Abstract
Clinical reasoning involves coordinated thinking strategies targeted at gathering and analyzing relevant information to arrive at a high-quality clinical solution to patients' medical problems. The correctness and proper choice of clinical reasoning approach chosen by a clinician or machine affect the accuracy and acceptability of the diagnosis; moreover, another challenge that usually surfaces during clinical reasoning is the burden of reasoning out what is known as missing data. This implies that failure to measure-up to the requirement of an acceptable clinical reasoning procedure and inability to gather enough data will have adverse impact on patient's health. A major motivating factor necessitating research of models for automation and formalization of in clinical reasoning is due to its sensitivity and complexity. Although different formalism now exists, such as approximate reasoning and use of models or logical inferences, to curtail the issue of incompleteness of data and as well attain a high-quality clinical problem solving. However most of these formalisms have the drawback associated with their underlying methods of approximation of reasoning structures that usually mar the procedure and result of clinical problem solving process. The Select and Test (ST) algorithm offers close solution to the problems earlier stated. This paper presents an improved model of ST algorithm for clinical diagnosis and monitoring. This paper is focused on redesign of the ST model and the formalization of the approximate clinical reasoning. The redesigned ST model incorporates a monitoring module and mechanism for interacting with an ontology-based knowledge store. Specifically, the ST algorithm was modified to accommodate these additions to the ST model. Data was sourced through a retrospective study on breast cancer patients' records and through the administration of questionnaire at the Ahmadu Bello University Teaching Hospital (ABUTH) Zaria, Nigeria. In addition, Wisconsin datasets were used to test the resulting formalism. Empirical analysis of breast cancer diagnosis using the proposed model revealed that the accuracy of 88.72% was achieved. Similarly, a sensitivity of 1.0, specificity of 0.51 and an ROC point of (0.49, 1) was also attained. This paper presents an inference model and its approximate reasoning representation to diagnose and monitor the presence of a disease.
Highlights
Clinical reasoning which is often associated with machine reasoning is considered a branch of artificial intelligence (Kishan et al, 2012)
The author stated that diagnostic accuracy of any diagnosis test gives us an answer to the following question: How well this test discriminates between certain two conditions of interest? It is this discriminative ability that this paper measures by measuring diagnostic accuracy: True Positive (TP), True Negative (TN), False Negative (FN), False Positive (FP), Receiver Operating Characteristics (ROC), True Positive Rate (TPR) and False Positive Rate (FPR)
The Select and Test (ST) model we designed, which was augmented by a block diagram of the formalism for approximate reasoning, was meant to serve as an illustration of our proposal of using logical inferences in clinical solving problems
Summary
Clinical reasoning which is often associated with machine reasoning is considered a branch of artificial intelligence (Kishan et al, 2012). To tackle the problem of inaccurate models, designing models that can bridge the gap between theory and the reality of clinical practice will help clinicians to gain a better understanding of problems (Coiera, 2003). Application of such models is known as Clinical Decision Support Systems (CDSS), whose roles include: Information management, diagnoses and patient-specific consultation (Kawamoto et al, 2005), have improved clinical practice by 69% of trials (Shortliffe, 1987). This paper is an improvement on an inference model known Select and Test (ST) (Fernando and Henskens, 2013; Fernando and Henskens, 2016a; Ramoni and Stefanelli, 1992), similar to clinical diagnostic reasoning models are characterized by dual processing (Monteiro and Norman, 2013)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
