Classifying Pseudogout Using Machine Learning Approaches With Electronic Health Record Data

Fractures in Patients With Acute Calcium Pyrophosphate Crystal Arthritis Versus Matched Comparators in a Large Cohort Study

OBJECTIVE

Calcium pyrophosphate deposition (CPPD) disease was associated with osteopenia in two cross-sectional studies. We compared fracture risks in patients with acute calcium pyrophosphate (CPP) crystal arthritis versus matched comparators.

METHODS

We performed a longitudinal cohort study using electronic health record data from a single large academic health system, with data from 1991 to 2023. Patients with one or more episodes of acute CPP crystal arthritis were matched to comparators on the index date (first documentation of "pseudogout" or synovial fluid CPP crystals or matched encounter) and first encounter in the health system. The primary outcome was first fracture at the humerus, wrist, hip, or pelvis. We excluded patients with fracture before the index date. Covariates included demographics, body mass index, smoking, comorbidities, health care use, glucocorticoids, and osteoporosis treatments. We estimated incidence rates and adjusted hazard ratios for fracture. Sensitivity analyses excluded patients prescribed glucocorticoids, patients prescribed osteoporosis treatments, or patients with rheumatoid arthritis and additionally adjusted for chronic kidney disease.

RESULTS

We identified 1,148 patients with acute CPP crystal arthritis matched to 3,730 comparators, with a mean age of 73 years. Glucocorticoids and osteoporosis treatments were more frequent in the acute CPP crystal arthritis cohort. Fracture incidence rates were twice as high in the acute CPP crystal arthritis cohort (11.7 per 1,000 person-years) versus comparators (5.5 per 1,000 person-years). After multivariable adjustment, fracture relative risk was twice as high in the acute CPP crystal arthritis cohort (hazard ratio 1.8 [95% confidence interval 1.3-2.3]); results were similar in sensitivity analyses.

CONCLUSION

In this first published study of fractures and CPPD, fracture risk was nearly doubled in patients with acute CPP crystal arthritis.

Calcium pyrophosphate deposition disease: historical overview and potential gaps

CPPD disease can affect patients’ quality of life through its various clinical presentations. This mini-review discusses the evolution of CPPD from its discovery to current knowledge of its pathogenesis, genetic associations, diagnostics, and treatment options. Despite extensive research, the exact mechanisms of CPPD are not well understood, and there is a notable lack of knowledge about psychosocial impacts and patient experiences. This study aims to present a CPPD Disease Timeline identifying gaps in current knowledge and potential directions for future research. These findings contribute to a broader understanding of CPPD disease and emphasize the importance of continued research and innovation in this field.

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.

Patient-Reported Outcomes in Calcium Pyrophosphate Deposition Disease Compared to Gout and Osteoarthritis

OBJECTIVE

Calcium pyrophosphate deposition (CPPD) disease prevalence is similar to that of gout and osteoarthritis (OA), yet CPPD outcomes research greatly lags behind research in these other forms of arthritis. We compared validated patient-reported outcome measures in patients with CPPD vs gout and OA.

METHODS

Patients with CPPD were recruited from Brigham and Women's Hospital from 2018 to 2022. Presence of CPPD manifestations (acute calcium pyrophosphate [CPP] crystal arthritis, chronic CPP inflammatory arthritis, and/or OA with CPPD) was confirmed by medical record review. Baseline surveys included the Gout Assessment Questionnaire version 2.0, modified to ask about "pseudogout" rather than "gout"; Routine Assessment of Patient Index Data 3 (RAPID-3); and Western Ontario and McMaster Universities Osteoarthritis Index (WOMAC). We compared responses in patients with CPPD against published gout and OA cohort studies.

RESULTS

Among 47 patients with CPPD, the mean age was 71.9 years and 51% were female. Sixty-eight percent had at least 1 episode of acute CPP crystal arthritis, 40% had chronic CPP inflammatory arthritis, and 62% had OA with CPPD. Pain visual analog scale scores during a flare were similar in CPPD (mean 6.8 [SD 1.9]) and gout (mean 6.7 [SD 2.6]; P = 0.78). Patients with CPPD reported significantly greater unmet treatment need than patients with gout (P = 0.04). RAPID-3 scores in CPPD (mean 8.1 [SD 5.6]) were lower than in gout (mean 12.1 [SD 6.2]; P < 0.01) and similar in OA (mean 6.8 [SD 6.1]; P = 0.30). Patients with CPPD had significantly worse WOMAC stiffness scores than patients with mild OA, and significantly better WOMAC function scores than patients with severe OA.

CONCLUSION

Patients with CPPD may experience pain comparable to that in gout and OA and reported substantial unmet treatment needs.

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.

Researchers in rheumatology should avoid categorization of continuous predictor variables

BACKGROUND

Rheumatology researchers often categorize continuous predictor variables. We aimed to show how this practice may alter results from observational studies in rheumatology.

METHODS

We conducted and compared the results of two analyses of the association between our predictor variable (percentage change in body mass index [BMI] from baseline to four years) and two outcome variable domains of structure and pain in knee and hip osteoarthritis. These two outcome variable domains covered 26 different outcomes for knee and hip combined. In the first analysis (categorical analysis), percentage change in BMI was categorized as ≥ 5% decrease in BMI, < 5% change in BMI, and ≥ 5% increase in BMI, while in the second analysis (continuous analysis), it was left as a continuous variable. In both analyses (categorical and continuous), we used generalized estimating equations with a logistic link function to investigate the association between the percentage change in BMI and the outcomes.

RESULTS

For eight of the 26 investigated outcomes (31%), the results from the categorical analyses were different from the results from the continuous analyses. These differences were of three types: 1) for six of these eight outcomes, while the continuous analyses revealed associations in both directions (i.e., a decrease in BMI had one effect, while an increase in BMI had the opposite effect), the categorical analyses showed associations only in one direction of BMI change, not both; 2) for another one of these eight outcomes, the categorical analyses suggested an association with change in BMI, while this association was not shown in the continuous analyses (this is potentially a false positive association); 3) for the last of the eight outcomes, the continuous analyses suggested an association of change in BMI, while this association was not shown in the categorical analyses (this is potentially a false negative association).

CONCLUSIONS

Categorization of continuous predictor variables alters the results of analyses and could lead to different conclusions; therefore, researchers in rheumatology should avoid it.

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.

Confirming Prior and Identifying Novel Correlates of Acute Calcium Pyrophosphate Crystal Arthritis

OBJECTIVE

To investigate previously identified and novel correlates of acute calcium pyrophosphate (CPP) crystal arthritis among well-characterized cases.

METHODS

In this case-control study, we identified cases of acute CPP crystal arthritis using a validated algorithm (positive predictive value 81%) applied in the Partners HealthCare electronic health record (EHR). Cases were matched to general patient controls on the year of first EHR encounter and index date. Prespecified potential correlates included sex, race, and comorbidities and medications previously associated with CPP deposition/acute CPP crystal arthritis in the literature. We estimated odds ratios (ORs) and 95% confidence intervals using conditional logistic regression models adjusted for demographic characteristics, comorbidities, medications prescribed in the past 90 days, health care utilization, and multimorbidity score.

RESULTS

We identified 1,697 cases matched to 6,503 controls. Mean ± SD age was 73.7 ± 11.8 years, 56.7% were female, 80.8% were White, and 10.3% were Black. All prespecified covariates were more common in cases than controls. Osteoarthritis (OR 3.08), male sex (OR 1.35), rheumatoid arthritis (OR 2.09), gout (OR 2.83), proton pump inhibitors (OR 1.94), loop diuretics (OR 1.60), and thiazides (OR 1.46) were significantly associated with acute CPP crystal arthritis after full adjustment. Black race was associated with lower odds for acute CPP crystal arthritis compared to White race (OR 0.47).

CONCLUSION

Using a validated algorithm to identify nearly 1,700 patients with acute CPP crystal arthritis, we confirmed important correlates of this acute manifestation of CPP deposition. This is the first study to report higher odds for acute CPP crystal arthritis among males.

Proton-Pump Inhibitors and Risk of Calcium Pyrophosphate Deposition in a Population-Based Study

OBJECTIVE

There are no proven effective medical treatments to prevent calcium pyrophosphate crystal deposition (CPPD). Hypomagnesemia is a known CPPD risk factor. The present study was undertaken to carry out a real-world epidemiologic study on proton-pump inhibitor (PPI) use, which can cause hypomagnesemia, and CPPD risk.

METHODS

We conducted a time-stratified, propensity score (PS)-matched cohort study using the UK-based IQVIA Medical Research Data. We compared risk of incident CPPD among PPI users versus H2 blocker users using Cox proportional hazards models. We used greedy matching of incident PPI users 1:1 to incident histamine receptor 2 (H2 ) blocker users in 1-year cohort accrual blocks. Subjects were censored at time of drug switch. We evaluated incident use of PPI and H2 blockers prior to incident CPPD using a nested case-control study within the same cohort, matched 1:4 by age and sex using risk-set sampling.

RESULTS

We identified 81,102 PPI and H2 blocker initiators, with 113 and 63 incident cases of CPPD, respectively. In the case-control study when compared with nonusers, both PPI and H2 B users had higher risk of incident CPPD, with odds ratios (ORs) of 1.79 (95% confidence interval [95% CI] 1.55-2.07) and 1.52 (95% CI 1.14-2.03), respectively. Incident PPI use was nonsignificantly associated with incident CPPD (hazard ratio 1.03 [95% CI 0.75-1.41]) compared with H2 blocker use.

CONCLUSION

In this study using real-world data, incident use of PPIs was not associated with a higher risk of CPPD compared with incident H2 blocker use, although use of PPI and H2 blockers had higher risk compared with nonuse.

Risk of cardiovascular events in patients having had acute calcium pyrophosphate crystal arthritis

OBJECTIVES

Calcium pyrophosphate deposition (CPPD) disease, broadly defined, has been associated with increased risk of cardiovascular (CV) events. We investigated risk of CV events in patients with acute CPP crystal arthritis, the acute manifestation of CPPD.

METHODS

Cohort study using Mass General Brigham electronic health record (EHR) data, 1991-2017. Patients with acute CPP crystal arthritis were identified using a published machine learning algorithm with positive predictive value 81%. Comparators were matched on year of EHR entry and index date of patients with acute CPP crystal arthritis (first positive synovial fluid CPP result or mention of 'pseudogout', or matched encounter). Major adverse cardiovascular event (MACE) was a composite of non-fatal CV event (myocardial infarction, acute coronary syndrome, coronary revascularisation, stroke) and death. We estimated incidence rates (IRs) and adjusted hazard ratios for MACE, non-fatal CV event and death, allowing for differential estimates during years 0-2 and 2-10. Sensitivity analyses included: (1) patients with acute CPP crystal arthritis diagnosed during outpatient visits, (2) patients with linked Medicare data, 2007-2016 and (3)patients matched on number of CV risk factors.

RESULTS

We matched 1200 acute CPP crystal arthritis patients to 3810 comparators. IR for MACE in years 0-2 was 91/1000 person-years (p-y) in acute CPP crystal arthritis and 59/1000 p-y in comparators. In years 2-10, IR for MACE was 58/1000 p-y in acute CPP crystal arthritis and 53/1000 p-y in comparators. Acute CPP crystal arthritis was significantly associated with increased risk for MACE in years 0-2 (HR 1.32, 95% CI 1.01 to 1.73) and non-fatal CV event in years 0-2 (HR 1.92, 95% CI 1.12 to 3.28) and years 2-10 (HR 2.18, 95% CI 1.27 to 3.75), but not death. Results of sensitivity analyses were similar to the primary analysis; in the outpatient-only analysis, risk of non-fatal CVE was significantly elevated in years 2-10 but not in years 0-2.

CONCLUSIONS

Acute CPP crystal arthritis was significantly associated with elevated short and long-term risk for non-fatal CV event.

Review: Outcome measures in calcium pyrophosphate deposition

This review highlights outcomes for patients with calcium pyrophosphate deposition (CPPD) reported in prior studies and underscores challenges to assessing outcomes of this condition. Prior clinical studies of interventions for CPPD focused on joint damage and calcification on imaging tests, joint pain, swelling, and inflammatory biomarkers. Qualitative interviews with patients with CPPD and healthcare providers additionally identified flares, overall function, and use of analgesic medications as important outcomes. Imaging evidence of joint damage and calcification is likely to be outcomes in future clinical studies of CPPD, though reliability and sensitivity to change in CPPD require further testing for several imaging modalities. Challenges to outcome measurement in CPPD include questions of attribution of signs and symptoms to CPPD versus co-existing forms of arthritis, lack of therapies to prevent or dissolve calcium pyrophosphate crystal deposition, absence of validated patient- or physician-reported CPPD outcome measures, and scarcity of large cohorts in which to study outcomes of different clinical presentations of CPPD.

Machine Learning in Rheumatic Diseases

With advances in information technology, the demand for using data science to enhance healthcare and disease management is rapidly increasing. Among these technologies, machine learning (ML) has become ubiquitous and indispensable for solving complex problems in many scientific fields, including medical science. ML allows the development of guidelines and framing of the evaluation system for complex diseases based on massive data. In the analysis of rheumatic diseases, which are chronic and remarkably heterogeneous, ML can be anticipated to be extremely helpful in deciphering and revealing the inherent interrelationships in disease development and progression, which can further enhance the overall understanding of the disease, optimize patients' stratification, calibrate therapeutic strategies, and predict prognosis and outcomes. In this review, the basics of ML, its potential clinical applications in rheumatology, together with its strengths and limitations are summarized.

Clinical notes as prognostic markers of mortality associated with diabetes mellitus following critical care: A retrospective cohort analysis using machine learning and unstructured big data

BACKGROUND

Clinical notes are ubiquitous resources offering potential value in optimizing critical care via data mining technologies.

OBJECTIVE

To determine the predictive value of clinical notes as prognostic markers of 1-year all-cause mortality among people with diabetes following critical care.

MATERIALS AND METHODS

Mortality of diabetes patients were predicted using three cohorts of clinical text in a critical care database, written by physicians (n = 45253), nurses (159027), and both (n = 204280). Natural language processing was used to pre-process text documents and LASSO-regularized logistic regression models were trained and tested. Confusion matrix metrics of each model were calculated and AUROC estimates between models were compared. All predictive words and corresponding coefficients were extracted. Outcome probability associated with each text document was estimated.

RESULTS

Models built on clinical text of physicians, nurses, and the combined cohort predicted mortality with AUROC of 0.996, 0.893, and 0.922, respectively. Predictive performance of the models significantly differed from one another whereas inter-rater reliability ranged from substantial to almost perfect across them. Number of predictive words with non-zero coefficients were 3994, 8159, and 10579, respectively, in the models of physicians, nurses, and the combined cohort. Physicians' and nursing notes, both individually and when combined, strongly predicted 1-year all-cause mortality among people with diabetes following critical care.

CONCLUSION

Clinical notes of physicians and nurses are strong and novel prognostic markers of diabetes-associated mortality in critical care, offering potentially generalizable and scalable applications. Clinical text-derived personalized risk estimates of prognostic outcomes such as mortality could be used to optimize patient care.