibilities. Other systems such as the original Internist-1 program suggest a single best explanation for a patient’s symptoms.

The tools for Clinical decision making that analyze and manipulate patient data are important for accurate diagnosis and disease management and in reaching good clinical decisions

A CDSS is based on an input-process-output (IPO) model. The inputs for the CDSS process include patient-specific information such as diagnoses, medications, symptoms, laboratory data, demographics, and other clinically relevant information..

The CDSS process takes two different forms:

1. Knowledge based systems - that are governed by a set of rules.
2. Non-knowledge based systems - Use a computer as the central processing unit to learn from historical information and typically utilize machine learning algorithms.

The output from may be a diagnosis, procedure, prescription, etc. When the computer and the physician are presented with the same information, the output from the CDSS should mirror the physician’s decision.

One way to abuse the CDSS tool is to use it for purposes for which it is not intended. Another is to use the tool without adequate training. A third way is to use a tool incorrectly or carelessly.

A medical computer system may be used inappropriately if it was designed for on for clinical decision support but used in such a way as to cause a practitioner to abandon a diagnosis arrived at by sound clinical methods. Identifying qualifications and providing training must be key components of any movement to expand the use of decision support software.