Interpretable Machine Learning Methods for Monitoring Polymer Degradation in Extrusion of Polylactic Acid

This work investigates real-time monitoring of extrusion-induced degradation in different grades of PLA across a range of process conditions and machine set-ups. Data on machine settings together with in-process sensor data, including temperature, pressure, and near-infrared (NIR) spectra, are used as inputs to predict the molecular weight and mechanical properties of the product. Many soft sensor approaches based on complex spectral data are essentially 'black-box' in nature, which can limit industrial acceptability. Hence, the focus here is on identifying an optimal approach to developing interpretable models while achieving high predictive accuracy and robustness across different process settings. The performance of a Recursive Feature Elimination (RFE) approach was compared to more common dimension reduction and regression approaches including Partial Least Squares (PLS), iterative PLS (i-PLS), Principal Component Regression (PCR), ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest (RF). It is shown that for medical-grade PLA processed under moisture-controlled conditions, accurate prediction of molecular weight is possible over a wide range of process conditions and different machine settings (different nozzle types for downstream fibre spinning) with an RFE-RF algorithm. Similarly, for the prediction of yield stress, RFE-RF achieved excellent predictive performance, outperforming the other approaches in terms of simplicity, interpretability, and accuracy. The features selected by the RFE model provide important insights to the process. It was found that change in molecular weight was not an important factor affecting the mechanical properties of the PLA, which is primarily related to the pressure and temperature at the latter stages of the extrusion process. The temperature at the extruder exit was also the most important predictor of degradation of the polymer molecular weight, highlighting the importance of accurate melt temperature control in the process. RFE not only outperforms more established methods as a soft sensor method, but also has significant advantages in terms of computational efficiency, simplicity, and interpretability. RFE-based soft sensors are promising for better quality control in processing thermally sensitive polymers such as PLA, in particular demonstrating for the first time the ability to monitor molecular weight degradation during processing across various machine settings.

COVID-19: Rapid prototyping and production of face shields via flat, laser-cut, and 3D-printed models

The use of personal protective equipment (PPE) has become essential to reduce the transmission of coronavirus disease 2019 (COVID-19) as it prevents the direct contact of body fluid aerosols expelled from carriers. However, many countries have reported critical supply shortages due to the spike in demand during the outbreak in 2020. One potential solution to ease pressure on conventional supply chains is the local fabrication of PPE, particularly face shields, due to their simplistic design. The purpose of this paper is to provide a research protocol and cost implications for the rapid development and manufacturing of face shields by individuals or companies with minimal equipment and materials. This article describes a best practice case study in which the establishment of a local manufacturing hub resulted in the swift production of 12,000 face shields over a seven-week period to meet PPE shortages in the North-West region of Ireland. Protocols and processes for the design, materials sourcing, prototyping, manufacturing, and distribution of face shields are described. Three types of face shields were designed and manufactured, including Flat, Laser-cut, and 3D-printed models. Of the models tested, the Flat model proved the most cost-effective (€0.51/unit), while the Laser-cut model was the most productive (245 units/day). The insights obtained from this study demonstrate the capacity for local voluntary workforces to be quickly mobilised in response to a healthcare emergency, such as the COVID-19 pandemic.

Successful treatment of a recurrent post-dural puncture headache with an epidural blood patch 18 months after the initial dural puncture

Inadvertent dural puncture is a recognised complication of epidural insertion. Parturients are at increased risk of developing a post-dural puncture headache, which can be debilitating for a mother caring for a newborn infant. Epidural blood patch is an effective treatment in patients presenting acutely with post-dural puncture headaches but its efficacy in those with delayed presentation or with late recurrent post-dural puncture headache is less clear. We present the case of a woman with a recurrent post-dural puncture headache who was successfully treated with an epidural blood patch 18 months after the initial dural puncture. Patients who develop post-dural puncture headaches may remain symptomatic for some time and an epidural blood patch may be beneficial, following appropriate investigation.

A randomised controlled trial using the Epidrum for labour epidurals

The aim of our study was to determine if using the Epidrum to site epidurals improves success and reduces morbidity. Three hundred parturients requesting epidural analgesia for labour were enrolled. 150 subjects had their epidural sited using Epidrum and 150 using standard technique. We recorded subject demographics, operator experience, number of attempts, Accidental Dural Puncture rate, rate of failure to site epidural catheter, rate of failure of analgesia, Post Dural Puncture Headache and Epidural Blood Patch rates. Failure rate in Epidrum group was 9/150 (6%) vs 0 (0%) in the Control group (P = 0.003). There were four (2.66%) accidental dural punctures in the Epidrum group and none in the Control group (P = 0.060), and 2 epidurals out of 150 (1.33%) in Epidrum group were re-sited, versus 3/150 (2%) in the control group (P = 1.000). The results of our study do not suggest that using Epidrum improves success or reduces morbidity.

Anaesthesia for parturients with severe cystic fibrosis: a case series

Cystic fibrosis affects 1 in 1600-2500 live births and is inherited in an autosomal recessive manner. It primarily involves the respiratory, gastrointestinal and reproductive tracts, with impaired clearance of, and obstruction by, increasingly viscous secretions. Severe respiratory disease, diabetes and gastro-oesophageal reflux may result. Improvements in medical management and survival of cystic fibrosis patients means more are committing to pregnancies. Although guidance for anaesthesia in this patient group is available, management and outcome data associated with more severe cases are sparse. Patients with severe cystic fibrosis require multidisciplinary input and should be managed in a tertiary referral centre. Close monitoring of respiratory function and preoperative optimisation during pregnancy are mandatory. The risk of preterm labour and delivery is increased. Pregnancy and delivery can be managed successfully, even in patients with FEV1 <40% predicted. Neuraxial anaesthesia and analgesia should be the technique of choice for delivery. Postoperative care should be carried out in a critical care setting with the provision of postoperative ventilation if necessary.