Using Bayesian networks to identify musculoskeletal symptoms influencing the risk of developing psoriatic arthritis in people with psoriasis.

objectivesThe aim of this study was to explore the use of Bayesian networks (BNs) to understand the relationships between musculoskeletal symptoms and the development of PsA in people with psoriasis.

methodsIncident cases of psoriasis were identified for 1998 to 2015 from the UK Clinical Research Practice Datalink. Musculoskeletal symptoms (identified by Medcodes) were concatenated into primary groups, each made up of several subgroups. Baseline demographics for gender, age, BMI, psoriasis severity, alcohol use and smoking status were also extracted. Several BN structures were composed using a combination of expert knowledge and data-oriented modelling based on: (i) primary musculoskeletal symptom groups; (ii) musculoskeletal symptom subgroups and (iii) demographic variables. Predictive ability of the networks using the area under the receiver operating characteristic curve was calculated.

resultsOver one million musculoskeletal symptoms were extracted for the 90 189 incident cases of psoriasis identified, of which 1409 developed PsA. The BN analysis yielded direct relationships between gender, BMI, arthralgia, finger pain, fatigue, hand pain, hip pain, knee pain, swelling, back pain, myalgia and PsA. The best BN, achieved by using the more site-specific musculoskeletal symptom subgroups, was 76% accurate in predicting the development of PsA in a test set and had an area under the receiver operating characteristic curve of 0.73 (95% CI: 0.70, 0.75).

conclusionThe presented BN model may be a useful method to identify clusters of symptoms that predict the development of PsA with reasonable accuracy. Using a BN approach, we have shown that there are several symptoms which are predecessors of PsA, including fatigue, specific types of pain and swelling.