Incorporating natural language processing to improve classification of axial spondyloarthritis using electronic health records

Extracting patient lifestyle characteristics from Dutch clinical text with BERT models

BACKGROUND

BERT models have seen widespread use on unstructured text within the clinical domain. However, little to no research has been conducted into classifying unstructured clinical notes on the basis of patient lifestyle indicators, especially in Dutch. This article aims to test the feasibility of deep BERT models on the task of patient lifestyle classification, as well as introducing an experimental framework that is easily reproducible in future research.

METHODS

This study makes use of unstructured general patient text data from HagaZiekenhuis, a large hospital in The Netherlands. Over 148 000 notes were provided to us, which were each automatically labelled on the basis of the respective patients' smoking, alcohol usage and drug usage statuses. In this paper we test feasibility of automatically assigning labels, and justify it using hand-labelled input. Ultimately, we compare macro F1-scores of string matching, SGD and several BERT models on the task of classifying smoking, alcohol and drug usage. We test Dutch BERT models and English models with translated input.

RESULTS

We find that our further pre-trained MedRoBERTa.nl-HAGA model outperformed every other model on smoking (0.93) and drug usage (0.77). Interestingly, our ClinicalBERT model that was merely fine-tuned on translated text performed best on the alcohol task (0.80). In t-SNE visualisations, we show our MedRoBERTa.nl-HAGA model is the best model to differentiate between classes in the embedding space, explaining its superior classification performance.

CONCLUSIONS

We suggest MedRoBERTa.nl-HAGA to be used as a baseline in future research on Dutch free text patient lifestyle classification. We furthermore strongly suggest further exploring the application of translation to input text in non-English clinical BERT research, as we only translated a subset of the full set and yet achieved very promising results.

The association of TNF inhibitor use with incident cardiovascular events in radiographic axial spondyloarthritis

BACKGROUND

Whether tumor necrosis factor inhibitor (TNFi) use is cardioprotective among individuals with radiographic axial spondyloarthritis (r-axSpA), who have heightened cardiovascular (CV) risk, is unclear. We tested the association of TNFi use with incident CV outcomes in r-axSpA.

METHODS

We identified a r-axSpA cohort within a Veterans Affairs database between 2002 and 2019 using novel phenotyping methods and secondarily using ICD codes. TNFi use was assessed as a time-varying exposure using pharmacy dispense records. The primary outcome was incident CV disease identified using ICD codes for coronary artery disease, myocardial infarction or stroke. We fit Cox models with inverse probability weights to estimate the risk of each outcome with TNFi use versus non-use. Analyses were performed in the overall cohort, and separately in two periods (2002-2010, 2011-2019) to account for secular trends.

RESULTS

Using phenotyping we identified 26,928 individuals with an r-axSpA diagnosis (mean age 63.4 years, 94 % male); at baseline 3633 were TNFi users and 23,295 were non-users. During follow-up of a mean 3.3 ± 4.2 years, 674 (18.6 %) TNFi users had incident CVD versus 11,838 (50.8 %) non-users. In adjusted analyses, TNFi use versus non-use was associated with lower risk of incident CVD (HR 0.34, 95 % CI 0.29-0.40) in the cohort overall, and in the two time periods separately.

CONCLUSION

In this r-axSpA cohort identified using phenotyping methods, TNFi use versus non-use had a lower risk of incident CVD. These findings provide reassurance regarding the CV safety of TNFi agents for r-axSpA treatment. Replication of these results in other cohorts is needed.

Natural language processing to identify and characterize spondyloarthritis in clinical practice

OBJECTIVE

This study aims to use a novel technology based on natural language processing (NLP) to extract clinical information from electronic health records (EHRs) to characterise the clinical profile of patients diagnosed with spondyloarthritis (SpA) at a large-scale hospital.

METHODS

An observational, retrospective analysis was conducted on EHR data from all patients with SpA (including psoriatic arthritis (PsA)) at Hospital Universitario La Paz, between 2020 and 2022. Data were collected using Savana Manager, an NLP-based system, enabling the extraction of information from unstructured, free-text EHRs. Variables analysed included demographic data, SpA subtypes, comorbidities and treatments. The performance of the technology in detecting SpA clinical entities was evaluated through precision, recall and F-1 score metrics.

RESULTS

From a hospital population of 639 474 patients, 4337 (0.7%) patients had a diagnosis of SpA or their subtypes in their EHR. The population predominantly comprised men (55.3%) with a mean age of 50.9 years. Peripheral SpA (including PsA) was reported in 31.6%, axial SpA in 20.9%, both axial and peripheral SpA in 3.7%, while 43.7% of patients did not have the SpA subtype reported. Common comorbidities included hypertension (25.0%), dyslipidaemia (22.2%) and diabetes mellitus (15.5%). The use of conventional disease-modifying antirheumatic drugs (csDMARDs) and biological DMARDs (bDMARDs) was documented, with methotrexate (25.3% of patients) being the most used csDMARDs and adalimumab (10.6% of patients) the most used bDMARD. The NLP technology demonstrated high precision and recall, with all the assessed F-1 score values over 0.80, indicating reliable data extraction.

CONCLUSION

The application of NLP technology facilitated the characterisation of the SpA patient profile, including demographics, clinical features, comorbidities and treatments. This study supports the utility of NLP in enhancing the understanding of SpA and suggests its potential for improving patient management by extracting meaningful information from unstructured EHR data.

A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence

The digitization of medical records and expanding electronic health records has created an era of "Big Data" with an abundance of available information ranging from clinical notes to imaging studies. In the field of rheumatology, medical imaging is used to guide both diagnosis and treatment of a wide variety of rheumatic conditions. Although there is an abundance of data to analyze, traditional methods of image analysis are human resource intensive. Fortunately, the growth of artificial intelligence (AI) may be a solution to handle large datasets. In particular, computer vision is a field within AI that analyzes images and extracts information. Computer vision has impressive capabilities and can be applied to rheumatologic conditions, necessitating a need to understand how computer vision works. In this article, we provide an overview of AI in rheumatology and conclude with a five step process to plan and conduct research in the field of computer vision. The five steps include (1) project definition, (2) data handling, (3) model development, (4) performance evaluation, and (5) deployment into clinical care.

Barriers and facilitators in diagnosing axial spondyloarthritis: a qualitative study

INTRODUCTION

Diagnosis of axial spondyloarthritis (axSpA) is frequently delayed for years after symptom onset. However, little is known about patient and healthcare professional (HCP) perspectives on barriers and facilitators in axSpA diagnosis. This study explored the experiences and perceptions of both groups regarding the factors affecting the timely diagnosis of axSpA.

METHOD

Semi-structured interviews with patients with axSpA and axSpA-interested HCPs from the United Kingdom (UK) were performed by telephone or Microsoft Teams and focussed on the individuals' perspective of the diagnostic journey for axSpA. Interview transcripts were thematically analysed.

RESULTS

Fourteen patients with axSpA (10 female, 4 male) and 14 UK based HCPs were recruited, the latter comprising of 5 physiotherapists, 4 General Practitioners, 3 rheumatologists, a nurse, and an occupational therapist. Barriers to diagnosis identified by patients and HCPs were: difficult to diagnose, a lack of awareness, unclear referral pathways, patient behaviour and patient/HCP communication. Patient-identified facilitators of diagnosis were patient advocacy, clear referral processes and pathways, increased awareness, and serendipity. HCPs identified promoting awareness as a facilitator of diagnosis, along with symptom recognition, improvements to healthcare practice and patient/HCP communications.

CONCLUSION

Poor communication and a lack of understanding of axSpA in the professional and public spheres undermine progress towards timely diagnosis of axSpA. Improving communication and awareness for patients and HCPs, along with systemic changes in healthcare (such as improved referral pathways) could reduce diagnostic delay.

Radiographic and non-radiographic axial spondyloarthritis are not routinely distinguished in everyday clinical care: an analysis of real-world data from rheumatology practices

The categorization of axial spondyloarthritis (axSpA) into radiographic (r-axSpA) and non-radiographic (nr-axSpA) subtypes is important in clinical trials but may be of less value in clinical practice. This exploratory cross-sectional, multi-center study evaluated patients with axSpA under routine care at German clinical rheumatology sites (RHADAR real-world database), with a focus on imaging data used for diagnostic classifications. Our analyses included 371 patients with axSpA. The mean (standard deviation [SD]) age was 50.9 (14.0) years, disease duration was 16.4 (13.5) years, and 39.6% were female. Based on the rheumatologist's final assessment, almost half of patients had definite r-axSpA (n = 179; 48.2%), 53 (14.3%) had suspected r-axSpA, 112 (30.2%) had non-radiographic-axSpA (nr-axSpA), and 27 (7.3%) had undefined axSpA. Patients assessed with definite or suspected r-axSpA were more likely to be treated with disease-modifying antirheumatic drugs (DMARDs) (62.0% and 64.2%, respectively) compared with nr-axSpA or undefined axSpA patients (37.5% and 48.1%, respectively). Almost all patients (348/371; 93.8%) had sacroiliac joint imaging data (radiographs or magnetic resonance imaging) documented in their charts, but only 216 (58.2%) had conventional radiographs required for formal diagnosis of r-axSpA by modified New York criteria. Follow-up radiographic imaging in nr-axSpA patients was uncommon (23/216 [25.0%]) but confirmed r-axSpA in 9/23 patients (39.1%). In conclusion, radiographs were available for slightly more than half of axSpA patients. Follow-up imaging was infrequent during rheumatology care in Germany but confirmed r-axSpA in ~ 40% of patients originally considered to have nr-axSpA. The distinction between r-axSpA and nr-axSpA may be ill-defined in routine clinical practice.

Entry point of machine learning in axial spondyloarthritis

Axial spondyloarthritis (axSpA) is a globally prevalent and challenging autoimmune disease. Characterised by insidious onset and slow progression, the absence of specific clinical manifestations and biomarkers often leads to misdiagnosis, thereby complicating early detection and diagnosis of axSpA. Furthermore, the high heterogeneity of axSpA, its complex pathogenesis and the lack of specific drugs means that traditional classification standards and treatment guidelines struggle to meet the demands of personalised treatment. Recently, machine learning (ML) has seen rapid advancements in the medical field. By integrating large-scale data with diverse algorithms and using multidimensional data, such as patient medical records, laboratory examinations, radiological data, drug usage and molecular biology information, ML can be modelled based on real-world clinical issues. This enables the diagnosis, stratification, therapeutic efficacy prediction and prognostic evaluation of axSpA, positioning it as an emerging research topic. This study explored the application and progression of ML in the diagnosis and therapy of axSpA from five perspectives: early diagnosis, stratification, disease monitoring, drug efficacy evaluation and comorbidity prediction. This study aimed to provide a novel direction for exploring rational diagnostic and therapeutic strategies for axSpA.

Improving the accuracy of automated gout flare ascertainment using natural language processing of electronic health records and linked Medicare claims data

BACKGROUND

We aimed to determine whether integrating concepts from the notes from the electronic health record (EHR) data using natural language processing (NLP) could improve the identification of gout flares.

METHODS

Using Medicare claims linked with EHR, we selected gout patients who initiated the urate-lowering therapy (ULT). Patients' 12-month baseline period and on-treatment follow-up were segmented into 1-month units. We retrieved EHR notes for months with gout diagnosis codes and processed notes for NLP concepts. We selected a random sample of 500 patients and reviewed each of their notes for the presence of a physician-documented gout flare. Months containing at least 1 note mentioning gout flares were considered months with events. We used 60% of patients to train predictive models with LASSO. We evaluated the models by the area under the curve (AUC) in the validation data and examined positive/negative predictive values (P/NPV).

RESULTS

We extracted and labeled 839 months of follow-up (280 with gout flares). The claims-only model selected 20 variables (AUC = 0.69). The NLP concept-only model selected 15 (AUC = 0.69). The combined model selected 32 claims variables and 13 NLP concepts (AUC = 0.73). The claims-only model had a PPV of 0.64 [0.50, 0.77] and an NPV of 0.71 [0.65, 0.76], whereas the combined model had a PPV of 0.76 [0.61, 0.88] and an NPV of 0.71 [0.65, 0.76].

CONCLUSION

Adding NLP concept variables to claims variables resulted in a small improvement in the identification of gout flares. Our data-driven claims-only model and our combined claims/NLP-concept model outperformed existing rule-based claims algorithms reliant on medication use, diagnosis, and procedure codes.

Using natural language processing to explore characteristics and management of patients with axial spondyloarthritis and psoriatic arthritis treated under real-world conditions in Spain: SpAINET study

Background

Spondyloarthritis (SpA) is a group of related but phenotypically distinct inflammatory disorders that include axial SpA (axSpA) and psoriatic arthritis (PsA). Information on the characteristics and management of these patients in the real world remains scarce.

Objectives

To explore the characteristics and management [disease activity assessment and treatment with secukinumab (SEC) or other biologic disease-modifying antirheumatic drugs (bDMARDs)] of axSpA and PsA patients using natural language processing (NLP) in Electronic Health Records (EHRs).

Design

National, multicenter, observational, and retrospective study.

Methods

We analyzed free-text and structured clinical information from EHR at three hospitals. All adult patients with axSpA, PsA or non-classified SpA from 2018 to 2021 with minimum follow-up of three months were included when starting SEC or other bDMARDs. Clinical variables were extracted using EHRead® technology based on Systemized Nomenclature of Medicine-Clinical Terms (SNOMED CT) terminology.

Results

Out of 887,735 patients, 758 were included, of which 328 had axSpA [58.5% male; mean (SD) age of 50.7 (12.7) years], 365 PsA [54.8% female, 53.9 (12.4) years], and 65 non-classified SpA. Mean (SD) time since diagnosis was 36.8 (61.0) and 24.1 (35.2) months for axSpA and PsA, respectively. Only 116 axSpA patients (35.3%) had available Ankylosing Spondylitis Disease Activity Score (ASDAS) or Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) at bDMARD onset, of which 61 presented active disease. Disease Activity in PSoriatic Arthritis (DAPSA) or Disease Assessment Score - 28 joints (DAS-28) values at bDMARD onset were available for only 61 PsA (16.7%) patients, with 23 of them having active disease. The number of patients with available tender joint count or swollen joint count assessment was 68 (20.7%) and 59 (18%) for axSpA, and 115 (31.5%) and 119 (32.6%) for PsA, respectively. SEC was used in 63 (19.2%) axSpA patients and in 63 (17.3%) PsA patients.

Conclusion

Using NLP, the study showed that around one-third of axSpA and one-sixth of PsA patients have disease activity assessments with ASDAS/BASDAI or DAPSA/DAS-28, respectively, highlighting an area of improvement in these patients' management.

Machine Learning Pipeline for Predicting Bone Marrow Edema Along the Sacroiliac Joints on Magnetic Resonance Imaging

OBJECTIVE

We aimed to develop and validate a fully automated machine learning (ML) algorithm that predicts bone marrow edema (BME) on a quadrant level in sacroiliac (SI) joint magnetic resonance imaging (MRI).

METHODS

A computer vision workflow automatically locates the SI joints, segments regions of interest (ilium and sacrum), performs objective quadrant extraction, and predicts presence of BME, suggestive of inflammatory lesions, on a quadrant level in semicoronal slices of T1/T2-weighted MRI scans. Ground truth was determined by consensus among human readers. The inflammation classifier was trained using a ResNet18 backbone and five-fold cross-validated on scans of patients with spondyloarthritis (SpA) (n = 279), postpartum individuals (n = 71), and healthy subjects (n = 114). Independent SpA patient MRI scans (n = 243) served as test data set. Patient-level predictions were derived from aggregating quadrant-level predictions, ie, at least one positive quadrant.

RESULTS

The algorithm automatically detects the SI joints with a precision of 98.4% and segments ilium/sacrum with an intersection over union of 85.6% and 67.9%, respectively. The inflammation classifier performed well in cross-validation: area under the curve (AUC) 94.5%, balanced accuracy (B-ACC) 80.5%, and F1 score 64.1%. In the test data set, AUC was 88.2%, B-ACC 72.1%, and F1 score 50.8%. On a patient level, the model achieved a B-ACC of 81.6% and 81.4% in the cross-validation and test data set, respectively.

CONCLUSION

We propose a fully automated ML pipeline that enables objective and standardized evaluation of BME along the SI joints on MRI. This method has the potential to screen large numbers of patients with (suspected) SpA and is a step closer towards artificial intelligence-assisted diagnosis and follow-up.

Diagnostic delay in axial spondylarthritis: A lost battle?

Diagnostic delay in axial spondylarthritis (axSpA) remains an unacceptable worldwide problem; with evidence suggesting significant detrimental impact both clinically on the individual, and economically on society. There is therefore, a need for global action across various healthcare professions that come into contact with patients living, and suffering, with undiagnosed axSpA. Recent estimates of the median diagnostic delay suggest that globally, individuals with axSpA wait between 2 and 6 years for a diagnosis - revealing a clear benchmark for improvement. This timespan presents a window of opportunity for earlier diagnosis and intervention, which will likely improve patient outcomes. This review describes the current diagnostic delay as estimated across countries and over time, before presenting evidence from published strategies that may be implemented to improve this delay across primary and secondary care, including for specialties treating extra-musculoskeletal manifestations of axSpA (ophthalmology, gastroenterology, dermatology). Ongoing campaigns tackling delayed diagnosis in axSpA are also highlighted.

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.

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives

Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. Data-driven artificial intelligence (AI) methods can be employed for research on automatic pain assessment (APA). The goal is the development of objective, standardized, and generalizable instruments useful for pain assessment in different clinical contexts. The purpose of this article is to discuss the state of the art of research and perspectives on APA applications in both research and clinical scenarios. Principles of AI functioning will be addressed. For narrative purposes, AI-based methods are grouped into behavioral-based approaches and neurophysiology-based pain detection methods. Since pain is generally accompanied by spontaneous facial behaviors, several approaches for APA are based on image classification and feature extraction. Language features through natural language strategies, body postures, and respiratory-derived elements are other investigated behavioral-based approaches. Neurophysiology-based pain detection is obtained through electroencephalography, electromyography, electrodermal activity, and other biosignals. Recent approaches involve multimode strategies by combining behaviors with neurophysiological findings. Concerning methods, early studies were conducted by machine learning algorithms such as support vector machine, decision tree, and random forest classifiers. More recently, artificial neural networks such as convolutional and recurrent neural network algorithms are implemented, even in combination. Collaboration programs involving clinicians and computer scientists must be aimed at structuring and processing robust datasets that can be used in various settings, from acute to different chronic pain conditions. Finally, it is crucial to apply the concepts of explainability and ethics when examining AI applications for pain research and management.

Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review

BACKGROUND

Natural Language Processing (NLP) is widely used to extract clinical insights from Electronic Health Records (EHRs). However, the lack of annotated data, automated tools, and other challenges hinder the full utilisation of NLP for EHRs. Various Machine Learning (ML), Deep Learning (DL) and NLP techniques are studied and compared to understand the limitations and opportunities in this space comprehensively.

METHODOLOGY

After screening 261 articles from 11 databases, we included 127 papers for full-text review covering seven categories of articles: (1) medical note classification, (2) clinical entity recognition, (3) text summarisation, (4) deep learning (DL) and transfer learning architecture, (5) information extraction, (6) Medical language translation and (7) other NLP applications. This study follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines.

RESULT AND DISCUSSION

EHR was the most commonly used data type among the selected articles, and the datasets were primarily unstructured. Various ML and DL methods were used, with prediction or classification being the most common application of ML or DL. The most common use cases were: the International Classification of Diseases, Ninth Revision (ICD-9) classification, clinical note analysis, and named entity recognition (NER) for clinical descriptions and research on psychiatric disorders.

CONCLUSION

We find that the adopted ML models were not adequately assessed. In addition, the data imbalance problem is quite important, yet we must find techniques to address this underlining problem. Future studies should address key limitations in studies, primarily identifying Lupus Nephritis, Suicide Attempts, perinatal self-harmed and ICD-9 classification.

Development of a Natural Language Processing System for Extracting Rheumatoid Arthritis Outcomes From Clinical Notes Using the National Rheumatology Informatics System for Effectiveness Registry

OBJECTIVE

To accelerate the use of outcome measures in rheumatology, we developed and evaluated a natural language processing (NLP) pipeline for extracting these measures from free-text outpatient rheumatology notes within the American College of Rheumatology's Rheumatology Informatics System for Effectiveness (RISE) registry.

METHODS

We included all patients in RISE (2015-2018). The NLP pipeline extracted scores corresponding to 8 measures of rheumatoid arthritis (RA) disease activity (DA) and functional status (FS) documented in outpatient rheumatology notes. Score extraction performance was evaluated by chart review, and we assessed agreement with scores documented in structured data. We conducted an external validation of our NLP pipeline using data from rheumatology notes from an academic medical center that is not included in the RISE registry.

RESULTS

We processed over 34 million notes from 854,628 patients, 158 practices, and 24 electronic health record (EHR) systems from RISE. Manual chart review revealed a sensitivity, positive predictive value (PPV), and F1 score of 95%, 87%, and 91%, respectively. Substantial agreement was observed between scores extracted from RISE notes and scores derived from structured data (κ = 0.43-0.68 among DA and 0.86-0.98 among FS measures). In the external validation, we found a sensitivity, PPV, and F1 score of 92%, 69%, and 79%, respectively.

CONCLUSION

We developed an NLP pipeline to extract RA outcome measures from a national registry of notes from multiple EHR systems and found it to have good internal and external validity. This pipeline can facilitate measurement of clinical- and patient-reported outcomes for use in research and quality measurement.

Natural Language Processing to Improve Prediction of Incident Atrial Fibrillation Using Electronic Health Records

Background Models predicting atrial fibrillation (AF) risk, such as Cohorts for Heart and Aging Research in Genomic Epidemiology AF (CHARGE-AF), have not performed as well in electronic health records. Natural language processing (NLP) may improve models by using narrative electronic health record text. Methods and Results From a primary care network, we included patients aged ≥65 years with visits between 2003 and 2013 in development (n=32 960) and internal validation cohorts (n=13 992). An external validation cohort from a separate network from 2015 to 2020 included 39 051 patients. Model features were defined using electronic health record codified data and narrative data with NLP. We developed 2 models to predict 5-year AF incidence using (1) codified+NLP data and (2) codified data only and evaluated model performance. The analysis included 2839 incident AF cases in the development cohort and 1057 and 2226 cases in internal and external validation cohorts, respectively. The C-statistic was greater (P<0.001) in codified+NLP model (0.744 [95% CI, 0.735-0.753]) compared with codified-only (0.730 [95% CI, 0.720-0.739]) in the development cohort. In internal validation, the C-statistic of codified+NLP was modestly higher (0.735 [95% CI, 0.720-0.749]) compared with codified-only (0.729 [95% CI, 0.715-0.744]; P=0.06) and CHARGE-AF (0.717 [95% CI, 0.703-0.731]; P=0.002). Codified+NLP and codified-only were well calibrated, whereas CHARGE-AF underestimated AF risk. In external validation, the C-statistic of codified+NLP (0.750 [95% CI, 0.740-0.760]) remained higher (P<0.001) than codified-only (0.738 [95% CI, 0.727-0.748]) and CHARGE-AF (0.735 [95% CI, 0.725-0.746]). Conclusions Estimation of 5-year risk of AF can be modestly improved using NLP to incorporate narrative electronic health record data.

Natural language processing in low back pain and spine diseases: A systematic review

Natural Language Processing (NLP) is a discipline at the intersection between Computer Science (CS), Artificial Intelligence (AI), and Linguistics that leverages unstructured human-interpretable (natural) language text. In recent years, it gained momentum also in health-related applications and research. Although preliminary, studies concerning Low Back Pain (LBP) and other related spine disorders with relevant applications of NLP methodologies have been reported in the literature over the last few years. It motivated us to systematically review the literature comprised of two major public databases, PubMed and Scopus. To do so, we first formulated our research question following the PICO guidelines. Then, we followed a PRISMA-like protocol by performing a search query including terminologies of both technical (e.g., natural language and computational linguistics) and clinical (e.g., lumbar and spine surgery) domains. We collected 221 non-duplicated studies, 16 of which were eligible for our analysis. In this work, we present these studies divided into sub-categories, from both tasks and exploited models’ points of view. Furthermore, we report a detailed description of techniques used to extract and process textual features and the several evaluation metrics used to assess the performance of the NLP models. However, what is clear from our analysis is that additional studies on larger datasets are needed to better define the role of NLP in the care of patients with spinal disorders.

Radiomic Quantification for MRI Assessment of Sacroiliac Joints of Patients with Spondyloarthritis

Spondyloarthritis (SpA) is a group of diseases primarily involving chronic inflammation of the spine and peripheral joints, as evaluated by magnetic resonance imaging (MRI). Considering the complexity of SpA, we performed a retrospective study to discover quantitative/radiomic MRI-based features correlated with SpA. We also investigated different fat-suppression MRI techniques to develop detection models for inflammatory sacroiliitis. Finally, these model results were compared with those of experienced musculoskeletal radiologists, and the concordance level was evaluated. Examinations of 46 consecutive patients were obtained using SPAIR (spectral attenuated inversion recovery) and STIR (short tau inversion recovery) MRI sequences. Musculoskeletal radiologists manually segmented the sacroiliac joints for further extraction of 230 MRI features from gray-level histogram/matrices and wavelet filters. These features were associated with sacroiliitis, SpA, and the current biomarkers of ESR (erythrocyte sedimentation rate), CRP (C-reactive protein), BASDAI (Bath Ankylosing Spondylitis Activity Index), BASFI (Bath Ankylosing Spondylitis Functional Index), and MASES (Maastricht Ankylosing Spondylitis Enthesis Score). The Mann-Whitney U test showed that the radiomic markers from both MRI sequences were associated with active sacroiliitis and with SpA and its axial and peripheral subtypes (p < 0.05). Spearman's coefficient also identified a correlation between MRI markers and data from clinical practice (p < 0.05). Fat-suppression MRI models yielded performances that were statistically equivalent to those of specialists and presented strong concordance in identifying inflammatory sacroiliitis. SPAIR and STIR acquisition protocols showed potential for the evaluation of sacroiliac joints and the composition of a radiomic model to support the clinical assessment of SpA.

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.

[Artificial intelligence-supported treatment in rheumatology : Principles, current situation and perspectives]

Computer-guided clinical decision support systems have been finding their way into practice for some time, mostly integrated into electronic medical records. The primary goals are to improve the quality of treatment, save time and avoid errors. These are mostly rule-based algorithms that recognize drug interactions or provide reminder functions. Through artificial intelligence (AI), clinical decision support systems can be disruptively further developed. New knowledge is constantly being created from data through machine learning in order to predict the individual course of a patient's disease, identify phenotypes or support treatment decisions. Such algorithms already exist for rheumatological diseases. Automated image recognition and disease prediction in rheumatoid arthritis are the most advanced; however, these have not yet been sufficiently tested or integrated into existing decision support systems. Rather than dictating the AI-assisted choice of treatment to the doctor, future clinical decision systems are seen as hybrid decision support, always involving both the expert and the patient. There is also a great need for security through comprehensible and auditable algorithms to sustainably guarantee the quality and transparency of AI-assisted treatment recommendations in the long term.

Identifying Patients With Axial Spondyloarthritis in Large Datasets: Expanding Possibilities for Observational Research

OBJECTIVE

Observational research of axial spondyloarthritis (axSpA) is limited by a lack of methods for identifying diverse axSpA phenotypes in large datasets. Algorithms were previously designed to identify a broad spectrum of patients with axSpA, including patients not identifiable with diagnosis codes. The study objective was to estimate the performance of axSpA identification methods in the general Veterans Affairs (VA) population.

METHODS

A patient sample with known axSpA status (n = 300) was established with chart review. For feasibility, this sample was enriched with veterans with axSpA risk factors. Algorithm performance outcomes included sensitivities, positive predictive values (PPV), and F1 scores (an overall performance metric combining sensitivity and PPV). Performance was estimated with unweighted outcomes for the axSpA-enriched sample and inverse probability weighted (IPW) outcomes for the general VA population. These outcomes were also assessed for traditional identification methods using diagnosis codes for the ankylosing spondylitis (AS) subtype of axSpA.

RESULTS

The mean age was 54.7 and 92% were male. Unweighted F1 scores (0.59-0.74) were higher than IPW F1 scores (0.48-0.65). The full algorithm had the best overall performance (F1_IPW 0.65). The Early Algorithm was the most inclusive (sensitivity_IPW 0.90, PPV_IPW 0.38). The traditional method using ≥ 2 AS diagnosis codes from rheumatology had the highest PPV (PPV_IPW 0.84, sensitivity_IPW 0.34).

CONCLUSION

The axSpA identification methods demonstrated a range of performance attributes in the general VA population that may be appropriate for various types of studies. The novel identification algorithms may expand the scope of research by enabling identification of more diverse axSpA populations.