ABSTRACT
INTRODUCTION: Riluzole, a sodium-glutamate antagonist which is FDA approved for ALS has shown promising pre-clinical results and is clinically safe in SCI patients. METHOD(S): The RISCIS trial is an international, multi-center, prospective, double-blinded, randomized, placebo-controlled Phase II/ III trial. Patients with ASIA A-C, C4-C8 SCI and <12 hours from injury were randomized between Riluzole, at an oral dose of 100mg BID for the first 24 hours followed by 50mg BID for the following 13 days, and placebo control. RESULT(S): Due to the impact of the global COVID-19 pandemic this trial was terminated prior to completion. 193 patients were randomized with a follow-up rate of 82.7% at 180-days. No statistical difference was noted in the demographics and baseline injury characteristics between the two groups. At 6 months there was a median gain in total motor scores (TOTM) of 30.0 in the Riluzole group compared to 20.0 for the Placebo group. The improved motor outcomes did not reach statistical significance. Given the decreased sample size, additional sensitivity analyses were conducted. In the ASIA-C population, Riluzole was a significant improver of total motor scores (coefficient estimate: 14.10, p = 0.020) and upper motor scores (CE: 7.68, p = 0.040) at 6 months. ASIA B patients had higher reported independence, as measured by the SCIM score (45.3 vs. 27.3;p = 0.071) and change in mental health scores as measured by the SF-36 mental health domain (2.01 vs. -11.58;p: 0.0205) at 180 days. CONCLUSION(S): Despite the premature termination of the RISCIS trial due to the COVID-19 pandemic, 193 subjects were recruited into this trial. Primary analysis showed a 10-motor point gain in riluzoletreated subjects which did not reach significance. However, on secondary analysis, incomplete cervical SCI subjects (AIS B and C) showed significant gains in functional recovery.
ABSTRACT
This paper presents a factor graph-based model that takes comorbidities and clinical measurements as inputs and predicts intensive care unit (ICU) admissions 3 days and 7 days in advance for hospitalized COVID-19 patients. We applied the proposed model on a COVID-19 cohort from a large medical center in Chicago (with records from March 2020 to August 2021). We used the first occurrence of the Delta variant in the U.S., February 2021, as the threshold to divide the dataset into pre-Delta data (533 patients) and post-Delta data (56 patients). Our model demonstrated 0.82 AUC on the pre-Delta data and 0.87 AUC on the post-Delta data in 7-day predictions. Our contribution is a model that (i) explains relationships between different clinical features and provides interpretations for ICU admissions, (ii) outperforms existing methods for 7-day predictions, and (iii) maintains more robustness than existing models in predictions under the influence of the Delta variant. The proposed model could be used as a predictive tool in clinical practice to help clinicians in decision-making by predicting which patients will need ICU support in the future. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.