Response to: ‘Catching the falling star: points to consider when using propensity scores’ by Ouyang <i>et al</i>

Bergstra, Sytske Anne; Allaart, Cornelia F; Landewé, Robert

doi:10.1136/annrheumdis-2018-214892

Cited by 1 publication

(1 citation statement)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also no clear recommendations on treatment de-escalation in case of stable disease 5 despite disease activity-guided dose optimisation of biologic being efficient and cost-effective 6 . In other words, over- or undertreatment in RA is common, potentially resulting either in destructive disease flares or unnecessary side effects and costs 7 .…”

Section: Introductionmentioning

confidence: 99%

Personalized Prediction of Disease Activity in Patients with Rheumatoid Arthritis Using an Adaptive Deep Neural Network

Hügle

Walker

Finckh

et al. 2020

Preprint

View full text Add to dashboard Cite

Background: Rheumatoid arthritis (RA) lacks reliable biomarkers that predict disease evolution on an individual basis, potentially leading to over- and undertreatment. Deep neural networks learn from former experiences on a large scale and can be used to predict future events as a potential tool for personalized clinical assistance. Objective: To investigate deep learning for the prediction of individual disease activity in RA. Methods: Demographic and disease characteristics from over 9500 patients and 65.000 visits from the Swiss Quality Management (SCQM) database were used to train and evaluate an adaptive recurrent neural network (AdaptiveNet). Patient and disease characteristics along with clinical and patient reported outcomes, laboratory values and medication were used as input features. DAS28-BSR was used to predict active disease and future numeric individual disease activity by classification and regression, respectively. Results: AdaptiveNet predicted active disease defined as DAS28-BSR>2.6 at the next visit with an overall accuracy of 75.6% and a sensitivity and specificity of 84.2% and 61.5%, respectively. Regression allowed forecasting individual DAS28-BSR values with a mean squared error of 0.9, corresponding to a variation between predicted and true values at next visit of 8%. Apart from DAS28-BSR, the most influential characteristics to predict disease activity were joint pain, disease duration, age and duration of treatment. Longer disease duration, age >50 years or antibody positivity marginally improved prediction performance. Conclusion: Deep neural networks have the capacity to predict individual numeric disease activity in RA. Low specificity remains challenging and might benefit from alternative input data or outcome targets.

show abstract

Section: Introductionmentioning

confidence: 99%