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.

Sex Differences in Pain and Quantitative Sensory Testing in Patients With Rheumatoid Arthritis.

OBJECTIVE: Women with rheumatoid arthritis (RA) have higher pain and worse functional outcomes compared to men, even when treated with similar medications. The objective of this study was to identify sex differences in pain intensity, pain interference, and quantitative sensory tests (QST), which are independent of inflammation, in patients with RA. METHODS: This study is a post hoc analysis of participants in the Central Pain in Rheumatoid Arthritis cohort. Pain intensity was assessed using a 0-10 numeric rating scale. Pain interference was measured using a Patient-Reported Outcomes Measurement Information System computerized adaptive test. QST included pressure pain detection thresholds, temporal summation, and conditioned pain modulation. Women and men were compared using multiple linear regression, adjusted for age, education, race, research site, depression, obesity, RA disease duration, swollen joint count, and C-reactive protein. RESULTS: Mean ± SD pain intensity was 5.32 ± 2.29 among women with RA, compared to 4.60 ± 2.23 among men with RA (adjusted difference 0.83 [95% confidence interval (95% CI) 0.14, 1.53]). Women with RA had lower pressure pain detection thresholds at the trapezius (adjusted difference -1.22 [95% CI -1.73, -0.72]), wrist (adjusted difference -0.57 [95% CI -1.07, -0.06]), and knee (adjusted difference -1.10 [95% CI -2.00, -0.21]). No statistically significant differences in pain interference, temporal summation, and conditioned pain modulation were observed. CONCLUSION: Women reported higher pain intensity and lower pressure pain detection thresholds (higher pain sensitivity) than men. However, pain interference, temporal summation, and conditioned pain modulation did not differ between men and women.

Accuracy of the Apple watch for detection of AF: A multicenter experience.

INTRODUCTION: The Apple watch (AW) irregular rhythm notification (IRN) feature uses photoplethysmography to identify prolonged episodes of irregular rhythm suggestive of atrial fibrillation (AF). IRN is FDA cleared for those with no previous history of AF, however, these devices are increasingly being used for AF management.  The objective of the present study was to determine the accuracy of the IRN in subjects with a previous diagnosis of nonpermanent AF. METHODS: Subjects with a history of nonpermanent AF and either an insertable cardiac monitor (ICM) or cardiac implanted electronic device (CIED) with <5% ventricular pacing were fitted with an AW Series 5 for 6 months. AF episodes were compared between the ICM/CIED and IRN. The primary endpoints were sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of the IRN by subject for AF ≥1 h. Secondary endpoints were sensitivity and PPV by AF episode ≥1 h. Analysis was limited to a maximum of 10 ICM/CIED episodes per subject and included only those AF episodes occurring during active AW use confirmed by activity data. RESULTS: Thirty participants were enrolled. Mean age was 65.4 ± 12.2 years and 40% were female. There were 10 ICMs and 20 CIEDs. Eleven subjects had AF on ICM/CIED while the AW was worn, of whom 8 were detected by IRN. There were no false positive IRN detections by subject ("by subject" 72% sensitivity, 100% specificity, 100% PPV, and 90% NPV). Five subjects had AF only when the AW was not worn. There were a total of 70 AF episodes on ICM/CIED, 35 of which occurred while the AW was being worn. Of these, 21 were detected by IRN with 1 false positive ("by episode" sensitivity = 60.0%, PPV = 95.5%). CONCLUSION: In a population with known AF, the AW IRN had a low rate of false positive detections and high specificity. Sensitivity for detection by subject and by AF episode was lower. The current IRN algorithm appears accurate for AF screening as currently cleared, but increased sensitivity and wear times would be necessary for disease management.

Impact of pre-ablation weight loss on the success of catheter ablation for atrial fibrillation.

INTRODUCTION: Obesity is an established risk factor for recurrent atrial fibrillation (AF) after ablation. The impact of pre-procedure weight changes on freedom from AF (FFAF) after ablation in obese and nonobese patients is unknown. METHODS: A single-center retrospective cohort study of patients undergoing pulmonary vein isolation was performed. Before ablation, all candidates were encouraged to adopt healthy lifestyle habits according to American Heart Association guidelines, including weight loss, by their physician. The primary endpoint was FFAF through 1-year after completion of the 3-month blanking period. RESULTS: Of the 601 patients (68% male; average age 62.1 ± 10.3 years) included in analysis, 234 patients (38.9%) were obese (body mass index ≥ 30) and 315 (52.4%) had paroxysmal AF. FFAF was observed in 420 patients (69.9%) at 15 months. Percent change in weight that occurred during the year before ablation independently predicted FFAF through 15-months in all patients (adjusted odds ratio = 1.17, 95% confidence interval: 1.11-1.23). Subgroup analyses based on paroxysmal vs persistent AF, presence of obesity, and history of prior ablation were performed. Percent change in weight over the year before ablation was independently associated with FFAF in all subgroups except nonobese patients with persistent AF. CONCLUSION: Pre-ablation weight loss was associated with FFAF in both obese and nonobese patients. Further studies are needed to define the optimal approach to weight loss before AF ablation.

Sandwiched White Adipose Tissue: A Microphysiological System of Primary Human Adipose Tissue.

White adipose tissue (WAT) is a critical organ in both health and disease. However, physiologically faithful tissue culture models of primary human WAT remain limited, at best. In this study we describe a novel WAT culture system in which primary human WAT is sandwiched between tissue-engineered sheets of adipose-derived stromal cells. This construct, called "sandwiched white adipose tissue" (SWAT), can be defined as a microphysiological system (MPS) since it is a tissue-engineered, multicellular, three-dimensional organ construct produced using human cells. We validated SWAT against the National Institutes of Health MPS standards and found that SWAT is viable in culture for 8 weeks, retains physiologic responses to exogenous signaling, secretes adipokines, and engrafts into animal models. These attributes position SWAT as a powerful tool for the study of WAT physiology, pathophysiology, personalized medicine, and pharmaceutical development.