Personalized prediction of disease activity in patients with rheumatoid arthritis using an adaptive deep neural network

Abstract

Background Deep neural networks learn from former experiences on a large scale and can be used to predict future disease activity as potential clinical decision support. AdaptiveNet is a novel adaptive recurrent neural network optimized to deal with heterogeneous and missing clinical data. Objective We investigate AdaptiveNet for the prediction of individual disease activity in patients from a rheumatoid arthritis (RA) registry. 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 the network. Patient characteristics, clinical and patient reported outcomes, laboratory values and medication were used as input features. DAS28-BSR served as a target to predict active RA and future numeric individual disease activity by classification and regression. Results AdaptiveNet predicted active disease defined as DAS28-BSR >2.6 at the next visit with an overall accuracy of 75.6% (SD +- 0.7%) and a sensitivity and specificity of 84.2% (SD +- 1.6%) and 61.5% (SD +- 3.6%), respectively. Prediction performance was significantly higher in patients with a disease duration >3 years and positive rheumatoid factor. Regression allowed forecasting individual DAS28-BSR values with a mean squared error (MSE) of 0.9 (SD +- 0.05). This corresponds to a 8% deviation between estimated and real DAS28-BSR values. Compared to linear regression, random forest and support vector machines, AdaptiveNet showed an increased performance of over 7% in MSE. Medication played a minor role in the prediction of RA disease activity. Conclusion AdaptiveNet has a superior capacity to predict numeric RA disease activity compared to classical machine learning architectures. All investigated models had limitations in low specificity.

Role of Deep Learning in Predicting Aging-Related Diseases: A Scoping Review

“…Multiple studies have developed DL methods for disease prediction using clinical and/or non-clinical data and attained promising results. Compared with the conventional classification ML models, most of the reviewed studies involving DL models reported higher prediction performance [72,75,86,88]. These findings pave the path to DL models, assisting clinical experts in better diagnosing health conditions in elderly people.…”

“…Such diseases could otherwise trigger inflammation that could lead to irreversible damage in aging people. The study in [75] demonstrated a comprehensive classification and regression analysis using a novel DL on rheumatoid arthritis to determine concrete numerical predictions of disease activity instead of just classifying high or low risk patients, henceforth making treating-to-(predicted)-target strategies better. It was observed that female patients face a higher risk of clinical progression in rheumatoid arthritis.…”

Big data analyses and individual health profiling in the arena of rheumatic and musculoskeletal diseases (RMDs)

“…Prediction models using clinical data and multi-omics to forecast the risk of RMD development, predict disease outcomes, and response to antirheumatic treatments as a premise for individualized approach to medication selection in rheumatology. 47 , 62 – 71 These studies are expected to inform prognosis of RMDs and to aid in improving treatment outcomes by overcoming the currently used ‘trial-and-error’ approach to treatment of RMDs. Most of these studies are hypothesis-generating and their clinical utility is uncertain.…”

“…To address the clinical practice gap of incomplete documentation of disease activity scores for RA and SLE in real-world datasets, studies have applied ML methods for estimation and prediction of DAS28-ESR (AUC = 0.73) and SLEDAI measures (AUC = 0.93), using large RA and SLE registry data. 63 , 76 Such endeavours enable more effective use of real-world data sources for research and can potentially support personalized care approach in clinical practice.…”

Learning from chess engines: how reinforcement learning could redefine clinical decision-making in rheumatology

“…In supervised learning, clinical decision support consists primarily of predictions of specific events, such as the future disease status (eg, remission or flares) 4. Through regression analyses with deep neural networks, for example, algorithms trained on clinical data are already used to predict numerical values such as the DAS28-BSR at next visit 5. Predictions are therefore decision-making aids by providing a more or less concrete look into the future.…”