Our mission is to improve healthcare delivery and patient outcomes, by developing, implementing, and disseminating innovations based on data science and operations research. We provide strategic and operational decision support, pioneer Healthcare Systems thinking, and promote positive change.
Reducing 72-Hour Post Discharge Adverse Events, Development of REDD Model
Transitional care interventions can be utilized to reduce post-hospital discharge adverse events (AEs). However, no methodology exists to effectively identify high-risk patients of any disease across multiple hospital sites and patient populations for short-term postdischarge AEs. The 3-day REDD (Readmissions, ED Visits, and Deaths) model predicts high-risk patients with fair discriminative power. The discriminative power of the 30-day REDD model is also better than the previously reported models under similar settings. The 3-day REDD model has been implemented and is being used to identify patients at risk for AEs.
Predicting No-shows & Late Cancellations to Improve Clinic Utilization in Neurology
Patients not attending appointments is a common problem in healthcare. This often results in compromised patient care, wasted clinical resources, and limited access for other patients. Most of the current strategies to manage “no-shows” are proven to be ineffective and costly when applied to the entire population, and few efforts have been made to accurately target and intervene on patients likely to no-show. This research aims to construct models using Artificial Neural Networks to predict the risk of a no-show for a given appointment. The dataset for this study contains 3 million appointments over a two-year period and includes clinic, provider, and patient specific attributes. The models provide the opportunity to identify patients with a high likelihood to no-show, enabling targeted interventions that have the ability to reduce no-show rates, and in turn improve patient care, provider utilization, and patient access to care.
Strategic Bed Analysis Model (StratBAM)
The ability to accurately measure and assess current and potential health care system capacities is an issue of local and national significance. Recent joint statements by the Institute of Medicine and the Agency for Healthcare Research and Quality have emphasized the need to apply industrial and systems engineering principles to improving health care quality and patient safety outcomes. To address this need, a decision support tool was developed for planning and budgeting of current and future bed capacity, and evaluating potential process improvement efforts. The Strategic Bed Analysis Model (StratBAM) is a discrete-event simulation model created after a thorough analysis of patient flow and data from Geisinger’s electronic health records. The model is generalizable and can be appropriately scaled for larger and smaller health care settings.
Reducing Inpatient Crowding with Informed Surgical Scheduling
A surgical schedule impacts multiple services within a health system and presents a daily challenge at most hospitals. This research focuses on assessing the current scheduling process and developing the Surgical Capacity, Operations, and Resource Evaluation (SCORE) tool that measures the impact of a given schedule with respect to system-wide quality and operational metrics at Geisinger. In addition, the SCORE tool will serve as a foundation for future surgical schedule improvement efforts by ensuring operational feasibility to prevent local optimization. Matching the availability of surgical resources to uncertain patient demand on a daily basis is instrumental in order to avoid compromised care, delays, and underutilized operating rooms and resources. The SCORE tool was successfully built to estimate the resource requirements generated by a schedule within and around the operating room anticipating the downstream effect on the inpatient units. This research lays the groundwork for improving system performance of an inpatient hospital through enhanced surgical scheduling.
Early Warning Score Part II
This research will develop, validate, and verify a risk prediction model using retrospective Geisinger data. That analysis will be benchmarked against the current inpatient risk algorithm performance, Modified Early Warning Score (MEWS), and other available risk prediction algorithms such as eCART.
Outpatient Provider Scheduling Optimization for Pediatric GI
This project will define the current outpatient scheduling process, develop methods to measure the quality of any given schedule, create a model to optimize the scheduling process with an interface for leadership, and then generalize this model to other specialties throughout the health system.
ENT Thyroid Surgery Time
This research aims to better understand what factors influence Thyroidectomy procedure length by utilizing text mining to extract usable discrete fields for ultrasound results.
Geisinger Community Medical Center Emergency Department Capacity Protocol
The goal of this project is to create a tool that can consistently document when an Emergency Department capacity code is called, when it is cleared, and the reason the code was initiated in the first place. The research will analyze historical data for trends and work to establish a metric that can monitor the daily capacity, as well as other key metrics that can help develop an understanding of the when and why the different codes are initiated.
This research aims to create a sustainable and efficient clinic that can continuously accommodate the growing space demand by more efficiently using existing clinic space. The goal will be to shift clinic operations from scheduled room assignments to flexible room assignments, increase the effective use of room resources and improve patient satisfaction through decreased Room-to-Physician time. This process will pilot within Geisinger’s General Surgery department.
By utilizing descriptive analysis of patient access in terms of waiting times, this project aims to analyze the demand for specific service lines in terms of current volume and opportunity volume. The goal will be to provide decision support tools to enable provider procurement at optimal periods and levels to help improve patient access