Application of machine learning in rheumatic disease research

Systemic lupus in the era of machine learning medicine

Artificial intelligence and machine learning applications are emerging as transformative technologies in medicine. With greater access to a diverse range of big datasets, researchers are turning to these powerful techniques for data analysis. Machine learning can reveal patterns and interactions between variables in large and complex datasets more accurately and efficiently than traditional statistical methods. Machine learning approaches open new possibilities for studying SLE, a multifactorial, highly heterogeneous and complex disease. Here, we discuss how machine learning methods are rapidly being integrated into the field of SLE research. Recent reports have focused on building prediction models and/or identifying novel biomarkers using both supervised and unsupervised techniques for understanding disease pathogenesis, early diagnosis and prognosis of disease. In this review, we will provide an overview of machine learning techniques to discuss current gaps, challenges and opportunities for SLE studies. External validation of most prediction models is still needed before clinical adoption. Utilisation of deep learning models, access to alternative sources of health data and increased awareness of the ethics, governance and regulations surrounding the use of artificial intelligence in medicine will help propel this exciting field forward.

Prediction of the acceptance of telemedicine among rheumatic patients: a machine learning-powered secondary analysis of German survey data

Telemedicine (TM) has augmented healthcare by enabling remote consultations, diagnosis, treatment, and monitoring of patients, thereby improving healthcare access and patient outcomes. However, successful adoption of TM depends on user acceptance, which is influenced by technical, socioeconomic, and health-related factors. Leveraging machine learning (ML) to accurately predict these adoption factors can greatly contribute to the effective utilization of TM in healthcare. The objective of the study was to compare 12 ML algorithms for predicting willingness to use TM (TM try) among patients with rheumatic and musculoskeletal diseases (RMDs) and identify key contributing features. We conducted a secondary analysis of RMD patient data from a German nationwide cross-sectional survey. Twelve ML algorithms, including logistic regression, random forest, extreme gradient boosting (XGBoost), and neural network (deep learning) were tested on a subset of the dataset, with the inclusion of only RMD patients who answered "yes" or "no" to TM try. Nested cross-validation was used for each model. The best-performing model was selected based on area under the receiver operator characteristic (AUROC). For the best-performing model, a multinomial/multiclass ML approach was undertaken with the consideration of the three following classes: "yes", "no", "do not know/not answered". Both one-vs-one and one-vs-rest strategies were considered. The feature importance was investigated using Shapley additive explanation (SHAP). A total of 438 RMD patients were included, with 26.5% of them willing to try TM, 40.6% not willing, and 32.9% undecided (missing answer or "do not know answer"). This dataset was used to train and test ML models. The mean accuracy of the 12 ML models ranged from 0.69 to 0.83, while the mean AUROC ranged from 0.79 to 0.90. The XGBoost model produced better results compared with the other models, with a sensitivity of 70%, specificity of 91% and positive predictive value of 84%. The most important predictors of TM try were the possibility that TM services were offered by a rheumatologist, prior TM knowledge, age, self-reported health status, Internet access at home and type of RMD diseases. For instance, for the yes vs. no classification, not wishing that TM services were offered by a rheumatologist, self-reporting a bad health status and being aged 60-69 years directed the model toward not wanting to try TM. By contrast, having Internet access at home and wishing that TM services were offered by a rheumatologist directed toward TM try. Our findings have significant implications for primary care, in particular for healthcare professionals aiming to implement TM effectively in their clinical routine. By understanding the key factors influencing patients' acceptance of TM, such as their expressed desire for TM services provided by a rheumatologist, self-reported health status, availability of home Internet access, and age, healthcare professionals can tailor their strategies to maximize the adoption and utilization of TM, ultimately improving healthcare outcomes for RMD patients. Our findings are of high interest for both clinical and medical teaching practice to fit changing health needs caused by the growing number of complex and chronically ill patients.

Imbalanced machine learning classification models for removal biosimilar drugs and increased activity in patients with rheumatic diseases

OBJECTIVE

Predict long-term disease worsening and the removal of biosimilar medication in patients with rheumatic diseases.

METHODOLOGY

Observational, retrospective descriptive study. Review of a database of patients with immune-mediated inflammatory rheumatic diseases who switched from a biological drug (biosimilar or non-biosimilar) to a biosimilar drug for at least 6 months. We selected the most important variables, from 18 variables, using mutual information tests. As patients with disease worsening are a minority, it is very difficult to make models with conventional machine learning techniques, where the best models would always be trivial. For this reason, we computed different types of imbalanced machine learning models, choosing those with better f1-score and mean ROC AUC.

RESULTS

We computed the best-imbalanced machine learning models to predict disease worsening and the removal of the biosimilar, with f1-scores of 0.52 and 0.63, respectively. Both models are decision trees. In the first one, two important factors are switching of biosimilar and age, and in the second, the relevant variables are optimization and the value of the initial PCR.

CONCLUSIONS

Biosimilar drugs do not always work well for rheumatic diseases. We obtain two imbalanced machine learning models to detect those cases, where the drug should be removed or where the activity of the disease increases from low to high. In our decision trees appear not previously studied variables, such as age, switching, or optimization.

Artificial intelligence-based preventive, personalized and precision medicine for cardiovascular disease/stroke risk assessment in rheumatoid arthritis patients: a narrative review

The challenges associated with diagnosing and treating cardiovascular disease (CVD)/Stroke in Rheumatoid arthritis (RA) arise from the delayed onset of symptoms. Existing clinical risk scores are inadequate in predicting cardiac events, and conventional risk factors alone do not accurately classify many individuals at risk. Several CVD biomarkers consider the multiple pathways involved in the development of atherosclerosis, which is the primary cause of CVD/Stroke in RA. To enhance the accuracy of CVD/Stroke risk assessment in the RA framework, a proposed approach involves combining genomic-based biomarkers (GBBM) derived from plasma and/or serum samples with innovative non-invasive radiomic-based biomarkers (RBBM), such as measurements of synovial fluid, plaque area, and plaque burden. This review presents two hypotheses: (i) RBBM and GBBM biomarkers exhibit a significant correlation and can precisely detect the severity of CVD/Stroke in RA patients. (ii) Artificial Intelligence (AI)-based preventive, precision, and personalized (aiP3) CVD/Stroke risk AtheroEdge™ model (AtheroPoint™, CA, USA) that utilizes deep learning (DL) to accurately classify the risk of CVD/stroke in RA framework. The authors conducted a comprehensive search using the PRISMA technique, identifying 153 studies that assessed the features/biomarkers of RBBM and GBBM for CVD/Stroke. The study demonstrates how DL models can be integrated into the AtheroEdge™-aiP3 framework to determine the risk of CVD/Stroke in RA patients. The findings of this review suggest that the combination of RBBM with GBBM introduces a new dimension to the assessment of CVD/Stroke risk in the RA framework. Synovial fluid levels that are higher than normal lead to an increase in the plaque burden. Additionally, the review provides recommendations for novel, unbiased, and pruned DL algorithms that can predict CVD/Stroke risk within a RA framework that is preventive, precise, and personalized.

Understanding the role and adoption of artificial intelligence techniques in rheumatology research: An in-depth review of the literature

The major and upward trend in the number of published research related to rheumatic and musculoskeletal diseases, in which artificial intelligence plays a key role, has exhibited the interest of rheumatology researchers in using these techniques to answer their research questions. In this review, we analyse the original research articles that combine both worlds in a five- year period (2017-2021). In contrast to other published papers on the same topic, we first studied the review and recommendation articles that were published during that period, including up to October 2022, as well as the publication trends. Secondly, we review the published research articles and classify them into one of the following categories: disease identification and prediction, disease classification, patient stratification and disease subtype identification, disease progression and activity, treatment response, and predictors of outcomes. Thirdly, we provide a table with illustrative studies in which artificial intelligence techniques have played a central role in more than twenty rheumatic and musculoskeletal diseases. Finally, the findings of the research articles, in terms of disease and/or data science techniques employed, are highlighted in a discussion. Therefore, the present review aims to characterise how researchers are applying data science techniques in the rheumatology medical field. The most immediate conclusions that can be drawn from this work are: multiple and novel data science techniques have been used in a wide range of rheumatic and musculoskeletal diseases including rare diseases; the sample size and the data type used are heterogeneous, and new technical approaches are expected to arrive in the short-middle term.

Quantitative prediction of radiographic progression in patients with axial spondyloarthritis using neural network model in a real-world setting

BACKGROUND

Predicting radiographic progression in axial spondyloarthritis (axSpA) remains limited because of the complex interaction between multiple associated factors and individual variability in real-world settings. Hence, we tested the feasibility of artificial neural network (ANN) models to predict radiographic progression in axSpA.

METHODS

In total, 555 patients with axSpA were split into training and testing datasets at a 3:1 ratio. A generalized linear model (GLM) and ANN models were fitted based on the baseline clinical characteristics and treatment-dependent variables for the modified Stoke Ankylosing Spondylitis Spine Score (mSASSS) of the radiographs at follow-up time points. The mSASSS prediction was evaluated, and explainable machine learning methods were used to provide insights into the model outcome or prediction.

RESULTS

The R² values of the fitted models were in the range of 0.90-0.95 and ANN with an input of mSASSS as the number of each score performed better (root mean squared error (RMSE) = 2.83) than GLM or input of mSASSS as a total score (RMSE = 2.99-3.57). The ANN also effectively captured complex interactions among variables and their contributions to the transition of mSASSS over time in the fitted models. Structural changes constituting the mSASSS scoring systems were the most important contributing factors, and no detectable structural abnormalities at baseline were the most significant factors suppressing mSASSS change.

CONCLUSIONS

Clinical and radiographic data-driven ANN allows precise mSASSS prediction in real-world settings. Correct evaluation and prediction of spinal structural changes could be beneficial for monitoring patients with axSpA and developing a treatment plan.

Machine Learning for Diagnosis of Systemic Lupus Erythematosus: A Systematic Review and Meta-Analysis

Background

Application of machine learning (ML) for identification of systemic lupus erythematosus (SLE) has been recently drawing increasing attention, while there is still lack of evidence-based support.

Methods

Systematic review and meta-analysis are conducted to evaluate its diagnostic accuracy and application prospect. PubMed, Embase, Cochrane Library, and Web of Science libraries are searched, in combination with manual searching and literature retrospection, for studies regarding machine learning for identifying SLE and neuropsychiatric systemic lupus erythematosus (NPSLE). Quality Assessment of Diagnostic Accuracy Studies (QUADA-2) is applied to assess the quality of included studies. Diagnostic accuracy of the SLE model and NPSLE model is assessed using the bivariate fixed-effect model, and the data are pooled. Summary receiver operator characteristic curve (SROC) is plotted, and area under the curve (AUC) is calculated.

Results

Eighteen (18) studies are included, in which ten (10) focused on SLE and eight (8) on NPSLE. The AUC of SLE identification is 0.95, the sensitivity is 0.90, the specificity is 0.89, the PLR is 8.4, the NLR is 0.12, and the DOR is 73. AUC of NPSLE identification is 0.89, the sensitivity is 0.83, the specificity is 0.83, the PLR is 5.0, the NLR is 0.20, and the DOR is 25.

Conclusion

Machine learning presented remarkable performance in identification of SLE and NPSLE. Based on the convenience for inclusion factor collection and non-invasiveness of detection, machine learning is expected to be widely applied in clinical practice to assist medical decision making.

Recent advances in the use of machine learning and artificial intelligence to improve diagnosis, predict flares, and enrich clinical trials in lupus

PURPOSE OF REVIEW

Machine learning is a computational tool that is increasingly used for the analysis of medical data and has provided the promise of more personalized care.

RECENT FINDINGS

The frequency with which machine learning analytics are reported in lupus research is comparable with that of rheumatoid arthritis and cancer, yet the clinical application of these computational tools has yet to be translated into better care. Considerable work has been applied to the development of machine learning models for lupus diagnosis, flare prediction, and classification of disease using histology or other medical images, yet few models have been tested in external datasets and independent centers. Application of machine learning has yet to be reported for lupus clinical trial enrichment and automated identification of eligible patients. Integration of machine learning into lupus clinical care and clinical trials would benefit from collaborative development between clinicians and data scientists.

SUMMARY

Although the application of machine learning to lupus data is at a nascent stage, initial results suggest a promising future.

The development of a web-based app employing machine learning for delirium prevention in long-term care facilities in South Korea

Background

Long-term care facilities (LCFs) in South Korea have limited knowledge of and capability to care for patients with delirium. They also often lack an electronic medical record system. These barriers hinder systematic approaches to delirium monitoring and intervention. Therefore, this study aims to develop a web-based app for delirium prevention in LCFs and analyse its feasibility and usability.

Methods

The app was developed based on the validity of the AI prediction model algorithm. A total of 173 participants were selected from LCFs to participate in a study to determine the predictive risk factors for delerium.

The app was developed in five phases: (1) the identification of risk factors and preventive intervention strategies from a review of evidence-based literature, (2) the iterative design of the app and components of delirium prevention, (3) the development of a delirium prediction algorithm and cloud platform, (4) a pilot test and validation conducted with 33 patients living in a LCF, and (5) an evaluation of the usability and feasibility of the app, completed by nurses (Main users).

Results

A web-based app was developed to predict high risk of delirium and apply preventive interventions accordingly. Moreover, its validity, usability, and feasibility were confirmed after app development. By employing machine learning, the app can predict the degree of delirium risk and issue a warning alarm. Therefore, it can be used to support clinical decision-making, help initiate the assessment of delirium, and assist in applying preventive interventions.

Conclusions

This web-based app is evidence-based and can be easily mobilised to support care for patients with delirium in LCFs. This app can improve the recognition of delirium and predict the degree of delirium risk, thereby helping develop initiatives for delirium prevention and providing interventions. Moreover, this app can be extended to predict various risk factors of LCF and apply preventive interventions. Its use can ultimately improve patient safety and quality of care.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12911-022-01966-8.

Fast machine learning annotation in the medical domain: a semi-automated video annotation tool for gastroenterologists

Background

Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g., visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between.

Methods

In our framework, an expert reviews the video and annotates a few video frames to verify the object’s annotations for the non-expert. In a second step, a non-expert has visual confirmation of the given object and can annotate all following and preceding frames with AI assistance. After the expert has finished, relevant frames will be selected and passed on to an AI model. This information allows the AI model to detect and mark the desired object on all following and preceding frames with an annotation. Therefore, the non-expert can adjust and modify the AI predictions and export the results, which can then be used to train the AI model.

Results

Using this framework, we were able to reduce workload of domain experts on average by a factor of 20 on our data. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated AI model enhances the annotation speed further. Through a prospective study with 10 participants, we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool.

Conclusion

In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.

Machine learning predictive models for acute pancreatitis: A systematic review

INTRODUCTION

Acute pancreatitis (AP) is a common clinical pancreatic disease. Patients with different severity levels have different clinical outcomes. With the advantages of algorithms, machine learning (ML) has gradually emerged in the field of disease prediction, assisting doctors in decision-making.

METHODS

A systematic review was conducted using the PubMed, Web of Science, Scopus, and Embase databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Publication time was limited from inception to 29 May 2021. Studies that have used ML to establish predictive tools for AP were eligible for inclusion. Quality assessment of the included studies was conducted in accordance with the IJMEDI checklist.

RESULTS

In this systematic review, 24 of 2,913 articles, with a total of 8,327 patients and 47 models, were included. The studies could be divided into five categories: 10 studies (42%) reported severity prediction; 10 studies (42%), complication prediction; 3 studies (13%), mortality prediction; 2 studies (8%), recurrence prediction; and 2 studies (8%), surgery timing prediction. ML showed great accuracy in several prediction tasks. However, most of the included studies were retrospective in nature, conducted at a single centre, based on database data, and lacked external validation. According to the IJMEDI checklist and our scoring criteria, two studies were considered to be of high quality. Most studies had an obvious bias in the quality of data preparation, validation, and deployment dimensions.

CONCLUSION

In the prediction tasks for AP, ML has shown great potential in assisting decision-making. However, the existing studies still have some deficiencies in the process of model construction. Future studies need to optimize the deficiencies and further evaluate the comparability of the ML systems and model performance, so as to consequently develop high-quality ML-based models that can be used in clinical practice.

An introduction to machine learning and analysis of its use in rheumatic diseases

Machine learning (ML) is a computerized analytical technique that is being increasingly employed in biomedicine. ML often provides an advantage over explicitly programmed strategies in the analysis of multidimensional information by recognizing relationships in the data that were not previously appreciated. As such, the use of ML in rheumatology is increasing, and numerous studies have employed ML to classify patients with rheumatic autoimmune inflammatory diseases (RAIDs) from medical records and imaging, biometric or gene expression data. However, these studies are limited by sample size, the accuracy of sample labelling, and absence of datasets for external validation. In addition, there is potential for ML models to overfit or underfit the data and, thereby, these models might produce results that cannot be replicated in an unrelated dataset. In this Review, we introduce the basic principles of ML and discuss its current strengths and weaknesses in the classification of patients with RAIDs. Moreover, we highlight the successful analysis of the same type of input data (for example, medical records) with different algorithms, illustrating the potential plasticity of this analytical approach. Altogether, a better understanding of ML and the future application of advanced analytical techniques based on this approach, coupled with the increasing availability of biomedical data, may facilitate the development of meaningful precision medicine for patients with RAIDs.

Complex Machine-Learning Algorithms and Multivariable Logistic Regression on Par in the Prediction of Insufficient Clinical Response to Methotrexate in Rheumatoid Arthritis

The goals of this study were to examine whether machine-learning algorithms outperform multivariable logistic regression in the prediction of insufficient response to methotrexate (MTX); secondly, to examine which features are essential for correct prediction; and finally, to investigate whether the best performing model specifically identifies insufficient responders to MTX (combination) therapy. The prediction of insufficient response (3-month Disease Activity Score 28-Erythrocyte-sedimentation rate (DAS28-ESR) > 3.2) was assessed using logistic regression, least absolute shrinkage and selection operator (LASSO), random forest, and extreme gradient boosting (XGBoost). The baseline features of 355 rheumatoid arthritis (RA) patients from the “treatment in the Rotterdam Early Arthritis CoHort” (tREACH) and the U-Act-Early trial were combined for analyses. The model performances were compared using area under the curve (AUC) of receiver operating characteristic (ROC) curves, 95% confidence intervals (95% CI), and sensitivity and specificity. Finally, the best performing model following feature selection was tested on 101 RA patients starting tocilizumab (TCZ)-monotherapy. Logistic regression (AUC = 0.77 95% CI: 0.68–0.86) performed as well as LASSO (AUC = 0.76, 95% CI: 0.67–0.85), random forest (AUC = 0.71, 95% CI: 0.61 = 0.81), and XGBoost (AUC = 0.70, 95% CI: 0.61–0.81), yet logistic regression reached the highest sensitivity (81%). The most important features were baseline DAS28 (components). For all algorithms, models with six features performed similarly to those with 16. When applied to the TCZ-monotherapy group, logistic regression’s sensitivity significantly dropped from 83% to 69% (p = 0.03). In the current dataset, logistic regression performed equally well compared to machine-learning algorithms in the prediction of insufficient response to MTX. Models could be reduced to six features, which are more conducive for clinical implementation. Interestingly, the prediction model was specific to MTX (combination) therapy response.

Digital health technologies: opportunities and challenges in rheumatology

The past decade in rheumatology has seen tremendous innovation in digital health technologies, including the electronic health record, virtual visits, mobile health, wearable technology, digital therapeutics, artificial intelligence and machine learning. The increased availability of these technologies offers opportunities for improving important aspects of rheumatology, including access, outcomes, adherence and research. However, despite its growth in some areas, particularly with non-health-care consumers, digital health technology has not substantially changed the delivery of rheumatology care. This Review discusses key barriers and opportunities to improve application of digital health technologies in rheumatology. Key topics include smart design, voice enablement and the integration of electronic patient-reported outcomes. Smart design involves active engagement with the end users of the technologies, including patients and clinicians through focus groups, user testing sessions and prototype review. Voice enablement using voice assistants could be critical for enabling patients with hand arthritis to effectively use smartphone apps and might facilitate patient engagement with many technologies. Tracking many rheumatic diseases requires frequent monitoring of patient-reported outcomes. Current practice only collects this information sporadically, and rarely between visits. Digital health technology could enable patient-reported outcomes to inform appropriate timing of face-to-face visits and enable improved application of treat-to-target strategies. However, best practice standards for digital health technologies do not yet exist. To achieve the potential of digital health technology in rheumatology, rheumatology professionals will need to be more engaged upstream in the technology design process and provide leadership to effectively incorporate the new tools into clinical care.

Quantitative Predictive Modelling Approaches to Understanding Rheumatoid Arthritis: A Brief Review

Rheumatoid arthritis is a chronic autoimmune disease that is a major public health challenge. The disease is characterised by inflammation of synovial joints and cartilage erosion, which lead to chronic pain, poor life quality and, in some cases, mortality. Understanding the biological mechanisms behind the progression of the disease, as well as developing new methods for quantitative predictions of disease progression in the presence/absence of various therapies is important for the success of therapeutic approaches. The aim of this study is to review various quantitative predictive modelling approaches for understanding rheumatoid arthritis. To this end, we start by briefly discussing the biology of this disease and some current treatment approaches, as well as emphasising some of the open problems in the field. Then, we review various mathematical mechanistic models derived to address some of these open problems. We discuss models that investigate the biological mechanisms behind the progression of the disease, as well as pharmacokinetic and pharmacodynamic models for various drug therapies. Furthermore, we highlight models aimed at optimising the costs of the treatments while taking into consideration the evolution of the disease and potential complications.

Development of Rheumatoid Arthritis Classification from Electronic Image Sensor Using Ensemble Method

Rheumatoid arthritis (RA) is an autoimmune illness that impacts the musculoskeletal system by causing chronic, inflammatory, and systemic effects. The disease often becomes progressive and reduces physical function, causes suffering, fatigue, and articular damage. Over a long period of time, RA causes harm to the bone and cartilage of the joints, weakens the joints' muscles and tendons, eventually causing joint destruction. Sensors such as accelerometer, wearable sensors, and thermal infrared camera sensor are widely used to gather data for RA. In this paper, the classification of medical disorders based on RA and orthopaedics datasets using Ensemble methods are discussed. The RA dataset was gathered from the analysis of white blood cell classification using features extracted from the image of lymphocytes acquired from a digital microscope with an electronic image sensor. The orthopaedic dataset is a benchmark dataset for this study, as it posed a similar classification problem with several numerical features. Three ensemble algorithms such as bagging, Adaboost, and random subspace were used in the study. These ensemble classifiers use k-NN (K-nearest neighbours) and Random forest (RF) as the base learners of the ensemble classifiers. The data classification is accessed using holdout and 10-fold cross-validation evaluation methods. The assessment was based on set of performance measures such as precision, recall, F-measure, and receiver operating characteristic (ROC) curve. The performance was also measured based on the comparison of the overall classification accuracy rate between different ensembles classifiers and the base learners. Overall, it was found that for Dataset 1, random subspace classifier with k-NN shows the best results in terms of overall accuracy rate of 97.50% and for Dataset 2, bagging-RF shows the highest overall accuracy rate of 94.84% over different ensemble classifiers. The findings indicate that the efficiency of the base classifiers with ensemble classifier have substantially improved.

Machine learning-based prediction of radiographic progression in patients with axial spondyloarthritis

INTRODUCTION

Machine learning is applied to characterize the risk and predict outcomes in multi-dimensional data. The prediction of radiographic progression in axial spondyloarthritis (axSpA) remains limited. Hence, we tested the feasibility of supervised machine learning algorithms to predict radiographic progression in axSpA.

METHODS

This is a retrospective and hospital-based study. Clinical and laboratory data obtained from two independent axSpA groups were used as training and testing datasets. Radiographic progression over 2 years was assessed using the modified Stoke Ankylosing Spondylitis Spine Score (mSASSS) and mSASSS worsening by ≥ two units was defined as progression. Seven machine learning models with different algorithms were fitted, and their performance for the testing dataset was assessed using receiver-operating characteristic (ROC) and precision-recall (PR) curve.

RESULTS

The training and testing groups had equivalent characteristics, and radiographic progression was identified in 25.3% and 23.7%, respectively. The generalized linear model (GLM) and support vector machine (SVM) were the top two best-performing models with an average area-under-curve (AUC) of ROC of over 0.78. SVM had the higher AUC of PR compared with GLM (0.56 versus 0.51). Balanced accuracy was over 65% in all models. mSASSS was the most informative variable, followed by the presence of syndesmophyte(s) at the baseline and sacroiliac joint grades.

CONCLUSIONS

Clinical and radiographic data-driven predictive models showed reasonable performance in the prediction of radiographic progression in axSpA. Further modelling with larger and more detailed data could provide an excellent opportunity for the clinical translation of the predictive models to the management of high-risk patients.Key Points• Clinical and radiographic data-driven predictive models showed reasonable performance in the prediction of radiographic progression in axSpA.• Further modelling with larger and more detailed data could provide an excellent opportunity for the clinical translation of the predictive models to the management of high-risk patients.