Systemic lupus erythematosus phenotypes formed from machine learning with a specific focus on cognitive impairment

Abstract

Objective To phenotype SLE based on symptom burden (disease damage, system involvement and patient reported outcomes), with a specific focus on objective and subjective cognitive function. Methods SLE patients aged 18–65 underwent objective cognitive assessment using the ACR Neuropsychological Battery (ACR-NB) and data was collected on demographic and clinical variables, disease burden/activity, health related quality of life (HRQoL), depression, anxiety, fatigue and perceived cognitive deficits. Similarity network fusion (SNF) was used to identify patient subtypes. Differences between the subtypes were evaluated using Kruskal-Wallis and chi-square tests. Results Of the 238 patients, 90% were female, mean age 41 ± 12 and disease duration 14 ± 10 years at the study visit. The SNF analysis defined two subtypes (A and B) with distinct patterns in objective and subjective cognitive function, disease burden/damage, HRQoL, anxiety and depression. Subtype A performed worst on all significantly different tests of objective cognitive function (p < 0.03) compared with subtype B. Subtype A also, had greater levels of subjective cognitive function (p < 0.001), disease burden/damage (p < 0.04), HRQoL (p < 0.001) and psychiatric measures (p < 0.001) compared with subtype B. Conclusion This study demonstrates the complexity of cognitive impairment (CI) in SLE and that individual, multi-factorial phenotypes exist. Those with greater disease burden, from SLE specific factors or other factors associated with chronic conditions, report poorer cognitive functioning and perform worse on objective cognitive measures. By exploring different ways of phenotyping SLE we may better define CI in SLE. Ultimately, this will aid our understanding of personalised CI trajectories and identification of appropriate treatments.

Cognitive Performance in Patients with Systemic Lupus Erythematosus Using the Ped-ANAM

“…A systematic review showed a pooled prevalence of CI of 39% [ 26 ]. In studies using the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA), the CI prevalence was 11.1% based on the MMSE and 61.1% based on the MoCA [ 36 , 37 ]. The two batteries (MMSE and MoCA), as well as the ANAM batteries, are screening tools for cognitive function rather than diagnostic tests [ 35 , 36 , 37 ].…”

“…In studies using the Mini-Mental State Examination (MMSE) and the Montreal Cognitive Assessment (MoCA), the CI prevalence was 11.1% based on the MMSE and 61.1% based on the MoCA [ 36 , 37 ]. The two batteries (MMSE and MoCA), as well as the ANAM batteries, are screening tools for cognitive function rather than diagnostic tests [ 35 , 36 , 37 ]. The assessment of CI through traditional batteries observed a prevalence ranging from 15% to 79% [ 26 ].…”

“…Assessment of CI in SLE is not standardized, and attribution of CI to SLE can be difficult, as medications, infections, metabolic disorders, and hypertension can also cause CI [ 31 , 36 , 37 ]. CI has been associated with a variety of clinical and laboratory features, such as disease activity, antiphospholipid antibodies, presence of neuropsychiatric manifestations, pain, depression, and anxiety [ 31 , 36 , 37 ]. In our study, disease activity and NPSLE were associated with CI in aSLE [ 27 , 28 , 29 , 30 ].…”

The Effects of Systemic Lupus–Related Cognitive Impairments on Activities of Daily Living and Life Role Participation: A Qualitative Framework Study

“…25 All participants met ACR revised criteria for the classification of SLE or three ACR criteria and a typical biopsy lesion of SLE, 4,26,27 Disease Activity Index-2000 28 and Systemic Lupus International Collaborating Clinics/ACR Damage Index, 29 respectively, and prednisone dose. Objective CI was measured using the modified ACR neuropsychological battery (ACR-NB) as described elsewhere 30 and subjective CI using the Perceived Deficits Questionnaire (PDQ-20). 31 Interview structure and analysis.…”

SVM-Based Model Combining Patients’ Reported Outcomes and Lymphocyte Phenotypes of Depression in Systemic Lupus Erythematosus

“…The occurrence and development of depression is a multi-step, time-dependent process caused by many factors, and no single factor can explain the outcome of depression in SLE patients. Moreover, it was reported that the predictive performance of a single factor was worse than that of multivariate predictive models [10,11]. Therefore, a depression risk prediction model should be constructed in conjunction with multidimensional factors to improve its sensitivity and specificity.…”