Detection of primary Sjögren’s syndrome in primary care: developing a classification model with the use of routine healthcare data and machine learning

Automatically pre-screening patients for the rare disease aromatic l-amino acid decarboxylase deficiency using knowledge engineering, natural language processing, and machine learning on a large EHR population

OBJECTIVES

Electronic health record (EHR) data may facilitate the identification of rare diseases in patients, such as aromatic l-amino acid decarboxylase deficiency (AADCd), an autosomal recessive disease caused by pathogenic variants in the dopa decarboxylase gene. Deficiency of the AADC enzyme results in combined severe reductions in monoamine neurotransmitters: dopamine, serotonin, epinephrine, and norepinephrine. This leads to widespread neurological complications affecting motor, behavioral, and autonomic function. The goal of this study was to use EHR data to identify previously undiagnosed patients who may have AADCd without available training cases for the disease.

MATERIALS AND METHODS

A multiple symptom and related disease annotated dataset was created and used to train individual concept classifiers on annotated sentence data. A multistep algorithm was then used to combine concept predictions into a single patient rank value.

RESULTS

Using an 8000-patient dataset that the algorithms had not seen before ranking, the top and bottom 200 ranked patients were manually reviewed for clinical indications of performing an AADCd diagnostic screening test. The top-ranked patients were 22.5% positively assessed for diagnostic screening, with 0% for the bottom-ranked patients. This result is statistically significant at P < .0001.

CONCLUSION

This work validates the approach that large-scale rare-disease screening can be accomplished by combining predictions for relevant individual symptoms and related conditions which are much more common and for which training data is easier to create.

Prediction of Sjögren's disease diagnosis using matched electronic dental-health record data

BACKGROUND

Sjögren's disease (SD) is an autoimmune disease that is difficult to diagnose early due to its wide spectrum of clinical symptoms and overlap with other autoimmune diseases. SD potentially presents through early oral manifestations prior to showing symptoms of clinically significant dry eyes or dry mouth. We examined the feasibility of utilizing a linked electronic dental record (EDR) and electronic health record (EHR) dataset to identify factors that could be used to improve early diagnosis prediction of SD in a matched case-control study population.

METHODS

EHR data, including demographics, medical diagnoses, medication history, serological test history, and clinical notes, were retrieved from the Indiana Network for Patient Care database and dental procedure data were retrieved from the Indiana University School of Dentistry EDR. We examined EHR and EDR history in the three years prior to SD diagnosis for SD cases and the corresponding period in matched non-SD controls. Two conditional logistic regression (CLR) models were built using Least Absolute Shrinkage and Selection Operator regression. One used only EHR data and the other used both EHR and EDR data. The ability of these models to predict SD diagnosis was assessed using a concordance index designed for CLR.

RESULTS

We identified a sample population of 129 cases and 371 controls with linked EDR-EHR data. EHR factors associated with an increased risk of SD diagnosis were the usage of lubricating throat drugs with an odds ratio (OR) of 14.97 (2.70-83.06), dry mouth (OR = 6.19, 2.14-17.89), pain in joints (OR = 2.54, 1.34-4.76), tear film insufficiency (OR = 27.04, 5.37-136.), and rheumatoid factor testing (OR = 6.97, 1.94-25.12). The addition of EDR data slightly improved model concordance compared to the EHR only model (0.834 versus 0.811). Surgical dental procedures (OR = 2.33, 1.14-4.78) were found to be associated with an increased risk of SD diagnosis while dental diagnostic procedures (OR = 0.45, 0.20-1.01) were associated with decreased risk.

CONCLUSION

Utilizing EDR data alongside EHR data has the potential to improve prediction models for SD. This could improve the early diagnosis of SD, which is beneficial to slowing or preventing complications of SD.

Novel multiclass classification machine learning approach for the early-stage classification of systemic autoimmune rheumatic diseases

OBJECTIVE

Systemic autoimmune rheumatic diseases (SARDs) encompass a diverse group of complex conditions with overlapping clinical features, making accurate diagnosis challenging. This study aims to develop a multiclass machine learning (ML) model for early-stage SARDs classification using accessible laboratory indicators.

METHODS

A total of 925 SARDs patients were included, categorised into SLE, Sjögren's syndrome (SS) and inflammatory myositis (IM). Clinical characteristics and laboratory markers were collected and nine key indicators, including anti-dsDNA, anti-SS-A60, anti-Sm/nRNP, antichromatin, anti-dsDNA (indirect immunofluorescence assay), haemoglobin (Hb), platelet, neutrophil percentage and cytoplasmic patterns (AC-19, AC-20), were selected for model building. Various ML algorithms were used to construct a tripartite classification ML model.

RESULTS

Patients were divided into two cohorts, cohort 1 was used to construct a tripartite classification model. Among models assessed, the random forest (RF) model demonstrated superior performance in distinguishing SLE, IM and SS (with area under curve=0.953, 0.903 and 0.836; accuracy= 0.892, 0.869 and 0.857; sensitivity= 0.890, 0.868 and 0.795; specificity= 0.910, 0.836 and 0.748; positive predictive value=0.922, 0.727 and 0.663; and negative predictive value= 0.854, 0.915 and 0.879). The RF model excelled in classifying SLE (precision=0.930, recall=0.985, F1 score=0.957). For IM and SS, RF model outcomes were (precision=0.793, 0.950; recall=0.920, 0.679; F1 score=0.852, 0.792). Cohort 2 served as an external validation set, achieving an overall accuracy of 87.3%. Individual classification performances for SLE, SS and IM were excellent, with precision, recall and F1 scores specified. SHAP analysis highlighted significant contributions from antibody profiles.

CONCLUSION

This pioneering multiclass ML model, using basic laboratory indicators, enhances clinical feasibility and demonstrates promising potential for SARDs classification. The collaboration of clinical expertise and ML offers a nuanced approach to SARDs classification, with potential for enhanced patient care.

Prevalence and comorbidities of Sjogren's syndrome patients in the Community of Madrid: A population-based cross-sectional study

OBJECTIVES

To estimate the prevalence, sociodemographic characteristics and comorbidities of Sjogren's syndrome (SS) patients in the Community of Madrid.

METHODS

A population-based cross-sectional cohort of SS patients was derived from the information system for rare diseases in the Community of Madrid (SIERMA) and confirmed by a physician. The prevalence per 10,000 inhabitants among people aged ≥18years in June 2015 was calculated. Sociodemographic data and accompanying disorders were recorded. Univariate and bivariate analyses were performed.

RESULTS

A total of 4,778 SS patients were confirmed in SIERMA; 92.8% were female, with a mean age of 64.3 (standard deviation=15.4) years. A total of 3,116 (65.2%) patients were classified as primary SS (pSS), and 1,662 (34.8%) as secondary SS (sSS). The prevalence of SS among people aged ≥18 years was 8.4/10,000 (95%Confidence interval [CI]=8.2-8.7). The prevalence of pSS was 5.5/10,000 (95%CI=5.3-5.7), and that of sSS was 2.8/10,000 (95%CI=2.7-2.9), with rheumatoid arthritis (20.3%) and systemic lupus erythematosus (8.5%) being the most prevalent associated autoimmune diseases. The most common comorbidities were hypertension (40.8%), lipid disorders (32.7%), osteoarthritis (27.7%) and depression (21.1%). The most prescribed medications were nonsteroidal anti-inflammatory drugs (31.9%), topical ophthalmic therapies (31.2%) and corticosteroids (28.0%).

CONCLUSION

The prevalence of SS in the Community of Madrid was similar to the overall prevalence worldwide observed in previous studies. SS was more frequent in women in their sixth decade. Two out of every three SS cases were pSS, while one-third were associated predominantly with rheumatoid arthritis and systemic lupus erythematosus.

Reliability of non-contact tongue diagnosis for Sjögren's syndrome using machine learning method

Sjögren's syndrome (SS) is an autoimmune disease characterized by dry mouth. The cause of SS is unknown, and its diverse symptoms make diagnosis difficult. The Saxon test, an intraoral examination, is used as the primary diagnostic method for SS, however, the risk of salivary infection is problematic. Therefore, we investigate the possibility of diagnosing SS by non-contact and imaging observation of the tongue surface. In this study, we obtained tongue photographs of 60 patients at the Tsurumi University School of Dentistry outpatient clinic to clarify the relationship between the features of the tongue and SS. We divided the tongue into four regions, and the color of each region was transformed into CIE1976L*a*b* space and statistically analyzed. To clarify experimentally the possibility of SS diagnosis using tongue color, we employed three machine-learning models: logistic regression, support vector machine, and random forest. In addition, we constructed diagnostic prediction models based on the Bagging and Stacking methods combined with three machine-learning models for comparative evaluation. This analysis used dimensionality compression by principal component analysis to eliminate redundancy in tongue color information. We found a significant difference between the a* value of the rear part of the tongue and the b* value of the middle part of the tongue in SS and non-SS patients. In addition to the principal component scores of tongue color, the support vector machine was trained using age, and achieved high accuracy (71.3%) and specificity (78.1%). The results indicate that the prediction of SS diagnosis by tongue color reaches a level comparable to machine learning models trained using the Saxon test. This is the first study using machine learning to predict SS diagnosis by non-contact tongue observation. Our proposed method can potentially support early SS detection simply and conveniently, eliminating the risk of infection at diagnosis, and it should be validated and optimized in clinical practice.

Integration of Artificial Intelligence into the Approach for Diagnosis and Monitoring of Dry Eye Disease

Dry eye disease (DED) is one of the most common diseases worldwide that can lead to a significant impairment of quality of life. The diagnosis and treatment of the disease are often challenging because of the lack of correlation between the signs and symptoms, limited reliability of diagnostic tests, and absence of established consensus on the diagnostic criteria. The advancement of machine learning, particularly deep learning technology, has enabled the application of artificial intelligence (AI) in various anterior segment disorders, including DED. Currently, many studies have reported promising results of AI-based algorithms for the accurate diagnosis of DED and precise and reliable assessment of data obtained by imaging devices for DED. Thus, the integration of AI into clinical approaches for DED can enhance diagnostic and therapeutic performance. In this review, in addition to a brief summary of the application of AI in anterior segment diseases, we will provide an overview of studies regarding the application of AI in DED and discuss the recent advances in the integration of AI into the clinical approach for DED.