Using artificial intelligence for personal protective equipment guidance for healthcare workers in the COVID-19 pandemic and beyond.

Background: Current procedures for effective personal protective equipment (PPE) usage rely on the availability of trained observers or 'buddies' who, during the COVID-19 pandemic, are not always available. The application of artificial intelligence (AI) has the potential to overcome this limitation by assisting in complex task analysis. To date, AI use for PPE protocols has not been studied. In this paper we validate the performance of an AI PPE system in a hospital setting. Methods: A clinical cohort study of 74 healthcare workers (HCW) at a 144-bed University teaching hospital. Participants were recruited to use the AI system for PPE donning and doffing. Performance was validated by the current gold standard double-buddy system across seven donning and ten doffing steps based on local infection control guidelines. Results: The AI-PPE platform was 98.9% sensitive on doffing and 85.3% sensitive on donning, when compared to remediated double buddy. On average, buddy correction of PPE was required 3.8 ± 1.5% of the time. The average time taken to don was 240 ± 51.5 seconds and doff was 241 ± 35.3 seconds. Conclusion: This study demonstrates the ability of an AI model to analyse PPE donning and doffing with real-time feedback for remediation. The AI platform can identify complex multi-task PPE donning and doffing in a single validated system. This AI system can be employed to train, audit, and thereby improve compliance whilst reducing reliance on limited HCW resources. Further studies may permit the development of this educational tool into a medical device with other industry uses for safety.

Reversal of collateral ventilation using endoscopic polymer foam in COPD patients undergoing endoscopic lung volume reduction with endobronchial valves: A controlled parallel group trial.

BACKGROUND AND OBJECTIVE: We have previously described reversal of collateral ventilation (CV) in a severe chronic obstructive pulmonary disease (COPD) patient with endoscopic polymer foam (EPF), prior to endoscopic lung volume reduction (ELVR) with valves. The aim of this study was to investigate the efficacy of this in a larger cohort and compare outcomes with a similar cohort with no CV. METHODS: Patients with severe COPD, with the left upper lobe (LUL) targeted for ELVR, were assessed for CV with high resolution computed tomography (HRCT). If fissure completeness was >95% they were enrolled as controls for valves alone (endobronchial valve control group [EBV-CTRL]). If fissure completeness was 80%-95%, defects were mapped to the corresponding segment, where EPF was instilled following confirmation of CV with CHARTIS. EBVs were inserted 1 month afterwards. RESULTS: Fourteen patients were enrolled into both arms. After 6 months, there were significant improvements in both groups in forced expiratory volume in 1 s (FEV1; +19.7% EPF vs. +27.7% EBV-CTRL, p < 0.05); residual volume (RV; -16.2% EPF vs. -20.1% EBV-CTRL, p = NS); SGRQ (-15.1 EPF vs. -16.6 EBV-CTRL p = NS) and 6 min walk (+25.8% EPF [77.2 m] vs. +28.4% [82.3 m] EBV-CTRL p = NS). Patients with fissural defects mapped to the lingula had better outcomes than those mapped to other segments (FEV1 +22.9% vs. +16.3% p < 0.05). There were no serious adverse reactions to EPF. CONCLUSION: EPF successfully reverses CV in severe COPD patients with a left oblique fissure that is 80%-95% complete. Following EBV, outcomes are similar to patients with complete fissures undergoing ELVR with EBV alone. EPF therapy to reverse CV potentially increases the number of COPD patients suitable for ELVR with minimal adverse reactions.

Low-Fouling and Biodegradable Protein-Based Particles for Thrombus Imaging.

Nanomedicine holds great promise for vascular disease diagnosis and specific therapy, yet rapid sequestration by the mononuclear phagocytic system limits the efficacy of particle-based agents. The use of low-fouling polymers, such as poly(ethylene glycol), efficiently reduces this immune recognition, but these nondegradable polymers can accumulate in the human body and may cause adverse effects after prolonged use. Thus, new particle formulations combining stealth, low immunogenicity and biocompatible features are required to enable clinical use. Here, a low-fouling particle platform is described using exclusively protein material. A recombinant protein with superior hydrophilic characteristics provided by the amino acid repeat proline, alanine, and serine (PAS) is designed and cross-linked into particles with lysine (K) and polyglutamic acid (E) using mesoporous silica templating. The obtained PASKE particles have low-fouling behavior, have a prolonged circulation time compared to albumin-based particles, and are rapidly degraded in the cell's lysosomal compartment. When labeled with near-infrared fluorescent molecules and functionalized with an anti-glycoprotein IIb/IIIa single-chain antibody targeting activated platelets, the particles show potential as a noninvasive molecular imaging tool in a mouse model of carotid artery thrombosis. The PASKE particles constitute a promising biodegradable and versatile platform for molecular imaging of vascular diseases.