Machine Learning Techniques for Predicting Risks of Late Delivery

Supply chain is a cornerstone of the eCommerce industry and is a key component in its growth. Supply chain data analytics and risk management in the eCommerce space have picked up steam in recent times. With the availability of suitable & capable resources for big data and artificial intelligence, predictive analytics has become a significant area of interest to achieve organizational excellence by exploiting data available and developing data-driven support systems. The existing literature in supply chain risk management explain various methods assisting to identify & mitigate risks using big data and machine learning (ML) techniques across industries. Although ML techniques are used in various industries, not many aspects of eCommerce had utilized predictive analytics to their benefit. In the eCommerce industry, delivery is paramount for the business. During COVID-19 pandemic, needs changed. Reliable delivery services are preferred to speedy delivery. Multiple parameters involve delivering the product to a customer as per promised due date. This research will try to predict the risks of late deliveries to online shopping customers by analyzing the historical data using machine learning techniques and comparing them by multiple performance metrics. As a part of this comparative study, a new hybrid technique which is a combination of Logistic Regression, XGBoost, Light GBM, and Random Forest is built which has outperformed all the other ensemble and individual algorithms with respect to accuracy, specificity, precision, and F1-score. This study will benefit the eCommerce companies to improve their customer satisfaction by predicting late deliveries accurately and early. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Comparison of Subjective and Physiological Stress Levels in Home and Office Work Environments

Work stress can have serious deleterious effects for individuals and society and therefore its management is of great importance. Work environment has been demonstrated as one of the significant factors effecting work stress. Recently, COVID-19 has led to an increased frequency of individuals working in hybrid work environments mainly comprising of home and office environments. The effects these work environments have on individuals’ mental stress is important to understand for both employers and employees so they can mitigate and effectively manage the mental stress. In this paper, we present an intelligent approach to predict the stress occurrences using the physiological data acquired from individuals working in both remote and office locations. Multiple factors are collected related to physiological indicators of stress and subjective performance level. We developed a boosted tree ensemble model which produced binary stress classification accuracy of 99.9%. The statistical outcomes indicate that there is no overall correlation between mental stress and productivity, however there is some indication of mental stress being is influenced by the work environment, the time of day and the day of the week. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Evaluation of high flow local extraction for controlling aerosol plumes in operating theaters

SARS-CoV-2 can be transmitted through contact with fomite, respiratory droplets, and aerosolized viruses. Recent evidence suggests that aerosol transmission represents a significant route of infection. In relation to healthcare workers (HCWs), much attention has been focused on personal protective equipment, yet this is the lowest level of the Centers for Disease Control and Prevention hierarchy of controls. Although engineering controls are prominent in the hierarchy, little attention has been given to developing effective interventions. This study aims to evaluate the performance of a simple extraction device in a clinical setting. This was accomplished by using a high flow local extraction (HFLE) that was connected to the existing ventilation system of the hospital on one end and to an intake nozzle near the patient's airway on the other end. Propylene glycol was aerosolized through a physiological test apparatus to simulate the breath of a patient. The field of interest was illuminated using a laser sheet in two planes from the model, namely, the sagittal plane and the transverse plane, and the movement of the simulated aerosol was recorded using a video camera to assess the dispersion of the aerosol qualitatively. In the meantime, the concentration of the aerosol particles was measured using a particle meter to evaluate the effectiveness of the extraction quantitatively. It was found that the HFLE device could effectively reduce the dispersion of the exhaled aerosols to undetectable levels when it was positioned within 250 mm from the mouth. This result has significance in the safety of HCWs involved in the management of patients with infectious diseases and may also have potential applications in other clinical areas with high airflow in the ventilation systems. © 2022 Author(s).

Roles of caregivers in physiological data collection experiments with people with dementia and mitigating the impacts of COVID-19

Timely detection of behavioural and psychological symptoms of dementia is important for the prevention and reduction of distress for people with dementia and their loved ones. Wearable computingbased systems can be used to predict such difficulties in a timely manner, but a data collection experiment is needed to collect data to develop such a system. Caregivers can be vital assets in such experiments, however, often face high burden and stress due to their caring obligations. An even greater burden has been experienced by many due to the ongoing COVID-19 pandemic. In this paper, the roles that caregivers played in physiological data collections are reviewed. Three main roles were identified as being performed by caregivers in such data collection experiments: observation of difficulties;consenting for participants and themselves;device set-up and maintenance. Roles such as aiding in recruitment and providing information to participants before and during the study were also performed. Each of these roles can present their own burdens, which can be mitigated in a number of ways. Overall, it is vital that researchers consider the burden that may be placed on the caregiver who is fulfilling any of these roles in an experiment with sufficient mitigations to those burdens being implemented. Furthermore, we propose a pivot in our research towards analysing stress during the pandemic, justifying how this will help towards developing a system to detect dementia-related difficulties. © 2021 IEEE.

The protekduo as double lumen arterial return cannula in extracorporeal membrane oxygenation

Objective: We present 3 cases of acute respiratory distress syndrome (ARDS) secondary to COVID-19 pneumonia who required veno-venous extracorporeal membrane oxygenation (V-V ECMO) using the ProtekDuo right ventricular assist device (RVAD). Method: The first patient was transferred to our institution for advanced management, having a ProtekDuo with an oxygenator in veno - pulmonary- arterial(V-pA) position. The patient remained hypoxemic and therefore we modified the configuration using a 25 Fr femoral multistage drainage cannula that was inserted for venous drainage only. The arterial return tubing was spliced and using a Y-connector, arterialized blood was returned through both lumina of the ProtekDuo. Based on this experience we changed 2 more patients who were on ProtekDuo to this new configuration. Results: This modified novel configuration resulted in significantly increased oxygenation (SpO2 from 78% to 100%) and flow (from 4.2 LPM to 7.0 LPM) in patient #1. The patient recovered and was successfully weaned and separated from ProtekDuo after 44 days, of which 29 days were on the modified configuration, without any device-related complications. Patient #2 has been successfully weaned off ECMO and presently is undergoing physiotherapy and rehabilitation. Patient #3 has recently been placed on V-pA ECMO and is presently being managed. Discussion: This modified novel configuration is presently under investigation and exact mechanisms need to be described. Direct return of arterialized blood into the pulmonary artery without mixing in the right atrium and reduction of shunt fraction may play major roles. Conclusion: This novel configuration appears beneficial and safe without right atrial strain.

Review of Methods for Data Collection Experiments with People with Dementia and the Impact of COVID-19

The development of a wearable-based system for detecting difficulties in the daily lives of people with dementia would be highly useful in the day-to-day management of the disease. To develop such a system, it would be necessary to identify physiological indicators of the difficulties, which can be identified by analyzing physiological datasets from people with dementia. However, there is no such data available to researchers. As such, it is vital that data is collected and made available in future. In this paper we perform a review of past physiological data collection experiments conducted with people with dementia and evaluate the methods used at each stage of the experiment. Consideration is also given to the impacts and limitations imposed by the COVID-19 pandemic and lockdowns both on the people with dementia- such people being one of the most at risk and affected groups- and on the efficacy and safety of each of the methods. It is concluded that the choice of method to be utilized in future data collection experiments is heavily dependent on the type and severity of the dementia the participants are experiencing, and that the choice of remote or COVID-secure methods should be used during the COVID-19 pandemic;many of the methods reviewed could allow for the spread of the virus if utilized during a pandemic. © 2021, Springer Nature Switzerland AG.

Learner Driven Call Center to increase Convalescent Plasma Donation in COVID-19

Background. Convalescent plasma (CP) may be obtained from patients who have recovered from the novel coronavirus disease, COVID-19, caused by the virus SARS-CoV-2. Although not FDA approved, preliminary data suggests patients who receive convalescent plasma from recovered donors may have shortened recovery time and symptom reduction. The purpose of the study is to detail learner recruitment of convalescent plasma donation (CPD) for treating hospitalized COVID-19 patients. Methods. Prisma Health Midlands formed a multidisciplinary CP donation team, consisting of seven COVID-19-certified pharmacy learner volunteers, two pharmacists, and two providers. Primary eligibility criteria were SARS-CoV-2 polymerase chain reaction (PCR) positivity at least 28 days prior to donation and asymptomatic for a minimum of 14 days. Donors were excluded based on FDA guidelines for CPD, limiting ineligible contact. Team learners were trained on call techniques and subsequently contacted, educated, and requested candidates donate through this program. Willing donors were then linked to The Blood Connection to circulate CP back into the Prisma Health System, creating a self-sustaining and closed-loop donation cycle. Results. In total, 253 recovered adult patients with positive SARS-CoV-2 PCR test results were evaluated. 195 patients met baseline inclusion criteria for contact. This pre-screen reduced call and travel time for ineligible candidates. 108 patients were successfully reached. Of the 108, n=79 (73.14%) accepted referral to The Blood Connection, and n=29 (26.85%) were no longer candidates primarily due to patient communicated new exclusionary factors, such as active COVID-19 symptoms. The program allowed for rapid, internal access to CP for patients hospitalized with COVID-19 at Prisma Health Midlands. Conclusion. Interest and awareness in COVID-19 CPD was successfully increased upon direct communication from the team and was felt to represent a personnel intense but successful model for recruiting potential CP donors. This program educated and utilized learners during this pandemic to enhance Prisma Health's ability to obtain CP for hospitalized patients using a closed system.