Daniel Adomako Asamoah

Business analytics: Research and teaching perspectives

Business analytics and big data are being discussed everywhere right now. The objective of this paper is to provide a research and teaching introduction to business analytics. It begins by providing a quick overview of the three types of analytics. To assist the future analytics professionals, we identify various sectors of the analytics industry and provide a classification of different types of industry participants. Then it includes a brief description of some current research projects under way in our team. We also note some research opportunities in Big Data analytics. The paper also concludes with a discussion of teaching opportunities in analytics.

Improving rounding in critical care environments through management of interruptions

Efficient and effective functioning of intensive care units (ICU) has a significant impact on the safety of patients who are critically sick, performance of care providers, utilization of clinical resources, and is essential for improving the overall healthcare delivery. This study focuses on developing a better understanding of ICU rounding process, which is a team-based activity and is routinely conducted with the objective of providing an error-free and customized treatment plan for each patient admitted to an ICU. However, rounding process is complex, ill-understood and marred by numerous inefficiencies. In this study, we develop process framework for ICU care delivery that integrates various pathophysiologic, care delivery and intervention processes. We do this by examining the rounding workflow of two major teaching hospitals in the US. One major issue for rounding process is interruptions. We suggest and test strategies for improving ICU rounding workflow by managing interruptions. This is accomplished through the development of simulation models to compare the relative merits of controlling interruptions in ICU with respect to overall rounding completion time. We found that as much as 39% time savings can be realized with alternate interruption control methods.

Keep the conversations going: engagement-based customer segmentation on online social service platforms

Most businesses and organizations develop online services as a value-added offering, which is a significant revenue stream from their existing user base. Such services may be enhanced with social elements to serve as value-added tools for user attraction and retention. Social elements may allow users to post content, share information and directly interact with each other. Investments in these social features are for naught if they do not encourage users to engage on the platform effectively. However, common ways to segment customers by their engagement is hindered by the statistical nature of behavioral data based on social elements. To address this important concern, this paper presents a methodological framework for engagement-based customer segmentation able to appropriately consider signals from social elements. It argues why the traditional approaches for user segmentation is ill-suited and advocates for the integration of kernel functions with clustering to segment, identify and understand user engagement profiles. The framework is demonstrated with real data from a large, very active OSS.

RFID-based information visibility for hospital operations: exploring its positive effects using discrete event simulation

Long queues and wait times often occur at hospitals and affect smooth delivery of health services. To improve hospital operations, prior studies have developed scheduling techniques to minimize patient wait times. However, these studies lack in demonstrating how such techniques respond to real-time information needs of hospitals and efficiently manage wait times. This article presents a multi-method study on the positive impact of providing real-time scheduling information to patients using the RFID technology. Using a simulation methodology, we present a generic scenario, which can be mapped to real-life situations, where patients can select the order of laboratory services. The study shows that information visibility offered by RFID technology results in decreased wait times and improves resource utilization. We also discuss the applicability of the results based on field interviews granted by hospital clinicians and administrators on the perceived barriers and benefits of an RFID system.

Evaluating electronic health record systems: a system dynamics simulation

Implementing electronic health record (EHR) systems in the next few years is on the agenda for many healthcare organizations. Before investing in an EHR system, however, decision makers need to identify and measure the benefits of such systems. We propose using a system dynamics (SD) approach to measuring the benefits of EHR systems. Using an SD approach, it is possible to map complex relationships among clinical processes in hospitals into a model by which one can dynamically measure the effect of any changes in the parameters over time. Simulation of EHR implementations using an SD model produces useful data on the benefits of EHRs that are hard to obtain through empirical data collection methods. The results of an SD model can then be transformed into economic values to estimate financial performance. This paper presents an example of an SD model and its application in EHR decision making.

Interdisciplinarity in Data Science Pedagogy: A Foundational Design

ABSTRACT Data science is an interdisciplinary field that generates insights in data to aid decision-making. Recognizing that data scientists must be interdisciplinary, agile, and able to adapt to data analysis across many domains, both academia and the industry are striving to integrate interdisciplinary learning and transferable skills into data science curriculum. This paper introduces an interdisciplinary approach to teaching the foundations of data science. We evaluate two different interdisciplinary formats. The first format considers collaborative efforts among instructors with different academic disciplines. The second involves a sole instructor that discusses data science concepts from different disciplines and related to business processes, computer science, and programming. We demonstrate that interdisciplinarity ensures favorable learning experiences and produces high learning outcomes. We also show that our course design maintains and promotes interdisciplinarity even in situations where logistical constraints would not support the use of multiple instructors to deliver one course.