The Primitive Cognitive Network Process in healthcare and medical decision making: Comparisons with the Analytic Hierarchy Process

Highlights

• Indicating the rating scale problems of the Analytic Hierarchy Process (AHP), and proposing the paired interval scale addressing the limitations.

• Introducing Primitive Cognitive Network Process (P-CNP) to medical treatment decision making, and showing how to use it from laymen perspective.

• Demonstrating how the current AHP data to medical decision can be converted to P-CNP data, which is further processed by the P-CNP.

• Applications with the AHP data can be revised by P-CNP to explore the more reliable research findings or make more reliable decisions.

• P-CNP can be a promising decision making approach to evaluate medical and healthcare decisions.

Abstract

Analytic Hierarchy Process (AHP) is increasingly applied to healthcare and medical research and applications. However, knowledge representation of pairwise reciprocal matrix is still dubious. This research discusses the related drawbacks, and recommends pairwise opposite matrix as the ideal alternative. Pairwise opposite matrix is the key foundation of Primitive Cognitive Network Process (P-CNP), which revises the AHP approach with practical changes. A medical decision treatment evaluation using AHP is revised by P-CNP with a step-by-step tutorial. Comparisons with AHP have been discussed. The proposed method could be a promising decision tool to replace AHP to share information among patients or/and doctors, and to evaluate therapies, medical treatments, health care technologies, medical resources, and healthcare policies.

Introduction

Analytic Hierarchy Process (AHP) [1], [2], [3] and Analytic Network Process (ANP) [4] are ones of the popular decision making tools. [5], [6], [7] comprehensively reviewed and classified numerous AHP/ANP's applications in various domains. Regarding the AHP applications to medical and health care, [5] reviewed fifty articles from 1981 to 2006, and classified them in seven categories: diagnosis, patient participation, therapy/treatment, organ transplantation, project and technology evaluation and selection, human resource planning, and health care evaluation and policy.

AHP applications to health care and medical research are still growing. [8], [9] demonstrated the tutorial review to promote applications of AHP in medical and healthcare decision making. [10] combined AHP and goal programming in strategic enterprise resource planning (ERP) in a health-care system. Many medical studies used plenty of questionnaires of AHP design to conduct empirical research to prioritize criteria. For example, [11], [12] evaluated colorectal cancer. [13] prioritized a hierarchy of 12 user needs for computed tomography (CT) scanner. [14] elicited patient preferences for health technology assessment (HTA). [15] examined healthcare professionals’ assessments of risk factors. [16] prioritized multiple outcome measures of antidepressant drug treatment. [17] assessed the expanded national immunization programs (ENIPs) and evaluated two alternative health care policies in Korea. [18] conducted a case comparison of the fuzzy logic and AHP methods in the development of medical diagnosis system involving basic symptoms elicitation and analysis. [19] compared the performance of AHP and Conjoint Analysis (CA) in eliciting patient preferences for treatment alternatives for stroke rehabilitation. [20] determined the most appropriate method for construction of a sequential decision tree in the management of rectal cancer, using various patient-specific criteria and treatments such as surgery, chemotherapy, and radiotherapy.

[21] reviewed methodological developments of AHP in views of problem modeling, pairwise comparisons, judgment scales, derivation methods, consistency indices, incomplete matrix, synthesis of the weights, sensitivity analysis and group decisions. Some debates of the AHP can be found in [22], [23], [24], [25], [26], [27], [28], [29], [30].

The core notion of AHP is the paired comparison using paired ratio scale and used in a pairwise reciprocal matrix. [31], [32], [33] indicated that the basic numerical definition of paired ratio scale $a_{ij}=w_i/w_j$ for paired comparison inappropriately represents the perception and cognition of paired difference and potentially producing misapplications, and suggested the paired interval (or differential) scale, $b_{ij}=v_i-v_j$, which replaces paired ratio scale, as the basis for Primitive Cognitive Network Process (P-CNP), which is to distinguish from AHP. Table 1 presents different terminologies to distinguish the Analytic Hierarchy/Network Process from proposed Cognitive Network Process, in order to avoid confusion of two methods. The Cognitive Hierarchy Process (or Primitive CNP) is the basic model of the CNP, whilst the Analytic Hierarchy Process is the basic model of the ANP.

The word “cognitive” implies that CNP uses the paired interval scale in a native way to represent our perception of paired difference as the expert judgment using paired ratio scale in AHP is questionable. For instance, we can more easily determine the answer or have less chance of errors for the difference of two than the ratio of two. The word “cognitive” could refer to cognitive sciences domain for the paired comparisons, as human cognitions of paired comparisons on the basis of measurement scale, number system and arithmetic operations are open to discuss.

The rest of this study is organized as follows. Section 2 discusses the flaws of paired ratio scale and the advantages of paired interval scale. Section 3 illustrates the concept of the Primitive Cognitive Network Process. Section 4 presents an application to Dogbite Treatment Decision using P-CNP. Section 5 discusses the comparisons with AHP, and the conclusion is in Section 6.