Automated surveillance for central line-associated bloodstream infection in intensive care units

Systematic scoping review of automated systems for the surveillance of healthcare-associated bloodstream infections related to intravascular catheters

INTRODUCTION

Intravascular catheters are crucial devices in medical practice that increase the risk of healthcare-associated infections (HAIs), and related health-economic adverse outcomes. This scoping review aims to provide a comprehensive overview of published automated algorithms for surveillance of catheter-related bloodstream infections (CRBSI) and central line-associated bloodstream infections (CLABSI).

METHODS

We performed a scoping review based on a systematic search of the literature in PubMed and EMBASE from 1 January 2000 to 31 December 2021. Studies were included if they evaluated predictive performance of automated surveillance algorithms for CLABSI/CRBSI detection and used manually collected surveillance data as reference. We assessed the design of the automated systems, including the definitions used to develop algorithms (CLABSI versus CRBSI), the datasets and denominators used, and the algorithms evaluated in each of the studies.

RESULTS

We screened 586 studies based on title and abstract, and 99 were assessed based on full text. Nine studies were included in the scoping review. Most studies were monocentric (n = 5), and they identified CLABSI (n = 7) as an outcome. The majority of the studies used administrative and microbiological data (n = 9) and five studies included the presence of a vascular central line in their automated system. Six studies explained the denominator they selected, five of which chose central line-days. The most common rules and steps used in the algorithms were categorized as hospital-acquired rules, infection rules (infection versus contamination), deduplication, episode grouping, secondary BSI rules (secondary versus primary BSI), and catheter-associated rules.

CONCLUSION

The automated surveillance systems that we identified were heterogeneous in terms of definitions, datasets and denominators used, with a combination of rules in each algorithm. Further guidelines and studies are needed to develop and implement algorithms to detect CLABSI/CRBSI, with standardized definitions, appropriate data sources and suitable denominators.

The accuracy of fully-automated algorithms for the surveillance of central venous catheter-related bloodstream infection in hospitalised patients

BACKGROUND

Continuous surveillance for healthcare-associated infections such as central venous catheter-related bloodstream infections (CVC-BSI) is crucial for prevention. However, traditional surveillance methods are resource-intensive and prone to bias. This study aimed to develop and validate fully-automated surveillance algorithms for CVC-BSI.

METHODS

Two algorithms were developed using electronic health record data from 1000 admissions with a positive blood culture (BCx) at Karolinska University Hospital from 2017: (1) Combining microbiological findings in BCx and CVC cultures with BSI symptoms; (2) Only using microbiological findings. These algorithms were validated in 5170 potential CVC-BSI-episodes from all admissions in 2018-2019, and results extrapolated to all potential CVC-BSI-episodes within this period (n = 181,354). The reference standard was manual record review according to ECDC's definition of microbiologically confirmed CVC-BSI (CRI3-CVC).

RESULTS

In the potential CVC-BSI-episodes, 51 fulfilled ECDC's definition and the algorithms identified 47 and 49 episodes as CVC-BSI, respectively. Both algorithms performed well in assessing CVC-BSI. Overall, algorithm 2 performed slightly better with in the total period a sensitivity of 0.880 (95%-CI 0.783-0.959), specificity of 1.000 (95%-CI 0.999-1.000), PPV of 0.918 (95%-CI 0.833-0.981) and NPV of 1.000 (95%-CI 0.999-1.000). Incidence according to the reference and algorithm 2 was 0.33 and 0.31 per 1000 in-patient hospital-days, respectively.

CONCLUSIONS

Both fully-automated surveillance algorithms for CVC-BSI performed well and could effectively replace manual surveillance. The simpler algorithm, using only microbiology data, is suitable when BCx testing adheres to recommendations, otherwise the algorithm using symptom data might be required. Further validation in other settings is necessary to assess the algorithms' generalisability.

Healthcare-associated infections and conditions in the era of digital measurement

As the third edition of the Compendium of Strategies to Prevent Healthcare-Associated Infections in Acute Care Hospitals is released with the latest recommendations for the prevention and management of healthcare-associated infections (HAIs), a new approach to reporting HAIs is just beginning to unfold. This next generation of HAI reporting will be fully electronic and based largely on existing data in electronic health record (EHR) systems and other electronic data sources. It will be a significant change in how hospitals report HAIs and how the Centers for Disease Control and Prevention (CDC) and other agencies receive this information. This paper outlines what that future electronic reporting system will look like and how it will impact HAI reporting.

Predictive performance of automated surveillance algorithms for intravascular catheter bloodstream infections: a systematic review and meta-analysis

BACKGROUND

Intravascular catheter infections are associated with adverse clinical outcomes. However, a significant proportion of these infections are preventable. Evaluations of the performance of automated surveillance systems for adequate monitoring of central-line associated bloodstream infection (CLABSI) or catheter-related bloodstream infection (CRBSI) are limited.

OBJECTIVES

We evaluated the predictive performance of automated algorithms for CLABSI/CRBSI detection, and investigated which parameters included in automated algorithms provide the greatest accuracy for CLABSI/CRBSI detection.

METHODS

We performed a meta-analysis based on a systematic search of published studies in PubMed and EMBASE from 1 January 2000 to 31 December 2021. We included studies that evaluated predictive performance of automated surveillance algorithms for CLABSI/CRBSI detection and used manually collected surveillance data as reference. We estimated the pooled sensitivity and specificity of algorithms for accuracy and performed a univariable meta-regression of the different parameters used across algorithms.

RESULTS

The search identified five full text studies and 32 different algorithms or study populations were included in the meta-analysis. All studies analysed central venous catheters and identified CLABSI or CRBSI as an outcome. Pooled sensitivity and specificity of automated surveillance algorithm were 0.88 [95%CI 0.84-0.91] and 0.86 [95%CI 0.79-0.92] with significant heterogeneity (I2 = 91.9, p < 0.001 and I2 = 99.2, p < 0.001, respectively). In meta-regression, algorithms that include results of microbiological cultures from specific specimens (respiratory, urine and wound) to exclude non-CRBSI had higher specificity estimates (0.92, 95%CI 0.88-0.96) than algorithms that include results of microbiological cultures from any other body sites (0.88, 95% CI 0.81-0.95). The addition of clinical signs as a predictor did not improve performance of these algorithms with similar specificity estimates (0.92, 95%CI 0.88-0.96).

CONCLUSIONS

Performance of automated algorithms for detection of intravascular catheter infections in comparison to manual surveillance seems encouraging. The development of automated algorithms should consider the inclusion of results of microbiological cultures from specific specimens to exclude non-CRBSI, while the inclusion of clinical data may not have an added-value. Trail Registration Prospectively registered with International prospective register of systematic reviews (PROSPERO ID CRD42022299641; January 21, 2022). https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022299641.

Automating surveillance for healthcare-associated infections: Rationale and current realities (Part I/III)

Infection surveillance is one of the cornerstones of infection prevention and control. Measurement of process metrics and clinical outcomes, such as detection of healthcare-associated infections (HAIs), can be used to support continuous quality improvement. HAI metrics are reported as part of the CMS Hospital-Acquired Conditions Program, and they influence facility reputation and financial outcomes.

Healthcare-associated infections in adult intensive care unit patients: Changes in epidemiology, diagnosis, prevention and contributions of new technologies

Patients in intensive care units (ICUs) are at high risk for healthcare-acquired infections (HAI) due to the high prevalence of invasive procedures and devices, induced immunosuppression, comorbidity, frailty and increased age. Over the past decade we have seen a successful reduction in the incidence of HAI related to invasive procedures and devices. However, the rate of ICU-acquired infections remains high. Within this context, the ongoing emergence of new pathogens, further complicates treatment and threatens patient outcomes. Additionally, the SARS-CoV-2 (COVID-19) pandemic highlighted the challenge that an emerging pathogen provides in adapting prevention measures regarding both the risk of exposure to caregivers and the need to maintain quality of care. ICU nurses hold a special place in the prevention and management of HAI as they are involved in basic hygienic care, steering and implementing quality improvement initiatives, correct microbiological sampling, and aspects antibiotic stewardship. The emergence of more sensitive microbiological techniques and our increased knowledge about interactions between critically ill patients and their microbiota are leading us to rethink how we define HAIs and best strategies to diagnose, treat and prevent these infections in the ICU. This multidisciplinary expert review, focused on the ICU setting, will summarise the recent epidemiology of ICU-HAI, discuss the place of modern microbiological techniques in their diagnosis, review operational and epidemiological definitions and redefine the place of several controversial preventive measures including antimicrobial-impregnated medical devices, chlorhexidine-impregnated washcloths, catheter dressings and chlorhexidine-based mouthwashes. Finally, general guidance is suggested that may reduce HAI incidence and especially outbreaks in ICUs.

Diagnostic accuracy of electronic surveillance tool for catheter-associated urinary tract infections in tertiary care hospitals: A meta-analysis

BACKGROUND

Automated systems have been developed to reduce labor-intensive manual recordings during nosocomial infection surveillance. The diagnostic accuracies of these systems have differed in various settings.

METHODS

We designed this meta-analysis to evaluate the diagnostic accuracy of an electronic surveillance tool for catheter-associated urinary tract infections (CAUTIs) in tertiary care hospitals. We systematically searched databases such as Medline, Scopus, Cochrane library and Embase (from inception until November 2019) for relevant studies. We assessed the quality of trials using the diagnostic accuracy studies-2 tool, and performed a meta-analysis to obtain a pooled sensitivity and specificity for electronic surveillance. We included 6 studies with 16,492 patients in the analysis.

RESULTS

We found a pooled sensitivity of electronic diagnostic surveillance for CAUTIs of 97.5% (95% confidence interval [CI], 67.6-99.9%) and a pooled specificity of 92.6% (95% CI, 55.2-99.2%). The diagnostic odds ratio was 494 (95% CI, 89-2747). The positive likelihood ratio was 13.1 (95% CI, 1.63-105.8) and the negative likelihood ratio 0.02 (95% CI, 0.001-0.40). A bivariate box plot indicated the possibility of heterogeneity between the included studies.

CONCLUSION

Our review suggests that electronic surveillance is useful for diagnosing CAUTIs among hospitalized patients in tertiary care hospitals due to its high sensitivity and specificity.

Computer Informatics for Infection Control

Computer informatics have the potential to improve infection control outcomes in surveillance, prevention, and public health. Surveillance activities include surveillance of infections, device use, and facility/ward outbreak detection and investigation. Prevention activities include awareness of multidrug-resistant organism carriage on admission, identification of high-risk individuals or populations, reducing device use, and antimicrobial stewardship. Enhanced communication with public health and other health care facilities across networks includes automated electronic communicable disease reporting, syndromic surveillance, and regional outbreak detection. Computerized public health networks may represent the next major evolution in infection control. This article reviews the use of informatics for infection control.

Do we need to change catheter-related bloodstream infection surveillance in the Netherlands? A qualitative study among infection prevention professionals

OBJECTIVES

Catheter-related bloodstream infections (CRBSI) are a common healthcare-associated infection and therefore targeted by surveillance programmes in many countries. Concerns, however, have been voiced regarding the reliability and construct validity of CRBSI surveillance and the connection with the current diagnostic procedures. The aim of this study was to explore the experiences of infection control practitioners (ICPs) and medical professionals with the current CRBSI surveillance in the Netherlands and their suggestions for improvement.

DESIGN

Qualitative study using focus group discussions (FGDs) with ICPs and medical professionals separately, followed by semistructured interviews to investigate whether the points raised in the FGDs were recognised and confirmed by the interviewees. Analyses were performed using thematic analyses.

SETTING

Basic, teaching and academic hospitals in the Netherlands.

PARTICIPANTS

24 ICPs and 9 medical professionals.

RESULTS

Main themes derived from experiences with current surveillance were (1) ICPs' doubt regarding the yield of surveillance given the low incidence of CRBSI, the high workload and IT problems; (2) the experienced lack of leadership and responsibility for recording information needed for surveillance and (3) difficulties with applying and interpreting the CRBSI definition. Suggestions were made to simplify the surveillance protocol, expand the follow-up and surveillance to homecare settings, simplify the definition and customise it for specific patient groups. Participants reported hoping for and counting on automatisation solutions to support future surveillance.

CONCLUSIONS

This study reveals several problems with the feasibility and acceptance of the current CRBSI surveillance and proposes several suggestions for improvement. This provides valuable input for future surveillance activities, thereby taking into account automation possibilities.

PRAISE: providing a roadmap for automated infection surveillance in Europe

INTRODUCTION

Healthcare-associated infections (HAI) are among the most common adverse events of medical care. Surveillance of HAI is a key component of successful infection prevention programmes. Conventional surveillance - manual chart review - is resource intensive and limited by concerns regarding interrater reliability. This has led to the development and use of automated surveillance (AS). Many AS systems are the product of in-house development efforts and heterogeneous in their design and methods. With this roadmap, the PRAISE network aims to provide guidance on how to move AS from the research setting to large-scale implementation, and how to ensure the delivery of surveillance data that are uniform and useful for improvement of quality of care.

METHODS

The PRAISE network brings together 30 experts from ten European countries. This roadmap is based on the outcome of two workshops, teleconference meetings and review by an independent panel of international experts.

RESULTS

This roadmap focuses on the surveillance of HAI within networks of healthcare facilities for the purpose of comparison, prevention and quality improvement initiatives. The roadmap does the following: discusses the selection of surveillance targets, different organizational and methodologic approaches and their advantages, disadvantages and risks; defines key performance requirements of AS systems and suggestions for their design; provides guidance on successful implementation and maintenance; and discusses areas of future research and training requirements for the infection prevention and related disciplines. The roadmap is supported by accompanying documents regarding the governance and information technology aspects of implementing AS.

CONCLUSIONS

Large-scale implementation of AS requires guidance and coordination within and across surveillance networks. Transitions to large-scale AS entail redevelopment of surveillance methods and their interpretation, intensive dialogue with stakeholders and the investment of considerable resources. This roadmap can be used to guide future steps towards implementation, including designing solutions for AS and practical guidance checklists.

Electronically assisted surveillance systems of healthcare-associated infections: a systematic review

Background

Surveillance of healthcare-associated infections (HAI) is the basis of each infection control programme and, in case of acute care hospitals, should ideally include all hospital wards, medical specialties as well as all types of HAI. Traditional surveillance is labour intensive and electronically assisted surveillance systems (EASS) hold the promise to increase efficiency.

Objectives

To give insight in the performance characteristics of different approaches to EASS and the quality of the studies designed to evaluate them.

Methods

In this systematic review, online databases were searched and studies that compared an EASS with a traditional surveillance method were included. Two different indicators were extracted from each study, one regarding the quality of design (including reporting efficiency) and one based on the performance (e.g. specificity and sensitivity) of the EASS presented.

Results

A total of 78 studies were included. The majority of EASS (n = 72) consisted of an algorithm-based selection step followed by confirmatory assessment. The algorithms used different sets of variables. Only a minority (n = 7) of EASS were hospital-wide and designed to detect all types of HAI. Sensitivity of EASS was generally high (> 0.8), but specificity varied (0.37–1). Less than 20% (n = 14) of the studies presented data on the efficiency gains achieved.

Conclusions

Electronically assisted surveillance of HAI has yet to reach a mature stage and to be used routinely in healthcare settings. We recommend that future studies on the development and implementation of EASS of HAI focus on thorough validation, reproducibility, standardised datasets and detailed information on efficiency.

Effect of infectious disease consultation on mortality and treatment of patients with candida bloodstream infections: a retrospective, cohort study

BACKGROUND

Candida bloodstream infection is associated with high mortality. Infectious disease consultation improves outcomes in several infections, including Staphylococcus aureus and cryptococcosis, as well as multidrug-resistant organisms. We aimed to examine the association between infectious disease consultation and differences in management with mortality in candida bloodstream infections.

METHODS

In this retrospective, single-centre cohort study, we reviewed the medical charts of all patients admitted to Barnes-Jewish Hospital (St Louis, MO, USA), a tertiary referral centre, aged 18 years or older with candida bloodstream infection from 2002 to 2015. We collected data for demographics, comorbidities, predisposing factors, all-cause mortality, antifungal use, central-line removal, and ophthalmological and echocardiographic evaluation to assess 90-day all-cause mortality between individuals with and without an infectious disease consultation. For the survival analysis we used Cox proportional hazards model with inverse weighting by propensity score to assess the effects of infectious disease consultation on mortality and differences in management.

FINDINGS

Between Jan 1, 2002, and Dec 31, 2015, of 1794 patients assessed for eligibility, we analysed 1691 patients with candida bloodstream infection; 776 (45·9%) who had an infectious disease consultation and 915 (54·1%) who did not have an infectious disease consultation. All 1691 patients were included in the analysis. None were missing data. Most underlying comorbidities were evenly distributed between groups. 90-day mortality was lower in the infectious disease consultation group than in patients who did not receive an infectious disease consultation (29% [222/776] vs 51% [468/915]; p<0·0001). In the model with inverse weighting by the propensity score, infectious disease consultation was associated with a hazard ratio of 0·81 (95% CI 0·73-0·91; p<0·0001) for mortality. In the consultation group, median duration of antifungal therapy was longer (18 [IQR 14-35] vs 14 [6-20] days; p<0·0001) and central-line removal (587 [76%] of 776 vs 538 [59%] of 915; p<0·0001), echocardiography use (442 [57%] of 776 vs 305 [33%] of 915; p<0·0001), and ophthalmological examination (412 [53%] of 776 vs 160 [17%] of 915; p<0·0001) were more frequently done. Fewer patients in the infectious disease consultation group were not treated (13 [2%] of 776 vs 128 [14%] of 915; p<0·0001).

INTERPRETATION

Patients with candida bloodstream infection receiving an infectious disease consultation have lower mortality. This finding might be attributable to these individuals receiving a higher number of non-pharmacological, evidence-based interventions and lower amounts of non-treatment. These data suggest that an infectious disease consultation should be an integral part of clinical care of patients with candida bloodstream infection.

FUNDING

Astellas Global Development Pharma, Washington University Institute of Clinical and Translational Sciences, and the Agency for Healthcare Research and Quality.

Development and validation of a semi-automated surveillance system-lowering the fruit for non-ventilator-associated hospital-acquired pneumonia (nvHAP) prevention

Objectives

Conducting manual surveillance of non-ventilator-associated hospital-acquired pneumonia (nvHAP) using ECDC (European Centre for Disease Prevention and Control) surveillance criteria is very resource intensive. We developed and validated a semi-automated surveillance system for nvHAP, and describe nvHAP incidence and aetiology at our hospital.

Methods

We applied an automated classification algorithm mirroring ECDC definition criteria to distinguish patients ‘not at risk’ from patients ‘at risk’ for suffering from nvHAP. ‘At risk’-patients were manually screened for nvHAP. For validation, we applied the reference standard of full manual evaluation to three validation samples comprising 2091 patients.

Results

Among the 39 519 University Hospital Zurich inpatient discharges in 2017, the algorithm identified 2454 ‘at-risk’ patients, reducing the number of medical records to be manually screened by 93.8%. From this subset, nvHAP was identified in 251 patients (0.64%, 95%CI: 0.57–0.73). Sensitivity, negative predictive value, and accuracy of semi-automated surveillance versus full manual surveillance were lowest in the validation sample consisting of patients with HAP according to the International Classification of Diseases (ICD-10) discharge diagnostic codes, with 97.5% (CI: 93.7–99.3%), 99.2% (CI: 97.9–99.8%), and 99.4% (CI: 98.4–99.8%), respectively. The overall incidence rate of nvHAP was 0.83/1000 patient days (95%CI: 0.73–0.94), with highest rates in haematology/oncology, cardiac and thoracic surgery, and internal medicine including subspecialties.

Conclusions

The semi-automated surveillance demonstrated a very high sensitivity, negative predictive value, and accuracy. This approach significantly reduces manual surveillance workload, thus making continuous nvHAP surveillance feasible as a pivotal element for successful prevention efforts.

WMSS: A Web-Based Multitiered Surveillance System for Predicting CLABSI

Central-line-associated bloodstream infection (CLABSI) rates are a key quality metric for comparing hospital quality and safety. Manual surveillance systems for CLABSIs are time-consuming and often limited to intensive care units (ICUs). A computer-automated method of CLABSI detection can improve the validity of surveillance. A new web-based, multitiered surveillance system for predicting and reducing CLABSI is proposed. The system has the capability to collect patient-related data from hospital databases and hence predict the patient infection automatically based on knowledge discovery rules and CLABSI decision standard algorithms. In addition, the system has a built-in simulator for generating patients' data records, when needed, offering the capability to train nurses and medical staff for enhancing their qualifications. Applying the proposed system, both CLABSI rates and patient treatment costs can be reduced significantly. The system has many benefits, among which there is the following: it is a web-based system that can collect real patients' data from many IT resources using iPhone, iPad, laptops, Internet, scanners, and hospital databases. These facilities help to collect patients' actual data quickly and safely in electronic format and hence predict CLABSI efficiently. Automation of the patients' data diagnosis process helps in reducing CLABSI detection times. The system is multimedia-based; it uses text, colors, and graphics to enhance patient healthcare report generation and charts. It helps healthcare decision makers to review and approve policies and surveillance plans to reduce and prevent CLABSI.

Performance characteristics and associated outcomes for an automated surveillance tool for bloodstream infection

BACKGROUND

The objective of this study was to evaluate performance metrics and associated patient outcomes of an automated surveillance system, the blood Nosocomial Infection Marker (NIM).

METHODS

We reviewed records of 237 patients with and 36,927 patients without blood NIM using the National Healthcare Safety Network (NHSN) definition for laboratory-confirmed bloodstream infection (BSI) as the gold standard. We matched cases with noncases by propensity score and estimated attributable mortality and cost of NHSN-reportable central line-associated bloodstream infections (CLABSIs) and non-NHSN-reportable BSIs.

RESULTS

For patients with central lines (CL), the blood NIM had 73.2% positive predictive value (PPV), 99.9% negative predictive value (NPV), 89.2% sensitivity, and 99.7% specificity. For all patients regardless of CL status, the blood NIM had 53.6% PPV, 99.9% NPV, 84.0% sensitivity, and 99.9% specificity. For CLABSI cases compared with noncases, mortality was 17.5% versus 9.4% (P = .098), and median charge was $143,935 (interquartile range [IQR], $89,794-$257,447) versus $115,267 (IQR, $74,937-$173,053) (P < .01). For non-NHSN-reportable BSI cases compared with noncases, mortality was 23.6% versus 6.7% (P < .0001), and median charge was $86,927 (IQR, $54,728-$156,669) versus $62,929 (IQR, $36,743-$115,693) (P < .0001).

CONCLUSIONS

The NIM is an effective screening tool for BSI. Both NHSN-reportable and nonreportable BSI cases were associated with increased mortality and cost.

Data requirements for electronic surveillance of healthcare-associated infections

Electronic surveillance for healthcare-associated infections (HAIs) is increasingly widespread. This is driven by multiple factors: a greater burden on hospitals to provide surveillance data to state and national agencies, financial pressures to be more efficient with HAI surveillance, the desire for more objective comparisons between healthcare facilities, and the increasing amount of patient data available electronically. Optimal implementation of electronic surveillance requires that specific information be available to the surveillance systems. This white paper reviews different approaches to electronic surveillance, discusses the specific data elements required for performing surveillance, and considers important issues of data validation.

A Web-Based, Hospital-Wide Health Care-Associated Bloodstream Infection Surveillance and Classification System: Development and Evaluation

BACKGROUND

Surveillance of health care-associated infections is an essential component of infection prevention programs, but conventional systems are labor intensive and performance dependent.

OBJECTIVE

To develop an automatic surveillance and classification system for health care-associated bloodstream infection (HABSI), and to evaluate its performance by comparing it with a conventional infection control personnel (ICP)-based surveillance system.

METHODS

We developed a Web-based system that was integrated into the medical information system of a 2200-bed teaching hospital in Taiwan. The system automatically detects and classifies HABSIs.

RESULTS

In this study, the number of computer-detected HABSIs correlated closely with the number of HABSIs detected by ICP by department (n=20; r=.999 P<.001) and by time (n=14; r=.941; P<.001). Compared with reference standards, this system performed excellently with regard to sensitivity (98.16%), specificity (99.96%), positive predictive value (95.81%), and negative predictive value (99.98%). The system enabled decreasing the delay in confirmation of HABSI cases, on average, by 29 days.

CONCLUSIONS

This system provides reliable and objective HABSI data for quality indicators, improving the delay caused by a conventional surveillance system.

Increasing the Reliability of Fully Automated Surveillance for Central Line–Associated Bloodstream Infections

OBJECTIVE

To increase reliability of the algorithm used in our fully automated electronic surveillance system by adding rules to better identify bloodstream infections secondary to other hospital-acquired infections.

METHODS

Intensive care unit (ICU) patients with positive blood cultures were reviewed. Central line–associated bloodstream infection (CLABSI) determinations were based on 2 sources: routine surveillance by infection preventionists, and fully automated surveillance. Discrepancies between the 2 sources were evaluated to determine root causes. Secondary infection sites were identified in most discrepant cases. New rules to identify secondary sites were added to the algorithm and applied to this ICU population and a non-ICU population. Sensitivity, specificity, predictive values, and kappa were calculated for the new models.

RESULTS

Of 643 positive ICU blood cultures reviewed, 68 (10.6%) were identified as central line–associated bloodstream infections by fully automated electronic surveillance, whereas 38 (5.9%) were confirmed by routine surveillance. New rules were tested to identify organisms as central line–associated bloodstream infections if they did not meet one, or a combination of, the following: (I) matching organisms (by genus and species) cultured from any other site; (II) any organisms cultured from sterile site; (III) any organisms cultured from skin/wound; (IV) any organisms cultured from respiratory tract. The best-fit model included new rules I and II when applied to positive blood cultures in an ICU population. However, they didn’t improve performance of the algorithm when applied to positive blood cultures in a non-ICU population.

CONCLUSION

Electronic surveillance system algorithms may need adjustment for specific populations.

Infect. Control Hosp. Epidemiol. 2015;36(12):1396–1400

An electronic surveillance tool for catheter-associated urinary tract infection in intensive care units

BACKGROUND

Traditional methods of surveillance of catheter-associated urinary tract infections (CAUTIs) are error-prone and resource-intensive. To resolve these issues, we developed a highly sensitive electronic surveillance tool.

OBJECTIVE

To develop an electronic surveillance tool for CAUTIs and assess its performance.

METHODS

The study was conducted at a 947-bed tertiary care center. Patients included adults aged ≥18 years admitted to an intensive care unit between January 10 and June 30, 2012, with an indwelling urinary catheter during their admission. We identified CAUTIs using 4 methods: traditional surveillance (TS) (ie, manual chart review by ICPs), an electronic surveillance (ES) tool, augmented electronic surveillance (AES) (ie, ES with chart review on a subset of cases), and reference standard (RS) (ie, a subset of CAUTIs originally ascertained by TS or ES, confirmed by review). We assessed performance characteristics to RS for reviewed cases.

RESULTS

We identified 417 candidate CAUTIs in 308 patients; 175 (42.0%) of these candidate CAUTIs were selected for review, yielding 32 confirmed CAUTIs in 22 patients (RS). Compared with RS, the sensitivities of TS, ES, and AES were 43.8% (95% confidence interval [CI], 26.4%-62.3%), 100.0% (95% CI, 89.1%-100.0%), and 100.0% (95% CI, 89.1%-100.0%). Specificities were 82.5% (95% CI, 75.3%-88.4%), 2.8% (95% CI, 0.8%-7.0%), and 100.0% (95% CI, 97.5%-100.0%).

CONCLUSIONS

Electronic CAUTI surveillance offers a streamlined approach to improve reliability and resource burden of surveillance.

Development of trigger-based semi-automated surveillance of ventilator-associated pneumonia and central line-associated bloodstream infections in a Dutch intensive care

Background

Availability of a patient data management system (PDMS) has created the opportunity to develop trigger-based electronic surveillance systems (ESSs). The aim was to evaluate a semi-automated trigger-based ESS for the detection of ventilator-associated pneumonia (VAP) and central line-associated blood stream infections (CLABSIs) in the intensive care.

Methods

Prospective comparison of surveillance was based on a semi-automated ESS with and without trigger. Components of the VAP/CLABSI definition served as triggers. These included the use of VAP/CLABSI-related antibiotics, the presence of mechanical ventilation or an intravenous central line, and the presence of specific clinical symptoms. Triggers were automatically fired by the PDMS. Chest X-rays and microbiology culture results were checked only on patient days with a positive trigger signal from the ESS. In traditional screening, no triggers were used; therefore, chest X-rays and culture results had to be screened for all patient days of all included patients. Patients with pneumonia at admission were excluded.

Results

A total of 553 patients were screened for VAP and CLABSI. The incidence of VAP was 3.3/1,000 ventilation days (13 VAP/3,927 mechanical ventilation days), and the incidence of CLABSI was 1.7/1,000 central line days (24 CLABSI/13.887 central line days). For VAP, the trigger-based screening had a sensitivity of 92.3%, a specificity of 100%, and a negative predictive value of 99.8% compared to traditional screening of all patients. For CLABSI, sensitivity was 91.3%, specificity 100%, and negative predictive value 99.6%.

Conclusions

Pre-selection of patients to be checked for signs and symptoms of VAP and CLABSI by a computer-generated automated trigger system was time saving but slightly less accurate than conventional surveillance. However, this after-the-fact surveillance was mainly designed as a quality indicator over time rather than for precise determination of infection rates. Therefore, surveillance of VAP and CLABSI with a trigger-based ESS is feasible and effective.

Data use and effectiveness in electronic surveillance of healthcare associated infections in the 21st century: a systematic review

OBJECTIVE

As more electronic health records have become available during the last decade, we aimed to uncover recent trends in use of electronically available patient data by electronic surveillance systems for healthcare associated infections (HAIs) and identify consequences for system effectiveness.

METHODS

A systematic review of published literature evaluating electronic HAI surveillance systems was performed. The PubMed service was used to retrieve publications between January 2001 and December 2011. Studies were included in the review if they accurately described what electronic data were used and if system effectiveness was evaluated using sensitivity, specificity, positive predictive value, or negative predictive value. Trends were identified by analyzing changes in the number and types of electronic data sources used.

RESULTS

26 publications comprising discussions on 27 electronic systems met the eligibility criteria. Trend analysis showed that systems use an increasing number of data sources which are either medico-administrative or clinical and laboratory-based data. Trends on the use of individual types of electronic data confirmed the paramount role of microbiology data in HAI detection, but also showed increased use of biochemistry and pharmacy data, and the limited adoption of clinical data and physician narratives. System effectiveness assessments indicate that the use of heterogeneous data sources results in higher system sensitivity at the expense of specificity.

CONCLUSIONS

Driven by the increased availability of electronic patient data, electronic HAI surveillance systems use more data, making systems more sensitive yet less specific, but also allow systems to be tailored to the needs of healthcare institutes' surveillance programs.

Variations in identification of healthcare-associated infections

OBJECTIVE

Little is known about whether those performing healthcare-associated infection (HAI) surveillance vary in their interpretations of HAI definitions developed by the Centers for Disease Control and Prevention's National Healthcare Safety Network (NHSN). Our primary objective was to characterize variations in these interpretations using clinical vignettes. We also describe predictors of variation in responses.

DESIGN

Cross-sectional study.

SETTING

United States.

PARTICIPANTS

A sample of US-based members of the Society for Healthcare Epidemiology of America (SHEA) Research Network.

METHODS

Respondents assessed whether each of 6 clinical vignettes met criteria for an NHSN-defined HAI. Individual- and institutional-level data were also gathered.

RESULTS

Surveys were distributed to 143 SHEA Research Network members from 126 hospitals. In total, 113 responses were obtained, representing at least 61 unique hospitals (30 respondents did not identify a hospital); 79.2% (84 of 106 nonmissing responses) were infection preventionists, and 79.4% (81 of 102 nonmissing responses) worked at academic hospitals. Among the 6 vignettes, the proportion of respondents correctly characterizing the vignettes was as low as 27.3%. Combining all 6 vignettes, the mean percentage of correct responses was 61.1% (95% confidence interval, 57.7%-63.8%). Percentage of correct responses was associated with presence of a clinical background (ie, nursing or physician degrees) but not with hospital size or infection prevention and control department characteristics.

CONCLUSIONS

Substantial heterogeneity exists in the application of HAI definitions in this survey of infection preventionists and hospital epidemiologists. Our data suggest a need to better clarify these definitions, especially when comparing HAI rates across institutions.

Public health surveillance in the dialysis setting: opportunities and challenges for using electronic health records

The US Centers for Disease Control and Prevention has conducted public health surveillance for healthcare-associated infections (HAIs) in dialysis facilities since the 1970s, evolving from facility-level surveys to patient-level surveillance systems. The Centers for Medicare and Medicaid Services (CMS) recently implemented incentives for all end-stage renal disease (ESRD) facilities to monitor and report patient-level quality indicators to the Centers for Disease Control and Prevention's (CDC's) National Healthcare Safety Network (NHSN) in accordance with the NHSN Dialysis Event Protocol. These CMS incentives have led to a rapid increase in dialysis facility NHSN enrollment during 2012. Ongoing challenges to HAI surveillance in this setting include variability in the surveillance process, assurance of data quality, and staff time and resource requirements. Use of existing electronic health records (EHR), especially in conjunction with detection algorithms, has increasingly been shown to produce valid and reliable estimates of HAI frequency in acute care hospitals. Given the large number of dialysis facilities that are now beginning to conduct surveillance using NHSN, the typical lack of dedicated infection prevention personnel in those facilities, and the widespread use of EHR in large dialysis provider organizations, the use of EHR will probably become a cornerstone of surveillance in these settings. Implemented properly, the use of EHR to support public health surveillance has enormous potential to focus and strengthen infection prevention activities in dialysis facilities. Systematic, ongoing validation efforts will be vital to ensure that reported data are accurate, permit valid comparisons of facility performance, and effectively support improved outcomes for dialysis patients.

Diagnostic performance of electronic syndromic surveillance systems in acute care: a systematic review

CONTEXT

Healthcare Electronic Syndromic Surveillance (ESS) is the systematic collection, analysis and interpretation of ongoing clinical data with subsequent dissemination of results, which aid clinical decision-making.

OBJECTIVE

To evaluate, classify and analyze the diagnostic performance, strengths and limitations of existing acute care ESS systems.

DATA SOURCES

All available to us studies in Ovid MEDLINE, Ovid EMBASE, CINAHL and Scopus databases, from as early as January 1972 through the first week of September 2012.

STUDY SELECTION

Prospective and retrospective trials, examining the diagnostic performance of inpatient ESS and providing objective diagnostic data including sensitivity, specificity, positive and negative predictive values.

DATA EXTRACTION

Two independent reviewers extracted diagnostic performance data on ESS systems, including clinical area, number of decision points, sensitivity and specificity. Positive and negative likelihood ratios were calculated for each healthcare ESS system. A likelihood matrix summarizing the various ESS systems performance was created.

RESULTS

The described search strategy yielded 1639 articles. Of these, 1497 were excluded on abstract information. After full text review, abstraction and arbitration with a third reviewer, 33 studies met inclusion criteria, reporting 102,611 ESS decision points. The yielded I2 was high (98.8%), precluding meta-analysis. Performance was variable, with sensitivities ranging from 21% -100% and specificities ranging from 5%-100%.

CONCLUSIONS

There is significant heterogeneity in the diagnostic performance of the available ESS implements in acute care, stemming from the wide spectrum of different clinical entities and ESS systems. Based on the results, we introduce a conceptual framework using a likelihood ratio matrix for evaluation and meaningful application of future, frontline clinical decision support systems.

Advances in electronic surveillance for healthcare-associated infections in the 21st Century: a systematic review

BACKGROUND

Traditional methodologies for healthcare-associated infection (HCAI) surveillance can be resource intensive and time consuming. As a consequence, surveillance is often limited to specific organisms or conditions. Various electronic databases exist within the healthcare setting and may be utilized to perform HCAI surveillance.

AIM

To assess the utility of electronic surveillance systems for monitoring and detecting HCAI.

METHODS

A systematic review of published literature on surveillance of HCAI was performed. Databases were searched for studies published between January 2000 and December 2011. Search terms were divided into infection, surveillance and data management terms, and combined using Boolean operators. Studies were included for review if they demonstrated or proposed the use of electronic systems for HCAI surveillance.

FINDINGS

In total, 44 studies met the inclusion criteria. For the majority of studies, emphasis was on the linkage of electronic databases to provide automated methods for monitoring infections in specific clinical settings. Twenty-one studies assessed the performance of their method with traditional surveillance methodologies or a manual reference method. Where sensitivity and specificity were calculated, these varied depending on the organism or condition being surveyed and the data sources employed.

CONCLUSIONS

The implementation of electronic surveillance was found to be feasible in many settings, with several systems fully integrated into hospital information systems and routine surveillance practices. The results of this review suggest that electronic surveillance systems should be developed to maximize the efficacy of abundant electronic data sources existing within hospitals.

Variations in catheter-related bloodstream infections rates based on local practices

Background

Catheter-related bloodstream infection (CRBSI) surveillance serves as a quality improvement measure that is often used to assess performance. We reviewed the total number of microbiological samples collected in three Belgian intensive care units (ICU) in 2009–2010, and we described variations in CRBSI rates based on two factors: microbiological documentation rate and CRBSI definition which includes clinical criterion for coagulase-negative Staphylococcus (CNS) episode.

Findings

CRBSI rates were 2.95, 1.13 and 1.26 per 1,000 estimated catheter-days in ICUs A, B and C, respectively. ICU B cultured fewer microbiological samples and reported the lowest CRBSI rate. ICU C had the highest documentation rate but was assisted by support available from the laboratory for processing single CNS positive blood cultures. With the exclusion of clinical criterion, CRBSI rates would be reduced by 19%, 45% and 0% in ICUs A, B and C, respectively.

Conclusion

CRBSI rates may be biased by differences of blood culture sampling and CRBSI definition. These observations suggest that comparisons of CRBSI rates in different ICUs remain difficult to interpret without knowledge of local practices.

Automated surveillance for healthcare-associated infections: opportunities for improvement

Surveillance of healthcare-associated infections is a cornerstone of infection prevention programs, and reporting of infection rates is increasingly required. Traditionally, surveillance is based on manual medical records review; however, this is very labor intensive and vulnerable to misclassification. Existing electronic surveillance systems based on classification algorithms using microbiology results, antibiotic use data, and/or discharge codes have increased the efficiency and completeness of surveillance by preselecting high-risk patients for manual review. However, shifting to electronic surveillance using multivariable prediction models based on available clinical patient data will allow for even more efficient detection of infection. With ongoing developments in healthcare information technology, implementation of the latter surveillance systems will become increasingly feasible. As with current predominantly manual methods, several challenges remain, such as completeness of postdischarge surveillance and adequate adjustment for underlying patient characteristics, especially for comparison of healthcare-associated infection rates across institutions.

A comparison of 3 metrics to identify health care-associated infections

BACKGROUND

The best approach to measurement of health care-associated infection rates is controversial.

METHODS

We compared 3 metrics to identify catheter-associated bloodstream infection (CA-BSI), catheter-associated urinary tract infection (CA-UTI), and ventilator-associated pneumonia (VAP) in 8 intensive care units during 2009. We evaluated traditional surveillance using National Healthcare Safety Network methodology, data mining with MedMined Data Mining Surveillance (CareFusion Corporation, San Diego, CA), and administrative coding with ICD-9-CM.

RESULTS

A total of 65 CA-BSI, 28 CA-UTI, and 48 VAP was identified. Traditional surveillance detected 58 CA-BSI and no false positives; data mining identified 51 cases but 51 false positives; administrative coding documented 6 cases and 6 false positives. Traditional surveillance detected 27 CA-UTI and no false positives; data mining identified 17 cases but 19 false positives; administrative coding documented 3 cases and 1 false-positive. Traditional surveillance detected 41 VAP and no false positives; data mining identified 26 cases but also 79 false positives; administrative coding found 17 cases and 13 false positives. Overall sensitivities were as follows: traditional surveillance, 0.84; data mining, 0.67; administrative coding, 0.18. Positive predictive values were as follows: traditional surveillance, 1.0; data mining, 0.39; administrative coding, 0.57.

CONCLUSION

Traditional surveillance proved superior in terms of sensitivity, positive predictive value, and rate estimation.

An electronic catheter-associated urinary tract infection surveillance tool

OBJECTIVE

To develop and validate an electronic surveillance tool for catheter-associated urinary tract infections (CAUTIs).

DESIGN

Retrospective cohort study.

SETTING

413-bed university-affiliated urban teaching hospital.

METHODS

An electronic surveillance tool was developed for CAUTI and urinary catheter utilization based on the objective components of the National Healthcare Safety Network (NHSN) definitions including fever, urinalysis, and urine culture. Results were compared to manual chart review by an infection preventionist (IP).

RESULTS

During January and February 2010, 204 positive urine cultures (≥10(3) colony-forming units/mL) were identified in 136 patients with indwelling urinary catheters during their hospitalization. The electronic surveillance tool detected 60 CAUTI cases and 7,098 catheter-days, yielding a CAUTI incidence rate of 8.5 per 1,000 catheter-days. Urinary catheter utilization ratios (Foley-days/patient-days) were: acute care units, 0.27 (3,637 of 13,229); intensive care units, 0.77 (3,461 of 4,469); and overall, 0.40 (7,098 of 17,698). In comparison, the IP identified 59 cases by manual review with a sensitivity of 51 of 59 (86.4%), specificity 136 of 145 (93.8%), and negative predictive value of 136 of 144 (94.4%). Fever was present in 54 of 59 (91.5%) of CAUTI cases identified manually, while subjective criteria were documented in only 6 of 59 (10.2%) infections. Agreement between the electronic surveillance and manual IP review was assessed as very good (κ, 0.80; 95% confidence interval, 0.71-0.89).

CONCLUSIONS

We report an attempt at automating surveillance for CAUTI. With a high negative predictive value, the electronic tool allows for more efficient CAUTI surveillance and facilitates housewide trending of rates and catheter utilization. This approach should be validated in different patient populations.

Electronic surveillance for healthcare-associated central line-associated bloodstream infections outside the intensive care unit

BACKGROUND

Manual surveillance for central line-associated bloodstream infections (CLABSIs) by infection prevention practitioners is time-consuming and often limited to intensive care units (ICUs). An automated surveillance system using existing databases with patient-level variables and microbiology data was investigated.

METHODS

Patients with a positive blood culture in 4 non-ICU wards at Barnes-Jewish Hospital between July 1, 2005, and December 31, 2006, were evaluated. CLABSI determination for these patients was made via 2 sources; a manual chart review and an automated review from electronically available data. Agreement between these 2 sources was used to develop the best-fit electronic algorithm that used a set of rules to identify a CLABSI. Sensitivity, specificity, predictive values, and Pearson's correlation were calculated for the various rule sets, using manual chart review as the reference standard.

RESULTS

During the study period, 391 positive blood cultures from 331 patients were evaluated. Eighty-five (22%) of these were confirmed to be CLABSI by manual chart review. The best-fit model included presence of a catheter, blood culture positive for known pathogen or blood culture with a common skin contaminant confirmed by a second positive culture and the presence of fever, and no positive cultures with the same organism from another sterile site. The best-performing rule set had an overall sensitivity of 95.2%, specificity of 97.5%, positive predictive value of 90%, and negative predictive value of 99.2% compared with intensive manual surveillance.

CONCLUSIONS

Although CLABSIs were slightly overpredicted by electronic surveillance compared with manual chart review, the method offers the possibility of performing acceptably good surveillance in areas where resources do not allow for traditional manual surveillance.

Automated detection of external ventricular and lumbar drain-related meningitis using laboratory and microbiology results and medication data

Objective

Monitoring of healthcare-associated infection rates is important for infection control and hospital benchmarking. However, manual surveillance is time-consuming and susceptible to error. The aim was, therefore, to develop a prediction model to retrospectively detect drain-related meningitis (DRM), a frequently occurring nosocomial infection, using routinely collected data from a clinical data warehouse.

Methods

As part of the hospital infection control program, all patients receiving an external ventricular (EVD) or lumbar drain (ELD) (2004 to 2009; n = 742) had been evaluated for the development of DRM through chart review and standardized diagnostic criteria by infection control staff; this was the reference standard. Children, patients dying <24 hours after drain insertion or with <1 day follow-up and patients with infection at the time of insertion or multiple simultaneous drains were excluded. Logistic regression was used to develop a model predicting the occurrence of DRM. Missing data were imputed using multiple imputation. Bootstrapping was applied to increase generalizability.

Results

537 patients remained after application of exclusion criteria, of which 82 developed DRM (13.5/1000 days at risk). The automated model to detect DRM included the number of drains placed, drain type, blood leukocyte count, C-reactive protein, cerebrospinal fluid leukocyte count and culture result, number of antibiotics started during admission, and empiric antibiotic therapy. Discriminatory power of this model was excellent (area under the ROC curve 0.97). The model achieved 98.8% sensitivity (95% CI 88.0% to 99.9%) and specificity of 87.9% (84.6% to 90.8%). Positive and negative predictive values were 56.9% (50.8% to 67.9%) and 99.9% (98.6% to 99.9%), respectively. Predicted yearly infection rates concurred with observed infection rates.

Conclusion

A prediction model based on multi-source data stored in a clinical data warehouse could accurately quantify rates of DRM. Automated detection using this statistical approach is feasible and could be applied to other nosocomial infections.

Current strategies for the prevention and management of central line-associated bloodstream infections

Central venous catheters are an invaluable tool for diagnostic and therapeutic purposes in today’s medicine, but their use can be complicated by bloodstream infections (BSIs). While evidence-based preventive measures are disseminated by infection control associations, the optimal management of established central line-associated BSIs has been summarized in infectious diseases guidelines. We prepared an overview of the state-of-the-art of prevention and management of central line-associated BSIs and included topics such as the role of antibiotic-coated catheters, the role of catheter removal in the management, and a review of currently used antibiotic compounds and the duration of treatment.

Quality of traditional surveillance for public reporting of nosocomial bloodstream infection rates

CONTEXT

Central line-associated bloodstream infection (BSI) rates, determined by infection preventionists using the Centers for Disease Control and Prevention (CDC) surveillance definitions, are increasingly published to compare the quality of patient care delivered by hospitals. However, such comparisons are valid only if surveillance is performed consistently across institutions.

OBJECTIVE

To assess institutional variation in performance of traditional central line-associated BSI surveillance.

DESIGN, SETTING, AND PARTICIPANTS

We performed a retrospective cohort study of 20 intensive care units among 4 medical centers (2004-2007). Unit-specific central line-associated BSI rates were calculated for 12-month periods. Infection preventionists, blinded to study participation, performed routine prospective surveillance using CDC definitions. A computer algorithm reference standard was applied retrospectively using criteria that adapted the same CDC surveillance definitions.

MAIN OUTCOME MEASURES

Correlation of central line-associated BSI rates as determined by infection preventionist vs the computer algorithm reference standard. Variation in performance was assessed by testing for institution-dependent heterogeneity in a linear regression model.

RESULTS

Forty-one unit-periods among 20 intensive care units were analyzed, representing 241,518 patient-days and 165,963 central line-days. The median infection preventionist and computer algorithm central line-associated BSI rates were 3.3 (interquartile range [IQR], 2.0-4.5) and 9.0 (IQR, 6.3-11.3) infections per 1000 central line-days, respectively. Overall correlation between computer algorithm and infection preventionist rates was weak (ρ = 0.34), and when stratified by medical center, point estimates for institution-specific correlations ranged widely: medical center A: 0.83; 95% confidence interval (CI), 0.05 to 0.98; P = .04; medical center B: 0.76; 95% CI, 0.32 to 0.93; P = .003; medical center C: 0.50, 95% CI, -0.11 to 0.83; P = .10; and medical center D: 0.10; 95% CI -0.53 to 0.66; P = .77. Regression modeling demonstrated significant heterogeneity among medical centers in the relationship between computer algorithm and expected infection preventionist rates (P < .001). The medical center that had the lowest rate by traditional surveillance (2.4 infections per 1000 central line-days) had the highest rate by computer algorithm (12.6 infections per 1000 central line-days).

CONCLUSIONS

Institutional variability of infection preventionist rates relative to a computer algorithm reference standard suggests that there is significant variation in the application of standard central line-associated BSI surveillance definitions across medical centers. Variation in central line-associated BSI surveillance practice may complicate interinstitutional comparisons of publicly reported central line-associated BSI rates.

Developing information technology for infection prevention surveillance

The potential to automate at least part of the surveillance process for health care-associated infections was seen as soon as hospitals began to implement computer systems. Progress toward automated surveillance has been ongoing for the last several decades. But as more information becomes available electronically in the healthcare setting, the promise of electronic surveillance for healthcare-associated infections has become closer to reality. Although true fully automated surveillance is not here yet, significant progress is being made at a number of centers for electronic surveillance of central catheter-associated bloodstream infections, ventilator-associated pneumonia, and other healthcare-associated infections. We review the progress that has been made in this area and issues that need to be addressed as surveillance systems are implemented, as well as promising areas for future development.

Detection of blood culture bacterial contamination using natural language processing

Microbiology results are reported in semi-structured formats and have a high content of useful patient information. We developed and validated a hybrid regular expression and natural language processing solution for processing blood culture microbiology reports. Multi-center Veterans Affairs training and testing data sets were randomly extracted and manually reviewed to determine the culture and sensitivity as well as contamination results. The tool was iteratively developed for both outcomes using a training dataset, and then evaluated on the test dataset to determine antibiotic susceptibility data extraction and contamination detection performance. Our algorithm had a sensitivity of 84.8% and a positive predictive value of 96.0% for mapping the antibiotics and bacteria with appropriate sensitivity findings in the test data. The bacterial contamination detection algorithm had a sensitivity of 83.3% and a positive predictive value of 81.8%.