Overdose deaths before and during the COVID-19 pandemic in a US county.

Introduction: Globally, overdose deaths increased near the beginning of the COVID-19 pandemic, which created availability and access barriers to addiction and social services. Especially in times of a crisis like a pandemic, local exposures, service availability and access, and system responses have major influence on people who use drugs. For policy makers to be effective, an understanding at the local level is needed. Methods: This retrospective epidemiologic study from 2019 through 2021 compares immediate and 20-months changes in overdose deaths from the pandemic start to 16 months before its arrival in Pinellas County, FL We examine toxicologic death records of 1,701 overdoses to identify relations with interdiction, and service delivery. Results: There was an immediate 49% increase (95% CI 23-82%, p < 0.0001) in overdose deaths in the first month following the first COVID deaths. Immediate increases were found for deaths involving alcohol (171%), heroin (108%), fentanyl (78%), amphetamines (55%), and cocaine (45%). Overdose deaths remained 27% higher (CI 4-55%, p = 0.015) than before the pandemic through 2021.Abrupt service reductions occurred when the pandemic began: in-clinic methadone treatment dropped by two-thirds, counseling by 38%, opioid seizures by 29%, and drug arrests by 56%. Emergency transport for overdose and naloxone distributions increased at the pandemic onset (12%, 93%, respectively) and remained higher through 2021 (15%, 377%,). Regression results indicate that lower drug seizures predicted higher overdoses, and increased 911 transports predicted higher overdoses. The proportion of excess overdose deaths to excess non-COVID deaths after the pandemic relative to the year before was 0.28 in Pinellas County, larger than 75% of other US counties. Conclusions: Service and interdiction interruptions likely contributed to overdose death increases during the pandemic. Relaxing restrictions on medical treatment for opioid addiction and public health interventions could have immediate and long-lasting effects when a major disruption, such as a pandemic, occurs. County level data dashboards comprised of overdose toxicology, and interdiction and service data, can help explain changes in overdose deaths. As a next step in predicting which policies and practices will best reduce local overdoses, we propose using simulation modeling with agent-based models to examine complex interacting systems.

Loitering behavior detection by spatiotemporal characteristics quantification based on the dynamic features of Automatic Identification System (AIS) messages.

The capability of the Automatic Identification System (AIS) to provide real-time worldwide coverage of ship tracks has made it possible for maritime authorities to utilize AIS as a means of surveillance to identify anomalies. Anomaly detection in maritime traffic is crucial as anomalous behavior may be a sign of either emergencies or illegal activities. Anomalous ships are recognized based on their behavior by manual examination. Such work requires extensive effort, especially for nationwide surveillance. To deal with this, researchers proposed computational methods to analyze vessel behavior. However, most approaches are region-dependent and require a profile of normality to detect anomalies, and amongst the six types of anomaly, loitering is the least explored. Loitering is not necessarily anomalous behavior as it is common for certain types of ships, such as pilot boats and research vessels. However, tankers and cargo ships normally do not engage in loitering. Based on 12-month manually examined data, nearly 60% of the identified anomalies were loitering, particularly for those of types cargo and tanker. Although manual identification is inefficient, automatically identifying abnormal vessels by merely implementing computing algorithms is not yet feasible. It still needs subject matter experts' assessments. This study proposes a region-independent method to automatically detect loitering without training normal instances and produces a ranked list of loitering vessels to facilitate further anomaly investigation. First, the loitering spatiotemporal characteristics are defined: (1) movement of frequent course change, with a certain speed, within a certain spatial range, (2) movement of frequent course change within traversed geodetic distance, (3) might demonstrate frequent extreme turning, and (4) extreme turning produces a significant discrepancy between the course over ground and the heading of the ship. Then, the characteristics are quantified by manipulating the dynamic information of AIS messages. Finally, the parameters to determine a loitering trajectory are formulated by comparing the rate of course change, speed, and the discrepancy between heading and course with the area of spatial range enclosing the trajectory and the geodetic distance between the start and end point. The loitering score of each trajectory is calculated with the parameters, and the Isolation Forest algorithm is employed to establish a threshold and rank. Then, geographic visualization is created for intuitive evaluation. An experiment was conducted on a real-world dataset covering a sea area of 610,116.37 km2. The results prove the efficacy of the proposed method. It remarkably outperforms the existing approach with 97% accuracy and 92% F-score. The experiment produces a ranked list of loitering vessels and an intuitive visualization in the relevant geographic area. In the realworld scenario, they are practical means to support further examination by human operators.

A data-driven decision support system with smart packaging in grocery store supply chains during outbreaks.

The unexpected emergence of the COVID-19 pandemic has changed how grocery shopping is done. The grocery retail stores need to ensure hygiene, quality, and safety concerns in-store shopping by providing "no-touch" smart packaging solutions for agri-food products. The benefit of smart packaging is to inform consumers about the freshness level of a packaged product without having direct contact. This paper proposes a data-driven decision support system that uses smart packaging as a smart product-service system to manage the sustainable grocery store supply chain during outbreaks to prevent food waste. The proposed model dynamically updates the price of a packaged perishable product depending on freshness level while reducing food waste and the number of rejected customers and maximising profit by increasing the inventory turnover rate of grocery stores. The model was tested on a hypothetical but realistic case study of a single product. The results of this study showed that stock capacities, freshness discount rate, freshness period, and quantity discounts significantly affect the performance of a grocery store supply chain during outbreaks.

Using real-time visualization system for data-driven decision support to achieve lung protective strategy: a retrospective observational study.

BACKGROUND: Although lung protective strategy and adjunctive intervention are associated with improved survival in patients with acute respiratory distress syndrome (ARDS), the implementation of effective therapies remains low. This study aimed to evaluate whether the use of business intelligence (BI) for real-time data visualization is associated with an improvement in lung protective strategy and adjunctive therapy. METHODS: A retrospective observational cohort study was conducted on patients with ARDS admitted between September 2020 and June 2021 at two intensive care units (ICUs) of a tertiary referral hospital in Taiwan. BI was imported for data visualization and integration to assist in clinical decision in one of the ICUs. The primary outcomes were the implementation of low tidal volume ventilation (defined as tidal volume/predicted body weight ≤ 8 mL/kg) within 24 h from ARDS onset. The secondary outcomes included ICU and hospital mortality rates. RESULTS: Among the 1201 patients admitted to the ICUs during the study period, 148 (12.3%) fulfilled the ARDS criteria, with 86 patients in the BI-assisted group and 62 patients in the standard-of-care (SOC) group. Disease severity was similar between the two groups. The application of low tidal volume ventilation strategy was significantly improved in the BI-assisted group compared with that in the SOC group (79.1% vs. 61.3%, p = 0.018). Despite their ARDS and disease severity, the BI-assisted group tended to achieve low tidal volume ventilation. The ICU and hospital mortality were lower in the BI-assisted group. CONCLUSIONS: The use of real-time visualization system for data-driven decision support was associated with significantly improved compliance to low tidal volume ventilation strategy, which enhanced the outcomes of patients with ARDS in the ICU.