1
|
Muizelaar H, Haas M, van Dortmont K, van der Putten P, Spruit M. Extracting patient lifestyle characteristics from Dutch clinical text with BERT models. BMC Med Inform Decis Mak 2024; 24:151. [PMID: 38831420 PMCID: PMC11149227 DOI: 10.1186/s12911-024-02557-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/03/2024] [Accepted: 05/28/2024] [Indexed: 06/05/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Hielke Muizelaar
- LIACS, Leiden University, P.O. Box 9512, Leiden, 2300RA, The Netherlands.
- Department of Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, Leiden, 2333ZA, The Netherlands.
| | - Marcel Haas
- Department of Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, Leiden, 2333ZA, The Netherlands
| | - Koert van Dortmont
- Department of Business Intelligence, HagaZiekenhuis, Els Borst-Eilersplein 275, Den Haag, 2545AA, The Netherlands
| | | | - Marco Spruit
- LIACS, Leiden University, P.O. Box 9512, Leiden, 2300RA, The Netherlands
- Department of Public Health and Primary Care, Leiden University Medical Center, Albinusdreef 2, Leiden, 2333ZA, The Netherlands
| |
Collapse
|
2
|
Liew JW, Treu T, Park Y, Ferguson JM, Rosser MA, Ho YL, Gagnon DR, Stovall R, Monach P, Heckbert SR, Gensler LS, Liao KP, Dubreuil M. The association of TNF inhibitor use with incident cardiovascular events in radiographic axial spondyloarthritis. Semin Arthritis Rheum 2024; 68:152482. [PMID: 38865875 DOI: 10.1016/j.semarthrit.2024.152482] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/26/2024] [Revised: 04/02/2024] [Accepted: 05/20/2024] [Indexed: 06/14/2024]
Abstract
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.
Collapse
Affiliation(s)
- Jean W Liew
- Section of Rheumatology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA.
| | - Timothy Treu
- Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, USA
| | - Yojin Park
- Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, USA
| | - Jacqueline M Ferguson
- Center for Innovation to Implementation, Veterans Affairs Palo Alto Health Care System, Menlo Park, CA, USA
| | - Morgan A Rosser
- Duke University, Department of Anesthesiology, Durham, NC, USA
| | - Yuk-Lam Ho
- Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, USA
| | - David R Gagnon
- Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, MA, USA; Department of Biostatistics, Boston University School of Public Health, Boston, MA, USA
| | - Rachael Stovall
- Division of Rheumatology, University of Washington, Seattle, WA, USA
| | - Paul Monach
- Rheumatology Section, VA Boston Healthcare System, Boston, MA, USA
| | - Susan R Heckbert
- Department of Epidemiology, University of Washington, Seattle, WA, USA
| | - Lianne S Gensler
- Division of Rheumatology, Department of Medicine, University of California San Francisco, San Francisco, CA, USA
| | - Katherine P Liao
- Brigham and Women's Hospital, Boston, MA, USA; Harvard Medical School, Boston, MA, USA, VA Boston Healthcare System, Boston, MA, USA; Section of Rheumatology, VA Boston Healthcare System; Division of Rheumatology, Inflammation, and Immunity, Brigham and Women's Hospital, Boston, MA, USA
| | - Maureen Dubreuil
- Section of Rheumatology, Boston University Chobanian & Avedisian School of Medicine, VA Boston Healthcare System, Boston, MA, USA
| |
Collapse
|
3
|
Benavent D, Benavent-Núñez M, Marin-Corral J, Arias-Manjón J, Navarro-Compán V, Taberna M, Salcedo I, Peiteado D, Carmona L, de Miguel E. Natural language processing to identify and characterize spondyloarthritis in clinical practice. RMD Open 2024; 10:e004302. [PMID: 38796183 PMCID: PMC11129039 DOI: 10.1136/rmdopen-2024-004302] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/05/2024] [Accepted: 05/07/2024] [Indexed: 05/28/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Diego Benavent
- Savana Research S.L, Madrid, Spain
- Rheumatology, Hospital Universitari de Bellvitge, L'Hospitalet de Llobregat, Spain
| | - María Benavent-Núñez
- Savana Research S.L, Madrid, Spain
- Nutrition Department, CEU San Pablo Monteprincipe School, Madrid, Spain
| | | | | | | | | | | | - Diana Peiteado
- Rheumatology, Hospital Universitario La Paz, Madrid, Spain
| | | | | |
Collapse
|
4
|
Mickley JP, Grove AF, Rouzrokh P, Yang L, Larson AN, Sanchez-Sotello J, Maradit Kremers H, Wyles CC. A Stepwise Approach to Analyzing Musculoskeletal Imaging Data With Artificial Intelligence. Arthritis Care Res (Hoboken) 2024; 76:590-599. [PMID: 37849415 DOI: 10.1002/acr.25260] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Revised: 08/27/2023] [Accepted: 10/13/2023] [Indexed: 10/19/2023]
Abstract
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.
Collapse
|
5
|
Hay CA, Packham J, Prior JA, Mallen CD, Ryan S. Barriers and facilitators in diagnosing axial spondyloarthritis: a qualitative study. Rheumatol Int 2024; 44:863-884. [PMID: 38472441 PMCID: PMC10980652 DOI: 10.1007/s00296-024-05554-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/11/2023] [Accepted: 01/31/2024] [Indexed: 03/14/2024]
Abstract
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.
Collapse
Affiliation(s)
| | - Jon Packham
- School of Medicine, Keele University, Keele, UK
- Academic Unit of Population and Lifespan Sciences, University of Nottingham, Nottingham, UK
- Midlands Partnership University NHS Foundation Trust, Stafford, UK
| | - James A Prior
- School of Medicine, Keele University, Keele, UK
- Midlands Partnership University NHS Foundation Trust, Stafford, UK
| | - Christian D Mallen
- School of Medicine, Keele University, Keele, UK
- Midlands Partnership University NHS Foundation Trust, Stafford, UK
| | - Sarah Ryan
- Midlands Partnership University NHS Foundation Trust, Stafford, UK
- School of Nursing and Midwifery, Keele University, Keele, UK
| |
Collapse
|
6
|
Kleinert S, Schuch F, Rapp P, Ronneberger M, Wendler J, Sternad P, Popp F, Bartz-Bazzanella P, von der Decken C, Karberg K, Gauler G, Wurth P, Späthling-Mestekemper S, Kuhn C, Vorbrüggen W, Welcker M. Radiographic and non-radiographic axial spondyloarthritis are not routinely distinguished in everyday clinical care: an analysis of real-world data from rheumatology practices. Rheumatol Int 2024; 44:653-661. [PMID: 37805981 DOI: 10.1007/s00296-023-05463-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/07/2023] [Accepted: 09/07/2023] [Indexed: 10/10/2023]
Abstract
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.
Collapse
Affiliation(s)
- Stefan Kleinert
- Praxisgemeinschaft Rheumatologie-Nephrologie (PGRN), Möhrendorferstr 1C, Erlangen, Germany.
- Med. Klinik 3, Rheumatologie/Klinische Immunologie, Universitätsklinik Würzburg, Würzburg, Germany.
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany.
| | - Florian Schuch
- Praxisgemeinschaft Rheumatologie-Nephrologie (PGRN), Möhrendorferstr 1C, Erlangen, Germany
| | - Praxedis Rapp
- Praxisgemeinschaft Rheumatologie-Nephrologie (PGRN), Möhrendorferstr 1C, Erlangen, Germany
| | - Monika Ronneberger
- Praxisgemeinschaft Rheumatologie-Nephrologie (PGRN), Möhrendorferstr 1C, Erlangen, Germany
| | - Joerg Wendler
- Praxisgemeinschaft Rheumatologie-Nephrologie (PGRN), Möhrendorferstr 1C, Erlangen, Germany
| | - Patrizia Sternad
- Medizinisches Versorgungszentrum für Rheumatologie Dr. M. Welcker GmbH, Planegg, Germany
| | - Florian Popp
- Medizinisches Versorgungszentrum für Rheumatologie Dr. M. Welcker GmbH, Planegg, Germany
| | - Peter Bartz-Bazzanella
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Rhein-Maas Klinikum, Wuerselen, Germany
| | - Cay von der Decken
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Medizinisches Versorgungszentrum Stolberg, Stolberg, Germany
| | - Kirsten Karberg
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Praxis für Rheumatologie und Innere Medizin, Berlin, Germany
| | - Georg Gauler
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Rheumatologische Schwerpunktpraxis, Osnabrück, Germany
| | - Patrick Wurth
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Rheumatologische Schwerpunktpraxis, Osnabrück, Germany
| | | | - Christoph Kuhn
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Rheumaärzte GmbH MVZ, Standort Ettlingen, Ettlingen, Germany
| | - Wolfgang Vorbrüggen
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Verein zur Förderung der Rheumatologie e.V., Würselen, Germany
| | - Martin Welcker
- RheumaDatenRhePort GbR (A Network of Rheumatologists), Planegg, Germany
- Medizinisches Versorgungszentrum für Rheumatologie Dr. M. Welcker GmbH, Planegg, Germany
| |
Collapse
|
7
|
Chen Y, Liu H, Yu Q, Qu X, Sun T. Entry point of machine learning in axial spondyloarthritis. RMD Open 2024; 10:e003832. [PMID: 38360037 PMCID: PMC10875480 DOI: 10.1136/rmdopen-2023-003832] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2023] [Accepted: 01/22/2024] [Indexed: 02/17/2024] Open
Abstract
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.
Collapse
Affiliation(s)
- Yuening Chen
- Department of Rheumatology, China Academy of Chinese Medical Sciences Guang'anmen Hospital, Beijing, China
| | - Hongxiao Liu
- Department of Rheumatology, China Academy of Chinese Medical Sciences Guang'anmen Hospital, Beijing, China
| | - Qing Yu
- Department of Rheumatology, China Academy of Chinese Medical Sciences Guang'anmen Hospital, Beijing, China
| | - Xinning Qu
- Department of Rheumatology, China Academy of Chinese Medical Sciences Guang'anmen Hospital, Beijing, China
| | - Tiantian Sun
- Department of Rheumatology, China Academy of Chinese Medical Sciences Guang'anmen Hospital, Beijing, China
| |
Collapse
|
8
|
Yoshida K, Cai T, Bessette LG, Kim E, Lee SB, Zabotka LE, Sun A, Mastrorilli JM, Oduol TA, Liu J, Solomon DH, Kim SC, Desai RJ, Liao KP. Improving the accuracy of automated gout flare ascertainment using natural language processing of electronic health records and linked Medicare claims data. Pharmacoepidemiol Drug Saf 2024; 33:e5684. [PMID: 37654015 PMCID: PMC10873073 DOI: 10.1002/pds.5684] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Revised: 06/20/2023] [Accepted: 08/12/2023] [Indexed: 09/02/2023]
Abstract
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.
Collapse
Affiliation(s)
- Kazuki Yoshida
- Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- OM1, Inc, Boston, MA, USA
| | - Tianrun Cai
- Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
| | - Lily G. Bessette
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Erin Kim
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Su Been Lee
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Luke E. Zabotka
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Alec Sun
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Julianna M. Mastrorilli
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Theresa A. Oduol
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Jun Liu
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Daniel H. Solomon
- Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Seoyoung C. Kim
- Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Rishi J. Desai
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
| | - Katherine P. Liao
- Division of Rheumatology, Inflammation, and Immunity, Department of Medicine, Brigham and Women’s Hospital, Boston, MA, USA
- Department of Medicine, Harvard Medical School, Boston, MA, USA
- Department of Biomedical Informatics, Harvard Medical School, Boston, MA, USA
| |
Collapse
|
9
|
Benavent D, Muñoz-Fernández S, De la Morena I, Fernández-Nebro A, Marín-Corral J, Castillo Rosa E, Taberna M, Sanabra C, Sastre C. 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. Ther Adv Musculoskelet Dis 2023; 15:1759720X231220818. [PMID: 38146537 PMCID: PMC10749530 DOI: 10.1177/1759720x231220818] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2023] [Accepted: 11/28/2023] [Indexed: 12/27/2023] Open
Abstract
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.
Collapse
Affiliation(s)
- Diego Benavent
- SAVANA Research S.L., Calle de Larra 12, Madrid 28013, Spain
| | - Santiago Muñoz-Fernández
- Hospital Universitario Infanta Sofía, Universidad Europea de Madrid, San Sebastián de los Reyes, Madrid, Spain
| | - Isabel De la Morena
- Department of Rheumatology, Hospital Clínico Universitario de Valencia, Valencia, Valencia, Spain
| | - Antonio Fernández-Nebro
- Instituto de Investigación Biomédica de Málaga (IBIMA)-Plataforma Bionand, Málaga, Spain
- UGC de Reumatología, Hospital Regional Universitario de Málaga, Málaga, Spain
- Departamento de Medicina, Universidad de Málaga, Málaga, Spain
| | | | | | | | | | - Carlos Sastre
- Medical Department, Novartis Farmacéutica SA., Barcelona, Spain
| | | |
Collapse
|
10
|
Roels J, De Craemer AS, Renson T, de Hooge M, Gevaert A, Van Den Berghe T, Jans L, Herregods N, Carron P, Van den Bosch F, Saeys Y, Elewaut D. Machine Learning Pipeline for Predicting Bone Marrow Edema Along the Sacroiliac Joints on Magnetic Resonance Imaging. Arthritis Rheumatol 2023; 75:2169-2177. [PMID: 37410803 DOI: 10.1002/art.42650] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/19/2022] [Revised: 06/22/2023] [Accepted: 06/26/2023] [Indexed: 07/08/2023]
Abstract
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.
Collapse
Affiliation(s)
- Joris Roels
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University, Ghent, Belgium
| | - Ann-Sophie De Craemer
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University Hospital, Ghent, Belgium
| | - Thomas Renson
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University Hospital, Ghent, Belgium
| | - Manouk de Hooge
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University Hospital, Ghent, Belgium
| | - Arne Gevaert
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University, Ghent, Belgium
| | | | | | | | - Philippe Carron
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University Hospital, Ghent, Belgium
| | - Filip Van den Bosch
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University Hospital, Ghent, Belgium
| | - Yvan Saeys
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University, Ghent, Belgium
| | - Dirk Elewaut
- Vlaams Instituut voor Biotechnologie - Universiteit Gent (VIB-UGent), Ghent-Zwijnaarde, and Ghent University Hospital, Ghent, Belgium
| |
Collapse
|
11
|
Barnett R, Gaffney K, Sengupta R. Diagnostic delay in axial spondylarthritis: A lost battle? Best Pract Res Clin Rheumatol 2023; 37:101870. [PMID: 37658016 DOI: 10.1016/j.berh.2023.101870] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Revised: 08/08/2023] [Accepted: 08/18/2023] [Indexed: 09/03/2023]
Abstract
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.
Collapse
Affiliation(s)
- Rosemarie Barnett
- Department for Health, University of Bath, Claverton Down, Bath, BA2 7AY, UK; Rheumatology Department, Royal National Hospital for Rheumatic Diseases & Brownsword Therapies Centre, Royal United Hospitals Bath NHS Foundation Trust, Combe Park, Bath, BA1 3NG, UK.
| | - Karl Gaffney
- Rheumatology Department, Norfolk and Norwich University Hospitals NHS Foundation Trust, Norfolk & Norwich, University Hospital, Colney Lane, Norwich NR4 7UY, UK.
| | - Raj Sengupta
- Rheumatology Department, Royal National Hospital for Rheumatic Diseases & Brownsword Therapies Centre, Royal United Hospitals Bath NHS Foundation Trust, Combe Park, Bath, BA1 3NG, UK.
| |
Collapse
|
12
|
Madrid-García A, Merino-Barbancho B, Rodríguez-González A, Fernández-Gutiérrez B, Rodríguez-Rodríguez L, Menasalvas-Ruiz E. Understanding the role and adoption of artificial intelligence techniques in rheumatology research: An in-depth review of the literature. Semin Arthritis Rheum 2023; 61:152213. [PMID: 37315379 DOI: 10.1016/j.semarthrit.2023.152213] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2022] [Revised: 04/28/2023] [Accepted: 05/02/2023] [Indexed: 06/16/2023]
Abstract
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.
Collapse
Affiliation(s)
- Alfredo Madrid-García
- Grupo de Patología Musculoesquelética. Hospital Clínico San Carlos, Prof. Martin Lagos s/n, Madrid, 28040, Spain; Escuela Técnica Superior de Ingenieros de Telecomunicación. Universidad Politécnica de Madrid, Avenida Complutense, 30, Madrid, 28040, Spain.
| | - Beatriz Merino-Barbancho
- Escuela Técnica Superior de Ingenieros de Telecomunicación. Universidad Politécnica de Madrid, Avenida Complutense, 30, Madrid, 28040, Spain
| | | | - Benjamín Fernández-Gutiérrez
- Grupo de Patología Musculoesquelética. Hospital Clínico San Carlos, Prof. Martin Lagos s/n, Madrid, 28040, Spain
| | - Luis Rodríguez-Rodríguez
- Grupo de Patología Musculoesquelética. Hospital Clínico San Carlos, Prof. Martin Lagos s/n, Madrid, 28040, Spain
| | - Ernestina Menasalvas-Ruiz
- Centro de Tecnología Biomédica. Universidad Politécnica de Madrid, Pozuelo de Alarcón, Madrid, 28223, Spain
| |
Collapse
|
13
|
Cascella M, Schiavo D, Cuomo A, Ottaiano A, Perri F, Patrone R, Migliarelli S, Bignami EG, Vittori A, Cutugno F. Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives. Pain Res Manag 2023; 2023:6018736. [PMID: 37416623 PMCID: PMC10322534 DOI: 10.1155/2023/6018736] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/22/2022] [Revised: 02/03/2023] [Accepted: 04/20/2023] [Indexed: 07/08/2023]
Abstract
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.
Collapse
Affiliation(s)
- Marco Cascella
- Division of Anesthesia and Pain Medicine, Istituto Nazionale Tumori IRCCS Fondazione G. Pascale, Naples 80131, Italy
| | - Daniela Schiavo
- Division of Anesthesia and Pain Medicine, Istituto Nazionale Tumori IRCCS Fondazione G. Pascale, Naples 80131, Italy
| | - Arturo Cuomo
- Division of Anesthesia and Pain Medicine, Istituto Nazionale Tumori IRCCS Fondazione G. Pascale, Naples 80131, Italy
| | - Alessandro Ottaiano
- SSD-Innovative Therapies for Abdominal Metastases, Istituto Nazionale Tumori di Napoli IRCCS “G. Pascale”, Via M. Semmola, Naples 80131, Italy
| | - Francesco Perri
- Head and Neck Oncology Unit, Istituto Nazionale Tumori IRCCS-Fondazione “G. Pascale”, Naples 80131, Italy
| | - Renato Patrone
- Dieti Department, University of Naples, Naples, Italy
- Division of Hepatobiliary Surgical Oncology, Istituto Nazionale Tumori IRCCS, Fondazione Pascale-IRCCS di Napoli, Naples, Italy
| | - Sara Migliarelli
- Department of Pharmacology, Faculty of Medicine and Psychology, University Sapienza of Rome, Rome, Italy
| | - Elena Giovanna Bignami
- Anesthesiology, Critical Care and Pain Medicine Division, Department of Medicine and Surgery, University of Parma, Parma, Italy
| | - Alessandro Vittori
- Department of Anesthesia and Critical Care, ARCO ROMA, Ospedale Pediatrico Bambino Gesù IRCCS, Rome 00165, Italy
| | - Francesco Cutugno
- Department of Electrical Engineering and Information Technologies, University of Naples “Federico II”, Naples 80100, Italy
| |
Collapse
|
14
|
Hossain E, Rana R, Higgins N, Soar J, Barua PD, Pisani AR, Turner K. Natural Language Processing in Electronic Health Records in relation to healthcare decision-making: A systematic review. Comput Biol Med 2023; 155:106649. [PMID: 36805219 DOI: 10.1016/j.compbiomed.2023.106649] [Citation(s) in RCA: 18] [Impact Index Per Article: 18.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/03/2022] [Revised: 01/04/2023] [Accepted: 02/07/2023] [Indexed: 02/12/2023]
Abstract
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.
Collapse
Affiliation(s)
- Elias Hossain
- School of Engineering & Physical Sciences, North South University, Dhaka 1229, Bangladesh.
| | - Rajib Rana
- School of Mathematics, Physics and Computing, University of Southern Queensland, Springfield Central QLD 4300, Australia
| | - Niall Higgins
- School of Management and Enterprise, University of Southern Queensland, Darling Heights QLD 4350, Australia; School of Nursing, Queensland University of Technology, Kelvin Grove, Brisbane, QLD 4000, Australia; Metro North Mental Health, Herston QLD 4029, Australia
| | - Jeffrey Soar
- School of Business, University of Southern Queensland, Springfield Central QLD 4300, Australia
| | - Prabal Datta Barua
- School of Business, University of Southern Queensland, Springfield Central QLD 4300, Australia
| | - Anthony R Pisani
- Center for the Study and Prevention of Suicide, University of Rochester, Rochester, NY, United States
| | - Kathryn Turner
- School of Nursing, Queensland University of Technology, Kelvin Grove, Brisbane, QLD 4000, Australia
| |
Collapse
|
15
|
Humbert-Droz M, Izadi Z, Schmajuk G, Gianfrancesco M, Baker MC, Yazdany J, Tamang S. Development of a Natural Language Processing System for Extracting Rheumatoid Arthritis Outcomes From Clinical Notes Using the National Rheumatology Informatics System for Effectiveness Registry. Arthritis Care Res (Hoboken) 2023; 75:608-615. [PMID: 35157365 DOI: 10.1002/acr.24869] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/20/2022] [Accepted: 02/10/2022] [Indexed: 11/07/2022]
Abstract
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.
Collapse
Affiliation(s)
- Marie Humbert-Droz
- Stanford Center for Biomedical Informatics Research, Stanford University, Stanford, California
| | | | - Gabriela Schmajuk
- University of California, San Francisco, San Francisco VA Medical Center, and Philip R. Lee Institute for Health Policy Studies, San Francisco, California
| | | | | | | | | |
Collapse
|
16
|
Ashburner JM, Chang Y, Wang X, Khurshid S, Anderson CD, Dahal K, Weisenfeld D, Cai T, Liao KP, Wagholikar KB, Murphy SN, Atlas SJ, Lubitz SA, Singer DE. Natural Language Processing to Improve Prediction of Incident Atrial Fibrillation Using Electronic Health Records. J Am Heart Assoc 2022; 11:e026014. [PMID: 35904194 PMCID: PMC9375475 DOI: 10.1161/jaha.122.026014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
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.
Collapse
Affiliation(s)
- Jeffrey M Ashburner
- Division of General Internal Medicine Massachusetts General Hospital Boston MA.,Harvard Medical School Boston MA
| | - Yuchiao Chang
- Division of General Internal Medicine Massachusetts General Hospital Boston MA.,Harvard Medical School Boston MA
| | - Xin Wang
- Cardiovascular Research Center Massachusetts General Hospital Boston MA
| | - Shaan Khurshid
- Cardiovascular Research Center Massachusetts General Hospital Boston MA.,Division of Cardiology Massachusetts General Hospital Boston MA
| | | | - Kumar Dahal
- Department of Rheumatology, Inflammation, and Immunity Brigham and Women's Hospital Boston MA
| | - Dana Weisenfeld
- Department of Rheumatology, Inflammation, and Immunity Brigham and Women's Hospital Boston MA
| | - Tianrun Cai
- Harvard Medical School Boston MA.,Department of Rheumatology, Inflammation, and Immunity Brigham and Women's Hospital Boston MA
| | - Katherine P Liao
- Harvard Medical School Boston MA.,Department of Rheumatology, Inflammation, and Immunity Brigham and Women's Hospital Boston MA
| | - Kavishwar B Wagholikar
- Harvard Medical School Boston MA.,Laboratory of Computer Science Massachusetts General Hospital Boston MA
| | - Shawn N Murphy
- Harvard Medical School Boston MA.,Research Information Science and Computing Mass General Brigham Somerville MA
| | - Steven J Atlas
- Division of General Internal Medicine Massachusetts General Hospital Boston MA.,Harvard Medical School Boston MA
| | - Steven A Lubitz
- Cardiovascular Research Center Massachusetts General Hospital Boston MA.,Cardiac Arrhythmia Service Massachusetts General Hospital Boston MA
| | - Daniel E Singer
- Division of General Internal Medicine Massachusetts General Hospital Boston MA.,Harvard Medical School Boston MA
| |
Collapse
|
17
|
Bacco L, Russo F, Ambrosio L, D’Antoni F, Vollero L, Vadalà G, Dell’Orletta F, Merone M, Papalia R, Denaro V. Natural language processing in low back pain and spine diseases: A systematic review. Front Surg 2022; 9:957085. [PMID: 35910476 PMCID: PMC9329654 DOI: 10.3389/fsurg.2022.957085] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2022] [Accepted: 06/27/2022] [Indexed: 11/13/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Luca Bacco
- Department of Engineering, Unit of Computer Systems and Bioinformatics, Campus Bio-Medico University of Rome, Rome, Italy
- ItaliaNLP Lab, National Research Council, Istituto di Linguistica Computazionale “Antonio Zampolli”, Pisa, Italy
- R&D Lab, Webmonks S.r.l., Rome, Italy
| | - Fabrizio Russo
- Department of Orthopaedic and Trauma Surgery, Campus Bio-Medico University Hospital Foundation, Rome, Italy
- Research Unit of Orthopaedic and Trauma Surgery, Campus Bio-Medico University of Rome, Rome, Italy
- Correspondence: Mario Merone Fabrizio Russo
| | - Luca Ambrosio
- Research Unit of Orthopaedic and Trauma Surgery, Campus Bio-Medico University of Rome, Rome, Italy
| | - Federico D’Antoni
- Department of Engineering, Unit of Computer Systems and Bioinformatics, Campus Bio-Medico University of Rome, Rome, Italy
| | - Luca Vollero
- Department of Engineering, Unit of Computer Systems and Bioinformatics, Campus Bio-Medico University of Rome, Rome, Italy
| | - Gianluca Vadalà
- Department of Orthopaedic and Trauma Surgery, Campus Bio-Medico University Hospital Foundation, Rome, Italy
- Research Unit of Orthopaedic and Trauma Surgery, Campus Bio-Medico University of Rome, Rome, Italy
| | - Felice Dell’Orletta
- ItaliaNLP Lab, National Research Council, Istituto di Linguistica Computazionale “Antonio Zampolli”, Pisa, Italy
| | - Mario Merone
- Department of Engineering, Unit of Computer Systems and Bioinformatics, Campus Bio-Medico University of Rome, Rome, Italy
- Correspondence: Mario Merone Fabrizio Russo
| | - Rocco Papalia
- Department of Orthopaedic and Trauma Surgery, Campus Bio-Medico University Hospital Foundation, Rome, Italy
- Research Unit of Orthopaedic and Trauma Surgery, Campus Bio-Medico University of Rome, Rome, Italy
| | - Vincenzo Denaro
- Department of Orthopaedic and Trauma Surgery, Campus Bio-Medico University Hospital Foundation, Rome, Italy
| |
Collapse
|
18
|
Tenório APM, Ferreira-Junior JR, Dalto VF, Faleiros MC, Assad RL, Louzada-Junior P, Nogueira-Barbosa MH, Rangayyan RM, de Azevedo-Marques PM. Radiomic Quantification for MRI Assessment of Sacroiliac Joints of Patients with Spondyloarthritis. J Digit Imaging 2022; 35:29-38. [PMID: 34997373 PMCID: PMC8854535 DOI: 10.1007/s10278-021-00559-7] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2021] [Revised: 11/24/2021] [Accepted: 12/01/2021] [Indexed: 02/03/2023] Open
Abstract
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.
Collapse
Affiliation(s)
| | - José Raniery Ferreira-Junior
- Ribeirão Preto Medical School, University of São Paulo, Av. dos Bandeirantes, 3900 Ribeirão Preto, SP 14049-900 São Paulo, Brazil
| | - Vitor Faeda Dalto
- Ribeirão Preto Medical School, University of São Paulo, Av. dos Bandeirantes, 3900 Ribeirão Preto, SP 14049-900 São Paulo, Brazil
| | - Matheus Calil Faleiros
- Ribeirão Preto Medical School, University of São Paulo, Av. dos Bandeirantes, 3900 Ribeirão Preto, SP 14049-900 São Paulo, Brazil
| | - Rodrigo Luppino Assad
- Ribeirão Preto Medical School, University of São Paulo, Av. dos Bandeirantes, 3900 Ribeirão Preto, SP 14049-900 São Paulo, Brazil
| | - Paulo Louzada-Junior
- Ribeirão Preto Medical School, University of São Paulo, Av. dos Bandeirantes, 3900 Ribeirão Preto, SP 14049-900 São Paulo, Brazil
| | - Marcello Henrique Nogueira-Barbosa
- Ribeirão Preto Medical School, University of São Paulo, Av. dos Bandeirantes, 3900 Ribeirão Preto, SP 14049-900 São Paulo, Brazil ,Department of Orthopedic Surgery, University of Missouri Health Care, Columbia, MO USA
| | | | | |
Collapse
|
19
|
Artificial Intelligence in Clinical Immunology. Artif Intell Med 2022. [DOI: 10.1007/978-3-030-64573-1_83] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
20
|
Kingsmore KM, Puglisi CE, Grammer AC, Lipsky PE. An introduction to machine learning and analysis of its use in rheumatic diseases. Nat Rev Rheumatol 2021; 17:710-730. [PMID: 34728818 DOI: 10.1038/s41584-021-00708-w] [Citation(s) in RCA: 32] [Impact Index Per Article: 10.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/04/2021] [Indexed: 02/07/2023]
Abstract
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.
Collapse
Affiliation(s)
| | | | - Amrie C Grammer
- AMPEL BioSolutions and RILITE Research Institute, Charlottesville, VA, USA
| | - Peter E Lipsky
- AMPEL BioSolutions and RILITE Research Institute, Charlottesville, VA, USA
| |
Collapse
|
21
|
Hügle T, Kalweit M. [Artificial intelligence-supported treatment in rheumatology : Principles, current situation and perspectives]. Z Rheumatol 2021; 80:914-927. [PMID: 34618208 PMCID: PMC8651581 DOI: 10.1007/s00393-021-01096-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 06/21/2021] [Indexed: 11/02/2022]
Abstract
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.
Collapse
Affiliation(s)
- Thomas Hügle
- Abteilung Rheumatologie, Universitätsspital Lausanne (CHUV) und Universität Lausanne, Avenue Pierre-Decker 4, 1011, Lausanne, Schweiz.
| | - Maria Kalweit
- Institut für Informatik, Albert-Ludwigs-Universität Freiburg, Universität Freiburg im Breisgau, Georges-Koehler-Allee 80, 79110, Freiburg im Breisgau, Deutschland
| |
Collapse
|
22
|
Artificial Intelligence in Clinical Immunology. Artif Intell Med 2021. [DOI: 10.1007/978-3-030-58080-3_83-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
23
|
Walsh JA, Pei S, Penmetsa GK, Overbury RS, Clegg DO, Sauer BC. Identifying Patients With Axial Spondyloarthritis in Large Datasets: Expanding Possibilities for Observational Research. J Rheumatol 2020; 48:685-692. [PMID: 33259327 DOI: 10.3899/jrheum.200570] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 08/13/2020] [Indexed: 11/22/2022]
Abstract
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 (F1IPW 0.65). The Early Algorithm was the most inclusive (sensitivityIPW 0.90, PPVIPW 0.38). The traditional method using ≥ 2 AS diagnosis codes from rheumatology had the highest PPV (PPVIPW 0.84, sensitivityIPW 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.
Collapse
Affiliation(s)
- Jessica A Walsh
- J.A. Walsh, MD, MBA, MSCI, S. Pei, PhD, R.S. Overbury, MD, B.C. Sauer, PhD, G.K. Penmetsa, MD, D.O. Clegg, MD, Salt Lake City Veterans Affairs and University of Utah Medical Centers, Department of Internal Medicine, Divisions of Rheumatology and Epidemiology, Salt Lake City, Utah, USA.
| | - Shaobo Pei
- J.A. Walsh, MD, MBA, MSCI, S. Pei, PhD, R.S. Overbury, MD, B.C. Sauer, PhD, G.K. Penmetsa, MD, D.O. Clegg, MD, Salt Lake City Veterans Affairs and University of Utah Medical Centers, Department of Internal Medicine, Divisions of Rheumatology and Epidemiology, Salt Lake City, Utah, USA
| | - Gopi K Penmetsa
- J.A. Walsh, MD, MBA, MSCI, S. Pei, PhD, R.S. Overbury, MD, B.C. Sauer, PhD, G.K. Penmetsa, MD, D.O. Clegg, MD, Salt Lake City Veterans Affairs and University of Utah Medical Centers, Department of Internal Medicine, Divisions of Rheumatology and Epidemiology, Salt Lake City, Utah, USA
| | - Rebecca S Overbury
- J.A. Walsh, MD, MBA, MSCI, S. Pei, PhD, R.S. Overbury, MD, B.C. Sauer, PhD, G.K. Penmetsa, MD, D.O. Clegg, MD, Salt Lake City Veterans Affairs and University of Utah Medical Centers, Department of Internal Medicine, Divisions of Rheumatology and Epidemiology, Salt Lake City, Utah, USA
| | - Daniel O Clegg
- J.A. Walsh, MD, MBA, MSCI, S. Pei, PhD, R.S. Overbury, MD, B.C. Sauer, PhD, G.K. Penmetsa, MD, D.O. Clegg, MD, Salt Lake City Veterans Affairs and University of Utah Medical Centers, Department of Internal Medicine, Divisions of Rheumatology and Epidemiology, Salt Lake City, Utah, USA
| | - Brian C Sauer
- J.A. Walsh, MD, MBA, MSCI, S. Pei, PhD, R.S. Overbury, MD, B.C. Sauer, PhD, G.K. Penmetsa, MD, D.O. Clegg, MD, Salt Lake City Veterans Affairs and University of Utah Medical Centers, Department of Internal Medicine, Divisions of Rheumatology and Epidemiology, Salt Lake City, Utah, USA
| |
Collapse
|
24
|
Zhao SS, Solomon DH, Goodson NJ. Comment on: Comorbidity burden in axial spondyloarthritis: a cluster analysis: reply. Rheumatology (Oxford) 2020; 59:692-693. [PMID: 31865393 DOI: 10.1093/rheumatology/kez573] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 10/25/2019] [Indexed: 12/16/2022] Open
Affiliation(s)
- Sizheng Steven Zhao
- Institute of Ageing and Chronic Disease, University of Liverpool, Liverpool, UK.,Department of Academic Rheumatology, Liverpool University Hospitals, Liverpool, UK.,Division of Rheumatology, Immunology and Allergy, Brigham and Women's Hospital, Boston, MA, USA
| | - Daniel H Solomon
- Division of Rheumatology, Immunology and Allergy, Brigham and Women's Hospital, Boston, MA, USA.,Division of Pharmacoepidemiology and Pharmacoeconomics, Brigham and Women's Hospital, Boston, MA, USA
| | - Nicola J Goodson
- Institute of Ageing and Chronic Disease, University of Liverpool, Liverpool, UK.,Department of Academic Rheumatology, Liverpool University Hospitals, Liverpool, UK
| |
Collapse
|