Rapid identification of inflammatory arthritis and associated adverse events following immune checkpoint therapy: a machine learning approach.

Introduction: Immune checkpoint inhibitor-induced inflammatory arthritis (ICI-IA) poses a major clinical challenge to ICI therapy for cancer, with 13% of cases halting ICI therapy and ICI-IA being difficult to identify for timely referral to a rheumatologist. The objective of this study was to rapidly identify ICI-IA patients in clinical data and assess associated immune-related adverse events (irAEs) and risk factors. Methods: We conducted a retrospective study of the electronic health records (EHRs) of 89 patients who developed ICI-IA out of 2451 cancer patients who received ICI therapy at Northwestern University between March 2011 to January 2021. Logistic regression and random forest machine learning models were trained on all EHR diagnoses, labs, medications, and procedures to identify ICI-IA patients and EHR codes indicating ICI-IA. Multivariate logistic regression was then used to test associations between ICI-IA and cancer type, ICI regimen, and comorbid irAEs. Results: Logistic regression and random forest models identified ICI-IA patients with accuracies of 0.79 and 0.80, respectively. Key EHR features from the random forest model included ICI-IA relevant features (joint pain, steroid prescription, rheumatoid factor tests) and features suggesting comorbid irAEs (thyroid function tests, pruritus, triamcinolone prescription). Compared to 871 adjudicated ICI patients who did not develop arthritis, ICI-IA patients had higher odds of developing cutaneous (odds ratio [OR]=2.66; 95% Confidence Interval [CI] 1.63-4.35), endocrine (OR=2.09; 95% CI 1.15-3.80), or gastrointestinal (OR=2.88; 95% CI 1.76-4.72) irAEs adjusting for demographics, cancer type, and ICI regimen. Melanoma (OR=1.99; 95% CI 1.08-3.65) and renal cell carcinoma (OR=2.03; 95% CI 1.06-3.84) patients were more likely to develop ICI-IA compared to lung cancer patients. Patients on nivolumab+ipilimumab were more likely to develop ICI-IA compared to patients on pembrolizumab (OR=1.86; 95% CI 1.01-3.43). Discussion: Our machine learning models rapidly identified patients with ICI-IA in EHR data and elucidated clinical features indicative of comorbid irAEs. Patients with ICI-IA were significantly more likely to also develop cutaneous, endocrine, and gastrointestinal irAEs during their clinical course compared to ICI therapy patients without ICI-IA.

Cost Implications of Insurance Associated Disparities in Post-Acute Traumatic Brain and Spinal Cord Injury Rehabilitation.

Abstract Post-acute care after spinal cord injury (SCI) or traumatic brain injury (TBI) influences neurological function regained. Inpatient rehabilitation facilities (IRFs) have more intensive care and result in lower mortality and better functional outcomes compared with skilled nursing facilities (SNFs). This study sought to quantify inpatient rehabilitation access by insurance and estimate the cost implications. We conducted a retrospective observational cohort study utilizing 2015-2017 California Office of Statewide Health Planning and Development database of injured adults with SCI and/or TBI. The primary predictor was insurance status. The outcome was discharge destination (home, IRFs, SNFs, long-term acute care [LTAC]) modeled using multi-variable multinomial mixed-effects logistic regression controlling for age, diagnosis, Weighted Elixhauser Comorbidity Index, and New Injury Severity Score. Cost of care for discharge to IRFs versus SNFs was estimated by adjusted quantile regression. Cost simulation predicted the adjusted cost difference if all publicly insured participants were discharged to an IRF. We identified 83,230 patients with an injury mechanism and a primary acute care hospitalization diagnosis of TBI (90.9%), SCI (8.3%), or both (0.8%) who were discharged to an IRF, SNF, LTAC, or home. Publicly insured patients were more likely than privately insured patients to go to SNFs versus IRFs (odds ratio [OR]: 2.17, 95% confidence interval [CI 2.01-2.34]). Sub-group analysis of 6416 participants showed an adjusted median total cost difference of $18,461 (95% CI [$5,908-$38,064]) and adjusted cost-per-day of the post-acute encounter of $1,045 (95% CI [$752-$2,399]) higher for discharge to IRFs versus SNFs. Cost simulation demonstrated an additional adjusted cost of $364M annually for universal IRF access for the publicly insured. Publicly insured SCI and TBI Californians are less frequently discharged to IRFs compared with their privately insured counterparts resulting in a lower short-term cost of care. However, the consequences of decreased intensive rehabilitation utilization in terms of functional recovery and long-term cost implications require further investigation.

Ultraviolet light induces increased T cell activation in lupus-prone mice via type I IFN-dependent inhibition of T regulatory cells.

Ultraviolet (UV) light is a known trigger of skin and possibly systemic inflammation in systemic lupus erythematosus (SLE) patients. Although type I interferons (IFN) are upregulated in SLE skin after UV exposure, the mechanisms to explain increased UVB-induced inflammation remain unclear. This paper compares the role of type I IFNs in regulating immune cell activation between wild-type and lupus-prone mice following UVB exposure. 10-week old female lupus-prone (NZM2328), wild-type (BALB/c) and iNZM mice (lack a functional type I IFN receptor on NZM2328 background) were treated on their dorsal skin with 100 mJ/cm2 of UVB for 5 consecutive days. Following UVB treatment, draining lymph node cell populations were characterized via flow cytometry and suppression assays; treated skin was examined for changes in expression of type I IFN genes. Only NZM2328 mice showed an increase in T cell numbers and activation 2 weeks post UVB exposure. This was preceded by a significant increase in UVB-induced type I IFN expression in NZM2328 mice compared to BALB/c mice. Following UVB exposure, both BALB/c and iNZM mice demonstrated an increase in functional T regulatory (TReg) cells; however, this was not seen in NZM2328 mice. These data suggest a skewed UVB-mediated T cell response in lupus-prone mice where activation of T cells is enhanced secondary to a type I IFN-dependent suppression of TReg cells. Thus, we propose type I IFNs are important for UVB-induced inflammation in lupus-prone mice and may be an effective target for prevention of UVB-mediated flares.

TLR7-Mediated Lupus Nephritis Is Independent of Type I IFN Signaling.

Systemic lupus erythematosus is an autoimmune disease characterized by increased type I IFNs, autoantibodies, and inflammatory-mediated multiorgan damage. TLR7 activation is an important contributor to systemic lupus erythematosus pathogenesis, but the mechanisms by which type I IFNs participate in TLR7-driven pathologic conditions remain uncertain. In this study, we examined the requirement for type I IFNs in TLR7-stimulated lupus nephritis. Lupus-prone NZM2328, INZM (which lack a functional type I IFN receptor), and NZM2328 IL-1ß-/- mice were treated at 10 wk of age on the right ear with R848 (TLR7 agonist) or control (DMSO). Autoantibody production and proteinuria were assessed throughout treatment. Multiorgan inflammation was assessed at the time of decline in health. Renal infiltrates and mRNA expression were also examined after 14 d of treatment. Both NZM2328 and INZM mice exhibited a decline in survival after 3-4 wk of R848 but not vehicle treatment. Development of splenomegaly and liver inflammation were dependent on type I IFN. Interestingly, autoantibody production, early renal infiltration of dendritic cells, upregulation of IL-1ß, and lupus nephritis occurred independent of type I IFN signaling. Development of TLR7-driven lupus nephritis was not abolished by the deletion of IL-1ß. Thus, although IFN-α is sufficient to induce nephritis acceleration, our data emphasize a critical role for IFN-independent signaling in TLR7-mediated lupus nephritis. Further, despite upregulation of IL-1ß after TLR7 stimulation, deletion of IL-1ß is not sufficient to reduce lupus nephritis development in this model.