1 of 15

Pressor Gauge

William Sweeney

Insight Fellow

Predicting the need for life-saving blood pressure medication

2 of 15

Problem: planning for pressor administration

goals of care discussion

1 in 4 ICU patients need pressors

increased testing and overnight vigilance

3 of 15

Solution: assess need for pressors in the next 12 hrs

Probability of pressor need

Streamlit

Docker

pH, pO2, pCO2

creatinine, Cl, Na, K,HCO3, BUN, glucose

hemoglobin, hematocrit, white blood cell, platelets

blood gas

CHEM-7

CBC

PTT

coags

age, weight, sex

Labs +

patient info

Hours since hosp. adm.

Current prediction

4 of 15

Workflow

Training and validation

Random forest classifier

(~12k train, 80/20 CV,

2.5k holdout)

Predictions

& live feature ranking

Feature selection

& time-binning

Data Source

~61 thousand ICU stays

~28 million lab records

>50 GB

-sought physician input (use labs!)

-Shapley scores ranking

Local DB

5 of 15

Data Cleaning

~35,000

adult, non-repeat ICU stays

w/o obvious error

~15,000

ICU stays remain

~20,000

presssors < 12 hrs post admission ,

pressor lasts < 15 min,

~61,000

ICU stays

~11,000

no pressors

~26,000

under 18,

weight > 750 lbs (misrecorded),

multiple ICUs visits

~4,000

with pressors

drop

drop

final ICU candidates (still need time-binning)

6 of 15

Time-binning features

Positive class

pressor event

-6

-12

-18

-24

-30

-36

-42

-48 hrs

Labs are taken every ~6 hrs, but not regularly

samples

aggregate labs within each window

Negative class

After dropping missing values:

~12k training samples

~3k test

7 of 15

Feature Selection

Patient info (3)

CHEM7 (7)

Blood gas (3)

CBC (4)

Coags (1)

Liver function markers (4)

+

Lactate

+

anion gap,

+

tot. abnormal labs (proxy for overall health)

25 features

8 of 15

Impact: 8 hours advanced notice!

AUROC: .70, @ 83% recall, 60% FPR

Mean prediction time to pressor event: 8 hrs

9 of 15

Impact: Overnight Care and Goals of Care

have goals of care discussions

increase testing and plan overnight care

That’s 8 hours of advanced notice to

10 of 15

William Sweeney

Seeking new adventures!

11 of 15

Backup Slides

12 of 15

Distribution of Pressor Times

13 of 15

liver/kidney function

blood acidosis

hemoglobin & hematocrit

electrolytes

14 of 15

CV Hyperparameter Tuning

Max tree depth

Number of estimators

Learning curve

15 of 15

Model Comparisons

XGBoost: AUROC .71

Logistic Regression: AUROC .67

Cox PH Regression

Naive Bayes: AUROC .65