Erfahrungen mit einem neuen Computer-gestützten System zur automatischen Erfassung und Überwachung von nosokomialen Infektionen an Intensivstationen –

MONI 4

A. Blacky, W. Koller, H. Mandl, und K.P. Adlassnig

Fully Automated Surveillance of Healthcare-Associated Infections with MONI-ICU

A Breakthrough in Clinical Infection Surveillance

ICU Wards at the Vienna General Hospital

• 13B1• 13B3• 13C1• 13C2• 13C3• 13H1• 13H3• 13I1• 13I2• 13I3• transplant ICU• neurosurgery ICU• NICU 9C• NICU E10• NICU E12

Erfolge bei der Infektions- prävention

Aufwand für die Surveillance

Hoher Dokumentationsaufwand bei hoher Datenredundanz:

Viele Daten liegen redundant in verschiedenen IT-Systemen vor . . .So often are the same data in various IT-Systems stored ….. Verwaltungssystem, Laborinformationssystem,Billingsystems, Laboratorysystems, ……Pflegedokumentation, Anästhesieinformationssystem,Caredocumentation, ……Medizinische Patientendokumentation, etc.

„Der Mensch ist für den Computer da“

Der Computer ist für die Menschen da!!!

Computers in Clinical Medicine

• step 1: patient administration– admission, transfer, discharge, and cost billing

• step 2: documentation of patients’ medical data– electronic health record: life-long, multimedia

• step 3: patient data retrieval– medical research databases (data mining)– quality assurance in the medical institution

• step 4: software-based clinical decision support– quality assurance for the particular patient

patient-specific alerts

infection control

natural-language definitions of nosocomial infections

Fuzzy theories

Artificial intelligence

Monitoring of

nosocomial infections

knowledge-based systems

fuzzy sets and logic

ICUICU

microbiology

cockpit surveillance remote

clinical data

Medicine

data on microorganisms

cockpit surveillance at ward ICU

Bloodstream Infections (BSI)

• bloodstream infection with

– recognized pathogen– clinical signs and growth

of same skin contaminant from two separate blood samples

– clinical signs and growth skin contaminant from blood and intravascular line in place and AB Therapy

– clinical signs and positive antigen test from blood

Bloodstream infection with clinical signs and growth of same skin contaminant from two separate blood samples

BSI-A2

1

clinical_signs_of_BSI (t-1d, t, t+1d)

same_skin_contaminant_from_two_separate_blood_samples

Decomposition—clinical signs

clinical_signs_of_BSI (t-1d, t, t+1d)[yesterday, today, tomorrow]

=fever (t-1d)

hypotension (t-1d)

clinical_signs_of_BSI (t-1d) = leucopenia (t-1d)

leucocytosis (t-1d)

CRP increased (t-1d)

fever (t)

hypotension (t)

clinical_signs_of_BSI (t) = leucopenia (t)

leucocytosis (t)

CRP increased (t)

fever (t+1d)

hypotension (t+1d)

clinical_signs_of_BSI (t+1d) = leucopenia (t+1d)

leucocytosis (t+1d)

CRP increased (t+1d)

fever (t-1d)

...

body temperature

fever (t)

thermoregulation applied

fever (t+1d)

...

Clinical signs—fever

data import

intensive care unit

maximum value of the day e.g., 38.5 C

C

1

037 37.5 38 38.5

Clinical Signs—CRP Increased

CRP increased (t-1d)

…

CRP increased (t)

CRP increased (t+1d)

…

data import

intensive care unit

maximum value of the day e.g., 5 mg/dl

mg/dl0

1 6

CRP

0.8

1

5

Decomposition—skin contaminant

first blood culture

- coagulase-negative staphylococci

- Micrococcus sp.

- Propionibacterium acnes

- Bacillus sp.

- Corynebacterium sp.

same_skin_contaminant_from_two_separate_blood_samples

second blood culture

- coagulase-negative staphylococci

- Micrococcus sp.

- Propionibacterium acnes

- Bacillus sp.

- Corynebacterium sp.

data import

microbiology

(within 48 hours)

Aller Anfang ist schwer . . .

Data sources and integration

HIS: hospital information system (here: HIS of the City of Vienna)PDMS: patient data management systems (here: CareVue by Philips)CDA: clinical data archiveISM: information support martLIS: laboratory information system of the microbiology (here: HIS of the City of Vienna)HIS DB: relational data base of medical data

LIS

PDMS s

CDA

ISMHIS

DBHIS

…

Moni 4

clinical data

microbiological data

CareVueCareVue

CareVueCareVue

administrative data +

HIS

patient-specific alerts

infection control

natural-language definitions of nosocomial infections

Fuzzy theories

Artificial intelligence

Monitoring of

nosocomial infections

knowledge-based systems

fuzzy sets and logic

ICUICU

microbiology

cockpit surveillance remote

clinical data

Medicine

data on microorganisms

cockpit surveillance at ward ICU

Cockpit Surveillance at the infection control unit

Catheter-Associated Symptomatic Urinary Tract Infection

completely fulfilled (100%)

Backtracking of the Logical Chain of Reasoning

patient has urinary catheter

Elevated CRP as a Clinical Sign present (100%)

Elevated CRP is Present 6 mg/dl is measured

Other Signs of Urinary Tract Infection Pyurie

Neues MONI 4: MONI ICU und MONI N- ICU

„The Next Generation“

n without HCAI with HCAI

patients 52ICU stays 55 44 11*

LOS (days)median:7 shortest:1 longest:25

patient days 422 367 55

* comprising 18 HCAI episodes: 7 with one, 1 with two and 3 with three distinct infection episodes during one stay

MONI 4: Evaluierung

1 ICU:

MONI reported: 11 stays with HCAI 44 stays without HCAI

HCAI present 8 (72.7%) 0 (0%)

HCAI absent 3* (27.3%) 44 (100%)

human expert reported:

HCAI present 8 (72.7%) 1** (2.3%)

HCAI absent 3*** (27.3%) 43 (97.7%)

# one or more HCAIs during one stay* 2 PN episodes and 1 CRI episode not reported due to missing import of electronic microbiology report ** human expert wrongly reported a UTI due to clinical notes in dismission report which could not be verified by any data in the patient charts (UT-colonisation only)*** human expert missed 2 CRI and 1 BSI episodes

HCAI condition# per ICU stay correctly or falsely identified by MONI and by the human expert

Sensitivity and specificity of automated MONI vs. human expert HCAI surveillance

MONI human expert

syndrome n sensitivity specificity sensitivity specificity

BSI 3 100% 100% 0% 100%

CRI 9 88.8% 100% 33.3% 100%

PN 5 40% 100% 100% 100%

overall HCAI** 11 72.7% 100% 72.7% 97.7%

** comprising 18 HCAI episodes: 7 with one, 1 with two and 3 with three distinct infection episodes during one stay

Conventional surveillance

MONI-ICU surveillance

Time spent82.5 h (100%)

12.5 h (15.2%)

Surveillance - Zeitbedarf

2 ICUs alle ICUs

Erfolge bei der Infektions- prävention

Aufwand für die Surveillance

Herzlichen Dank!

Der Computer ist für die Menschen da!!!