What is associated with painful polyneuropathy? A cross-sectional analysis of symptoms and signs in patients with painful and painless polyneuropathy.

ABSTRACT: It is still unclear how and why some patients develop painful and others painless polyneuropathy. The aim of this study was to identify multiple factors associated with painful polyneuropathies (NeuP). A total of 1181 patients of the multicenter DOLORISK database with painful (probable or definite NeuP) or painless (unlikely NeuP) probable or confirmed neuropathy were investigated clinically, with questionnaires and quantitative sensory testing. Multivariate logistic regression including all variables (demographics, medical history, psychological symptoms, personality items, pain-related worrying, life-style factors, as well as results from clinical examination and quantitative sensory testing) and machine learning was used for the identification of predictors and final risk prediction of painful neuropathy. Multivariate logistic regression demonstrated that severity and idiopathic etiology of neuropathy, presence of chronic pain in family, Patient-Reported Outcomes Measurement Information System Fatigue and Depression T-Score, as well as Pain Catastrophizing Scale total score are the most important features associated with the presence of pain in neuropathy. Machine learning (random forest) identified the same variables. Multivariate logistic regression archived an accuracy above 78%, random forest of 76%; thus, almost 4 out of 5 subjects can be classified correctly. This multicenter analysis shows that pain-related worrying, emotional well-being, and clinical phenotype are factors associated with painful (vs painless) neuropathy. Results may help in the future to identify patients at risk of developing painful neuropathy and identify consequences of pain in longitudinal studies.

Big data, big consortia, and pain: UK Biobank, PAINSTORM, and DOLORisk.

Chronic pain (CP) is a common and often debilitating disorder that has major social and economic impacts. A subset of patients develop CP that significantly interferes with their activities of daily living and requires a high level of healthcare support. The challenge for treating physicians is in preventing the onset of refractory CP or effectively managing existing pain. To be able to do this, it is necessary to understand the risk factors, both genetic and environmental, for the onset of CP and response to treatment, as well as the pathogenesis of the disorder, which is highly heterogenous. However, studies of CP, particularly pain with neuropathic characteristics, have been hindered by a lack of consensus on phenotyping and data collection, making comparisons difficult. Furthermore, existing cohorts have suffered from small sample sizes meaning that analyses, especially genome-wide association studies, are insufficiently powered. The key to overcoming these issues is through the creation of large consortia such as DOLORisk and PAINSTORM and biorepositories, such as UK Biobank, where a common approach can be taken to CP phenotyping, which allows harmonisation across different cohorts and in turn increased study power. This review describes the approach that was used for studying neuropathic pain in DOLORisk and how this has informed current projects such as PAINSTORM, the rephenotyping of UK Biobank, and other endeavours. Moreover, an overview is provided of the outputs from these studies and the lessons learnt for future projects.

Classification of painful or painless diabetic peripheral neuropathy and identification of the most powerful predictors using machine learning models in large cross-sectional cohorts.

BACKGROUND: To improve the treatment of painful Diabetic Peripheral Neuropathy (DPN) and associated co-morbidities, a better understanding of the pathophysiology and risk factors for painful DPN is required. Using harmonised cohorts (N = 1230) we have built models that classify painful versus painless DPN using quality of life (EQ5D), lifestyle (smoking, alcohol consumption), demographics (age, gender), personality and psychology traits (anxiety, depression, personality traits), biochemical (HbA1c) and clinical variables (BMI, hospital stay and trauma at young age) as predictors. METHODS: The Random Forest, Adaptive Regression Splines and Naive Bayes machine learning models were trained for classifying painful/painless DPN. Their performance was estimated using cross-validation in large cross-sectional cohorts (N = 935) and externally validated in a large population-based cohort (N = 295). Variables were ranked for importance using model specific metrics and marginal effects of predictors were aggregated and assessed at the global level. Model selection was carried out using the Mathews Correlation Coefficient (MCC) and model performance was quantified in the validation set using MCC, the area under the precision/recall curve (AUPRC) and accuracy. RESULTS: Random Forest (MCC = 0.28, AUPRC = 0.76) and Adaptive Regression Splines (MCC = 0.29, AUPRC = 0.77) were the best performing models and showed the smallest reduction in performance between the training and validation dataset. EQ5D index, the 10-item personality dimensions, HbA1c, Depression and Anxiety t-scores, age and Body Mass Index were consistently amongst the most powerful predictors in classifying painful vs painless DPN. CONCLUSIONS: Machine learning models trained on large cross-sectional cohorts were able to accurately classify painful or painless DPN on an independent population-based dataset. Painful DPN is associated with more depression, anxiety and certain personality traits. It is also associated with poorer self-reported quality of life, younger age, poor glucose control and high Body Mass Index (BMI). The models showed good performance in realistic conditions in the presence of missing values and noisy datasets. These models can be used either in the clinical context to assist patient stratification based on the risk of painful DPN or return broad risk categories based on user input. Model's performance and calibration suggest that in both cases they could potentially improve diagnosis and outcomes by changing modifiable factors like BMI and HbA1c control and institute earlier preventive or supportive measures like psychological interventions.

Cohort profile: DOLORisk Dundee: a longitudinal study of chronic neuropathic pain.

PURPOSE: Neuropathic pain is a common disorder of the somatosensory system that affects 7%-10% of the general population. The disorder places a large social and economic burden on patients as well as healthcare services. However, not everyone with a relevant underlying aetiology develops corresponding pain. DOLORisk Dundee, a European Union-funded cohort, part of the multicentre DOLORisk consortium, was set up to increase current understanding of this variation in onset. In particular, the cohort will allow exploration of psychosocial, clinical and genetic predictors of neuropathic pain onset. PARTICIPANTS: DOLORisk Dundee has been constructed by rephenotyping two pre-existing Scottish population cohorts for neuropathic pain using a standardised 'core' study protocol: Genetics of Diabetes Audit and Research in Tayside Scotland (GoDARTS) (n=5236) consisting of predominantly type 2 diabetics from the Tayside region, and Generation Scotland: Scottish Family Health Study (GS:SFHS; n=20 221). Rephenotyping was conducted in two phases: a baseline postal survey and a combined postal and online follow-up survey. DOLORisk Dundee consists of 9155 participants (GoDARTS=1915; GS:SFHS=7240) who responded to the baseline survey, of which 6338 (69.2%; GoDARTS=1046; GS:SFHS=5292) also responded to the follow-up survey (18 months later). FINDINGS TO DATE: At baseline, the proportion of those with chronic neuropathic pain (Douleur Neuropathique en 4 Questions questionnaire score ≥3, duration ≥3 months) was 30.5% in GoDARTS and 14.2% in Generation Scotland. Electronic record linkage enables large scale genetic association studies to be conducted and risk models have been constructed for neuropathic pain. FUTURE PLANS: The cohort is being maintained by an access committee, through which collaborations are encouraged. Details of how to do this will be available on the study website (http://dolorisk.eu/). Further follow-up surveys of the cohort are planned and funding applications are being prepared to this effect. This will be conducted in harmony with similar pain rephenotyping of UK Biobank.

DOLORisk: study protocol for a multi-centre observational study to understand the risk factors and determinants of neuropathic pain.

Background: Neuropathic pain is an increasingly prevalent condition and has a major impact on health and quality of life. However, the risk factors for the development and maintenance of neuropathic pain are poorly understood. Clinical, genetic and psychosocial factors all contribute to chronic pain, but their interactions have not been studied in large cohorts. The DOLORisk study aims to study these factors. Protocol: Multicentre cross-sectional and longitudinal cohorts covering the main causes leading to neuropathic pain (e.g. diabetes, surgery, chemotherapy, traumatic injury), as well as rare conditions, follow a common protocol for phenotyping of the participants. This core protocol correlates answers given by the participants on a set of questionnaires with the results of their genetic analyses. A smaller number of participants undergo deeper phenotyping procedures, including neurological examination, nerve conduction studies, threshold tracking, quantitative sensory testing, conditioned pain modulation and electroencephalography. Ethics and dissemination: All studies have been approved by their regional ethics committees as required by national law. Results are disseminated through the DOLORisk website, scientific meetings, open-access publications, and in partnership with patient organisations. Strengths and limitations: Large cohorts covering many possible triggers for neuropathic painMulti-disciplinary approach to study the interaction of clinical, psychosocial and genetic risk factorsHigh comparability of the data across centres thanks to harmonised protocolsOne limitation is that the length of the questionnaires might reduce the response rate and quality of responses of participants.