-
JMIR Formative Research Jun 2024Psoriasis vulgaris (PsV) and psoriatic arthritis (PsA) are complex, multifactorial diseases significantly impacting health and quality of life. Predicting treatment...
Using Automated Machine Learning to Predict Necessary Upcoming Therapy Changes in Patients With Psoriasis Vulgaris and Psoriatic Arthritis and Uncover New Influences on Disease Progression: Retrospective Study.
BACKGROUND
Psoriasis vulgaris (PsV) and psoriatic arthritis (PsA) are complex, multifactorial diseases significantly impacting health and quality of life. Predicting treatment response and disease progression is crucial for optimizing therapeutic interventions, yet challenging. Automated machine learning (AutoML) technology shows promise for rapidly creating accurate predictive models based on patient features and treatment data.
OBJECTIVE
This study aims to develop highly accurate machine learning (ML) models using AutoML to address key clinical questions for PsV and PsA patients, including predicting therapy changes, identifying reasons for therapy changes, and factors influencing skin lesion progression or an abnormal Bath Ankylosing Spondylitis Disease Activity Index (BASDAI) score.
METHODS
Clinical study data from 309 PsV and PsA patients were extensively prepared and analyzed using AutoML to build and select the most accurate predictive models for each variable of interest.
RESULTS
Therapy change at 24 weeks follow-up was modeled using the extreme gradient boosted trees classifier with early stopping (area under the receiver operating characteristic curve [AUC] of 0.9078 and logarithmic loss [LogLoss] of 0.3955 for the holdout partition). Key influencing factors included the initial systemic therapeutic agent, the Classification Criteria for Psoriatic Arthritis score at baseline, and changes in quality of life. An average blender incorporating three models (gradient boosted trees classifier, ExtraTrees classifier, and Eureqa generalized additive model classifier) with an AUC of 0.8750 and LogLoss of 0.4603 was used to predict therapy changes for 2 hypothetical patients, highlighting the significance of these factors. Treatments such as methotrexate or specific biologicals showed a lower propensity for change. An average blender of a random forest classifier, an extreme gradient boosted trees classifier, and a Eureqa classifier (AUC of 0.9241 and LogLoss of 0.4498) was used to estimate PASI (Psoriasis Area and Severity Index) change after 24 weeks. Primary predictors included the initial PASI score, change in pruritus levels, and change in therapy. A lower initial PASI score and consistently low pruritus were associated with better outcomes. BASDAI classification at onset was analyzed using an average blender of a Eureqa generalized additive model classifier, an extreme gradient boosted trees classifier with early stopping, and a dropout additive regression trees classifier with an AUC of 0.8274 and LogLoss of 0.5037. Influential factors included initial pain, disease activity, and Hospital Anxiety and Depression Scale scores for depression and anxiety. Increased pain, disease activity, and psychological distress generally led to higher BASDAI scores.
CONCLUSIONS
The practical implications of these models for clinical decision-making in PsV and PsA can guide early investigation and treatment, contributing to improved patient outcomes.
PubMed: 38738977
DOI: 10.2196/55855 -
Frontiers in Medicine 2024Ankylosing spondylitis (AS) is a chronic, inflammatory, and autoimmune disease. This condition primarily affects the axial skeleton and presents direct foot involvement,...
BACKGROUND
Ankylosing spondylitis (AS) is a chronic, inflammatory, and autoimmune disease. This condition primarily affects the axial skeleton and presents direct foot involvement, such as Achilles enthesitis or plantar fascia involvement.
OBJECTIVE
This study aimed to investigate the impact of foot health on the quality of life of individuals with AS compared to a control group without AS.
MATERIALS AND METHODS
A sample of 112 subjects was recruited, with a mean age of 46.80 ± 10.49 years, divided into two groups: 56 individuals with AS (cases) and 56 individuals without AS (controls). Demographic data were collected, and the scores obtained in the Foot Health Status Questionnaire domains were recorded.
RESULTS
Of the participants, 27.79% ( = 30) were men and 73.21% ( = 82) were women. The mean age in the group was 46.80 ± 10.49. Significant differences ( < 0.05) were found in the domains of foot function, foot pain, footwear, overall foot health, general health-related physical activity, and social capacity between the AS group and the control group.
CONCLUSION
Individuals with AS exhibited a decreased quality of life, as indicated by their Foot Health Status Questionnaire scores.
PubMed: 38737760
DOI: 10.3389/fmed.2024.1355803 -
Journal of Clinical Medicine May 2024Patients with inflammatory arthropathies exhibit an increased cardiovascular disease (CVD) risk as compared to the general population, which is not fully quantified by...
Patients with inflammatory arthropathies exhibit an increased cardiovascular disease (CVD) risk as compared to the general population, which is not fully quantified by the conventional CVD risk scores. Biotechnological disease-modifying drugs (bDMARDs) have proved beneficial to reduce the overall CVD risk in these patients, although CVD remains a major cause of increased mortality. Since it has been shown that pulse wave parameters and in particular carotid-femoral pulse wave velocity (cfPWV) are predictors of CVD risk, the aim of this study was to evaluate their changes in patients with inflammatory arthropathies before and after bDMARD therapy. Pulse wave parameters were evaluated with applanation tonometry in patients with ankylosing spondylitis (AS), psoriatic arthritis (PsA), and rheumatoid arthritis (RA), before and after two years of bDMARD therapy. At baseline, cfPWV was significantly associated with age ( < 0.001) and, among pulse wave parameters, the subendocardial viability ratio was negatively associated with C-reactive protein (CRP) ( = 0.04) and the HAQ-disability index ( = 0.03). At baseline, PsA patients showed a higher percentage of male subjects, higher CRP, and the highest cfPWV values ( = 0.048). After two years, pulse wave parameters improved in the AS and RA groups, but not in the PsA group. Our data confirm that pulse wave parameters are potentially reversible after bDMARD therapy, as they improved in AS and RA patients. In PsA patients, there were no changes, which may be due to the higher percentage of male subjects and higher baseline cfPWV values.
PubMed: 38731213
DOI: 10.3390/jcm13092684 -
RMD Open May 2024There is a paucity of data on long-term clinical responses in patients with non-radiographic axial spondyloarthritis (nr-axSpA) based on their baseline objective signs... (Randomized Controlled Trial)
Randomized Controlled Trial
OBJECTIVE
There is a paucity of data on long-term clinical responses in patients with non-radiographic axial spondyloarthritis (nr-axSpA) based on their baseline objective signs of inflammation such as MRI or C-reactive protein (CRP) levels. This study reports clinical outcomes up to 3 years of the C-axSpAnd trial, including safety follow-up extension (SFE) from Weeks 52 to 156, stratified by patients' baseline MRI and CRP status.
METHODS
C-axSpAnd (NCT02552212) was a phase 3, multicentre study that evaluated certolizumab pegol (CZP) in patients with active nr-axSpA who had active sacroiliitis on MRI and/or elevated CRP. In this post hoc analysis, efficacy outcomes are reported to Week 156 of C-axSpAnd for patients stratified according to their MRI and CRP status at Week 0 (MRI+/CRP-, MRI-/CRP+ and MRI+/CRP+).
RESULTS
Across all outcome measures, including major improvement in Ankylosing Spondylitis Disease Activity Score (ASDAS-MI) and Assessment of SpondyloArthritis international Society criteria ≥40% response (ASAS40), outcomes were generally sustained in SFE patients from Week 52 to Week 156. MRI+/CRP+ patients showed numerically higher or comparable responses relative to MRI-/CRP+ and MRI+/CRP- patients at Weeks 52 and 156; however, all three subgroups demonstrated substantial improvements from Week 0 (in CZP-randomised patients, ASDAS-MI at Week 156 [observed case]: MRI+/CRP+: 73.1%, MRI-/CRP+: 52.2%, MRI+/CRP-: 30.4%; ASAS40: MRI+/CRP+: 76.9%, MRI-/CRP+: 62.5%, MRI+/CRP-: 65.2%).
CONCLUSIONS
In patients with nr-axSpA and objective signs of inflammation, long-term clinical outcomes achieved after 1 year were generally sustained at 3 years across MRI+/CRP+, MRI-/CRP+ and MRI+/CRP- subgroups.
Topics: Humans; Certolizumab Pegol; Magnetic Resonance Imaging; C-Reactive Protein; Male; Female; Adult; Treatment Outcome; Axial Spondyloarthritis; Middle Aged; Biomarkers; Severity of Illness Index
PubMed: 38724259
DOI: 10.1136/rmdopen-2023-003884 -
Clinical Case Reports May 2024Neuromyelitis optica spectrum disorder is an autoimmune disease, rarely presents with antiphospholipid syndrome. Diagnosis and management of NMOSD are challenging in the...
KEY CLINICAL MESSAGE
Neuromyelitis optica spectrum disorder is an autoimmune disease, rarely presents with antiphospholipid syndrome. Diagnosis and management of NMOSD are challenging in the background of diverse presentations, especially in resource-limited settings.
ABSTRACT
Neuromyelitis optica spectrum disorder (NMOSD) is a progressive demyelinating autoimmune condition resulting from the autoantibodies produced against aquaporin-4 (AQP-4) proteins which are widely distributed in astrocytes in the nervous system. In the setting of NMOSD, it is very crucial to consider other autoimmune diseases as differential diagnoses or co-occurrences due to the diversity of symptoms. NMOSD co-exists with other autoimmune diseases such as myasthenia gravis, thyroid disease, ankylosing spondylitis, pernicious anemia, thrombotic thrombocytopenic purpura, ulcerative colitis, and systemic lupus erythematosus. Few cases of antiphospholipid syndrome co-existing with NMOSD have been reported. In resource-limited settings, the published data are scarce, and therefore, autoimmune diseases are poorly studied. Therefore, late diagnosis and delayed treatment initiation pose long-term sequelae and hence poor prognosis. Here, we present a case of an African woman in her early 40s presenting with bilateral progressive loss of vision, transverse myelitis, extensive longitudinal hyperintense T2 cervical lesion, and AQP-4 autoantibody keeping with NMOSD. The co-existence of antiphospholipid syndrome, in this case, was supported by a history of recurrent pregnancy loss and positive antiphospholipid antibodies. This case underscores the importance of individualized-based medicine, especially in resource-limited settings.
PubMed: 38721556
DOI: 10.1002/ccr3.8818 -
Clinical, Cosmetic and Investigational... 2024Previous studies have suggested a relationship between autoimmune diseases and the risk of facial skin aging. However, evidence from population-based studies on this...
PURPOSE
Previous studies have suggested a relationship between autoimmune diseases and the risk of facial skin aging. However, evidence from population-based studies on this topic is limited, leaving the causal association between these factors unknown. This study aimed to systematically evaluate the causal effects of 18 autoimmune diseases on the risk of facial skin aging, aim of providing strategies to mitigate early facial aging in patients with autoimmune diseases.
PATIENTS AND METHODS
We conducted univariate Mendelian randomization (UVMR) analyses to examine the causal relationship between 18 autoimmune diseases and facial aging using publicly available summary data from genome-wide association studies (GWASs). We also conducted multivariate Mendelian randomization (MVMR) analyses to adjust for confounding factors, including smoking, alcohol consumption, and body mass index (BMI).
RESULTS
The main inverse variance weighted (IVW) method revealed that genetically proxied ankylosing spondylitis (AS) (OR 1.017; 95% CI: 1.003-1.031; =0.018), sicca syndrome (SS) (OR 1.008; 95% CI: 1.005-1.011; = 2.66×10), systemic lupus erythematosus (SLE) (OR 1.006; 95% 1.001-1.011; =0.014), multiple sclerosis (MS) (OR 1.004; 95% CI: 1.001-1.007; =0.021), primary sclerosing cholangitis (PSC) (OR 1.002; 95% CI: 1.000-1.004; =0.023), and celiac disease (CeD) (OR 1.002; 95% CI: 1.001-1.004; =0.009) were significantly associated with higher risk of facial aging. After adjusting for potential confounding factors, the association persisted between AS, SLE, and CeD.
CONCLUSION
These findings indicated that autoimmune diseases play a causal role in facial skin aging. Therefore, patients with autoimmune diseases should take appropriate measures to prevent early facial aging.
PubMed: 38716190
DOI: 10.2147/CCID.S456126 -
Cureus Apr 2024It is rare for quadriparesis to manifest as a symptom of tropical illnesses. With a history of only one fever episode one week prior, our patient, a 48-year-old...
It is rare for quadriparesis to manifest as a symptom of tropical illnesses. With a history of only one fever episode one week prior, our patient, a 48-year-old male with obesity and prediabetes, who was also known to have ankylosing spondylitis, presented with acute onset flaccid quadriparesis. He did not exhibit any additional symptoms of dengue, such as bleeding tendencies, petechial rashes, thrombocytopenia, or febrile episodes. Upon examination, it was discovered that he had extremely low serum potassium levels and was dengue non-specific antigen 1 (NS1) positive. His hyperinsulinemia, as seen by elevated C peptide levels, most likely caused a transcellular shift that was then triggered by the dengue infection, leading to hypokalemic paralysis.
PubMed: 38716013
DOI: 10.7759/cureus.57739 -
European Journal of Case Reports in... 2024Autoimmune diseases are not contraindications for immune checkpoint inhibitors (ICI) therapy in patients with cancer. However, immune-related adverse events (irAEs) are...
BACKGROUND
Autoimmune diseases are not contraindications for immune checkpoint inhibitors (ICI) therapy in patients with cancer. However, immune-related adverse events (irAEs) are frequently observed in patients receiving ICIs including dermatitis, thyroiditis, colitis, and pneumonitis. Thrombocytopenic purpura, aplasia, and haemophagocytic lymphohistiocytosis (HLH) are rarely observed during ICIs.
CASE DESCRIPTION
We report the case of a male patient with pre-existing untreated HLA B27 and ankylosing spondylitis with gastric cancer and liver metastases. The 79-year-old man was treated with anti-HER2 trastuzumab and anti-PD-1 nivolumab. Seventeen days after the seventh cycle of treatment, he presented at the emergency department with acute fever, confusion, and hypotension. Laboratory results showed pancytopenia, and elevation of ferritin and triglyceride. No infections were detected. Although not seen in a bone marrow biopsy, clinical presentation, and absence of infection, together with an H-score of 263, indicated HLH. The patient was treated with dexamethasone for four days and discharged on a tapering dose of steroids. At the two-month follow-up, clinical presentation was normal and blood test almost normalised. At 8 months, no liver metastases were observed.
CONCLUSIONS
In a patient with a pre-existing autoimmune condition, immunotherapy led to the development of HLH, which was controlled by glucocorticoid. Absence of the feature of haemophagocytosis in the bone marrow biopsy did not exclude the diagnosis, as HLH can occur in the spleen or in the liver. Glucocorticoid therapy did not prevent the anti-cancer effect of ICIs, and liver metastases disappeared 8 months post-HLH. This case warrants further research on the interplay between autoimmunity and ICI response, as well as ICI-induced irAEs.
LEARNING POINTS
Haemophagocytic lymphohistiocytosis (HLH) post seventh cycle of trastuzumab (anti-HER2) and nivolumab (anti-PD-1) was controlled with glucocorticoid.Breach of tolerance was due to immunotherapy-induced HLH in a patient with pre-existing autoimmune condition (HLA B27- positive ankylosing spondylitis).There was a complete disappearance of liver metastases 8 months post-HLH.
PubMed: 38715877
DOI: 10.12890/2024_004370 -
General Hospital Psychiatry 2024To investigate whether the association between depression and inflammatory joint disease (IJD; rheumatoid arthritis [RA], psoriatic arthritis [PsA], ankylosing...
OBJECTIVE
To investigate whether the association between depression and inflammatory joint disease (IJD; rheumatoid arthritis [RA], psoriatic arthritis [PsA], ankylosing spondylitis/spondyloarthropathies [AS], and juvenile idiopathic arthritis [JIA]) is affected by the severity or treatment-resistance of depression.
METHOD
Parallel cohort studies and case-control studies among 600,404 patients with a depressive episode identified in Swedish nationwide administrative registers. Prospective and retrospective risk for IJD in patients with depression was compared to matched population comparators, and the same associations were investigated in severe or treatment-resistant depression. Analyses were adjusted for comorbidities and sociodemographic covariates.
RESULTS
Patients with depression had an increased risk for later IJD compared to population comparators (adjusted hazard ratio (aHR) for any IJD 1.34 [95% CI 1.30-1.39]; for RA 1.27 [1.15-1.41]; PsA 1.45 [1.29-1.63]; AS 1.32 [1.15-1.52]). In case-control studies, patients with depression more frequently had a history of IJD compared to population controls (adjusted odds ratio (aOR) for any IJD 1.43 [1.37-1.50]; RA 1.39 [1.29-1.49]; PsA 1.59 [1.46-1.73]; AS 1.49 [1.36-1.64]; JIA 1.52 [1.35-1.71]). These associations were not significantly different for severe depression or TRD.
CONCLUSION
IJD and depression are bidirectionally associated, but this association does not seem to be influenced by the severity or treatment resistance of depression.
Topics: Humans; Sweden; Female; Male; Case-Control Studies; Adult; Middle Aged; Depressive Disorder, Treatment-Resistant; Comorbidity; Arthritis, Rheumatoid; Arthritis, Psoriatic; Aged; Registries; Severity of Illness Index; Spondylitis, Ankylosing; Arthritis, Juvenile; Young Adult; Cohort Studies; Adolescent
PubMed: 38714100
DOI: 10.1016/j.genhosppsych.2024.04.007 -
Frontiers in Immunology 2024Previous research has partially revealed distinct gut microbiota in ankylosing spondylitis (AS). In this study, we performed non-targeted fecal metabolomics in AS in...
OBJECTIVE
Previous research has partially revealed distinct gut microbiota in ankylosing spondylitis (AS). In this study, we performed non-targeted fecal metabolomics in AS in order to discover the microbiome-metabolome interface in AS. Based on prospective cohort studies, we further explored the impact of the tumor necrosis factor inhibitor (TNFi) on the gut microbiota and metabolites in AS.
METHODS
To further understand the gut microbiota and metabolites in AS, along with the influence of TNFi, we initiated a prospective cohort study. Fecal samples were collected from 29 patients with AS before and after TNFi therapy and 31 healthy controls. Metagenomic and metabolomic experiments were performed on the fecal samples; moreover, validation experiments were conducted based on the association between the microbiota and metabolites.
RESULTS
A total of 7,703 species were annotated using the metagenomic sequencing system and by profiling the microbial community taxonomic composition, while 50,046 metabolites were identified using metabolite profiling. Differential microbials and metabolites were discovered between patients with AS and healthy controls. Moreover, TNFi was confirmed to partially restore the gut microbiota and the metabolites. Multi-omics analysis of the microbiota and metabolites was performed to determine the associations between the differential microbes and metabolites, identifying compounds such as oxypurinol and biotin, which were correlated with the inhibition of the pathogenic bacteria and the promotion of the probiotic bacteria . Through experimental studies, the relationship between microbes and metabolites was further confirmed, and the impact of these two types of microbes on the enterocytes and the inflammatory cytokine interleukin-18 (IL-18) was explored.
CONCLUSION
In summary, multi-omics exploration elucidated the impact of TNFi on the gut microbiota and metabolites and proposed a novel therapeutic perspective: supplementation of compounds to inhibit potential pathogenic bacteria and to promote potential probiotics, therefore controlling inflammation in AS.
Topics: Humans; Spondylitis, Ankylosing; Gastrointestinal Microbiome; Probiotics; Male; Female; Metabolome; Adult; Feces; Metagenomics; Middle Aged; Prospective Studies; Metabolomics; Bacteria; Tumor Necrosis Factor Inhibitors
PubMed: 38711505
DOI: 10.3389/fimmu.2024.1369116