Real-Time and Data-Driven Operation Optimization and Knowledge Discovery for an Enterprise Information System

An enterprise information system (EIS) is an integrated data-applications platform characterized by diverse, heterogeneous, and distributed data sources. For many enterprises, a number of business processes still depend heavily on static rule-based methods and extensive human expertise. Enterprises are faced with the need for optimizing operation scheduling, improving resource utilization, discovering useful knowledge, and making data-driven decisions.

This thesis research is focused on real-time optimization and knowledge discovery that addresses workflow optimization, resource allocation, as well as data-driven predictions of process-execution times, order fulfillment, and enterprise service-level performance. In contrast to prior work on data analytics techniques for enterprise performance optimization, the emphasis here is on realizing scalable and real-time enterprise intelligence based on a combination of heterogeneous system simulation, combinatorial optimization, machine-learning algorithms, and statistical methods.

On-demand digital-print service is a representative enterprise requiring a powerful EIS.We use real-life data from Reischling Press, Inc. (RPI), a digit-print-service provider (PSP), to evaluate our optimization algorithms.

In order to handle the increase in volume and diversity of demands, we first present a high-performance, scalable, and real-time production scheduling algorithm for production automation based on an incremental genetic algorithm (IGA). The objective of this algorithm is to optimize the order dispatching sequence and balance resource utilization. Compared to prior work, this solution is scalable for a high volume of orders and it provides fast scheduling solutions for orders that require complex fulfillment procedures. Experimental results highlight its potential benefit in reducing production inefficiencies and enhancing the productivity of an enterprise.

We next discuss analysis and prediction of different attributes involved in hierarchical components of an enterprise. We start from a study of the fundamental processes related to real-time prediction. Our process-execution time and process status prediction models integrate statistical methods with machine-learning algorithms. In addition to improved prediction accuracy compared to stand-alone machine-learning algorithms, it also performs a probabilistic estimation of the predicted status. An order generally consists of multiple series and parallel processes. We next introduce an order-fulfillment prediction model that combines advantages of multiple classification models by incorporating flexible decision-integration mechanisms. Experimental results show that adopting due dates recommended by the model can significantly reduce enterprise late-delivery ratio. Finally, we investigate service-level attributes that reflect the overall performance of an enterprise. We analyze and decompose time-series data into different components according to their hierarchical periodic nature, perform correlation analysis,

and develop univariate prediction models for each component as well as multivariate models for correlated components. Predictions for the original time series are aggregated from the predictions of its components. In addition to a significant increase in mid-term prediction accuracy, this distributed modeling strategy also improves short-term time-series prediction accuracy.

In summary, this thesis research has led to a set of characterization, optimization, and prediction tools for an EIS to derive insightful knowledge from data and use them as guidance for production management. It is expected to provide solutions for enterprises to increase reconfigurability, accomplish more automated procedures, and obtain data-driven recommendations or effective decisions.

Costa Rica's payment for environmental services program: intention, implementation, and impact.

We evaluated the intention, implementation, and impact of Costa Rica's program of payments for environmental services (PSA), which was established in the late 1990s. Payments are given to private landowners who own land in forest areas in recognition of the ecosystem services their land provides. To characterize the distribution of PSA in Costa Rica, we combined remote sensing with geographic information system databases and then used econometrics to explore the impacts of payments on deforestation. Payments were distributed broadly across ecological and socioeconomic gradients, but the 1997-2000 deforestation rate was not significantly lower in areas that received payments. Other successful Costa Rican conservation policies, including those prior to the PSA program, may explain the current reduction in deforestation rates. The PSA program is a major advance in the global institutionalization of ecosystem investments because few, if any, other countries have such a conservation history and because much can be learned from Costa Rica's experiences.

Multiple Response System: Evaluation of Policy Change in North Carolina's Child Welfare System.

Systemic challenges within child welfare have prompted many states to explore new strategies aimed at protecting children while meeting the needs of families, but doing so within the confines of shrinking budgets. Differential Response has emerged as a promising practice for low or moderate risk cases of child maltreatment. This mixed methods evaluation explored various aspects of North Carolina's differential response system, known as the Multiple Response System (MRS), including: child safety, timeliness of response and case decision, frontloading of services, case distribution, implementation of Child and Family Teams, collaboration with community-based service providers and Shared Parenting. Utilizing Child Protective Services (CPS) administrative data, researchers found that compared to matched control counties, MRS: had a positive impact on child safety evidenced by a decline in the rates of substantiations and re-assessments; temporarily disrupted timeliness of response in pilot counties but had no effect on time to case decision; and increased the number of upfront services provided to families during assessment. Qualitative data collected through focus groups with providers and phone interviews with families provided important information on key MRS strategies, highlighting aspects that families and social workers like as well as identifying areas for improvement. This information is useful for continuous quality improvement efforts, particularly related to the development of training and technical assistance programs at the state and local level.

Reduced length of hospital stay in colorectal surgery after implementation of an enhanced recovery protocol.

BACKGROUND: Enhanced recovery after surgery (ERAS) is a multimodal approach to perioperative care that combines a range of interventions to enable early mobilization and feeding after surgery. We investigated the feasibility, clinical effectiveness, and cost savings of an ERAS program at a major U. S. teaching hospital. METHODS: Data were collected from consecutive patients undergoing open or laparoscopic colorectal surgery during 2 time periods, before and after implementation of an ERAS protocol. Data collected included patient demographics, operative, and perioperative surgical and anesthesia data, need for analgesics, complications, inpatient medical costs, and 30-day readmission rates. RESULTS: There were 99 patients in the traditional care group, and 142 in the ERAS group. The median length of stay (LOS) was 5 days in the ERAS group compared with 7 days in the traditional group (P < 0.001). The reduction in LOS was significant for both open procedures (median 6 vs 7 days, P = 0.01), and laparoscopic procedures (4 vs 6 days, P < 0.0001). ERAS patients had fewer urinary tract infections (13% vs 24%, P = 0.03). Readmission rates were lower in ERAS patients (9.8% vs 20.2%, P = 0.02). DISCUSSION: Implementation of an enhanced recovery protocol for colorectal surgery at a tertiary medical center was associated with a significantly reduced LOS and incidence of urinary tract infection. This is consistent with that of other studies in the literature and suggests that enhanced recovery programs could be implemented successfully and should be considered in U.S. hospitals.

Phylotastic! Making tree-of-life knowledge accessible, reusable and convenient.

BACKGROUND: Scientists rarely reuse expert knowledge of phylogeny, in spite of years of effort to assemble a great "Tree of Life" (ToL). A notable exception involves the use of Phylomatic, which provides tools to generate custom phylogenies from a large, pre-computed, expert phylogeny of plant taxa. This suggests great potential for a more generalized system that, starting with a query consisting of a list of any known species, would rectify non-standard names, identify expert phylogenies containing the implicated taxa, prune away unneeded parts, and supply branch lengths and annotations, resulting in a custom phylogeny suited to the user's needs. Such a system could become a sustainable community resource if implemented as a distributed system of loosely coupled parts that interact through clearly defined interfaces. RESULTS: With the aim of building such a "phylotastic" system, the NESCent Hackathons, Interoperability, Phylogenies (HIP) working group recruited 2 dozen scientist-programmers to a weeklong programming hackathon in June 2012. During the hackathon (and a three-month follow-up period), 5 teams produced designs, implementations, documentation, presentations, and tests including: (1) a generalized scheme for integrating components; (2) proof-of-concept pruners and controllers; (3) a meta-API for taxonomic name resolution services; (4) a system for storing, finding, and retrieving phylogenies using semantic web technologies for data exchange, storage, and querying; (5) an innovative new service, DateLife.org, which synthesizes pre-computed, time-calibrated phylogenies to assign ages to nodes; and (6) demonstration projects. These outcomes are accessible via a public code repository (GitHub.com), a website (http://www.phylotastic.org), and a server image. CONCLUSIONS: Approximately 9 person-months of effort (centered on a software development hackathon) resulted in the design and implementation of proof-of-concept software for 4 core phylotastic components, 3 controllers, and 3 end-user demonstration tools. While these products have substantial limitations, they suggest considerable potential for a distributed system that makes phylogenetic knowledge readily accessible in computable form. Widespread use of phylotastic systems will create an electronic marketplace for sharing phylogenetic knowledge that will spur innovation in other areas of the ToL enterprise, such as annotation of sources and methods and third-party methods of quality assessment.

Implementation of automated reporting of estimated glomerular filtration rate among Veterans Affairs laboratories: a retrospective study.

BACKGROUND: Automated reporting of estimated glomerular filtration rate (eGFR) is a recent advance in laboratory information technology (IT) that generates a measure of kidney function with chemistry laboratory results to aid early detection of chronic kidney disease (CKD). Because accurate diagnosis of CKD is critical to optimal medical decision-making, several clinical practice guidelines have recommended the use of automated eGFR reporting. Since its introduction, automated eGFR reporting has not been uniformly implemented by U. S. laboratories despite the growing prevalence of CKD. CKD is highly prevalent within the Veterans Health Administration (VHA), and implementation of automated eGFR reporting within this integrated healthcare system has the potential to improve care. In July 2004, the VHA adopted automated eGFR reporting through a system-wide mandate for software implementation by individual VHA laboratories. This study examines the timing of software implementation by individual VHA laboratories and factors associated with implementation. METHODS: We performed a retrospective observational study of laboratories in VHA facilities from July 2004 to September 2009. Using laboratory data, we identified the status of implementation of automated eGFR reporting for each facility and the time to actual implementation from the date the VHA adopted its policy for automated eGFR reporting. Using survey and administrative data, we assessed facility organizational characteristics associated with implementation of automated eGFR reporting via bivariate analyses. RESULTS: Of 104 VHA laboratories, 88% implemented automated eGFR reporting in existing laboratory IT systems by the end of the study period. Time to initial implementation ranged from 0.2 to 4.0 years with a median of 1.8 years. All VHA facilities with on-site dialysis units implemented the eGFR software (52%, p<0.001). Other organizational characteristics were not statistically significant. CONCLUSIONS: The VHA did not have uniform implementation of automated eGFR reporting across its facilities. Facility-level organizational characteristics were not associated with implementation, and this suggests that decisions for implementation of this software are not related to facility-level quality improvement measures. Additional studies on implementation of laboratory IT, such as automated eGFR reporting, could identify factors that are related to more timely implementation and lead to better healthcare delivery.