Accuracy of identifying hospital acquired venous thromboembolism by administrative coding: implications for big data and machine learning research.

Big data analytics research using heterogeneous electronic health record (EHR) data requires accurate identification of disease phenotype cases and controls. Overreliance on ground truth determination based on administrative data can lead to biased and inaccurate findings. Hospital-acquired venous thromboembolism (HA-VTE) is challenging to identify due to its temporal evolution and variable EHR documentation. To establish ground truth for machine learning modeling, we compared accuracy of HA-VTE diagnoses made by administrative coding to manual review of gold standard diagnostic test results. We performed retrospective analysis of EHR data on 3680 adult stepdown unit patients identifying HA-VTE. International Classification of Diseases, Ninth Revision (ICD-9-CM) codes for VTE were identified. 4544 radiology reports associated with VTE diagnostic tests were screened using terminology extraction and then manually reviewed by a clinical expert to confirm diagnosis. Of 415 cases with ICD-9-CM codes for VTE, 219 were identified with acute onset type codes. Test report review identified 158 new-onset HA-VTE cases. Only 40% of ICD-9-CM coded cases (n = 87) were confirmed by a positive diagnostic test report, leaving the majority of administratively coded cases unsubstantiated by confirmatory diagnostic test. Additionally, 45% of diagnostic test confirmed HA-VTE cases lacked corresponding ICD codes. ICD-9-CM coding missed diagnostic test-confirmed HA-VTE cases and inaccurately assigned cases without confirmed VTE, suggesting dependence on administrative coding leads to inaccurate HA-VTE phenotyping. Alternative methods to develop more sensitive and specific VTE phenotype solutions portable across EHR vendor data are needed to support case-finding in big-data analytics.

Supplementing Existing Societal Risk Models for Surgical Aortic Valve Replacement With Machine Learning for Improved Prediction.

Background This study evaluated the role of supplementing Society of Thoracic Surgeons (STS) risk models for surgical aortic valve replacement with machine learning (ML). Methods and Results Adults undergoing isolated surgical aortic valve replacement in the STS National Database between 2007 and 2017 were included. ML models for operative mortality and major morbidity were previously developed using extreme gradient boosting. Concordance and discordance in predicted risk between ML and STS models were defined using equal-size tertile-based thresholds of risk. Calibration metrics and discriminatory capability were compared between concordant and discordant patients. A total of 243 142 patients were included. Nearly all calibration metrics were improved in cases of concordance. Similarly, concordance indices improved substantially in cases of concordance for all models with the exception of deep sternal wound infection. The greatest improvements in concordant versus discordant cases were in renal failure: ML model (concordance index, 0.660 [95% CI, 0.632-0.687] discordant versus 0.808 [95% CI, 0.794-0.822] concordant) and STS model (concordance index, 0.573 [95% CI, 0.549-0.576] discordant versus 0.797 [95% CI, 0.782-0.811] concordant) (each P<0.001). Excluding deep sternal wound infection, the concordance indices ranged from 0.549 to 0.660 for discordant cases and 0.674 to 0.808 for concordant cases. Conclusions Supplementing ML models with existing STS models for surgical aortic valve replacement may have an important role in risk prediction and should be explored further. In particular, for the roughly 25% to 50% of patients demonstrating discordance in estimated risk between ML and STS, there appears to be a substantial decline in predictive performance suggesting vulnerability of the existing models in these patient subsets.

Outbreak of Pseudomonas aeruginosa Infections from a Contaminated Gastroscope Detected by Whole Genome Sequencing Surveillance.

BACKGROUND: Traditional methods of outbreak investigations utilize reactive whole genome sequencing (WGS) to confirm or refute the outbreak. We have implemented WGS surveillance and a machine learning (ML) algorithm for the electronic health record (EHR) to retrospectively detect previously unidentified outbreaks and to determine the responsible transmission routes. METHODS: We performed WGS surveillance to identify and characterize clusters of genetically-related Pseudomonas aeruginosa infections during a 24-month period. ML of the EHR was used to identify potential transmission routes. A manual review of the EHR was performed by an infection preventionist to determine the most likely route and results were compared to the ML algorithm. RESULTS: We identified a cluster of 6 genetically related P. aeruginosa cases that occurred during a 7-month period. The ML algorithm identified gastroscopy as a potential transmission route for 4 of the 6 patients. Manual EHR review confirmed gastroscopy as the most likely route for 5 patients. This transmission route was confirmed by identification of a genetically-related P. aeruginosa incidentally cultured from a gastroscope used on 4of the 5 patients. Three infections, 2 of which were blood stream infections, could have been prevented if the ML algorithm had been running in real-time. CONCLUSIONS: WGS surveillance combined with a ML algorithm of the EHR identified a previously undetected outbreak of gastroscope-associated P. aeruginosa infections. These results underscore the value of WGS surveillance and ML of the EHR for enhancing outbreak detection in hospitals and preventing serious infections.

Automated data mining of the electronic health record for investigation of healthcare-associated outbreaks.

BACKGROUND: Identifying routes of transmission among hospitalized patients during a healthcare-associated outbreak can be tedious, particularly among patients with complex hospital stays and multiple exposures. Data mining of the electronic health record (EHR) has the potential to rapidly identify common exposures among patients suspected of being part of an outbreak. METHODS: We retrospectively analyzed 9 hospital outbreaks that occurred during 2011-2016 and that had previously been characterized both according to transmission route and by molecular characterization of the bacterial isolates. We determined (1) the ability of data mining of the EHR to identify the correct route of transmission, (2) how early the correct route was identified during the timeline of the outbreak, and (3) how many cases in the outbreaks could have been prevented had the system been running in real time. RESULTS: Correct routes were identified for all outbreaks at the second patient, except for one outbreak involving >1 transmission route that was detected at the eighth patient. Up to 40 or 34 infections (78% or 66% of possible preventable infections, respectively) could have been prevented if data mining had been implemented in real time, assuming the initiation of an effective intervention within 7 or 14 days of identification of the transmission route, respectively. CONCLUSIONS: Data mining of the EHR was accurate for identifying routes of transmission among patients who were part of the outbreak. Prospective validation of this approach using routine whole-genome sequencing and data mining of the EHR for both outbreak detection and route attribution is ongoing.

Cardiorespiratory instability in monitored step-down unit patients: using cluster analysis to identify patterns of change.

Cardiorespiratory instability (CRI) in monitored step-down unit (SDU) patients has a variety of etiologies, and likely manifests in patterns of vital signs (VS) changes. We explored use of clustering techniques to identify patterns in the initial CRI epoch (CRI1; first exceedances of VS beyond stability thresholds after SDU admission) of unstable patients, and inter-cluster differences in admission characteristics and outcomes. Continuous noninvasive monitoring of heart rate (HR), respiratory rate (RR), and pulse oximetry (SpO2) were sampled at 1/20 Hz. We identified CRI1 in 165 patients, employed hierarchical and k-means clustering, tested several clustering solutions, used 10-fold cross validation to establish the best solution and assessed inter-cluster differences in admission characteristics and outcomes. Three clusters (C) were derived: C1) normal/high HR and RR, normal SpO2 (n = 30); C2) normal HR and RR, low SpO2 (n = 103); and C3) low/normal HR, low RR and normal SpO2 (n = 32). Clusters were significantly different based on age (p < 0.001; older patients in C2), number of comorbidities (p = 0.008; more C2 patients had ≥ 2) and hospital length of stay (p = 0.006; C1 patients stayed longer). There were no between-cluster differences in SDU length of stay, or mortality. Three different clusters of VS presentations for CRI1 were identified. Clusters varied on age, number of comorbidities and hospital length of stay. Future study is needed to determine if there are common physiologic underpinnings of VS clusters which might inform clinical decision-making when CRI first manifests.

Dynamic and Personalized Risk Forecast in Step-Down Units. Implications for Monitoring Paradigms.

RATIONALE: Cardiorespiratory insufficiency (CRI) is a term applied to the manifestations of loss of normal cardiorespiratory reserve and portends a bad outcome. CRI occurs commonly in hospitalized patients, but its risk escalation patterns are unexplored. OBJECTIVES: To describe the dynamic and personal character of CRI risk evolution observed through continuous vital sign monitoring of individual step-down unit patients. METHODS: Using a machine learning model, we estimated risk trends for CRI (defined as exceedance of vital sign stability thresholds) for each of 1,971 admissions (1,880 unique patients) to a 24-bed adult surgical trauma step-down unit at an urban teaching hospital in Pittsburgh, Pennsylvania using continuously recorded vital signs from standard bedside monitors. We compared and contrasted risk trends during initial 4-hour periods after step-down unit admission, and again during the 4 hours immediately before the CRI event, between cases (ever had a CRI) and control subjects (never had a CRI). We further explored heterogeneity of risk escalation patterns during the 4 hours before CRI among cases, comparing personalized to nonpersonalized risk. MEASUREMENTS AND MAIN RESULTS: Estimated risk was significantly higher for cases (918) than control subjects (1,053; P ≤ 0.001) during the initial 4-hour stable periods. Among cases, the aggregated nonpersonalized risk trend increased 2 hours before the CRI, whereas the personalized risk trend became significantly different from control subjects 90 minutes ahead. We further discovered several unique phenotypes of risk escalation patterns among cases for nonpersonalized (14.6% persistently high risk, 18.6% early onset, 66.8% late onset) and personalized risk (7.7% persistently high risk, 8.9% early onset, 83.4% late onset). CONCLUSIONS: Insights from this proof-of-concept analysis may guide design of dynamic and personalized monitoring systems that predict CRI, taking into account the triage and real-time monitoring utility of vital signs. These monitoring systems may prove useful in the dynamic allocation of technological and clinical personnel resources in acute care hospitals.

Detecting linkages between human illness and Salmonella isolates in food using a new tool for spatio-temporal analysis of multi-stream data.

We present a prototype tool designed to enable computationally efficient visualization of data and its spatio-temporal analysis by food safety and public health investigators. Its utility is evaluated in the following contexts: (1) Investigation of relationships between cases of Salmonella related human illness and Salmonella positives in meat and poultry products at USDA regulated establishments; (2) Identification and detection of patterns in food safety data which may impact public health.