Case Studies 1. Patient volume Purpose: Predict patient volume, understand drivers of volume Approach: model sources of admissions (sequence and survival.

Slides:



Advertisements
Similar presentations
Welcome package (customization) FLL July IT requirements -Hardware recommendations -Contact information -Clinical / technical contact -Office addresses.
Advertisements

Health IT Certificate Series. 2 Why Health IT? Health information technology (health IT) makes it possible for health.
PCC Data Entry Coding Que Albuquerque Area Office Coding Que Training 1/18/07 – 1/19/07.
VI. Facility Designations VI-1. Facility Designations Objective: Participants will understand: 1) The three types of facilities that can be designated,
PwC and Medical Necessity Issues and Concerns Emerging OIG scrutiny on medical necessity; nearly 500 hospitals on national target list for Medicare compliance.
5/24/20151 Fitting the Pieces Together Utilizing a Hospitalist in the ED to Reduce Admissions Presented by: Patty Williamson, CFO Isidoros Vardaros, M.D.
The Role of Information Technology For A Private Medical Practice Noel Chua Rosalinda Raymundo.
ICU Clinical Information Management System An Investigation for a Pediatric Intensive Care Unit Steven Sousa Ann Thompson.
Nursing Diagnosis Chapter Copyright 2004 by Delmar Learning, a division of Thomson Learning, Inc. Nursing Diagnosis  The term nursing diagnosis.
It’s A Success! Achieving Cost-Effective Disease Management in CHF Sherry Shults, RN BSN CIO South Carolina Heart Center.
INTRODUCTION TO ICD-9-CM PART TWO ICD-9-CM Official Guidelines (Sections II and III): Selection of Principal Diagnosis/Additional Diagnoses for Inpatient.
Medication History: Keeping our patients safe. How do we get all of the correct details?
Clinical Management Nutr 564: Management Summer 2005.
By : Alanoud Al Saleh. What is PACS quality control ? The PACS monitor quality control (QC) program objectives are:  to ensure consistent display performance.
Presented by Kara R. Flickinger, RN.  Describe content of Lean Six Sigma  Describe & evaluate implementation of Lean Six Sigma in nursing.  Evaluate.
Health Care Workforce needs for an industry in transformation Katrina M. Lambrecht, JD, MBA Vice President, Institutional Strategic Initiatives Office.
Using a Patient Portal for Electronic Communication With Patients With Cancer: Implications for Nurses Oncology Nursing Forum Elizabeth S. Rodriguez, DNP,
Department of Human Services Promoting patient care through effective patient flow System wide implementation January – July 2005.
M Purpose Improvement Tools/Methods Limitations / Lessons Learned Results Process Improvement Improving Hospital-Acquired Pressure Ulcers at Discharge.
Chapter 23 Includes Supplements 4 through 8. The Revenue Equation.
Early Detection of Hospitalized Patients with Previously Diagnosed Obstructive Sleep Apnea Using Computer Decision Support Alerts R. Scott Evans, Vrena.
Medical Records. What are medical records?  Legal documents  Management of patient care  Alert healthcare providers to changes in patient conditions.
A Pilot Study of a Care Coordination Model in a Community Health Center Peak Vista Community Health Centers September 16, 2015 Public Health in the Rockies.
Medical Coding II Seminar 6.
Copyright © 2008 Delmar Learning. All rights reserved. Unit 8 Observation, Reporting, and Documentation.
Medicare Documentation & ICD-9-CM Coding Presented by Rhonda Anderson, RHIA President Anderson Health Information Systems, Inc
Risk Assessment Farrokh Alemi, Ph.D.. Session Objectives 1.Discuss the role of risk assessment in the TQM process. 2.Describe the five severity indices.
7-1 Chapter 7 Ambulatory Healthcare © 2012 The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill.
Put Prevention Into Practice. Understand the PPIP Program What is Put Prevention Into Practice (PPIP)? What is Put Prevention Into Practice (PPIP)? Why.
Nicole Sutherlin Brianna Mays Eliza Guthorn John McDonough.
School of Health Sciences Week 4! AHIMA Practice Brief Fundamentals of Health Information HI 140 Instructor: Alisa Hayes, MSA, RHIA, CCRC.
Appendices. Appendix 1: Supplementary Data Tables Trends in the Overall Health Care Market.
The State of America’s Hospitals – Taking the Pulse CHART PACK.
Basic Nursing: Foundations of Skills & Concepts Chapter 9
The National Hospital Care Survey Linda McCaig, M.P.H. National Center for Health Statistics August 8, 2012.
Chapter 18 by Sheldon Prial and Schuyler F. Hoss Overview of Home Telehealth.
THE SOONER, THE BETTER: A FEEL LIKE HOME FACILITY FOR JUST DISCHARGED ELDERLY PATIENTS Chiara Martini EAFIP Workshop Manchester, 24 th November 2015.
E-MDs Reference Report All information obtained from references provided by vendor.
Copyright © 2011, 2006 by Saunders an imprint of Elsevier Inc. UNDERSTANDING HOSPITAL BILLING AND CODING CHAPTER 3 Hospital Organizational Structure and.
Memphis, TN Thomas Duarte, Executive Director, MSeHA.
Improving Care Coordination and Readmissions Using Real Time Predictive Analytics from an HIE New Jersey / Delaware Valley HIMSS Conference Atlantic City,
Utilizing the Patient Safety Indicators for Improvement Anita Gottlieb, MA, APN, CPHQ St. Joseph’s Mercy Health System Hot Springs, Arkansas.
Statistics Terminology. Statistics The mathematics of the collection, organization, summarization, and analysis of numerical data Involves both numbers.
CQN Team Presentation Ohio Cleveland Clinic Children’s Hospital Kim Giuliano, MD Sharon O’Brien, MA Ivana Wilson, Medical Secretary.
Bundled Payments for Care Improvement (BPCI) Alliance for Health Reform Capitol Hill Briefing Jim Garnham Dir. Contracting & Payment Innovation.
Bee Wise…Immunize! ™ Bee Wise…Immunize! ™ A Back-to-School Collaborative A Back-to-School Collaborative.
PREDICTIVE ANALYTICS IN AN ACO WORLD OSF HEALTHCARE EXPERIENCE OCTOBER 2014.
Chapter 4 Nursing Process and Critical Thinking Copyright © 2014, 2009 by Saunders, an imprint of Elsevier Inc. All rights reserved.
HI250 Medical Coding II Seminar 9. Unit 9 E/M codes E/M codes Evaluation and Management coding Evaluation and Management coding Documentation in the patient’s.
Clinical Decision Support Implementation Victoria Ferguson, COO - Program Manager Christopher Taylor, CIO – Business Owner Monica Kaileh, CMIO – Steering.
Chart 3.1: Inpatient Admissions in Community Hospitals, 1993 – 2013 Source: Avalere Health analysis of American Hospital Association Annual Survey data,
CTC Clinical Strategy and Cost Committee
Evaluation and management (E/M) Services
Mary Fournogerakis, BSN, RN, OCN Rebecca Martin, BSN, RN, OCN, BMTCN
ENG 491 Competitive Success/snaptutorial.com
DAT 565 Competitive Success-- snaptutorial.com
HLT 205 Competitive Success-- snaptutorial.com
ORG 711 Competitive Success-- snaptutorial.com
DAT 565 Competitive Success/tutorialrank.com
HLT 205Competitive Success/tutorialrank.com
ORG 711Competitive Success/tutorialrank.com
DAT 565 Education for Service-- snaptutorial.com
ORG 711 Teaching Effectively-- snaptutorial.com
DAT 565 Teaching Effectively-- snaptutorial.com
The Nursing Process and Pharmacology Jeanelle F. Jimenez RN, BSN, CCRN
Inpatient and Outpatient Coding
Chapter 2 Nursing Process
Module 6 Part 3 Choosing the Correct Type of Control Chart Limits
Risk Stratification for Care Management
Assigning Risk Categories to Patients
Presentation transcript:

Case Studies 1

Patient volume Purpose: Predict patient volume, understand drivers of volume Approach: model sources of admissions (sequence and survival analysis) and discharges Results: Aggregate forecast was better than their baseline forecast More insight into service line forecasts, variation over time Patient volume was predicted to day and nurses station Created the ability to do ‘what-if’ analysis 2

Patient volume 3 Algorithms Outpatient Clinics Emergenc y Dept. Physician Office Activity Day of the week Length of stay Nurse unit Predicted daily census by nurses station

Customer segmentation 4

Demand by customer segment Demand Landscape: The height represents potential demand; the areas represent ZIP code areas.

Demand by customer Segment Service 1, White, Youth 2015 High Demand Medium Demand Low Demand Facility Service 2, African American, Male, Service 3, White, Female 2015

Chart Review Purpose: Identify a less costly, more efficient and effective way to obtain information from physician notes. Approach: competition between text mining and two teams of professionals Results: Text mining was as good as or better than the professional teams for –Assigning state of patient into taxonomy provided for the diagnosis –Assigning ‘positive’, negative’ or ‘neutral’ assessment of patient compared to previous visit and from first encounter assessment Text mining identified valuable information not sought after but is valuable –documented observations of health change not associated with the diagnosis Text mining is not successful when physician notes are lacking –Text mining was used to predict physician assigned scales of specific observation ‘measures’

Device failure Purpose: Anticipate and understand device failures using technician notes Approach: Text mining, categorization, root cause analysis, early warning Results: More efficient and effective corrective action –Design, engineering, vendor selection, packaging, labeling and customer education Early warning system, producing alerts when failure rates exceed previous (similar product) experienced component failure rates. Predicted future warranty work from identified rates, installed base of product, implemented corrective actions (to mitigate historical failure rates)