23
1 Improving Sepsis Care with Data Analytics Session 243, February 14, 2019 Mischa Adams, MSN, RN, CCRN, Clinical Standards Coordinator Sarah Jenson, Analytics Director

Improving Sepsis Care with Data Analytics

  • Upload
    others

  • View
    6

  • Download
    0

Embed Size (px)

Citation preview

Page 1: Improving Sepsis Care with Data Analytics

1

Improving Sepsis Care with Data AnalyticsSession 243, February 14, 2019

Mischa Adams, MSN, RN, CCRN, Clinical Standards Coordinator

Sarah Jenson, Analytics Director

Page 2: Improving Sepsis Care with Data Analytics

2

Mischa Adams MSN, RN, CCRN Clinical Standards Coordinator

Consulting Fees: Cheetah Medical

Sarah Jenson, MS

Has no real or apparent conflicts of interest to report.

Conflict of Interest

Page 3: Improving Sepsis Care with Data Analytics

3

• History of Sepsis at Allina

• Program Development

• Data Access

• Improvement

• Future

Agenda

Page 4: Improving Sepsis Care with Data Analytics

4

• LO1: Describe how a data-driven approach to sepsis care can improve patient outcomes

• LO2: Describe how a healthcare organization can use data to monitor performance and gain clinician buy-in

• LO3: Explain why an enterprise data warehouse with dedicated septic analytics is essential to increase early identification of sepsis and adherence to treatment bundles

Learning Objectives

Page 5: Improving Sepsis Care with Data Analytics

5

Allina Health is the Minnesota Region’s Broadest Care System

About Allina:

• 85 clinic sites and ambulatory care centers.

• 5,000 physicians.

• 3.0 million+ clinic visits.

• 12 hospitals.

• 103,000+ inpatient hospital admissions.

• $4B in revenue.

• 31% Twin Cities inpatient market share.

Page 6: Improving Sepsis Care with Data Analytics

6

In the U.S., over 1.5 million people are treated for sepsis annually.

One in four people with sepsis die, making improving early

identification and providing patients with timely treatment a top

priority.

Sepsis

Seymour CW, Rea TD, Kahn JM, Walkey AJ, Yealy DM, Angus DC: Severe sepsis in pre-hospital emergency care: analysis of incidence, care, and outcome. Am J Respir Crit Care Med 2012, 186(12):1264-1271.

Page 7: Improving Sepsis Care with Data Analytics

7

• What are your system’s primary challenges for improving sepsis care?

1. Lack of timely recognition

2. Lack of data

3. Wide variation of care practices

4. Other / Unsure

Poll Question

https://live.eventbase.com/polls?event=himss19&polls=4893

Page 8: Improving Sepsis Care with Data Analytics

8

• Clinician awareness of assessment and interventions required for sepsis core measures

• Multiple, often conflicting, procedures to activate a sepsis alert (an early warning notification within the EMR indicating the patient meets criteria for sepsis)

• Fourteen different sepsis order sets

• Understanding documentation processes to accurately reflect patient care

• Lack of data visibility to understand performance

Challenges

Page 9: Improving Sepsis Care with Data Analytics

9

Sepsis at Allina Health

0%

5%

10%

15%

20%

25%

30%

0

50

100

150

200

250

300

350

Mort

alit

y R

ate

Sepsis

Vis

it V

olu

me

Sepsis Mortality over Time

Visits In-Hospital Mortality Rate

AATP

Nurse

Coordinators

Hired Ordersets

Updated

Fluid End

Time

Mandatory

Nursing

Education

Released

Inpatient

Electronic

Screening

Page 10: Improving Sepsis Care with Data Analytics

10

• Develop Sepsis Program

– Leaders from Emergency Medicine, Intensivists, Hospitalists, and Nursing

– Ancillary Pharmacy and Laboratory teams included as necessary

• Sepsis Program Coordinators are registered nurses (RN) with both clinical expertise and performance improvement skills.

– Monitor performance and facilitate process improvement efforts at the point of care

– Ensuring protocols are in alignment with current best practices.

– Develop and Deliver Education

– Deliver Provider feedback

Support

Page 11: Improving Sepsis Care with Data Analytics

11

• Where do most of your patients have the first occurrence of Severe Sepsis or Septic Shock?

1. Emergency Room

2. ICU

3. Med/Surg unit

4. Unsure

Poll Question

https://live.eventbase.com/polls?event=himss19&polls=4895

Page 12: Improving Sepsis Care with Data Analytics

12

• More than 85 percent of Allina Health Sepsis patients had infection with organ dysfunction identified in the ED

– Physician education timely identification and treatment

– Nursing education focused on the early identification of sepsis at triage and rapid initiation of sepsis orders.

Focus

0

200

400

600

800

1,000

Sepsis Volume

ED Identification IP Identification

Page 13: Improving Sepsis Care with Data Analytics

13

• Improving identification of sepsis patients for coding purposes and provider education

• Evaluation of Best Practice Alerts (BPAs)

• Automated identification of organ dysfunction

• Identifies gaps and variation in sepsis care

• Assess Protocol-based interventions

• Provide feedback to physicians about how adherence to bundles improved outcomes

Data Unlocks Improvements

Page 14: Improving Sepsis Care with Data Analytics

14

Please use this blank slide if more space is

required for charts, graphs, etc.

Remember to delete this slide, if not needed.

Page 15: Improving Sepsis Care with Data Analytics

15

• What is your average time from sepsis recognition to antibiotic administration?

1. 0-60 minutes

2. 60-120 minutes

3. 120-180 minutes

4. Unsure / Data is not available

Poll Question

https://live.eventbase.com/polls?event=himss19&polls=4894

Page 16: Improving Sepsis Care with Data Analytics

16

• Early identification has reduced the number of patients developing Septic Shock

Reducing Septic Shock

0

5

10

15

20

25

30

35

Qtr1 Qtr2 Qtr3 Qtr4 Qtr1 Qtr2 Qtr3 Qtr4 Qtr1 Qtr2 Qtr3 Qtr4 Qtr1 Qtr2 Qtr3 Qtr4 Qtr1 Qtr2 Qtr3 Qtr4

2014 2015 2016 2017 2018

Rate

per

100 S

epsis

Adm

issio

ns

Sepsis Volume -Rate per 100 Sepsis Admissions

Septic Shock Severe Sepsis

Page 17: Improving Sepsis Care with Data Analytics

17

• Increasing control and decreasing overall average time from identification of sepsis to antibiotic order.

Antibiotic Timing

0

100

200

300

400

500

600

700

Avg Time Zero to Abx Order UCL LCL Mean

Page 18: Improving Sepsis Care with Data Analytics

18

• Demonstrated improvement in Fluid Administration timing

Fluid Administration

0

20

40

60

80

100

120

140

Avg Time Zero to Fluid Complete UCL LCL Mean

Page 19: Improving Sepsis Care with Data Analytics

19

Page 20: Improving Sepsis Care with Data Analytics

20

Page 21: Improving Sepsis Care with Data Analytics

21

• 18.6% Relative reduction in mortality rate and 10.9% relative

reduction in hospital Length of Stay (LOS) for all patients with

sepsis

• 30.3% relative reduction in morality rate and 18.4% relative

reduction in hospital LOS for patients with sever sepsis and septic

shock

• $1.1 million in annual cost savings, the result of efficiencies and

substantial reductions in hospital LOS for patients with severe

sepsis or septic shock

Results

Page 22: Improving Sepsis Care with Data Analytics

22

• 2019 shift focus to Inpatient presentation of Sepsis

• Ongoing monitoring of ED Shock cases

Future

Page 23: Improving Sepsis Care with Data Analytics

23

• Please complete online session evaluation

Questions

[email protected]

Sarah JensonMischa Adams

[email protected]