سیستم پشتیبانی تصمیم گیری هوشمند مبتنی بر دانش متخصصان این زمینه در درمان درد گردن و شانه شغلی

This research develops a fuzzy knowledge-based decision support system (FKBDSS) that measures and predicts the degree of severity of the work-related risk associated with shoulder and neck pain (SNP) that is a prevalent pain complaint in an occupational environment. Assessing the harshness of SNP is a dreary chore, since the risk factors are featured with imprecision, uncertainty and vagueness. Predicting SNP subjective risk level provides key decision support information to medical practitioners in diagnosis. The objective involves knowledge acquisition performed through literature analysis, traditional and concept mapping interviews with domain experts comprising neurologist, orthopaedist, psychologist and physiotherapist to identify risk factors that include mechanical, physical and psychosocial categories. The determination of ranking the relative factor importance has accomplished using analytic hierarchy processing (AHP) analysis. The linguistic variables that qualify risk levels are quantified using fuzzy set theory (FST) that provides linguistic and numeric value outputs to predict the hazard level of SNP.

In occupational medicine, terms such as repetitive strain injury (RSI), cumulative trauma disorder (CTD), occupational cervicobrachial disorder (OCD), or work-related musculoskeletal disorder (WMSD), have been used [1]. Musculoskeletal disorders (MSDs) have become an increasing problem in the working environment. It is the vital reason for occupational hazard [2]. It has been estimated that in every month as many as one-third of adults in general population experience SNP symptoms with some associated disability namely limitation in activities of daily living [3]. According to van der Windt et al. [4], inability to work, loss of productivity, occupational illness and inability to carry out household activities can be a considerable burden to the patient as well as to society. According to the large survey made by Bongers [5] three-fourth of the general population have musculoskeletal symptoms specifically SNP. Also the number of epidemiological studies, i.e., studies of the distribution and determinants of disease in human population (here SNP) reporting on potential risk factors for SNP has greatly increased in the past decade. Though several factors cause SNP, work-related factors play an important part. Work place conditions are important contributors to SNP occurrence and so there has been much research into the possible relation between features of the working environment and the development of SNP in the occupational group [6]. Many studies have been conducted on SNP and variety of risk factors at work has been documented [3], [4], [5], [7] and [8]. It is hypothesized that many factors impact an individual's likelihood of developing SNP. There is a disparity in the occurrence of SNP for workers with similar backgrounds and work activities. The risk factors sourcing SNP are uncertain and vague among the people in the same working environment. Hence it is difficult to find the set of risk factors that creates SNP and predict their severity [4] and [7]. Also SNP occurs due to individual or combination of more than one specialized medical fields such as orthopedics, neurology, psychology, etc [3] and [8]. So it involves diagnosis of medical practitioners of all or few above said fields. This practice will complicate the diagnosis process, finding the risk factors causing SNP from any single or combination of many of the specialized medical fields will become a tedious procedure. Nowadays practitioners are interested in identifying accurate methods for evaluating the risk factors of SNP in an occupational setting. The inconsistency in the occurrence of SNP in workers with similar backgrounds and work activities provides an uncertain block in the development of a system for widespread use in evaluating the development of SNP. Thus SNP is one of the most important problems threatening the occupational society; it is essential to find a system that is capable of handling all of the medical fields causing SNP and quantifies the risk level of SNP. This research is an attempt to build a FKBDSS that assists to overcome this problem. The proposed system uses AHP for representing the magnitude of the qualitative risk factors, since it provides a quantitative method for analyzing subjective information [9] and [10]. To address the uncertainty associated with the definition and modeling of SNP risk factors FST has been incorporated [10] and [11]. It derives relative strength of the risk factors from three predominant predefined factors thereby enabling the construction of the proposed model. The justification for applying such Fuzzy Knowledge-Based Systems (FKBS) driven solutions is that biological systems are so complex that the development of computerized systems within such environments is not always a straightforward exercise. In practice, a precise model may not exist for biological systems or it may be too difficult to define a model. In most cases fuzzy logic is considered to be an ideal tool as human minds work from approximate data, extract meaningful information and produce crisp solutions [12], [13] and [14].

The developed FKBDSS to predict the work-related risk level of SNP is a conceptual and methodological approach based on AHP analysis and FST offers an alternative decision process that permits the prediction system to acquire the knowledge and experience of expert physicians into account, thereby meeting the real clinical needs. The evaluation and validation process shows that the developed FKBDSS proves to be an accurate means for quantifying the prevalence of SNP that reveals the degree of severity. Also this can be expressed in qualitative form based on the defined LRLs. The results of this research show that the devised prediction model is a convenient tool that supports medical practitioners in SNP diagnosis. It is a promising method for addressing the complexity and variability associated with SNP. The proposed system helps an individual at remote corners to receive the intelligent diagnosis. It is concluded that the devised system have the potential to improve the quality of clinical decision making, the outcomes of health services and strengthen the patient–doctor relationship.