Machine learning to understand risks for severe COVID-19 outcomes: a retrospective cohort study of immune-mediated inflammatory diseases, immunomodulatory medications, and comorbidities in a large US health-care system.

BACKGROUND: In the context of immune-mediated inflammatory diseases (IMIDs), COVID-19 outcomes are incompletely understood and vary considerably depending on the patient population studied. We aimed to analyse severe COVID-19 outcomes and to investigate the effects of the pandemic time period and the risks associated with individual IMIDs, classes of immunomodulatory medications (IMMs), chronic comorbidities, and COVID-19 vaccination status. METHODS: In this retrospective cohort study, clinical data were derived from the electronic health records of an integrated health-care system serving patients in 51 hospitals and 1085 clinics across seven US states (Providence St Joseph Health). Data were observed for patients (no age restriction) with one or more IMID and for unmatched controls without IMIDs. COVID-19 was identified with a positive nucleic acid amplification test result for SARS-CoV-2. Two timeframes were analysed: March 1, 2020-Dec 25, 2021 (pre-omicron period), and Dec 26, 2021-Aug 30, 2022 (omicron-predominant period). Primary outcomes were hospitalisation, mechanical ventilation, and mortality in patients with COVID-19. Factors, including IMID diagnoses, comorbidities, long-term use of IMMs, and COVID-19 vaccination status, were analysed with multivariable logistic regression (LR) and extreme gradient boosting (XGB). FINDINGS: Of 2 167 656 patients tested for SARS-CoV-2, 290 855 (13·4%) had confirmed COVID-19: 15 397 (5·3%) patients with IMIDs and 275 458 (94·7%) without IMIDs. In the pre-omicron period, 169 993 (11·2%) of 1 517 295 people who were tested for COVID-19 tested positive, of whom 23 330 (13·7%) were hospitalised, 1072 (0·6%) received mechanical ventilation, and 5294 (3·1%) died. Compared with controls, patients with IMIDs and COVID-19 had higher rates of hospitalisation (1176 [14·6%] vs 22 154 [13·7%]; p=0·024) and mortality (314 [3·9%] vs 4980 [3·1%]; p<0·0001). In the omicron-predominant period, 120 862 (18·6%) of 650 361 patients tested positive for COVID-19, of whom 14 504 (12·0%) were hospitalised, 567 (0·5%) received mechanical ventilation, and 2001 (1·7%) died. Compared with controls, patients with IMIDs and COVID-19 (7327 [17·3%] of 42 249) had higher rates of hospitalisation (13 422 [11·8%] vs 1082 [14·8%]; p<0·0001) and mortality (1814 [1·6%] vs 187 [2·6%]; p<0·0001). Age was a risk factor for worse outcomes (adjusted odds ratio [OR] from 2·1 [95% CI 2·0-2·1]; p<0·0001 to 3·0 [2·9-3·0]; p<0·0001), whereas COVID-19 vaccination (from 0·082 [0·080-0·085]; p<0·0001 to 0·52 [0·50-0·53]; p<0·0001) and booster vaccination (from 2·1 [2·0-2·2]; p<0·0001 to 3·0 [2·9-3·0]; p<0·0001) status were associated with better outcomes. Seven chronic comorbidities were significant risk factors during both time periods for all three outcomes: atrial fibrillation, coronary artery disease, heart failure, chronic kidney disease, chronic obstructive pulmonary disease, chronic liver disease, and cancer. Two IMIDs, asthma (adjusted OR from 0·33 [0·32-0·34]; p<0·0001 to 0·49 [0·48-0·51]; p<0·0001) and psoriasis (from 0·52 [0·48-0·56] to 0·80 [0·74-0·87]; p<0·0001), were associated with a reduced risk of severe outcomes. IMID diagnoses did not appear to be significant risk factors themselves, but results were limited by small sample size, and vasculitis had high feature importance in LR. IMMs did not appear to be significant, but less frequently used IMMs were limited by sample size. XGB outperformed LR, with the area under the receiver operating characteristic curve for models across different time periods and outcomes ranging from 0·77 to 0·92. INTERPRETATION: Our results suggest that age, chronic comorbidities, and not being fully vaccinated might be greater risk factors for severe COVID-19 outcomes in patients with IMIDs than the use of IMMs or the IMIDs themselves. Overall, there is a need to take age and comorbidities into consideration when developing COVID-19 guidelines for patients with IMIDs. Further research is needed for specific IMIDs (including IMID severity at the time of SARS-CoV-2 infection) and IMMs (considering dosage and timing before a patient's first COVID-19 infection). FUNDING: Pfizer, Novartis, Janssen, and the National Institutes of Health.

Use of a Novel Artificial Intelligence System Leads to the Detection of Significantly Higher Number of Adenomas During Screening and Surveillance Colonoscopy: Results From a Large, Prospective, US Multicenter, Randomized Clinical Trial.

INTRODUCTION: Adenoma per colonoscopy (APC) has recently been proposed as a quality measure for colonoscopy. We evaluated the impact of a novel artificial intelligence (AI) system, compared with standard high-definition colonoscopy, for APC measurement. METHODS: This was a US-based, multicenter, prospective randomized trial examining a novel AI detection system (EW10-EC02) that enables a real-time colorectal polyp detection enabled with the colonoscope (CAD-EYE). Eligible average-risk subjects (45 years or older) undergoing screening or surveillance colonoscopy were randomized to undergo either CAD-EYE-assisted colonoscopy (CAC) or conventional colonoscopy (CC). Modified intention-to-treat analysis was performed for all patients who completed colonoscopy with the primary outcome of APC. Secondary outcomes included positive predictive value (total number of adenomas divided by total polyps removed) and adenoma detection rate. RESULTS: In modified intention-to-treat analysis, of 1,031 subjects (age: 59.1 ± 9.8 years; 49.9% male), 510 underwent CAC vs 523 underwent CC with no significant differences in age, gender, ethnicity, or colonoscopy indication between the 2 groups. CAC led to a significantly higher APC compared with CC: 0.99 ± 1.6 vs 0.85 ± 1.5, P = 0.02, incidence rate ratio 1.17 (1.03-1.33, P = 0.02) with no significant difference in the withdrawal time: 11.28 ± 4.59 minutes vs 10.8 ± 4.81 minutes; P = 0.11 between the 2 groups. Difference in positive predictive value of a polyp being an adenoma among CAC and CC was less than 10% threshold established: 48.6% vs 54%, 95% CI -9.56% to -1.48%. There were no significant differences in adenoma detection rate (46.9% vs 42.8%), advanced adenoma (6.5% vs 6.3%), sessile serrated lesion detection rate (12.9% vs 10.1%), and polyp detection rate (63.9% vs 59.3%) between the 2 groups. There was a higher polyp per colonoscopy with CAC compared with CC: 1.68 ± 2.1 vs 1.33 ± 1.8 (incidence rate ratio 1.27; 1.15-1.4; P < 0.01). DISCUSSION: Use of a novel AI detection system showed to a significantly higher number of adenomas per colonoscopy compared with conventional high-definition colonoscopy without any increase in colonoscopy withdrawal time, thus supporting the use of AI-assisted colonoscopy to improve colonoscopy quality ( ClinicalTrials.gov NCT04979962).

Combined ERCP and EUS in one session is safe in elderly patients when compared to non-elderly patients: outcomes in 206 combined procedures.

AIMS: Combined ERCP/EUS is becoming common. Combined procedures are frequently performed in elderly patients. We hypothesized that combined ERCP/EUS is equally safe in elderly patients when compared to non-elderly patients. METHODS: This was a retrospective single-center study comparing outcomes in elderly and non-elderly patients undergoing combined ERCP/EUS. RESULTS: A total of 206 patients were included. Mean age was 65 years (M:F 113:93); 99 were <65 years and 107 were >65. Indications included: jaundice (51%), abnormal imaging (17%), pancreatic tumor (11%), abdominal pain (5%), stent placement/change (5%), acute or chronic pancreatitis (5%), other (6%). Fine needle aspiration was performed in 134 (65%) procedures. Malignancy was identified in 142/206 (69%) patients. Mean Charlson Comorbidity Index (CCI) was 7.5 (range 0-22). Among patients <65 years old there were no immediate adverse events. Long-term adverse events in patients <65 (within 30 days) included cholangitis (1), increasing abdominal pain (4), post-ERCP pancreatitis (3), nausea/vomiting (1), increasing fatigue (1), and increasing jaundice (1). A subgroup analysis among geriatric patients (>65) was performed. Mean CCI was 8.2 (range 0-22). There was one immediate adverse event of non-sustained ventricular tachycardia in a 76-year old. Long-term adverse events included increasing fatigue (1), nausea/vomiting (2), increasing abdominal pain (2), urosepsis (1), fever (2) and dehydration (1). There were no statistically significant differences in outcomes in elderly compared to non-elderly patients. Elderly patients had higher CCI scores (p = 0.04). CONCLUSION: Combined ERCP/EUS in one session is safe in the general population and elderly patients, with no more adverse events than in non-elderly patients.

Prevalence of significant neoplasia in FOBT-positive patients on warfarin compared with those not on warfarin.

OBJECTIVES: The fecal occult blood test (FOBT) is widely used for colorectal cancer screening. However, the impact of warfarin use on FOBT sensitivity and specificity remains unclear. This study compares the relative risk of neoplasia in FOBT-positive patients stratified by warfarin use. METHODS: The Clinical Outcomes Research Initiative database was used to identify patients with positive FOBT as the only indication for colonoscopy during 2005-2006. Patients were categorized on the basis of documented warfarin status within a 30-day period before FOBT. We compared the demographics and prevalence of significant colon findings (defined as polyp >9 mm or suspected malignant tumor) among the two groups. After adjusting for confounding variables, logistic regression was used to estimate the odds ratio of significant findings in warfarin-positive vs. warfarin-negative patients. RESULTS: Of 10,266 patients with positive FOBT, 372 used warfarin, 9,265 did not use warfarin, and 629 were excluded because of missing warfarin status. Warfarin-positive patients were more likely male (65 vs. 50%; P<0.0001), Caucasian (88 vs. 80%; P<0.0001), and veterans (53 vs. 33%; P<0.0001). The prevalence of a significant finding was greater in the warfarin group, 16 vs. 11.4% (P<0.01). After adjusting for age and sex, the relative risk of significant colon findings among warfarin-positive patients was not significantly different from warfarin-negative patients (odds ratio 1.1, 95% confidence interval: 0.81-1.44). CONCLUSIONS: No increased risk for significant colonic findings among FOBT-positive patients according to warfarin use was identified. These findings suggest that continuing warfarin before FOBT will not affect the positive predictive value of this screening test.

Morphologic evidence that neurokinin B modulates gonadotropin-releasing hormone secretion via neurokinin 3 receptors in the rat median eminence.

Recent studies suggest that arcuate neurokinin B (NKB) neurons play a role in the regulation of gonadotropin secretion, but there is little information on the relationship between these neurons and the hypothalamic reproductive axis. In the present study, dual-label fluorescent immunohistochemistry was used to visualize the relationship between gonadotropin-releasing hormone (GnRH) neurons and either proNKB or NK3 receptor (NK3R) immunoreactivity. Immunocytochemistry was also combined with i.p. injections of the fluorescent retrograde tracer aminostilbamidine to determine whether arcuate neuroendocrine neurons expressed either proNKB or NK3R. A dense interweaving and close apposition of GnRH and proNKB-immunoreactive (ir) fibers was observed within the rat median eminence, where GnRH axons expressed NK3R immunoreactivity. These data provide morphological evidence that NKB neurons could influence GnRH secretion via interaction with NK3R in the rat median eminence. Colocalization of GnRH and NK3R was also identified in fiber tracts converging within the organum vasculosum of the lamina terminalis. In contrast, only a small number (16%) of GnRH-ir somata exhibited NK3R staining. ProNKB and NK3R-ir somata were identified within the arcuate nucleus, but none of these neurons were labeled by aminostilbamidine. Thus, we found no evidence that arcuate NKB neurons project to the primary capillary plexus of the portal system. Arcuate neuroendocrine neurons, however, were surrounded and closely apposed by proNKB-ir puncta and fibers. These data suggest that NKB neurons could indirectly influence anterior pituitary function by inputs to arcuate neuroendocrine neurons, but through a receptor other than NK3R. Our results provide an anatomic framework for putative interactions between NKB neurons and the hypothalamic reproductive axis.