medexter®

Vom Forschungsergebnis in die klinische Routine –Klinische Entscheidungsunterstützung mit Moni-ICU

Klaus-Peter Adlassnig

Section for Medical Expert and Knowledge-Based SystemsCenter for Medical Statistics, Informatics, and Intelligent SystemsMedical University of ViennaSpitalgasse 23A-1090 Vienna, Austria

and

Medexter Healthcare GmbHBorschkegasse 7/5A-1090 Vienna, Austria

Workshop GMDS-Arbeitsgruppe „Wissensbasierte Systeme in der Medizin“, Berlin,04 April 2011

medexter®

ESBL - extended spectrum beta-lactamase

VRE - vancomycin-resistant enterococcus

MDR-TB - multidrug-resistant tuberculosis

increaseddisposition by low immunity

MRSA - methicillin-resistant Staphylococcus aureus

exposure to pathogens

entry sites

medexter®

Moni-ICU

knowledge-based identification and automated monitoring of hospital-acquired infections in adult patients in intensive care units

patient-specific alerts

infection control

natural-language definitions of nosocomial

infections

Fuzzy theories

Artificial intelligence

Monitoringof

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

medexter®

Processing layers

linguistic NI definitions

basic concepts:symptoms, signs, test results, clinical findings

intermediate concepts:pathophysiological states

abstraction:rules, type-1 & type-2 fuzzy sets, temporal abstraction

feature extraction:mean values, scores, …

preprocessing: missing data, plausibility, …

ICU + NICU patient data bases

y inference stepsreasoning

symbols

data-to-symbolconversion

data

x inference steps

layer n-x-y-1

layer 2

layer 1

layer n-x-y

layer n-y

layer n (goal)

layer 0 (start)

… ……

CDC, HELICS, KISS

Constituents of hospital-acquired infection (HAI) case definitions with HELICS

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 CC

1

037 37.5 38 38.5

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)

medexter®

medexter®

Results by Moni-ICU

• 35 HELICS + 19 KISS definitions of ICU-acquired infections– 6 + 3 definitions of bloodstream infections– 17 + 9 definitions of ICU-acquired pneumonias– 9 + 7 definitions of urinary tract infections– 3 + 0 definitions of central venous catheter-related infections

• Moni-ICU is operated at 12 ICUs at the Vienna GeneralHospital (96 beds)

• Moni-ICU is connected to HIS, LIS, and PDMS

• cockpit surveillance for infection control unit– automated daily and/or manual activation

• evaluation over a period of 2 months (2 ICUs)– 24 out of 28 patients TP (detected and correct), 0 FPs, 4 FNs (cause:

missing data, variable missing in rule condition, …), many TNs– manual evaluation of criteria: each episode of infection > 2 hours– with Moni: < 5 min per episode

medexter®

Sources of success

• clinical* no diagnoses* two-step reporting

• methodological* pure knowledge-based system* consensual classification criteria* hierarchical layers of data and knowledge* fuzzy set theory and logic

• technical* separation of PDMS data collection, service-oriented rule engine server,

knowledge packages, and web-based infection control application* integration of different hospital IT systems (HIS, LIS, PDMS, CDSS server)

• administrative* no additional data entry* almost uniform PDMS data sources at 12 ICUs* support by medical administration* several lead users