Understanding and predicting COVID-19 clinical trial completion vs. cessation

Parallel-Forms Reliability and Minimal Detectable Change of the Four Telerehabilitation Version Mobility-Related Function Scales in Stroke Survivors

OBJECTIVE

To investigate the parallel-forms reliability, minimal detectable change with 95% confidence interval (MDC95), and feasibility of the 4 telerehabilitation version mobility-related function scales: Fugl-Meyer Assessment-lower extremity subscale (Tele-FMA-LE), Berg Balance Scale (Tele-BBS), Tinetti Performance Oriented Mobility Assessment-Gait subscale (Tele-POMA-G), and Rivermead Mobility Index (Tele-RMI).

DESIGN

Reliability and agreement study and cross-sectional study.

SETTING

Medical center.

PARTICIPANTS

Stroke survivors' ability to independently walk 3 meters with assistive devices, age of ≥18 years for participants and their partners, stable physical condition, and absence of cognitive impairment (N=60).

INTERVENTIONS

Not applicable.

MAIN OUTCOMES MEASURES

Parallel-forms reliability and MDC95 of Tele-FMA-LE, Tele-BBS, Tele-POMA-G, and Tele-RMI.

RESULTS

No significant differences (P>.05) were observed among the mean scores of the telerehabilitation version and face-to-face version mobility-related function scales. Intraclass correlation coefficients (ICCs) indicated good reliability for most scales, with Tele-FMA-LE, Tele-BBS, and Tele-RMI scores achieving values of 0.81, 0.78, and 0.84. Tele-POMA-G scores demonstrated moderate reliability (ICC=0.72). Weighted kappa (κw) showed good-to-excellent reliability for most individual items (κw>0.60). The MDCs of the Tele-FMA-LE, Tele-BBS, Tele-POMA-G, and Tele-RMI were 5.84, 8.10, 2.74, and 1.31, respectively. Bland-Altman analysis showed adequate agreement between tele-assessment and face-to-face assessment for all scales. The 5 dimensions affirm the robust feasibility of tele-assessment: assessment time, subjective fatigue perception, overall preference, participant satisfaction, and system usability.

CONCLUSIONS

The study demonstrates good parallel-forms reliability, MDC, and promising feasibility of the 4 telerehabilitation version mobility-related function scales (Tele-FMA-LE, Tele-BBS, Tele-POMA-G, and Tele-RMI) in survivors of stroke.

Tertiary drug information sources for treatment and prevention of COVID-19

Objective

To evaluate tertiary drug information databases in terms of scope, consistency of content, and completeness of COVID-19 drug information.

Methods

Five electronic drug information databases: Clinical Pharmacology, Lexi-Drugs, AHFS DI (American Hospital Formulary Service Drug Information), eFacts and Comparisons, and Micromedex In-Depth Answers, were evaluated in this cross-sectional evaluation study, with data gathered from October 2021 through February 2022. Two study investigators independently extracted data (parallel extraction) from each resource. Descriptive statistics were primarily used to evaluate scope (i.e., whether the resource addresses use of the medication for treatment or prevention of COVID-19) and completeness of content (i.e., whether full information is provided related to the use of the medication for treatment or prevention of COVID-19) based on a 10-point scale. To analyze consistency among resources for scope, the Fleiss multi-rater kappa was used. To analyze consistency among resources for type of recommendation (i.e., in favor, insufficient evidence, against), a two-way mixed effects intraclass coefficient was calculated.

Results

A total of 46 drug monographs, including 3 vaccination monographs, were evaluated. Use of the agents for treatment of COVID-19 was most frequently addressed in Lexi-Drugs (73.9%), followed by eFacts and Comparisons (71.7%), and Micromedex (54.3%). The highest overall median completeness score was held by AHFS DI followed by Micromedex, and Clinical Pharmacology. There was moderate consistency in terms of scope (kappa 0.490, 95% CI 0.399-0.581, p<0.001) and recommendations (intraclass correlation coefficient 0.518, 95% CI 0.385-0.651, p<0.001).

Conclusion

Scope and completeness results varied by resource, with moderate consistency of content among resources.

Deep learning-based risk prediction for interventional clinical trials based on protocol design: A retrospective study

Success rate of clinical trials (CTs) is low, with the protocol design itself being considered a major risk factor. We aimed to investigate the use of deep learning methods to predict the risk of CTs based on their protocols. Considering protocol changes and their final status, a retrospective risk assignment method was proposed to label CTs according to low, medium, and high risk levels. Then, transformer and graph neural networks were designed and combined in an ensemble model to learn to infer the ternary risk categories. The ensemble model achieved robust performance (area under the receiving operator characteristic curve [AUROC] of 0.8453 [95% confidence interval: 0.8409-0.8495]), similar to the individual architectures but significantly outperforming a baseline based on bag-of-words features (0.7548 [0.7493-0.7603] AUROC). We demonstrate the potential of deep learning in predicting the risk of CTs from their protocols, paving the way for customized risk mitigation strategies during protocol design.

A machine learning study of COVID-19 serology and molecular tests and predictions

Serology and molecular tests are the two most commonly used methods for rapid COVID-19 infection testing. The two types of tests have different mechanisms to detect infection, by measuring the presence of viral SARS-CoV-2 RNA (molecular test) or detecting the presence of antibodies triggered by the SARS-CoV-2 virus (serology test). A handful of studies have shown that symptoms, combined with demographic and/or diagnosis features, can be helpful for the prediction of COVID-19 test outcomes. However, due to nature of the test, serology and molecular tests vary significantly. There is no existing study on the correlation between serology and molecular tests, and what type of symptoms are the key factors indicating the COVID-19 positive tests. In this study, we propose a machine learning based approach to study serology and molecular tests, and use features to predict test outcomes. A total of 2,467 donors, each tested using one or multiple types of COVID-19 tests, are collected as our testbed. By cross checking test types and results, we study correlation between serology and molecular tests. For test outcome prediction, we label 2,467 donors as positive or negative, by using their serology or molecular test results, and create symptom features to represent each donor for learning. Because COVID-19 produces a wide range of symptoms and the data collection process is essentially error prone, we group similar symptoms into bins. This decreases the feature space and sparsity. Using binned symptoms, combined with demographic features, we train five classification algorithms to predict COVID-19 test results. Experiments show that XGBoost achieves the best performance with 76.85% accuracy and 81.4% AUC scores, demonstrating that symptoms are indeed helpful for predicting COVID-19 test outcomes. Our study investigates the relationship between serology and molecular tests, identifies meaningful symptom features associated with COVID-19 infection, and also provides a way for rapid screening and cost effective detection of COVID-19 infection.

Suspension of Oncology Randomized Clinical Trials during the COVID-19 Pandemic: A Cross-Sectional Evaluation of COVID-Related Suspensions

We conducted a cross-sectional analysis of ClinicalTrials.gov-registered oncology randomized controlled trials between September 2019 and December 2021 to identify predictors of trial suspensions. The dataset included 1,183 oncology trials, of which 384 (32.5%) were suspended. COVID-19 accounted for 47 (12.2%) suspensions. Trials that were single center- or US-based had higher odds of COVID-19 (ORs: 3.85 and 2.48, 95% CIs: 1.60-11.50 and 1.28-4.93, respectively) or any-reason suspensions (ORs: 2.33 and 2.04, 95% CIs: 1.46-3.45 and 1.40-2.76, respectively). Phase two (OR 1.27), three (OR 6.45) and four trials (OR 11.5) had increased odds of COVID-19 suspensions, compared to phase one trials.