Dataset Information

Exploration of machine learning methods to predict systemic lupus erythematosus hospitalizations.

ABSTRACT:

Objectives

Systemic lupus erythematosus (SLE) is a heterogeneous disease characterized by disease flares which can require hospitalization. Our objective was to apply machine learning methods to predict hospitalizations for SLE from electronic health record (EHR) data.

Methods

We identified patients with SLE in a longitudinal EHR-based cohort with ≥2 outpatient rheumatology visits between 2012 and 2019. We applied multiple machine learning methods to predict hospitalizations with a primary diagnosis code for SLE, including decision tree, random forest, naive Bayes, logistic regression, and an ensemble method. Candidate predictors were derived from structured EHR features, including demographics, laboratory tests, medications, ICD-9/10 codes for SLE manifestations, and healthcare utilization. We used two approaches to assess these variables over longitudinal follow-up, including the incorporation of lagged features to capture changes over time of clinical data. The performance of each model was evaluated by overall accuracy, the F statistic, and the area under the receiver operator curve (AUC).

Results

We identified 1996 patients with SLE. 4.6% were hospitalized for SLE in their most recent year of follow-up. Random forest models had highest performance in predicting SLE hospitalizations, with AUC 0.751 and AUC 0.772 for two approaches (averaging and progressive), respectively. The leading predictors of SLE hospitalizations included dsDNA positivity, C3 level, blood cell counts, and inflammatory markers as well as age and albumin.

Conclusion

We have demonstrated that machine learning methods can predict SLE hospitalizations. We identified key predictors of these events including known markers of SLE disease activity; further validation in external cohorts is warranted.

SUBMITTER: Jorge AM

PROVIDER: S-EPMC9547899 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Exploration of machine learning methods to predict systemic lupus erythematosus hospitalizations.

Jorge April M AM Smith Dylan D Wu Zhiyao Z Chowdhury Tashrif T Costenbader Karen K Zhang Yuqing Y Choi Hyon K HK Feldman Candace H CH Zhao Yijun Y

Lupus 20220714 11

<h4>Objectives</h4>Systemic lupus erythematosus (SLE) is a heterogeneous disease characterized by disease flares which can require hospitalization. Our objective was to apply machine learning methods to predict hospitalizations for SLE from electronic health record (EHR) data.<h4>Methods</h4>We identified patients with SLE in a longitudinal EHR-based cohort with ≥2 outpatient rheumatology visits between 2012 and 2019. We applied multiple machine learning methods to predict hospitalizations with ...[more]

PMID: 35835534

Similar Datasets

Project description:OBJECTIVE:Limited evidences are available on biomarkers to recognize Systemic Lupus erythematosus (SLE) patients at risk to develop erosive arthritis. Anti-citrullinated peptide antibodies (ACPA) have been widely investigated and identified in up to 50% of X-ray detected erosive arthritis; conversely, few studies evaluated anti-carbamylated proteins antibodies (anti-CarP). Here, we considered the application of machine learning models to identify relevant factors in the development of ultrasonography (US)-detected erosive damage in a large cohort of SLE patients with joint involvement. METHODS:We enrolled consecutive SLE patients with arthritis/arthralgia. All patients underwent joint (DAS28, STR) and laboratory assessment (detection of ACPA, anti-CarP, Rheumatoid Factor, SLE-related antibodies). The bone surfaces of metacarpophalangeal and proximal interphalangeal joints were assessed by US: the presence of erosions was registered with a dichotomous value (0/1), obtaining a total score (0-20). Concerning machine learning techniques, we applied and compared Logistic Regression and Decision Trees in conjunction with the feature selection Forward Wrapper method. RESULTS:We enrolled 120 SLE patients [M/F 8/112, median age 47.0 years (IQR 15.0); median disease duration 120.0 months (IQR 156.0)], 73.3% of them referring at least one episode of arthritis. Erosive damage was identified in 25.8% of patients (mean±SD 0.7±1.6), all of them with clinically evident arthritis. We applied Logistic Regression in conjunction with the Forward Wrapper method, obtaining an AUC value of 0.806±0.02. As a result of the learning procedure, we evaluated the relevance of the different factors: this value was higher than 35% for ACPA and anti-CarP. CONCLUSION:The application of Machine Learning Models allowed to identify factors associated with US-detected erosive bone damage in a large SLE cohort and their relevance in determining this phenotype. Although the scope of this study is limited by the small sample size and its cross-sectional nature, the results suggest the relevance of ACPA and anti-CarP antibodies in the development of erosive damage as also pointed out in other studies.

Project description:ObjectiveThe Systemic Lupus International Collaborating Clinics (SLICC) frailty index (FI) predicts mortality and damage accrual in systemic lupus erythematosus (SLE), but its association with hospitalizations has not been described. Our objective was to estimate the association of baseline SLICC-FI values with future hospitalizations in the SLICC inception cohort.MethodsBaseline SLICC-FI scores were calculated. The number and duration of inpatient hospitalizations during follow-up were recorded. Negative binomial regression was used to estimate the association between baseline SLICC-FI values and the rate of hospitalizations per patient-year of follow-up. Linear regression was used to estimate the association of baseline SLICC-FI scores with the proportion of follow-up time spent in the hospital. Multivariable models were adjusted for relevant baseline characteristics.ResultsThe 1,549 patients with SLE eligible for this analysis were mostly female (88.7%), with a mean ± SD age of 35.7 ± 13.3 years and a median disease duration of 1.2 years (interquartile range 0.9-1.5) at baseline. Mean ± SD baseline SLICC-FI was 0.17 ± 0.08. During mean ± SD follow-up of 7.2 ± 3.7 years, 614 patients (39.6%) experienced 1,570 hospitalizations. Higher baseline SLICC-FI values (per 0.05 increment) were associated with more frequent hospitalizations during follow-up, with an incidence rate ratio of 1.21 (95% confidence interval [95% CI] 1.13-1.30) after adjustment for baseline age, sex, glucocorticoid use, immunosuppressive use, ethnicity/location, SLE Disease Activity Index 2000 score, SLICC/American College of Rheumatology Damage Index score, and disease duration. Among patients with ≥1 hospitalization, higher baseline SLICC-FI values predicted a greater proportion of follow-up time spent hospitalized (relative rate 1.09 [95% CI 1.02-1.16]).ConclusionThe SLICC-FI predicts future hospitalizations among incident SLE patients, further supporting the SLICC-FI as a valid health measure in SLE.

Project description:ObjectivesA novel longitudinal clustering technique was applied to comprehensive autoantibody data from a large, well-characterised, multinational inception systemic lupus erythematosus (SLE) cohort to determine profiles predictive of clinical outcomes.MethodsDemographic, clinical and serological data from 805 patients with SLE obtained within 15 months of diagnosis and at 3-year and 5-year follow-up were included. For each visit, sera were assessed for 29 antinuclear antibodies (ANA) immunofluorescence patterns and 20 autoantibodies. K-means clustering on principal component analysis-transformed longitudinal autoantibody profiles identified discrete phenotypic clusters. One-way analysis of variance compared cluster enrolment demographics and clinical outcomes at 10-year follow-up. Cox proportional hazards model estimated the HR for survival adjusting for age of disease onset.ResultsCluster 1 (n=137, high frequency of anti-Smith, anti-U1RNP, AC-5 (large nuclear speckled pattern) and high ANA titres) had the highest cumulative disease activity and immunosuppressants/biologics use at year 10. Cluster 2 (n=376, low anti-double stranded DNA (dsDNA) and ANA titres) had the lowest disease activity, frequency of lupus nephritis and immunosuppressants/biologics use. Cluster 3 (n=80, highest frequency of all five antiphospholipid antibodies) had the highest frequency of seizures and hypocomplementaemia. Cluster 4 (n=212) also had high disease activity and was characterised by multiple autoantibody reactivity including to antihistone, anti-dsDNA, antiribosomal P, anti-Sjögren syndrome antigen A or Ro60, anti-Sjögren syndrome antigen B or La, anti-Ro52/Tripartite Motif Protein 21, antiproliferating cell nuclear antigen and anticentromere B). Clusters 1 (adjusted HR 2.60 (95% CI 1.12 to 6.05), p=0.03) and 3 (adjusted HR 2.87 (95% CI 1.22 to 6.74), p=0.02) had lower survival compared with cluster 2.ConclusionFour discrete SLE patient longitudinal autoantibody clusters were predictive of long-term disease activity, organ involvement, treatment requirements and mortality risk.

Project description:Systemic lupus erythematosus (SLE) is a complex autoimmune disease that affects several organs and causes variable clinical symptoms. Exploring new insights on genetic factors may help reveal SLE etiology and improve the survival of SLE patients. The current study is designed to identify key genes involved in SLE and develop potential diagnostic biomarkers for SLE in clinical practice. Expression data of all genes of SLE and control samples in GSE65391 and GSE72509 datasets were downloaded from the Gene Expression Omnibus (GEO) database. A total of 11 accurate differentially expressed genes (DEGs) were identified by the "limma" and "RobustRankAggreg" R package. All these genes were functionally associated with several immune-related biological processes and a single KEGG (Kyoto Encyclopedia of Genes and Genome) pathway of necroptosis. The PPI analysis showed that IFI44, IFI44L, EIF2AK2, IFIT3, IFITM3, ZBP1, TRIM22, PRIC285, XAF1, and PARP9 could interact with each other. In addition, the expression patterns of these DEGs were found to be consistent in GSE39088. Moreover, Receiver operating characteristic (ROC) curves analysis indicated that all these DEGs could serve as potential diagnostic biomarkers according to the area under the ROC curve (AUC) values. Furthermore, we constructed the transcription factor (TF)-diagnostic biomarker-microRNA (miRNA) network composed of 278 nodes and 405 edges, and a drug-diagnostic biomarker network consisting of 218 nodes and 459 edges. To investigate the relationship between diagnostic biomarkers and the immune system, we evaluated the immune infiltration landscape of SLE and control samples from GSE6539. Finally, using a variety of machine learning methods, IFI44 was determined to be the optimal diagnostic biomarker of SLE and then verified by quantitative real-time PCR (qRT-PCR) in an independent cohort. Our findings may benefit the diagnosis of patients with SLE and guide in developing novel targeted therapy in treating SLE patients.

Dataset Information

Exploration of machine learning methods to predict systemic lupus erythematosus hospitalizations.

Objectives

Methods

Results

Conclusion

Publications

Exploration of machine learning methods to predict systemic lupus erythematosus hospitalizations.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets