HIPxChange

Recently, healthcare has seen a sharp rise in the implementation of machine learning derived algorithms for predicting risk across a broad range of clinical scenarios. The Number Needed to Treat Thresholding Toolkit created by HIP Investigator, Dr. Brian Patterson of the BerbeeWalsh Department of Emergency Medicine, allows users to generate similar graphs, either from raw data of an algorithm’s performance in a given population, or applying an algorithm with known test characteristics at various thresholds to a theoretical population.

Predictive analytics has the potential to transform the health care system by using existing data to predict and prevent poor clinical outcomes, provide targeted care, and lower costs. A challenge for health systems is selecting and implementing predictive models within clinical and operational workflows.

To guide health systems through the process of selecting and implementing a predictive model within their system, the UW Health Applied Data Science team and the Health Innovation Program developed a toolkit to support planning for and implementation of a predictive model. This toolkit was tested through the implementation of a sepsis prediction model in the inpatient setting at UW Health, a large Midwestern academic health system with four hospitals.

The Case Management Benefit Scoring System Toolkit is now available on HIPxChange. Dr. Maureen Smith (HIP Investigator), Dr. Menggang Yu (HIP Investigator), and Dr. Jared Huling (an Assistant Professor of Statistics at The Ohio State University) partnered with the UW academic health system (UW Health) to implement a benefit scoring system that is used to identify patients for enrollment into case management.

Dr. Barbara Bowers, the Founding Director of the Center for Aging Research and Education, recently published the Implementing Change in Long-Term Care Toolkit on HIPxChange. This toolkit was designed to assist organizations, and the staff who work there, to implement changes that will improve care quality and to sustain them. In this toolkit you will find case studies, exercises, worksheets, tools, system-level questions, reading guides and case studies in five clinical practice areas that are often the focus of culture change efforts: elimination, skin, falls, nutrition and psychosocial well-being.

Dr. Barbara King, the Executive Director of the Center for Aging Research and Education recently published the Geriatric Simulations Toolkit on HIPxChange. In this toolkit you will find concrete guidance and materials to use in four simulations related to caring for older adults. Also included are reflections from students and instructors that have experienced the simulations, recommended resources, and tool recommendations for those wishing to evaluate implementation of the simulations and their impact on learners. View the toolkit on HIPxChange here.

HIP Investigator, Dr. Andrew Quanbeck published the toolkit, Decision-framing to Incorporate Stakeholder Perspectives in Implementation. Dr. Quanbeck is an assistant professor in the Department of Family Medicine and Community Health within the University of Wisconsin-Madison School of Medicine & Public Health. This toolkit contains information on how people make decisions, and how common decision-making biases can affect the success of implementation projects.

Dr. Margaret “Gretchen” Schwarze and Anne Buffington from the Wisconsin Surgical Outcomes Research Program (WiSOR) recently published Question Coding Schema: A Toolkit to Count and Categorize Questions During Surgical Consultation. The toolkit is a measurement tool for characterizing the number and types of questions patients and family members ask during surgical consultations. It enables researchers to count and describe the categories of questions that patients and family members ask while meeting with their surgeon. View the toolkit on HIPxChange here.

Dr. Maureen Smith, Director of Health Innovation Program at UW School of Medicine and Public Health recently published the Health Innovation Program DRG Categories toolkit. The goal of this toolkit is to categorize the readmission of patients discharged to a SNF from an inpatient stay by grouping those patients into diagnosis-related group (DRG) clusters based on the joint likelihood of readmission and discharge to a SNF. This toolkit contains an Excel worksheet with the mappings from MS-DRGs to corresponding categories.

Healthcare-associated infections (HAIs) are an issue of public health importance, as approximately 722,000 people are afflicted by an HAI every year (1 in 25 hospitalized patients) and 75,000 people with HAIs die. Daily bathing treatments with chlorhexidine gluconate (CHG) for hospitalized patients is one evidence-based intervention targeting HAIs. However, it is often challenging to implement these daily bathing treatments widely across an organization.

Mammography screening is essential for early detection of breast cancer. However, guidelines vary on recommendations about the age and interval at which women should start receiving mammograms.

These conflicts arise from analysis of various observational studies and clinical trials that compared the benefits and harms of different screening recommendations, and drew variable conclusions.