J. Biomedical Science and Engineering, 2010, 3, 509-516 JBiSE
doi:10.4236/jbise.2010.35071 Published Online May 2010 (http://www.SciRP.org/journal/jbise/).
Advanced decision support for complex clinical decisions
Brain Keltch1, Yuan Lin1, Coskun Bayrak2
1
Department of Applied Science, University of Arkansas at Little Rock, USA;
2
Department of Computer Science, University of Arkansas at Little Rock, USA.
Email: bwkeltch@ualr.edu; yxlin1@ualr.edu; cxbayrak@ualr.edu
Received 1 March 2010; revised 11 March 2010, accepted 13 March 2010.
ABSTRACT makes integrated diagnostic and medical advice bases on
the collected patients’ information, providing reference
A Physician’s decision-making skills are directly re- for the clinical medical officers.
lated to the patient’s positive outcomes. Therefore, a
wealth of medical knowledge and clinical experience 1.2. Key Functions
are key assets for a physician to have. The goal here Clinical decision support systems vary greatly in their
is to use historical clinical data and relationships complexity, function, and application. A Recent study
processed by Artificial Intelligence (AI) techniques to [2] on health care information management four key
aid physicians in their decision making process. Pre- functions of CDSS were outlined as follows:
senting this information in a Clinical Decision Sup- 1) Administrative: Supporting clinical coding and
port System (CDSS) is an effective means to consoli- documentation, authorization of procedures, and re-
date decision results. The CDSS provides a large ferrals.
number of medical support functions to help clini- 2) Managing clinical complexity and details: Keep-
cians make the most reasonable diagnosis and choose ing patients on research and chemotherapy protocols;
the best treatment measures. Initial results have tracking orders, referrals follow-up, and preventive
shown great promise in accurately predicting Fibro- care.
sis Stage in Hepatitis patients. Utilizing this tool could 3) Cost control: Monitoring medication orders; avoi-
mitigate the need for some liver biopsies in the more ding duplicate or unnecessary tests.
than 170 million Hepatitis patients worldwide. The 4) Decision support: Supporting clinical diagnosis
prototype is extendable to accommodate additional and treatment plan processes; and promoting use of
techniques (for example genetic algorithms and logis- best practices, condition-specific guidelines, and popu-
tics regression) and additional medical domain solu- lation-based management.
tions (for example HIV/AIDS). Our project will focus on item four, the decision
support function and, in particular, utilization of his-
Keywords: Fibrosis; Clinical Decision Support; Decision torical laboratory data and outcome data processed
Tree; Neural Network through artificial intelligence tools. The combination
1. INTRODUCTION of historical data and predictive tools provides valu-
able information in the hands of physicians as they
1.1. CDSS Definition develop a course of treatment for a patient.
In hospital information systems (HIS), there are typically 2. BACKGROUND: AI TECHNIQUE IN
two main systems: Hospital Management Information
CDSS
Systems (HMIS) and Clinical Information Systems (CIS)
[1]. HMIS support the hospital administration and trans- Decisions about medical treatment are best made by a
action processing services while the CIS is used to sup- trained and experienced physician. These decision mak-
port the clinical staff activities, to collect and dispose of ers can benefit from historical data and artificial intelli-
clinical medical information, and to accumulate rich gence tools. Computer scientists have dreamed of creat-
clinical knowledge. The CIS also provide clinical advice, ing an “electronic brain” [3]. Computer scientists and
support clinics, assistant clinical decision-making and to doctors alike have been captivated by the potential such
enhance staff efficiency. Clinical decision support sys- a technology might have in medicine [4]. With intelli-
tems (CDSS) are part of the CIS. It is an information gent computers able to store and process vast stores of
system which uses expert systems and artificial intelli- knowledge, the hope was that they would become per-
gence (AI) technology to support clinical decision. It fect ‘doctors in a box’, assisting or surpassing clinicians
Published Online May 2010 in SciRes. http://www.scirp.org/journal/jbise
510 B. Keltch et al. / J. Biomedical Science and Engineering 3 (2010) 509-516
with