Group 7 Hospital Readmission Predictive Analytics

Slides:



Advertisements
Similar presentations
THE COMMONWEALTH FUND Developing Innovative Payment Approaches: Finding the Path to High Performance Stuart Guterman Vice President, Payment and System.
Advertisements

Redefining the H Survey Responses by Region Total649 Region 1 57 Region 2 61 Region 3 62 Region 4 54 Region 5 92 Region Region 7 77 Region 8 57 Region.
Improving care transitions at Harborview Medical Center Frederick M. Chen, MD, MPH Chief of Family Medicine Associate Professor, University of Washington.
INITIATING DISCHARGE PLANNING PRIOR TO ADMISSION Start Date: October 5, 2012 Report Date: April 5, 2013 Executive Sponsors: David Mountjoy, Dennis McGowan,
BY: STEPHANIE CLARKE-MAHONEY Does Case Management Work?
PREVENTING READMISSIONS OF CONGESTIVE HEART FAILURE PATIENTS Daidreanna Whiteman Senior Project Columbus State University Summer 2014.
Association between Systolic Blood Pressure and Congestive Heart Failure in Hypertensive Patients Mrs. Sutheera Intajarurnsan Doctor of Public Health Student.
TRANSLATING VISITS INTO PATIENTS USING AMBULATORY VISIT DATA (Hypertensive patient case study) by Esther Hing, M.P.H. and Julia Holmes, Ph.D U.S. DEPARTMENT.
Reduction Of Hospital Readmissions Hany Salama, MD Diplomat ABIM IM Hospice and Palliative Care Sleep Medicine.
Performance Measures 101 Presenter: Peggy Ketterer, RN, BSN, CHCA Executive Director, EQRO Services Health Services Advisory Group June 18, :15 p.m.–4:45.
Hospital Story Donna Collins, RN,MS/ CPHQ, Quality Manager, Weeks Medical Center, NH.
HLNDV Spring Institute 2014 May 2, 2014, 1:15-2:45pm Readmission Session.
Finding a Predictive Model for Post-Hospitalization Adverse Events Henry Carretta 1, PhD, MPH; Katrina McAfee 1,2, MS; Dennis Tsilimingras 1,3, MD, MPH.
From Knowledge to Practice Translation A Multidisciplinary Intervention to Reduce 30 day Heart Failure Readmissions.
Improving Care Coordination and Readmissions Using Real Time Predictive Analytics from an HIE New Jersey / Delaware Valley HIMSS Conference Atlantic City,
Can Nurses Assist Older CHF Patients With Self-Care? Sallie A. Alvarez NGR 5800 American Heart Association.
Vantage Care Positioning System®: Make Your Case with Medicare Spending Data November 2014 avalere.com.
Emergency Department Admission Refusals Requiring Readmission at an Academic Medical Center David R. Kumar MD, Adam E. Nevel MD/MBA, John P. Riordan MD.
Clinical Terminology and One Touch Coding for EPIC or Other EHR
Wireless Access SSID: cwag2017
EHR Coding and Reimbursement
Transition to Value Based Payment
Quality of Electronic Emergency Department Data: How Good Are They?
Home Health Remote Patient Monitoring For Heart Failure
David Radley and Cathy Schoen
Patient Registries and Health Outcomes in Diabetes: A Retrospective Study Nipa Shah, MD1; Fern Webb, PhD1; Liane Hannah, BSH1; Carmen Smotherman, MS2;
Clinical Data Exchange – Report Card
Exhibit 1 Adults with High Needs Have Higher Health Care Spending and Out-of-Pocket Costs Average annual out-of-pocket spending Average annual health.
Exercise Adherence in Patients with Diabetes: Evaluating the role of psychosocial factors in managing diabetes Natalie N. Young,1, 2 Jennifer P. Friedberg,1,
Dementia as leading co-morbidity in home bound seniors: A retrospective look at first year of inception of an NP-led medical house call practice Ron Billano.
The Many Careers of Pharmacy
1.03 PP3 Healthcare Trends.
BULGARIA Istanbul, February, Turkey
Evaluating Sepsis Guidelines and Patient Outcomes
Evaluating Policies in Cardiovascular Medicine
Courtney selby, Pharm.d. arcare pgy1 Community pharmacy resident
Development and Validation of HealthImpactTM: An Incident Diabetes Prediction Model Based on Administrative Data Rozalina G. McCoy, M.D.1, Vijay S. Nori,
Patient Medical Records
1.03 Healthcare Trends.
1.03 Healthcare Trends.
Insert Objective 1 Insert Objective 2 Insert Objective 3.
Engaging a Microsystem to Reduce 30-Day Readmissions on an Acute Care Unit Erin Johnson, MSN, RN, Sara Stetz, MSN, RN.
Peg Bradke and Rebecca Steinfield
2016 Annual Data Report, Vol 2, ESRD, Ch 14
ACO Population Health: Raising the Bar Along the Journey
1.03 Healthcare Trends.
Management of Type II Diabetes
Evaluating Your Health Insurance Needs and Options
Prior authorization and patient cost-sharing are least likely to be seen as effective in reducing unnecessary care. “How effective do you think each of.
Predicting Pneumonia & MRSA in Hospital Patients
The Research Question Aims
Current national average Impact on number of people
New Strategies to Reduce HF Readmissions
Selecting the Right Predictors
Optum’s Role in Mycare Ohio
John Malaty, MD Peter J. Carek, MD, MS Maribeth Porter, MD, MSCR
System Improvement Provisions of the Affordable Care Act
Current national average Impact on number of people
1.03 Healthcare Trends.
Illustrative Performance Improvement Targets
Patient engagement with digital therapeutic leads to reduction of A1C and costs in T2DM patients: Cost savings are correlated to both A1C drops as well.
1.03 Healthcare Trends.
1.03 Healthcare Trends.
Megan Eguchi, MPh Sana karam, md, phd
Palm Beach Community Readmissions Q3 2017–Q2 2018
Heart Failure Currently, an estimated 5.7 million Americans are living with heart failure. An additional 670,000 new cases are diagnosed annually, up.
Stroke Protocols Ensure Efficient Patient Intake, Diagnosis, Treatment
PowerPoint 16:9 Screen Ratio Template *
QUALITY: COORDINATED CARE
Using Large Databases for Research
Presentation transcript:

Group 7 Hospital Readmission Predictive Analytics Janet Scott Jeffrey Kaden

Executive Summary Goal Key findings Recommendations To understand the factors that predict whether or not a hyperglycemic patient is likely to be readmitted to the hospital within 30 days of an “encounter”. Key findings “number_inpatient” is a significant predictor Other significant variables are “metformin[Down]”, “number_outpatient”, “glipizide[No]”, and “A1Cresult[None]”. Males that are 50 years of age or older have a higher rate of readmission than other segments of the population, with the highest percentage of readmissions being Caucasian males between the ages of 70 and 80. Recommendations Create strategies and treatment plans to address this disease before it progresses, thereby improving the system.

Business Problem Main Objective Regulatory Requirements Identify which diabetic patients will be readmitted within 30 days of discharge. Regulatory Requirements The Affordable Care Act established the Hospital Readmissions Reduction Program (HRRP) Requires the Centers for Medicare & Medicaid Services (CMS) to reduce payments to hospitals with excess readmission rates. Hospital Benefit Enhanced patient outcomes Improve treatment Reduce 30 day readmissions Ensure payment from CMS

Basic Questions Being Investigated What the common characteristics are that predict which patients are likely to be readmitted to the hospital within 30 days? Age Sex Weight Race If the length of a patient’s stay in the hospital is a predictor of a readmission? If the number of diagnoses for a patient entered into the Electronic Medical Record (EMR) is an indicator for readmission? What are the top 5 factors that predict a diabetic readmission within 30 days?

Existing & Traditional Ways of Addressing the Issue Currently, very little is being done in real time Hospitals are mainly using Patient education Prescription drugs Diet plan Exercise plan Monitor blood sugar Historical data Sending patients to hospice care before going home Sending patients home with a support line in the event of an issue *Problem* Patients don’t always follow doctors advice

Data Sources Obtained by the Center for Clinical and Translational Research, Virginia Commonwealth University. Health Facts database De-identified the data as required by HIPPA Ranges from the year 1999 to 2008 130 hospitals 55 attributes

Data Preparation Selected specific data variables Cleansed Data From 55 variables down to 23 variable Cleansed Data Ensured data classifications were the same Divided data into testing and validation Testing 2/3 Validation 1/3

Findings (Logistic Regression) Scatterplot Matrix Bivariate Analysis

Findings (Logistic Regression) continued Nominal Logistic Fit Confusion Matrix

Findings (Clustering) Clustering Analysis Dengrogram Scatterplot Matrix K-means Highest Risk Patients Males, 50 years and older with an extended hospital stay Highest at risk group Caucasian Males between the ages of 70-80 with an extended hospital stay.

Conclusion Answered all of the basic questions being investigated Who will likely be readmitted within 30 days? Male, Caucasian, within the age range of 70 to 80 What are the key factors that increase readmission rates? Number of inpatient visits Patients Metformin level being down Number of outpatient visits If medication “Glipizide” was administered If patients A1C test was not performed.

Conclusion Cont. How hospitals would use data findings Use key factors or expand to additional factors to broaden scope of at risk patients Flags in the Electronic Medical Record (EMR) New evaluation of at risk patients Better discharge education on at risk patients Update existing & traditional ways of addressing the issue Share information and model with other hospitals