No abstract

No abstract

No abstract

BackgroundPrevention of persistent pain following breast cancer surgery, via early identification of patients at high risk, is a clinical need. Supervised machine-learning was used to identify parameters that predict persistence of significant pain.MethodsOver 500 demographic, clinical and psychological parameters were acquired up to 6 months after surgery from 1,000 women (aged 28–75 years) who were treated for breast cancer. Pain was assessed using an 11-point numerical rating scale before surgery and at months 1, 6, 12, 24, and 36. The ratings at months 12, 24, and 36 were used to allocate patents to either “persisting pain” or “non-persisting pain” groups. Unsupervised machine learning was applied to map the parameters to these diagnoses.ResultsA symbolic rule-based classifier tool was created that comprised 21 single or aggregated parameters, including demographic features, psychological and pain-related parameters, forming a questionnaire with “yes/no” items (decision rules). If at least 10 of the 21 rules applied, persisting pain was predicted at a cross-validated accuracy of 86% and a negative predictive value of approximately 95%.ConclusionsThe present machine-learned analysis showed that, even with a large set of parameters acquired from a large cohort, early identification of these patients is only partly successful. This indicates that more parameters are needed for accurate prediction of persisting pain. However, with the current parameters it is possible, with a certainty of almost 95%, to exclude the possibility of persistent pain developing in a woman being treated for breast cancer.Electronic supplementary materialThe online version of this article (10.1007/s10549-018-4841-8) contains supplementary material, which is available to authorized users.

We studied postoperative pain trajectories and associated factors. Expectation of severe postoperative pain was associated with higher intensity of experimental and postoperative pain.

BackgroundDiagnosing depression in chronic pain is challenging due to overlapping somatic symptoms. In questionnaires, such as the Beck Depression Inventory (BDI), responses may be influenced more by pain than by the severity of depression. In addition, previous studies have suggested that symptoms of negative self-image, a key element in depression, are uncommon in chronic pain-related depression. The object of this study is to assess the relationship of the somatic and cognitive-emotional items of BDI with the diagnosis of depression, pain intensity, and disability.MethodsOne hundred consecutive chronic pain patients completed the Structured Clinical Interview for DSM Disorders (SCID) for the diagnosis of major depressive disorder (MDD) according to DSM-IV. Two subscales of BDI (negative view of self and somatic-physical function) were created according to the factor model presented by Morley.ResultsIn the regression analysis, the somatic-physical function factor associated with MDD, while the negative view of self factor did not. Patients with MDD had higher scores in several of the BDI items when analysed separately. Insomnia and weight loss were not dependent on the depression diagnosis.LimitationsThe relatively small sample size and the selected patient sample limit the generalisability of the results.ConclusionsSomatic symptoms of depression are also common in chronic pain and should not be excluded when diagnosing depression in pain patients. Regardless of the assessment method, diagnosing depression in chronic pain remains a challenge and requires careful interpretation of symptoms.

Contact heat and cold pressure tests identify variability in pain sensitivity which is modified by factors such as anxiety, chronic pain, previous surgery, and smoking. High levels of anxiety are connected to increased pain sensitivity in experimental and acute postoperative pain.

No abstract