• Analyzing propensity of hospital readmissions of diabetic customers to reduce medical expenditure

      Bandi, Ravi; Pokhriyal, Shitanshu; Khan, Shakeel A. (2021)
      Background: A large portion of hospital inpatient management expenditure is due to high readmission rates. Diabetes is one of the leading causes of re admissions for chronically ill patients. Analyzing readmission patterns helps proactively manage and reduce readmission, thus resulting in reduced medical expenditure. Objective of the study is to find factors that lead to readmission of Diabetic patients and identify key influencers impacting readmission rates. Study Design Methods: The data originated from Cerner EMR systems with instances for over 70,000 patients and has information on Inpatient admission, diabetes type, length of stay, Lab tests performed, and medications administered across 130 US hospitals We used Logistic Regression, Na�ve Bayes and Classification tree methods and Data visualization by using key influencers to identify the key factors. Results & Findings: Using the above data mining and visualization techniques, the study had key findings as below: - Outpatient Diabetics above age 40 with HBA1c level more than 8 are more likely to readmit. - Inpatient diabetic patients with higher number of prescribed medications and number of procedures are less likely to get readmitted. - Serum level analysis shows that with High glucose serum levels, the readmission rates are higher. - Higher HbA1c in patients has a direct relationship with re admissions. - Lab Procedures show high correlation with medications, diagnosis, and time in Hospital.
    • Coworker Support Amplifies Reactions to the COVID-19 Pandemic for Working Parents

      Donnelly, Lilah; O'Brien, Kimberly; Shepard, Agnieszka (2021)
      The COVID-19 pandemic directly threatened our health and safety, while contradictory scientific and media reports generated uncertainty. Employees likely relied on their coworkers for emotional support and to make sense of the confusion. In this study, we evaluate the role of coworker support, which has been shown in the past to have either ameliorative (as a resource) or exacerbating (as social information) results. We use data, collected from a heterogeneous sample of working parents in May of 2020 (when most states were getting ready to lift their stay-at-home orders), to illustrate the path from resilient personal resources (measured as optimism, generalized self-efficacy, and internal locus of control) to fear of COVID-19 to workplace outcomes in a multiphasic study design. Employees with more optimism, generalized self-efficacy, and internal locus of control reported less fear of COVID-19, and in turn, less decrement to their workplace outcomes. This mediation is moderated by coworker support, such that the indirect effect is amplified by coworker support. This is consistent with previous research, which shows that coworker support can unintentionally corroborate and amplify employee stress perceptions. We therefore recommend that, when faced with significant adversity, organizations provide communication training oriented toward increasing positive coworker interactions and guiding social information.
    • Spaciotemporal analysis of COVID-19 to study impact of mobility on infection rate

      Hamza, Syed Ali; Bukhari, Syeda Sydra; Chandio, Sara Khan; Khan, Shakeel (2021)
      Background: COVID-19’s asymptomatic nature in some people makes it undetectable in initial days of contact and results in spread of the infection. Some countries have contained its spread, whereas some are still experiencing increasing cases. This study includes spaciotemporal analysis of COVID-19 and mobility data to provide insights in how the infection spreads while comparing the public mobility between the best and worst performing countries. Study Design/Method: The data about cases, recoveries, and deaths from Jan ’20 to Feb ’21 from John Hopkins-CSE is integrated with mobility data from Google. It is then analyzed at global level with further drilldowns into continent, countries, and states in US. Study includes comparative analysis between US and New Zealand to show which mobility parameters influenced the spread. Locations such as transit stations, retail, grocery, workspaces, residential areas, and parks were studied to find their impact. Findings: The analysis indicates that there was a short-term drop in mobility around workplaces, retail and grocery stores, and transit stores in United States along with a spike in the mobility across parks during the initial period. On the other hand, mobility has been under control in New Zealand. The study highlights that the areas with higher public activity shows higher infection rate, thus controlling the public movement around retail and grocery places has positive influence than complete shutdown of the workplaces.