From Cues to Nudge: A Knowledge-Based …surveillance.mcgill.ca/manuscripts/publ147_Shaban-Nejad...SYSTEMS-LEVEL QUALITY IMPROVEMENT From Cues to Nudge: A Knowledge-Based Framework

SYSTEMS-LEVEL QUALITY IMPROVEMENT

From Cues to Nudge: A Knowledge-Based Frameworkfor Surveillance of Healthcare-Associated Infections

Arash Shaban-Nejad1,2& Hiroshi Mamiya2 & Alexandre Riazanov3 & Alan J. Forster4 &

Christopher J. O. Baker2,5 & Robyn Tamblyn2& David L. Buckeridge2

Received: 3 June 2015 /Accepted: 30 September 2015# Springer Science+Business Media New York 2015

Abstract We propose an integrated semantic web frameworkconsisting of formal ontologies, web services, a reasoner and arule engine that together recommend appropriate level ofpatient-care based on the defined semantic rules and guide-lines. The classification of healthcare-associated infectionswithin the HAIKU (Hospital Acquired Infections – Knowl-edge in Use) framework enables hospitals to consistently fol-low the standards along with their routine clinical practice anddiagnosis coding to improve quality of care and patient safety.The HAI ontology (HAIO) groups over thousands of codesinto a consistent hierarchy of concepts, along with relation-ships and axioms to capture knowledge on hospital-associatedinfections and complications with focus on the big four types,surgical site infections (SSIs), catheter-associated urinary tractinfection (CAUTI); hospital-acquired pneumonia, and bloodstream infection. By employing statistical inferencing in ourstudy we use a set of heuristics to define the rule axioms toimprove the SSI case detection. We also demonstrate how theoccurrence of an SSI is identified using semantic e-triggers.

The e-triggers will be used to improve our risk assessment ofpost-operative surgical site infections (SSIs) for patients un-dergoing certain type of surgeries (e.g., coronary artery bypassgraft surgery (CABG)).

Keywords Ontologies . Knowledgemodeling .

Healthcare-associated infections . Surveillance . Semanticframework . Surgical site infections

Introduction

Healthcare-associated Infections (HAIs) affect millions ofpatients around the world, killing hundreds of thousandsand imposing, directly or indirectly, a significant socio-economic burden on healthcare systems [1]. Accordingto the Centers for Disease Control (CDC) [2], hospital-acquired infections in the U.S., where the point preva-lence of HAIs among hospitalized patients is 4 %, resultin an estimated 1.7 million infections, which lead to asmany as 99,000 deaths and cost up to $45 billion annually[3, 4]. Similar or higher rates of HAI occur in other coun-tries as well with an estimated 10.5 % of patients in Ca-nadian hospitals having an HAI [5]. Clinical assessmentand laboratory testing are generally used to detect andconfirm an infection, identify its origin, and determineappropriate infection control methods to stop the infectionfrom spreading within a healthcare institution. Failure tomonitor, and detect HAI in timely manner can delay di-agnosis, leading to complications (e.g., sepsis), andallowing an epidemic to spread.

To ensure the quality of care given to the patients inhealthcare settings, it is crucial to have systems that mon-itor for cases of HAI [6]. Our knowledge-based surveil-lance infrastructure enables monitoring for HAIs and

This article is part of the Topical Collection on Systems-Level QualityImprovement

* Arash [email protected]

1 School of Public Health, University of California at Berkeley, 50University Hall, 94720-7360 Berkeley, CA, USA

2 Department of Epidemiology and Biostatistics, McGill University,Montreal, QC, Canada

3 IPSNP Computing Inc, Suite 1000, 44 Chipman Hill, Station A, POBox 7289, Saint John, NB E2L 4S6, Canada

4 Faculty of Medicine, University of Ottawa, Ottawa, ON, Canada5 Department of Computer Science, University of New Brunswick,

Saint John, NB, Canada

J Med Syst (2016) 40:23 DOI 10.1007/s10916-015-0364-6

generates an alert when a suspect, probable, or confirmedcases of HAI is detected. In this paper we focus on sur-gical site infections (SSIs), one of the most commonhealthcare associated infections, accounting for about31 % of all HAIs among hospitalized patients in 2010 inU.S [7]. Diagnosis of an SSI relies mainly on direct ob-servation of physical signs and symptoms of infection inan incisional wound and a case cannot usually be con-firmed solely by analyzing data given in laboratory re-ports. Given the diversity, complexity and heterogeneityof HAI data, availability of a reference vocabulary is aprerequisite of creating an integrated knowledge-basedsystem. Despite several modifications and improvementsto existing terminologies made by the Centers for DiseaseControl and Prevention (CDC) in the last decade, e.g.,specifying the location of infections related to surgicaloperations and clarifying the criteria to identify the exactanatomic location of deep infections [8], inconsistencies,discrepancies, and confusion in the application of thecriteria in different medical/clinical practices still exist,and there is a need for further improvement and clarifica-tion of the current nomenclature [9].

While the Centers for Disease Control and Prevention(CDC) has provided a certain criteria as a guideline [8] toprevent, control and reduce HAIs, in the HAIKU project[10] we have brought together expertise in artificial intel-ligence, knowledge modeling, epidemiology, medicine,and infection control to explore how advances in semantictechnology can improve the analysis and detection ofHAIs. To develop a common understanding about the do-main of infection control and to achieve data interopera-bility in the area of healthcare-associated infections, wepresent the HAI Ontology as part of the HAIKU (HospitalAcquired Infections – Knowledge in Use) project. Theformal HAI ontology assists researchers and health pro-fessionals in analyzing medical records to identify andflag potential cases of HAIs among patients who couldbe at risk of acquiring an SSI.

In this paper we discuss the role and importance of theHAIKU semantic infrastructure to improve the detection ofHAI using semantic web technologies. The paper is organizedas follows: BExisting methods for detecting HAI^ section pre-sents an overview of existing tools and systems for managingnosocomial infections. The HAIKU ontology design and im-plementation along with the related semantic rules and axiomsdesigned for intelligent alerting are presented in BThe HAIontology: an overview^ and BTheHAIKU framework for casede tec t ion and repor t ing^ sec t ion , respec t ive ly.BAxiomatization using semantic and statistical analysis^ sec-tion presents our axiomatization process informed by statisti-cal analysis of existing datasets. The paper concludes inBConclusion^ section with a general discussion, a summaryof findings, and anticipated future work.

Existing methods for detecting HAI

Healthcare-associated Infections have been considered an im-portant healthcare quality outcome since Florence Nightingalereduced mortality rates through the application of septic tech-niques in field hospitals during the Crimean war [11]. HAIscontinue to be costly to individual patients and to the healthsystem. Although there are several different types of HAIs,five of them account for nearly all cases. These HAI types are:pneumonia, surgical site infections, urinary tract infections,bloodstream infections, and gastrointestinal infections [3, 5].The recognition that specific syndromes represent the majorityof infections was an important advancement in efforts to re-duce the incidence and impact of HAIs. While general ap-proaches to reduce infections have been employed since the1800s – including encouraging hand hygiene [12, 13] andenvironment cleaning [14, 15] – evidence-based preventivemeasures specifically designed for each of the five HAI syn-dromes now exist [16–20].

A cornerstone of HAI prevention and control is diseasesurveillance. The Centers for Disease Control and Preventionhas specified explicit criteria and cohort definitions to supportthe surveillance of various HAI syndromes [6]. Their efforts inthis domain began in the 1970s and led to the conduct of theSENIC Project [6], which evaluated the impact of infectionsurveillance on HAI incidence [21]. This study demonstratedthat systematic tracking of HAIs coupled with physician-levelfeedback significantly reduces infection risk [21]. Other re-searchers [22, 23] have also described the use of electronicsystems for the surveillance of hospital acquired infections,mainly through monitoring microbiology lab reports. As aresult of the SENIC Project, hospital based infection controlprograms have become a standard practice; and surveillance isa primary function of these programs. The task of surveil-lance, however, is not trivial. It is instructive to consider sur-veillance for surgical site infections as an example. Each day,patients undergoing surgery must be identified, baseline infor-mation recorded, and a method of follow-up identified. Then,practitioners must follow patients for 30 days following thesurgery to identify specific criteria indicative of infection [24].This monitoring requires extensive review of medical recordsand possibly a telephone interview with the patient. This man-ual process is time consuming and is expensive, requiringhighly skilled personnel. Due to the expense, hospitals mayforego surveillance or focus only on a subset of patients. Nei-ther of these alternatives is optimal and in spite of many yearsof experience and research, the detection and control of HAIsremains as a challenge.

However, many of the steps in the surveillance of HAIcould, in theory, be automated. The cohort identification couldbe simplified by taking advantage of information contained ininformation systems used tomanage operating rooms.Most ofthe criteria specifying increased risk of infection are contained

23 Page 2 of 12 J Med Syst (2016) 40:23

in other systems, such as laboratory, pharmacy, or administra-tive information systems. If this information could be com-bined in a consistent manner across disparate information sys-tems, then it might be possible to reduce the costs of infectioncontrol programs or to increase the number of patients coveredby them. The goal of our project is to create a logical frame-work using clear semantics to enable the consistent integrationof different data sources necessary for HAI surveillance, withan initial focus on SSI.

The HAI ontology: An overview

Many factors [25], including environmental, organizational,procedural, and personal factors, contribute to the occurrenceand severity of HAIs. The effectiveness of any detectionmeth-od is highly dependent on the quality of the integrated infor-mation derived from different data sources in various settingsincluding microbiological, clinical, and epidemiological data.We use ontologies along with other semantic technologies toalign these different data sources with one another and withknowledge-bases, regulations, and processes. An ontology, ora formal explicit specification of shared conceptualization[26], provides a semantic framework for knowledge dissemi-nation, exchange, and discovery via reasoning andinferencing. Ontologies capture the knowledge in a domainof interest through concepts, instances and relationships (tax-onomic and associative). The taxonomic relationships orga-nize concepts into sub/super (narrower/broader) concept treestructure, while associative relationships relate instances ofdefined concepts across taxonomies.

Methodology and data sources

The HAI Ontology has been implemented following an inte-grated and iterative V- model [27] methodology consisting ofthe following steps: i) scope definition; ii) data and knowledgeacquisition; iii) conceptualization through defining the mainconcepts, their attributes and the relationships within the do-main of interest; iv) integration; v) encoding using a formalontology language; vi) documentation and vii) evaluation.

In the conceptualization stage we have defined the onto-logical elements (concepts, relationships/attributes and logicalaxioms) based on expert interview, the results from a statisticalanalysis over our available datasets along with the CDC SSIcase definition criteria [6, 24] and a case–control study per-formed over a systematic review of 156 studies on SSIs andtheir associated factors and attributes [28]. In this study, weused the Ottawa Hospital (TOH) research data warehouse,[28] which contains data from 1996 to the present time. ware-house is a relational database that draws together data frommultiple source systems including the most important opera-tional information systems, such as laboratory (microbiology

and clinical chemistry), pharmacy, operating room, clinicalnotes, encounters and diagnoses (classified using ICD codes)patient registration system, patient demographics and move-ment, and patient abstracts (e.g., discharge abstract database(DAD), and the national ambulatory care reporting system(NACRS)).

Moreover to develop and validate detection methods wehave used clinical data along with the information extractedthrough exhaustive chart review to identify patients that haveexperienced surgical site infections. For surveillance of SSIs,the infection-control staff routinely collect demographic andoperational data about selected patients undergoing one ormore operative procedures during a specific observation timeperiod.

At the integration phase several databases (e.g., those con-taining information on hospital morbidity and discharge ab-stracts), existing bio-ontologies (e.g., SNOMED-CT [29],ICD-9,1 HL7-RIM,2 FMA,3 CheBI,4 Infectious Disease On-tology (IDO)), and textual resources have been used to designand implement the integrated HAI Ontology. The databasesand ontologies has been identified and selected based on ourrequirements and their compatibility with existing data ware-house schema architecture. The integration [10] has been doneat two structural and semantic levels. The structural integra-tion has been done by creating a homogeneous dataset in astandard ontology language. Semantic integration, which ismore challenging, has been performed partly manually andpa r t l y ( semi ) au toma t i c a l l y th rough us ing theSemanticScience Integrated Ontology (SIO) framework [30].

Ontological conceptualization

We use description logics and OWL 2.0 Web Ontology Lan-guage [31] to encode the ontological model. Figures 1 and 2demonstrate, respectively, a segment of the HAI Ontologyclass hierarchy representing different types of hospital ac-quired infections and different types of processes and opera-tions defined in the HAI Ontology, integrated within theSemanticScience Integrated Ontology (SIO) framework [30],created using Protégé5 ontology editor.

Figure 3 demonstrates a partial view of the HAI On-tology in Protégé with axiom definitions for SurgicalSite Infections.

An extra-simple-time-ontology has been created to managetemporal aspects of HAIKU. We also use the SADI

1 International Classification of Diseases, Version 92 HL7Reference InformationModel: www.hl7.org/implement/standards/rim.cfm3 T h e F o u n d a t i o n a l M o d e l o f A n a t om y O n t o l o g y :sig.biostr.washington.edu/projects/fm/AboutFM.html4 Chemical Entities of Biological Interest (ChEBI): https://www.ebi.ac.uk/chebi/5 http://protege.stanford.edu/

J Med Syst (2016) 40:23 Page 3 of 12 23

framework [32], which is a set of conventions for creatingHTTP-based Semantic Web services. It consume RDF6 doc-uments as input and produce RDF documents as output,which solves the syntactic interoperability problem as all ser-vices communicate in one language. We evaluate the HAIOntology by assessing its competency to answer the intendedqueries. Also to examine consistency of the ontology we uselogical reasoners. We have already formulated [10, 33] abroad range of semantic queries to improve HAI case identi-fication and enumeration, evaluation of HAI risk factors orcausative factors, identification or evaluation of diagnosticfactors.

Below is an example [33] of captured knowledge inthe HAI ontology represented in in N3 format [34],which is a variation of RDF with improved human-read-ability. It demonstrates an event such as BDiagnosis^ Bisperformed for^ a Bpatient^ within an specific timeBdiagnosis time^ and Bidentifies^ an Bincident^, whichcould be a Bsurgical site infection^ as Bconsequence of^a Bsurgery ,̂ in this case Bcoronary artery bypass graft^has been performed in a specific time (Bevent hastime^) Bsurgery time^. Looking at the Bblood cultureresult^ for Bblood culture test^ that Bhas time^ Btesttime^, Bspecifies finding^, which here is Bpositive bloodculture finding^ that ‘identifies microorganism^

Fig. 1 Different types ofHealthcare-associated infectionsdefined in HAIKU

Fig. 2 Different types of processes defined in the HAIOntology, integratedwithin the Semanticscience Integrated Ontology (SIO) framework 6 The Resource Description Framework (RDF): www.w3.org/RDF/

23 Page 4 of 12 J Med Syst (2016) 40:23

BSerratia Proteamaculans^ and its NCBI’s taxonomynumber: 28151. Then, a Bpharmacy service^, which isBa service for^ the Bpatient^ has been performed at

Bpharmacy service time^ to Bmanage^ a Bdrug product^,in this case BA-Hydrocort Inj^ with a specific drugidentification number (DIN) record.

The HAIKU framework for case detectionand reporting

As shown in Fig. 4, the HAIKU semantic web frameworkconsists of formal ontologies, web services, a reasoner and arule engine that together recommend appropriate level of ac-tions based on the defined semantic rules and guidelines. TheHAIKU semantic rules are modeled throughout a set of

iterative processes that consists of domain and context speci-fication, consensus knowledge acquisition from unstructuredtexts and literature, statistical/epidemiological analysis overexisting structured data available from the TOH data ware-house, interviewing with domain experts and end-users, eval-uation and conflicts resolution.

The semantic backbone, powered by the HAI ontology,assists us in reviewing medical records by identifying specific

J Med Syst (2016) 40:23 Page 5 of 12 23

Fig. 4 The HAIKU framework for automatic case detection

Fig. 3 Part of the HAI Ontology in Protégé representing axiom definitions for SSIs

23 Page 6 of 12 J Med Syst (2016) 40:23

terms and the association between them to generate patternsthat indicate at-risk patients. By linking relevant pieces of dataand information (e.g., signs and symptoms, type of medicalprocedures, length of hospitalization, drugs prescribed, namesof infectious agents), an e-trigger can be fired when the se-mantics imply a possible risk of SSI, allowing preventativemeasures can be taken.

In the knowledge engineering phase, as demonstratedin Fig. 4, after implementing the integrated HAI ontol-ogy [33] we used PSOA RuleML [35], to map the con-cepts in the ontology to instances of data in TOHdatawarehouse. For example, the population ofhaio:is_performed for and haio:identifies is captured bythe following rules:

Axiomatization using semantic and statisticalanalysis

We have defined a set of rule axioms to trigger specific actionsunder certain conditions. By using the ontology and a logicalreasoner together the system can issue alerts to support infec-tion control actions. We start our semantic analysis by

converting the existing knowledge, based on the CDC guide-line and our statistical analysis, into rule axioms. We specifythe rule axioms through multiple criteria such as type andduration of surgery, patients’ age and specifications,comorbidities/existing conditions, etc.

In our model we analyzed TOH data related to 732operative episodes among 729 patients (3 patients had 2

Table 1 Logistic regression coefficients in odds ratio indicating the predictive power of the trigger factors

Trigger Factors Odds Ratio lower 95 % CIb Upper 95 % CI

Systemic antibiotics likely for SSI started on or after post-operative day 2 7.59 4.29 13.50

Duration of the antibiotics usage abovea 1.06 1.03 1.09

Any CT (Computed Tomography) scan report with mention of specific SSI termsa 1.14 0.34 4.17

Readmission with presumed diagnosis of SSIa 15.44 6.78 38.18

Readmission to emergency room/reference center, or coded as urgenta 1.34 0.76 2.32

Any likely significant pathogens on wound culturea 1.38 0.69 2.70

a For specific conditions, refer to Table 2b CI - Confidence Interval

J Med Syst (2016) 40:23 Page 7 of 12 23

episodes each) who received a coronary artery bypassgraft (CABG) between July 1 2004 and June 30 2007.To define the indicators and trigger factors, we usedexisting knowledge in guidelines, biomedical literature,and insights obtained through the statistical analysis of

data in TOH data warehouse. Based on the semanticand statistical analysis and also following the guidelinepresented in [28] we generate the following three rulesfor issuing alerts for suspect, probable and confirmedcases of SSIs.

The semantic alerts are issued upon presentation ofone or more indicators for probable, suspect or con-firmed cases. The results from the statistical analysisare used to:

1. Power the knowledge acquisition phase by improving (orrevising our) conceptualization of the domain

2. Assess the result obtained in response to queries from ourknowledge-based system

23 Page 8 of 12 J Med Syst (2016) 40:23

The triggers most frequently associated with cardiacsurgical site infection in the literature have been sum-marized [28]. We used multivariable logistic regressionwith data in the TOH data warehouse to generate con-ditional predicted probabilities of SSI, based on thesetrigger factors (Table 1) [28].

Area Under the Receiver Operating Caharacteristic (AUC-ROC) curve: 0.91 (10-fold cross-validated estimate was 0.90)95 % CI: 0.88-0.94

As mentioned, the case identification rule has been defindin the HAIKU ontology as suspected (cutlure positive fromwould or blood specimen) and probable (IV antibiotics orthoracic CT order). The graphs below display the distributionof predicted probabilities among, probable cases, suspectedcases and the data including non-SSI instances (individuals).Figure 5a represents the density of predicted probabilityamong probable cases (lab result indicative of infection).The detailed search terms for this analysis have been shown

Table 2 Search terms for trigger factors used in the model (adapted from [28])

Trigger factor definitions Search terms or codes used

Microbiology Reports (Free text entry)

‘Any likely significant pathogens on woundculture’

‘obacter’; ‘staphylococcus aureus’; ‘escherischia’; ‘streptococcus’; pseudomonas’; ‘morganella’;‘serratia’; ‘stenotrophomonas’; ‘klebsiella’; ‘proteus’; providencia’; ‘coagulase negative’ (IFmoderate polymorphs or greater on gram); ‘multiple gram negative’ (IF heavy growth, ANDmoderate polymorphs or greater on gram); ‘enterococcus (IF heavy growth, AND moderatepolymorphs or greater on gram)

‘Any likely significant pathogens on bloodculture’

‘obacter’; ‘staphylococcus aureus’; ‘escherischia’; ‘streptococcus’; ‘pseudomonas’; ‘morganella’;‘serratia’; ‘stenotrophomonas’; ‘klebsiella’; ‘proteus’; ‘providencia’; ‘enterococcus’;‘haemophilus’; ‘propionibacterium’; ‘coagulase negative’ (IF had non-human derived materialimplanted in index operative episode)

Radiology Reports (Free text entry)

‘Any CT report with mention of specific SSIterms’

‘osteomyelitis’; ‘sternal infection’; ‘wound infection’; ‘mediastinitis’; ‘abscess’; ‘retrosternal fluid’;‘endocariditis’; ‘phlegmon’

Admitting Diagnoses (Free text entry)

‘Readmission with presumed diagnosis of SSI’ ‘endocarditis’; ‘infect’; ‘cellulitis’; ‘incision’; ‘wound’; ‘osteomyelitis’; ‘sepsis’; ‘I + D’; ‘abscess’;‘mediastinit’; ‘debride’; ‘sternal’

Pharmacy Records (Generic and Trade names, Drug Identification Numbers, Anatomic Therapeutic Chemical Classification codes, and AmericanHospital Formulary Service pharmacologic-therapeutic classifications for listed agents)

‘Systemic antibiotics likely for SSI started on orafter post-operative day 2’

cefazolin; cephalexin; clindamycin; cloxacillin; ertapenem; imipenem; linezolid; meropenem;nafcillin; penicillin; piperacillin; rifampin; rifampicin; ticarcillin; vancomycin

Fig. 5 a Density of predicted probability among probable cases (labindicative of infection, both gram positive and culture positive); bDensity of predicted probability among probable cases (culture positive

only); c Density of predicted probability among probable cases(postoperative systemic antibiotics); d Density of predicted probabilityamong probable cases (chest CTwith mentions of SSI specific terms)

J Med Syst (2016) 40:23 Page 9 of 12 23

at Table 2. The peak around predicted probability of 0.1 isprobably due to the gram stain test being non-specific forinfection.

The distribution represented in Fig. 5b is also based on labresults, but selected from positive culture results only which isexpected to be more specific to the presence of pathogen.However, overall accuracy of prediction in terms of AUC-ROC did not change significantly whether we use this criteriaor the non-specific one above, potentially due to the smallnumber of individuals that had culture alone (n=44) in ourdata resulting in the loss of precision in statistical quantity.Distribution of predicted probability among suspected cases(selected systemic antibiotics 2 days after index operation–see the list of antibiotics in Table 2) shown in Fig. 5c suggeststhat certain antibiotics orders are less predictive of SSI thanother as seen in the large peak at low value of predictiveprobability. Highly right-skewed distribution of predictedprobability density is observed among suspected case (thorac-ic CT result with suggestive terms of SSI) (Fig. 5d) implyingthe usefulness of the CTscan for the detection of SSI, althoughthe number of the individuals receiving the scan is small(n=38) and thus its statistical significance is inconclusive asseen in its confidence interval crossing the null effect (i.e.,1.0).

The weak predictive power of culture diagnosis seen in ourmodel does not preclude the importance of this test as it isalready established indicator of the infection (Ref-CDC); rath-er, this could be caused by the low yield of culture diagnosiswhen specimens were drawn after the initiation of antibioticstreatment (ref – I will find it today if necessary) or other factorsthat is not measured in this study. In contrast, extremely strongeffect of the presumed diagnosis of SSI at readmission seen inour model potentially reflects a high accuracy of readmissiondiagnosis in TOH. Thus, although existing knowledge such asthe CDC guideline will play a central role in developing thedetection rule, the predictive power of trigger factors maydiffer from one target population to another due to biologicaland non-biological variations reflecting local practice, such asthe accuracy of laboratory tests, patterns of medication use,and clinical diagnosis. Although the accuracy and precision ofstatistical algorithm is limited to the quality of data (e.g., sam-ple size and selection bias) and analytic methodology (e.g.,model selection), it can be highly useful to quantify the im-portance of trigger factors for a target population of interestand thus assist to achieve best detection performance at spe-cific context. Therefore, the importance of combining existingknowledge and statistical analysis will be highly critical oncethe evaluation of the detection systems is extended to othersettings, especially when strong heterogeneity acrosshealthcare or target population is expected.

E-triggers can be issued in response to queries retrievingconfirmed, suspect and probable SSI cases using logical rea-soners and rule engines. The logical reasoner controls the

consistency and satisfiability of the results and reveals redun-dancies and hidden dependencies.

Conclusion

In behavioral economics, nudges are used for positive rein-forcement and indirect suggestions to try to achieve non-forced compliance to improve the decision making of groupsand individuals. Using the same analogy, we define a semanticinfrastructure to issue semantic nudges to assist healthcareprofessionals and infection control practitioners in theirdecision-making process to effectively monitor healthcare-associated infections (HAIs), with a particular focus on surgi-cal site infections (SSIs). Since the rate of HAIs is a majorquality and performance indicator, healthcare settings are con-stantly under pressure to control, and minimize the incidenceof HAIs.

SSIs impose a huge burden on patients, hospitals, andhealthcare organizations. For the CABG procedure, post-surgery SSIs can substantially increase the length-of-stay inhospital [36]. Several known risk factors (e.g., obesity, oldage, and diabetes, duration of surgery) have been associatedwith incidence of SSIs. Multiples lists of cautionary steps,guidelines and strategies have been provided by different in-fection control agencies to improve the SSIs surveillance andprevention, to reduce the incidents of SSI.

In this study, we presented the HAIKU semantic web plat-form. This platform captures and integrates knowledge fromexisting guidelines, standards, and databases and generatestriggers to detect cases based on the HAI ontology (availablefor download from: http://surveillance.mcgill.ca/projects/haiku/HAI.owl), and the logical rules created throughsemantic and statistical analysis. The HAIKU frameworkenables health professionals and researchers to analyzeretrospective data on health-care associated infections andgenerate predictive models using the existing knowledge(i.e., literature findings, guidelines, statistical models) to issuealerts on potential cases of HAIs. It also assists them in mak-ing informed decisions regarding different procedures andpolicies about healthcare associated infections. While in thispaper we focused more on SSIs, the detection of other adverseevents due to infection could possibly benefit from the HAI-KU semantic framework as well, such as sepsis, C-difficileassociated diarrhea, and urinary tract infection.

One strength of this study is the use of statistical methodsalong with semantic technology to define e-triggers, whichprovides a coherent, efficient and consistent view of the dataextracted from various resources. Our research demonstratesthat a combination of parameters indicating infections, e.g.,antibiotic use and positive blood culture, along with the riskfactors, e.g., having old age, duration of a surgical procedure

23 Page 10 of 12 J Med Syst (2016) 40:23

leads to more accurate triggers to issue alerts for early detec-tion of HAIs.

The semantic rules can be used to recommend a certaincourse of actions given a specific situation occurring in ahealthcare setting. Issuing timely alerts and warnings can in-crease the efficiency of the healthcare system, and improve thequality of care in healthcare settings. We plan to implementthe HAIKU framework in multiple clinical sites so that we canevaluate the transferability of our approach. One limitation ofour work is related to the temporal reasoning. Since we areusing description logics to encode the HAI Ontology, tempo-ral reasoning can easily lead to undecidability. So, we arecurrently working on alternative approached to overcome thisproblem. In addition we are planning on enriching the onto-logical structure to extend our analysis for different types ofHAIs, as well as other adverse events such as sepsis andbleeding.

Acknowledgments The Canadian Foundation for Innovation (CFI),the Canadian Institutes of Health Research (CIHR), the Natural Sciences& Engineering Council of Canada (NSERC), and Canadian Network forthe Advancement of Research, Industry and Education (CANARIE) pro-vide funding for this research.

References

1. Douglas Scott II, R., The Direct Medical costs of Healthcare-Associated Infections in U.S. Hospitals and the Benefits ofPrevention. 2009 CDC Report: www.cdc.gov/hai/pdfs/hai/scott_costpaper.pdf.

2. Klevens, R. M., Edwards, J. R., Richards, C. L., Jr., Horan, T. C.,Gaynes, R. P., Pollock, D. A., and Cardo, D. M., Estimating healthcare-associated infections and deaths in U.S. hospitals, 2002.Public Health Rep 122(2):160–6, 2007.

3. Magill, S. S., Edwards, J. R., Bamberg, W., Beldavs, Z. G.,Dumyati, G., Kainer, M. A., et al., Multistate point-prevalence sur-vey of health care-associated infections. New England Journal ofMedicine 370(13):1198–208, 2014.

4. Scott, R. D., The direct medical costs of healthcare-associated in-fections in US hospitals and the benefits of prevention. Division ofHealthcare Quality Promotion National Center for Preparedness,Detection, and Control of Infectious Diseases, Centers for DiseaseControl and Prevention; 2009.

5. Gravel, D., Taylor, G., Ofner, M., Johnston, L., Loeb, M., Roth, V.R., et al., Point prevalence survey for healthcare-associated infec-tions within Canadian adult acute-care hospitals. Journal ofHospital Infection 66(3):243–8, 2007.

6. Horan, T. C., Andrus, M., and Dudeck, M. A., CDC/NHSN sur-veillance definition of health care-associated infection and criteriafor specific types of infections in the acute care setting. Americanjournal of infection control 36(5):309–32, 2008.

7. Magill, S. S., et al., Prevalence of healthcare-associated infectionsin acute care hospitals in Jacksonville. Florida. Infect Control HospEpidemiol 33(3):283–91, 2012.

8. Mangram, A. J., Horan, T. C., Pearson, M. L., Silver, L. C., andJarvis, W. R., Guideline for prevention of surgical site infection,1999. Hospital Infection Control Practices Advisory Committee.Infect Control Hosp Epidemiol. 20(4):250–78, 1999. quiz 279–80.

9. Lee, J. T., Precision, accuracy, clarity, meaning. Surg Infect(Larchmt) 8(1):1–4, 2007.

10. Shaban-Nejad, A., Rose, G. W., Okhmatovskaia, A., Riazanov, A.,Baker, C. J. O., Tamblyn, T., Forster, A. J., and Buckeridge, D. L.,Knowledge-based Surveillance for Preventing PostoperativeSurgical Site Infection. In proc. of MIE 2011, Studies in HealthTechnology and Informatics, IOS Press, 145–149.11, 2011.

11. Gill, C. J., and Gill, G. C., Nightingale in Scutari: Her legacyreexamined. Clinical infectious diseases 40(12):1799–805, 2005.

12. Boyce, J. M., and Pittet, D., Guideline for hand hygiene in health-care settings: recommendations of the Healthcare Infection ControlPractices Advisory Committee and the HICPAC/SHEA/APIC/IDSA Hand Hygiene Task Force. American journal of infectioncontrol 30(8):S1–S46, 2002.

13. Centre for Communicable Diseases and Infection Control, PublicHealth Agency of Canada. Hand hygiene practices in healthcaresettings. Ottawa, Ontario: Canadian Electronic Library, Centre forCommunicable Diseases and Infection Control, Public HealthAgency of Canada, 2012; 2012.

14. Rutala, W. A., Weber, D. J., Centers for Disease Control.,Guidelinefor disinfection and sterilization in healthcare facilities, 2008.Centers for Disease Control (US), 2008.

15. Centre for Communicable Diseases and Infection Control(Canada), Public Health Agency of Canada, Routine practicesand additional precautions for preventing the transmission of in-fection in healthcare settings. Ottawa, Ontario: CanadianElectronic Library, Centre for Communicable Diseases andInfection Control, Public Health Agency of Canada, 2012, 2012.

16. Mangram, A. J., Horan, T. C., Pearson, M. L., Silver, L. C., andJarvis, W. R., Guideline for prevention of surgical site infection,1999. American journal of infection control 27(2):97–134, 1999.

17. Healthcare Infection Control Practices Advisory Committee,Centers for Disease Control and Prevention, Guidelines forpreventing health-care-associated pneumonia, 2003 recommenda-tions of the CDC and the Healthcare Infection Control PracticesAdvisory Committee. Respiratory care 49(8):926, 2004.

18. O’Grady, N. P., Alexander, M., Burns, L. A., Dellinger, E. P.,Garland, J., Heard, S. O., et al., Guidelines for the prevention ofintravascular catheter-related infections. Clinical infectiousdiseases 52(9):e162–e193, 2011.

19. Public Health Agency of Canada, Centre for CommunicableDiseases and Infection Control, Canadian Electronic Library,Clostridium Difficile Infection - Infection Prevention and ControlGuidance for Management in Acute Care Settings. Public HealthAgency of Canada. Canadian Electronic Library. Canadian HealthResearch Collection, 2012.

20. Gould, C., Umscheid, C., Agarwal, R., Kuntz, G., Pegues, D., andHealthcare Infection Control Practices Advisory Committee,Guideline for prevention of catheter-associated urinary tract infec-tions 2009. Infect Control Hosp Epidemiol 31(4):319–26, 2010.

21. Haley, R.W., Culver, D. H.,White, J.W.,Morgan,W.M., Emori, T.G., Munn, V. P., et al., The efficacy of infection surveillance andcontrol progams in preventing nosocomial infections in USHospitals. American Journal of Epidemiology 121(2):182–205,1985.

22. Leth, R. A., and Møller, J. K., Surveillance of hospital-acquiredinfections based on electronic hospital registries. J. of HospitalInfection 62:71–79, 2006.

23. Sands, K., Vineyard, G., Livingston, J., Christiansen, C., and Platt,R., Efficient identification of postdischarge surgical site infections:Use of automated pharmacy dispensing information, administrativedata, and medical record information. J Infect Dis 179(2):434–441,1999.

24. Surgical Site Infection (SSI) Event, Procedure-Associated Module,Centers for Disease Control and Prevention, Office of InfectiousDiseases, National Center for Emerging and Zoonotic Infectious

J Med Syst (2016) 40:23 Page 11 of 12 23

Diseases (NCEZID), Division of Healthcare Quality Promotion(DHQP). Accessed on October 20, 2014. Available from: http://www.cdc.gov/nhsn/CPTcodes/ssi-cpt.html, 2014.

25. Ducel, G., Fabry, J., Nicolle, L. (eds.) Prevention of hospital-acquired infections: A practical guide. 2nd edition, World HealthOrganization (WHO), 2002. http://www.who.int/csr/resources/publications/whocdscsreph200212.pdf.

26. Gruber, T. R., A translation approach to portable ontology specifi-cations. Knowl. Acquis. 5:199–220, 1993.

27. Stevens, R., Goble, C. A., and Bechhofer, S., Ontology-basedknowledge representation for bioinformatics. Brief Bioinform1(4):398–414, 2000.

28. Rose G. W. Use of an Electronic Data Warehouse to EnhanceCardiac Surgical Site Infection Surveillance at a Large CanadianCentre. MSc Thesis, University of Ottawa, 2009.

29. Donnelly, K., SNOMED-CT: The advanced terminology and cod-ing system for eHealth. Stud. Health Technol. Inform. 121:279–290, 2006.

30. Dumontier, M., Baker, C. J., Baran, J., Callahan, A., Chepelev, L.,Cruz-Toledo, J., Del Rio, N. R., Duck, G., Furlong, L. I., Keath, N.,Klassen, D., McCusker, J. P., Queralt-Rosinach, N., Samwald, M.,Villanueva-Rosales, N., Wilkinson, M. D., and Hoehndorf, R., The

Semanticscience Integrated Ontology (SIO) for biomedical researchand knowledge discovery. J Biomed Semantics 5(1):14, 2014.

31. W3C OWL Working Group, OWL 2 Web Ontology Language.Available online: www.w3.org/TR/owl2-overview/ (accessed on30 May 2015).

32. Wilkinson, M., McCarthy, L., Vandervalk, B., Withers, D., Kawas,E., and Samadian, S., SADI, SHARE, and the in silico scientificmethod. BMC Bioinformatics 11(Suppl 12):S7, 2010.

33. Riazanov, A., Klein, A., Shaban-Nejad, A., Rose, G.W., Forster, A.J., Buckeridge, D. L., and Baker, C. J., Semantic querying of rela-tional data for clinical intelligence: A semantic web services-basedapproach. J Biomed Semantics 4(1):9, 2013.

34. Berners-Lee, T., Connolly, D., Kagal, L., Scharf, Y., andHendler, J.,N3Logic: A logical framework for the World Wide Web. Theoryand Practice of Logic Programming 8(3):249–269, 2008.

35. Boley, H., A RIF-Style semantics for RuleML-integrated position-al-slotted, object-applicative rules. In Proc. RuleML 2011, Vol.6826 of LNCS. Springer; pp. 194–211, 2011.

36. Cristofolini, M., Worlitzsch, D., Wienke, A., Silber, R. E., andBorneff-Lipp, M., Surgical site infections after coronary artery by-pass graft surgery: Incidence, perioperative hospital stay,readmissions, and revision surgeries. Infection 40:397–404, 2012.

23 Page 12 of 12 J Med Syst (2016) 40:23