Applied Clinical Informatics Applied Clinical Informatics aci de-de Tue, 27 Jun 17 07:08:25 +0200 Solving Interoperability in Translational Health Background: In the summer of 2016 an international group of biomedical and health informatics faculty and graduate students gathered for the 16th meeting of the International Partnership in Health Informatics Education (IPHIE) masterclass at the University of Utah campus in Salt Lake City, Utah. This international biomedical and health informatics workshop was created to share knowledge and explore issues in biomedical health informatics (BHI). Objective: The goal of this paper is to summarize the discussions of biomedical and health informatics graduate students who were asked to define interoperability, and make critical observations to gather insight on how to improve biomedical education. Methods: Students were assigned to one of four groups and asked to define interoperability and explore potential solutions to current problems of interoperability in health care. Results: We summarize here the student reports on the importance and possible solutions to the “interoperability problem” in biomedical informatics. Reports are provided from each of the four groups of highly qualified graduate students from leading BHI programs in the US, Europe and Asia. Conclusion: International workshops such as IPHIE provide a unique opportunity for graduate student learning and knowledge sharing. BHI faculty are encouraged to incorporate into their curriculum opportunities to exercise and strengthen student critical thinking to prepare our students for solving health informatics problems in the future.... A. M. Turner (1), J. C. Facelli (2), M. Jaspers (3), T. Wetter (4), D. Pfeifer (5), L. C. Gatewood (6), T. Adam (6), Y.-C. Li (7), M.-C. Lin (7), R. S. Evans (2), A. Beukenhorst (3), H. J. T. van Mens (3), E. Tensen (3), C. Bock (4), L. Fendrich (4), P. Seitz (4), J. Suleder (4), R. Aldelkhyyel (6), K. Bridgeman (6), Z. Hu (6), A. Sattler (6), S. Guo (7), I. Md. Mohaimenul (7), D. Anggraini Ningrum (7), H. Tung (7), J. Bian (2), J. M. Plasek (2), C. Rommel (2), J. Burke (1), H. Sohih (1) 27684 2017-06-21 13:12:05 Developing Mobile Clinical Decision Support for Nursing Home Staff Assessment of Urinary Tract... Background: Unique characteristics of nursing homes (NHs) contribute to high rates of inappropriate antibiotic use for asymptomatic bacteriuria (ASB), a benign condition. A mobile clinical decision support system (CDSS) may support NH staff in differentiating urinary tract infections (UTI) from ASB and reducing antibiotic days. Objectives: We used Goal-Directed Design to: 1) Characterize information needs for UTI identification and management in NHs; 2) Develop UTI Decide, a mobile CDSS prototype informed by personas and scenarios of use constructed from Aim 1 findings; 3) Evaluate the UTI Decide prototype with NH staff. Methods: Focus groups were conducted with providers and nurses in NHs in Denver, Colorado (n= 24). Qualitative descriptive analysis was applied to focus group transcripts to identify information needs and themes related to mobile clinical decision support for UTI identification and management. Personas representing typical end users were developed; typical clinical context scenarios were constructed using information needs as goals. Usability testing was performed using cognitive walk-throughs and a think-aloud protocol. Results: Four information needs were identified including guidance regarding resident assessment; communication with providers; care planning; and urine culture interpretation. Design of a web-based application incorporating a published decision support algorithm for evidence-based UTI diagnoses proceeded with a focus on nursing information needs during resident assessment and communication with providers. Certified nursing assistant (CNA) and registered nurse (RN) personas were constructed in 4 context scenarios with associated key path scenarios. After field testing, a high fidelity prototype of UTI Decide was completed and evaluated by potential end users. Design recommendations and content recommendations were elicited. Conclusions: Goal-Directed Design informed the development of a mobile CDSS supporting participant-identified information needs for UTI assessment and communication in NHs. Future work will include iterative deployment and evaluation of UTI Decide in NHs to decrease inappropriate use of antibiotics for suspected UTI.... W. Jones (1), C. Drake (1), D. Mack (1), B. Reeder (2), B. Trautner (3), H. Wald (1) 27683 2017-06-21 13:09:25 The Obesity Epidemic and the Potential of Augmented Reality M. K. Poku (1), N. A. Behkami (2), D. W. Bates (3, 4) 27645 2017-06-14 10:55:28 Development of Multivariable Models to Predict and Benchmark Transfusion in Elective Surgery... Background: Blood transfusion is a highly prevalent procedure in hospitalized patients and in some clinical scenarios it has lifesaving potential. However, in most cases transfusion is administered to hemodynamically stable patients with no benefit, but increased odds of adverse patient outcomes and substantial direct and indirect cost. Therefore, the concept of Patient Blood Management has increasingly gained importance to pre-empt and reduce transfusion and to identify the optimal transfusion volume for an individual patient when transfusion is indicated. Objectives: It was our aim to describe, how predictive modeling and machine learning tools applied on pre-operative data can be used to predict the amount of red blood cells to be transfused during surgery and to prospectively optimize blood ordering schedules. In addition, the data derived from the predictive models should be used to benchmark different hospitals concerning their blood transfusion patterns. Methods: 6,530 case records obtained for elective surgeries from 16 centers taking part in two studies conducted in 2004–2005 and 2009–2010 were analyzed. Transfused red blood cell volume was predicted using random forests. Separate models were trained for overall data, for each center and for each of the two studies. Important characteristics of different models were compared with one another. Results: Our results indicate that predictive modeling applied prior surgery can predict the transfused volume of red blood cells more accurately (correlation coefficient cc = 0.61) than state of the art algorithms (cc = 0.39). We found significantly different patterns of feature importance a) in different hospitals and b) between study 1 and study 2. Conclusion: We conclude that predictive modeling can be used to benchmark the importance of different features on the models derived with data from different hospitals. This might help to optimize crucial processes in a specific hospital, even in other scenarios beyond Patient Blood Management.... D. Hayn (1), K. Kreiner (1), H. Ebner (1), P. Kastner (1), N. Breznik (1), A. Rzepka (1), A. Hofmann (2), H. Gombotz (3), G. Schreier (1) 27644 2017-06-14 10:55:18 A FHIR Human Leukocyte Antigen (HLA) Interface for Platelet Transfusion Support Platelet transfusions are a cornerstone of therapy for patients who develop thrombocytopenia while undergoing Hematopoietic Stem Cell Transplantation (HSCT). Many patients who develop Platelet Transfusion Refractoriness (PTR) require HLA-matched platelets. Identifying these patients early could lead to better utilization of platelets as well as increased platelet counts. We built a SMART on FHIR visualization tool to aid the oncology, blood bank, and blood donor center teams in identifying these patients by showing trends in thrombocytopenia along with a computer generated calculated Panel Reactive Antibody (cPRA) level. To do this, we required a FHIR interface to our HLA database. We describe our methods and outcome for constructing this FHIR interface, as well as the architecture and data flow of HLA data from its proprietary database to the SMART on FHIR environment and application database along with RESTful cPRA web service calculator. Future work will evaluate the clinical impact of this platelet visualization tool and overall success of our FHIR implementation.... W. J. Gordon (1, 2, 3), J. Baronas (4), W. J. Lane (4, 3) 27603 2017-06-07 11:50:13 An Analysis of Patient Safety Incident Reports Associated with Electronic Health Record... Background: With the widespread use of electronic health records (EHRs) for many clinical tasks, interoperability with other health information technology (health IT) is critical for the effective delivery of care. While it is generally recognized that poor interoperability negatively impacts patient care, little is known about the specific patient safety implications. Understanding the patient safety implications will help prioritize interoperability efforts around architectures and standards. Objectives: Our objectives were to (1) identify patient safety incident reports that reflect EHR interoperability challenges with other health IT, and (2) perform a detailed analysis of these reports to understand the health IT systems involved, the clinical care processes impacted, whether the incident occurred within or between provider organizations, and the reported severity of the patient safety events. Methods: From a database of 1.735 million patient safety event (PSE) reports spanning multiple provider organizations, 2625 reports that were indicated as being health IT related by the event reporter were reviewed to identify EHR interoperability related reports. Through a rigorous coding process 209 EHR interoperability related events were identified and coded. Results: The majority of EHR interoperability PSE reports involved interfacing with pharmacy systems (i.e. medication related), followed by laboratory, and radiology. Most of the interoperability challenges in these clinical areas were associated with the EHR receiving information from other health IT systems as opposed to the EHR sending information to other systems. The majority of EHR interoperability challenges were within a provider organization and while many of the safety events reached the patient, only a few resulted in patient harm. Conclusions: Interoperability efforts should prioritize systems in pharmacy, laboratory, and radiology. Providers should recognize the need to improve EHRs interfacing with other health IT systems within their own organization.... K. T. Adams (1), R. Ratwani (2), J. L. Howe (1), A. Fong (1), J. S. Puthumana (1), K. M. Kellogg (1, 3), M. Gaunt (4), R. M. Ratwani (1, 3) 27602 2017-06-07 11:47:32 The effects of natural language processing on cross-institutional portability of influenza case... Objectives: This study evaluates the accuracy and portability of a natural language processing (NLP) tool for extracting clinical findings of influenza from clinical notes across two large healthcare systems. Effectiveness is evaluated on how well NLP supports downstream influenza case-detection for disease surveillance. Methods: We independently developed two NLP parsers, one at Intermountain Healthcare (IH) in Utah and the other at University of Pittsburgh Medical Center (UPMC) using local clinical notes from emergency department (ED) encounters of influenza. We measured NLP parser performance for the presence and absence of 70 clinical findings indicative of influenza. We then developed Bayesian network models from NLP processed reports and tested their ability to discriminate among cases of (1) influenza, (2) non-influenza influenza-like illness (NI-ILI), and (3) ‘other’ diagnosis. Results: On Intermountain Healthcare reports, recall and precision of the IH NLP parser were 0.71 and 0.75, respectively, and UPMC NLP parser, 0.67 and 0.79. On University of Pittsburgh Medical Center reports, recall and precision of the UPMC NLP parser were 0.73 and 0.80, respectively, and IH NLP parser, 0.53 and 0.80. Bayesian case-detection performance measured by AUROC for influenza versus non-influenza on Intermountain Healthcare cases was 0.93 (using IH NLP parser) and 0.93 (using UPMC NLP parser). Case-detection on University of Pittsburgh Medical Center cases was 0.95 (using UPMC NLP parser) and 0.83 (using IH NLP parser). For influenza versus NI-ILI on Intermountain Healthcare cases performance was 0.70 (using IH NLP parser) and 0.76 (using UPMC NLP parser). On University of Pisstburgh Medical Center cases, 0.76 (using UPMC NLP parser) and 0.65 (using IH NLP parser). Conclusion: In all but one instance (influenza versus NI-ILI using IH cases), local parsers were more effective at supporting case-detection although performances of non-local parsers were reasonable.... J. P. Ferraro (1, 2), Y. Ye (3, 4), P. H. Gesteland (1, 5), P. J. Haug (1, 2), F. R. Tsui (3, 4), G. F. Cooper (3), R. Van Bree (2), T. Ginter (6), A. J. Nowalk (7), M. Wagner (3, 4) 27575 2017-05-31 11:08:06 Rapid Adjustment of Clinical Decision Support in Response to Updated Recommendations for Palivizumab... Background: Palivizumab is effective at reducing hospitalizations due to respiratory syncytial virus among high-risk children, but is indicated for a small population. Identification of patients eligible to receive palivizumab is labor-intensive and error-prone. To support patient identification we developed Clinical Decision Support (CDS) based on published recommendations in 2012. This CDS was developed using a systematic process, which directly linked computer code to a recommendation’s narrative text. In 2014, updated recommendations were published, which changed several key criteria used to determine eligible patients. Objective: Assess the effort required to update CDS in response to new palivizumab recommendations and identify factors that impacted these efforts. Methods: We reviewed the updated American Academy of Pediatrics (AAP) policy statement from Aug 2014 and identified areas of divergence from the prior publication. We modified the CDS to account for each difference. We recorded time spent on each activity to approximate the total effort required to update the CDS. Results: Of the 15 recommendations in the initial policy statement, 7 required updating. The CDS update was completed in 11 person-hours. Comparison of old and new recommendations was facilitated by the AAP policy statement structure and required 3 hours. Validation of the revised logic required 2 hours by a clinical domain expert. An informaticist required 3 hours to update and test the CDS. This included adding 24 lines and deleting 37 lines of code. Updating relevant data queries took an additional 3 hours and involved 10 edits. Conclusion: We quickly adapted CDS in response to changes in recommendations for palivizumab administration. The consistent AAP policy statement structure and the link we developed between these statements and the CDS rules facilitated our efforts. We recommend that CDS implementers establish linkages between published narrative recommendations and their executable rules to facilitate maintenance efforts.... J. Michel (1, 2), L. H. Utidjian (1, 2), D. Karavite (2), A. Hogan (1), M. J. Ramos (2), J. Miller (2), R. N. Shiffman (2, 3), R. W. Grundmeier (1, 2) 27574 2017-05-31 10:58:07 Improving Medication Adherence with Two-way Short Message Service Reminders in Sickle Cell Disease... Introduction: Sickle cell disease (SCD) is a childhood and adult disease that primarily affects African Americans, characterized by life threatening sequelae mitigated by medications. One-way and two-way short message service (SMS) medication reminders have differing efficacy in chronic diseases. There is limited literature about SMS medication reminders in SCD. Objective: The goal of this study was to test the feasibility, defined by recruitment/acceptance, retention/attrition, and technology utilization, of two-way SMS medication reminders in individuals with SCD with and without asthma. Materials and Methods: Participants were randomly allocated to standard care or reminders. Two-way SMS reminders were automated using Research Electronic Data Capture (REDCap) for hydroxyurea, fluticasone, budesonide and montelukast. Adherence was measured using the Morisky Medication Adherence Scale-8 (MMAS-8). Asthma control was assessed using the Childhood and Adult-Asthma Control Tests (ACT). Participants were enrolled 28 to 60 days with a common termination date. Results: The recruitment rate was 95% (47/49) and 82.9% completed the study. Among the 47 study participants enrolled, 51.1% were male, 61.7% were adults, median age was 20 (range: 3 to 59), and 98% were African Americans. Of the 26 participants receiving messages, 20% responded on over 95% of the days and usage varied with an average response rate of 33%, ranging from 21% to 46%. Medication adherence scores improved significantly in the intervention group (3.42 before, 5.46 after; p=0.002), but not in the control group (3.90 before, 4.75 after; p=0.080). Childhood-ACT scores improved in the intervention group (19.20 before, 24.25 after). Adult-ACT scores within the intervention arm were unchanged (21.0 before, 22.0 after. ACT scores did not improve significantly. Conclusion: This study demonstrated the feasibility for two-way SMS medication reminders to improve medication adherence in a high-risk population where daily medication adherence is critical to health outcomes and quality of life.... Brandi M. Pernell (1, 2), M. R. DeBaun (1), K. Becker (3), M. Rodeghier (4), V. Bryant (1), R. M. Cronin (5) 27561 2017-05-24 07:44:23 Insulin Bolus Calculator in a Pediatric Hospital Background: Insulin dosing in hospitalized pediatric patients is challenging and requires dosing to be matched with the specific clinical and nutritional circumstances. We implemented a customized subcutaneous insulin bolus dose calculator tool integrated with the electronic health record to improve patient care. Here we describe this tool, its utilization and safety, and assess user satisfaction and perceptions of the tool. Methods: Blood glucose results for all patients who received insulin with and without the calculator tool were compared to assess safety. To assess user perceptions and satisfaction, a survey was sent to all identified users who interacted with the tool during the period from May 2015 to the end of November 2015. Survey responses were summarized, mean user satisfaction calculated, and correlation of Likert scale items with overall satisfaction assessed. Results: Hypoglycemia rates (2.2% and 2.9%, p = 0.17) and severe hypoglycemia rates (0.04% and 0.1%, p = 0.21) were similar for the groups that received insulin with and without the calculator tool. Overall satisfaction for all survey respondents was high (4.05, SD = 0.83). Physicians indicated a slightly higher satisfaction than nurses (4.33 versus 3.94, p = 0.04). User agreement with improvement of quality of care showed the highest correlation with overall satisfaction (r = 0.80, 95% CI 0.7 – 0.87). Conclusion: Implementation of an insulin calculator tool streamlined ordering and administration of insulin in a pediatric academic institution while maintaining patient safety. Users indicated high overall satisfaction with the tool.... M. B. Ateya (1), R. Aiyagari (2), C. Moran (3), K. Singer (3) 27560 2017-05-24 07:43:20 Advancing the integration of hospital IT Background: Planning and controlling surgical operations hugely impacts upon productivity, patient safety, and surgeons’ careers. Established, specialized software for this task is being increasingly replaced by “Operating Room (OR)-modules” appended to enterprise-wide resource planning (ERP) systems. As a result, usability problems are re-emerging and require developers’ attention. Objective: Systematic evaluation of the functionality and social repercussions of a global, market-leading IT business control system (SAP R3, Germany), adapted for real-time OR process steering. Methods: Field study involving document analyses, interviews, and a 73-item survey addressed to 77 qualified (> 1-year system experience) senior planning executives (end users; “planners”) working in surgical departments of university hospitals. Results: Planners reported that 57% of electronic operation requests contained contradictory information. Key screens contained clinically irrelevant areas (36 +/- 29%). Compared to the legacy system, users reported either no improvements or worse performance, in regard to co-ordination of OR stakeholders, intra-day program changes, and safety. Planners concluded that the ERP-planning module was “non-intuitive” (66%), increased planning work (56%, p=0.002), and did not impact upon either organizational mishap spectrum or frequency. Interviews evidenced intra-institutional power shifts due to increased system complexity. Planners resented e.g. a trend towards increased personal culpability for mishap. Conclusions: Highly complex enterprise system extensions may not be directly suited to specific process steering tasks in a high risk/low error-environment like the OR. In view of surgeons’ high primary task load, the repeated call for simpler IT is an imperative for ERP extensions. System design should consider a) that current OR IT suffers from an input limitation regarding planning-relevant real-time data, and b) that there are social processes that strongly affect planning and particularly ERP use beyond algorithms. Real improvement of clinical IT tools requires their independent evaluation according to standards developed for pharmaceutical subjects.... C. Engelmann (1), D. Ametowobla (2) 27543 2017-05-17 08:54:00 A hospital-wide transition from paper to digital problem-oriented clinical notes Objectives: To evaluate the use, usability, and physician satisfaction of a locally developed problem-oriented clinical notes application that replaced paper-based records in a large Dutch university medical center. Methods: Using a clinical notes database and an application event log file and a cross-sectional survey of usability, authors retrospectively analyzed system usage for medical specialties, users, and patients over 4 years. A standardized questionnaire measured usability. Authors analyzed the effects of sex, age, professional experience, training hours, and medical specialty on user satisfaction via univariate analysis of variance. Authors also examined the correlation between user satisfaction in relation to users’ intensity of use of the application. Results: In total 1,793 physicians used the application to record progress notes for 219,755 patients. The overall satisfaction score was 3.2 on a scale from 1 (highly dissatisfied) to 5 (highly satisfied). A statistically significant difference occurred in satisfaction by medical specialty, but no statistically significant differences in satisfaction took place by sex, age, professional experience, or training hours. Intensity of system use did not correlate with physician satisfaction. Conclusions: By two years after the start of the implementation, all medical specialties utilized the clinical notes application. User satisfaction was neutral (3.2 on a 1–5 scale). Authors believe that the significant factors facilitating this transition mirrored success factors reported by other groups: a generic, consistent, and transparent design of the application; intensive collaboration; continuous monitoring; and an incremental rollout.... F. H. J. M. Cillessen (1), P. F. de Vries Robbé (1), M. C. J. Biermans (1) 27542 2017-05-17 08:41:51 The Effects of Medication Alerts on Prescriber Response in a Pediatric Hospital Objective: More than 70% of hospitals in the United States have electronic health records (EHRs). Clinical decision support (CDS) presents clinicians with electronic alerts during the course of patient care; however, alert fatigue can influence a provider’s response to any EHR alert. The primary goal was to evaluate the effects of alert burden on user response to the alerts. Methods: We performed a retrospective study of medication alerts over a 24-month period (1/2013–12/2014) in a large pediatric academic medical center. The institutional review board approved this study. The primary outcome measure was alert salience, a measure of whether or not the prescriber took any corrective action on the order that generated an alert. We estimated the ideal number of alerts to maximize salience. Salience rates were examined for providers at each training level, by day of week, and time of day through logistic regressions. Results: While salience never exceeded 38%, 49 alerts/day were associated with maximal salience in our dataset. The time of day an order was placed was associated with alert salience (maximal salience 2am). The day of the week was also associated with alert salience (maximal salience on Wednesday). Provider role did not have an impact on salience. Conclusion: Alert burden plays a role in influencing provider response to medication alerts. An increased number of alerts a provider saw during a one-day period did not directly lead to decreased response to alerts. Given the multiple factors influencing the response to alerts, efforts focused solely on burden are not likely to be effective.... J. W. Dexheimer (1, 2), E. S. Kirkendall (2, 3, 4, 5), M. Kouril (2), P. A. Hagedorn (3, 4), T. Minich (3, 6), L. L. Duan (7), M. Mahdi (4), R. Szczesniak (8, 9), S. A. Spooner (2, 3, 4) 27512 2017-05-10 08:14:32 Towards Usable E-Health Background: The use of e-health can lead to several positive outcomes. However, the potential for e-health to improve healthcare is partially dependent on its ease of use. In order to determine the usability for any technology, rigorously developed and appropriate measures must be chosen. Objectives: To identify psychometrically tested questionnaires that measure usability of e-health tools, and to appraise their generalizability, attributes coverage, and quality. Methods: We conducted a systematic review of studies that measured usability of e-health tools using four databases (Scopus, PubMed, CINAHL, and HAPI). Non-primary research, studies that did not report measures, studies with children or people with cognitive limitations, and studies about assistive devices or medical equipment were systematically excluded. Two authors independently extracted information including: questionnaire name, number of questions, scoring method, item generation, and psychometrics using a data extraction tool with pre-established categories and a quality appraisal scoring table. Results: Using a broad search strategy, 5,558 potentially relevant papers were identified. After removing duplicates and applying exclusion criteria, 35 articles remained that used 15 unique questionnaires. From the 15 questionnaires, only 5 were general enough to be used across studies. Usability attributes covered by the questionnaires were: learnability (15), efficiency (12), and satisfaction (11). Memorability (1) was the least covered attribute. Quality appraisal showed that face/content (14) and construct (7) validity were the most frequent types of validity assessed. All questionnaires reported reliability measurement. Some questionnaires scored low in the quality appraisal for the following reasons: limited validity testing (7), small sample size (3), no reporting of user centeredness (9) or feasibility estimates of time, effort, and expense (7). Conclusions: Existing questionnaires provide a foundation for research on e-health usability. However, future research is needed to broaden the coverage of the usability attributes and psychometric properties of the available questionnaires.... V. E. C. Sousa (1), K. Dunn Lopez (1) 27511 2017-05-10 08:08:31 Advanced 3D movement analysis algorithms for robust functional capacity assessment Objectives: We developed a novel system for in home functional capacities assessment in frail older adults by analyzing the Timed Up and Go movements. This system aims to follow the older people evolution, potentially allowing a forward detection of motor decompensation in order to trigger the implementation of rehabilitation. However, the pre-experimentations conducted on the ground, in different environments, revealed some problems which were related to KinectTM operation. Hence, the aim of this actual study is to develop methods to resolve these problems. Methods: Using the KinectTM sensor, we analyze the Timed Up and Go test movements by measuring nine spatio-temporal parameters, identified from the literature. We propose a video processing chain to improve the robustness of the analysis of the various test phases: automatic detection of the sitting posture, patient detection and three body joints extraction. We introduce a realistic database and a set of descriptors for sitting posture recognition. In addition, a new method for skin detection is implemented to facilitate the patient extraction and head detection. 94 experiments were conducted to assess the robustness of the sitting posture detection and the three joints extraction regarding condition changes. Results: The results showed good performance of the proposed video processing chain: the global error of the sitting posture detection was 0.67%. The success rate of the trunk angle calculation was 96.42%. These results show the reliability of the proposed chain, which increases the robustness of the automatic analysis of the Timed Up and Go. Conclusions: The system shows good measurements reliability and generates a note reflecting the patient functional level that showed a good correlation with 4 clinical tests commonly used. We suggest that it is interesting to use this system to detect impairment of motor planning processes.... A. Hassani (1), A. Kubicki (2), F. Mourey (3, 4), F. Yang (1) 27510 2017-05-10 08:04:10 Open Access: Canary: An NLP Platform for Clinicians and Researchers Information Extraction methods can help discover critical knowledge buried in the vast repositories of unstructured clinical data. However, these methods are underutilized in clinical research, potentially due to the absence of free software geared towards clinicians with little technical expertise. The skills required for developing/using such software constitute a major barrier for medical researchers wishing to employ these methods. To address this, we have developed Canary, a free and open-source solution designed for users without natural language processing (NLP) or software engineering experience. It was designed to be fast and work out of the box via a user-friendly graphical interface. S. Malmasi (1), N. L. Sandor (2), N. Hosomura (1), M. Goldberg (3), S. Skentzos (4), A. Turchin (1) 27489 2017-05-03 07:52:37 Combining Contrast Mining with Logistic Regression To Predict Healthcare Utilization in a Managed... Background: Because 5% of patients incur 50% of healthcare expenses, population health managers need to be able to focus preventive and longitudinal care on those patients who are at highest risk of increased utilization. Predictive analytics can be used to identify these patients and to better manage their care. Data mining permits the development of models that surpass the size restrictions of traditional statistical methods and take advantage of the rich data available in the electronic health record (EHR), without limiting predictions to specific chronic conditions. Objective: The objective was to demonstrate the usefulness of unrestricted EHR data for predictive analytics in managed healthcare. Methods: In a population of 9,568 Medicare and Medicaid beneficiaries, patients in the highest 5% of charges were compared to equal numbers of patients with the lowest charges. Contrast mining was used to discover the combinations of clinical attributes frequently associated with high utilization and infrequently associated with low utilization. The attributes found in these combinations were then tested by multiple logistic regression, and the discrimination of the model was evaluated by the c-statistic. Results: Of 19,014 potential EHR patient attributes, 67 were found in combinations frequently associated with high utilization, but not with low utilization (support>20%). Eleven of these attributes were significantly associated with high utilization (p<0.05). A prediction model composed of these eleven attributes had a discrimination of 84%. Conclusions: EHR mining reduced an unusably high number of patient attributes to a manageable set of potential healthcare utilization predictors, without conjecturing on which attributes would be useful. Treating these results as hypotheses to be tested by conventional methods yielded a highly accurate predictive model. This novel, two-step methodology can assist population health managers to focus preventive and longitudinal care on those patients who are at highest risk for increased utilization.... L. Sheets (1, 2), G. F. Petroski (2), Y. Zhuang (3), M. A. Phinney (3), B. Ge (2), J. C. Parker (2), C.-R. Shyu (1) 27488 2017-05-03 07:50:43 Development and use of a clinical decision support tool for behavioral health screening in primary... Objective: Screening, brief intervention, and referral for treatment (SBIRT) for behavioral health (BH) is a key clinical process. SBIRT tools in electronic health records (EHR) are infrequent and rarely studied. Our goals were 1) to design and implement SBIRT using clinical decision support (CDS) in a commercial EHR; and 2) to conduct a pragmatic evaluation of the impact of the tools on clinical outcomes. Methods: A multidisciplinary team designed SBIRT workflows and CDS tools. We analyzed the outcomes using a retrospective descriptive convenience cohort with age-matched comparison group. Data extracted from the EHR were evaluated using descriptive statistics. Results: There were 2 outcomes studied: 1) development and use of new BH screening tools and workflows; and 2) the results of use of those tools by a convenience sample of 866 encounters. The EHR tools developed included a flowsheet for documenting screens for 3 domains (depression, alcohol use, and prescription misuse); and 5 alerts with clinical recommendations based on screening; and reminders for annual screening. Positive screen rate was 21% (≥1 domain) with 60% of those positive for depression. Screening was rarely positive in 2 domains (11%), and never positive in 3 domains. Positive and negative screens led to higher rates of documentation of brief intervention (BI) compared with a matched sample who did not receive screening, including changes in psychotropic medications, updated BH terms on the problem list, or referral for BH intervention. Clinical process outcomes changed even when screening was negative. Conclusions: Modified workflows for BH screening and CDS tools with clinical recommendations can be deployed in the EHR. Using SBIRT tools changed clinical process metrics even when screening was negative, perhaps due to conversations about BH not captured in the screening flowsheet. Although there are limitations to the study, results support ongoing investigation.... T. E. Burdick (1, 2, 3), R. S. Kessler (4, 5) 27456 2017-04-21 10:23:44 Application of Natural Language Processing and Network Analysis Techniques to Post-market Reports... Objective: To evaluate the feasibility of automated dose and adverse event information retrieval in supporting the identification of safety patterns. Methods: We extracted all rabbit Anti-Thymocyte Globulin (rATG) reports submitted to the United States Food and Drug Administration Adverse Event Reporting System (FAERS) from the product’s initial licensure in April 16, 1984 through February 8, 2016. We processed the narratives using the Medication Extraction (MedEx) and the Event-based Text-mining of Health Electronic Records (ETHER) systems and retrieved the appropriate medication, clinical, and temporal information. When necessary, the extracted information was manually curated. This process resulted in a high quality dataset that was analyzed with the Pattern-based and Advanced Network Analyzer for Clinical Evaluation and Assessment (PANACEA) to explore the association of rATG dosing with post-transplant lymphoproliferative disorder (PTLD). Results: Although manual curation was necessary to improve the data quality, MedEx and ETHER supported the extraction of the appropriate information. We created a final dataset of 1,380 cases with complete information for rATG dosing and date of administration. Analysis in PANACEA found that PTLD was associated with cumulative doses of rATG >8 mg/kg, even in periods where most of the submissions to FAERS reported low doses of rATG. Conclusion: We demonstrated the feasibility of investigating a dose-related safety pattern for a particular product in FAERS using a set of automated tools.... T. Botsis (1), M. Foster (1), N. Arya (1), K. Kreimeyer (1), A. Pandey (1), D. Arya (1) 27455 2017-04-21 10:20:50 Using telephony data to facilitate discovery of clinical workflows Background: Discovery of clinical workflows to target for redesign using methods such as Lean and Six Sigma is difficult. VoIP telephone call pattern analysis may complement direct observation and EMR-based tools in understanding clinical workflows at the enterprise level by allowing visualization of institutional telecommunications activity. Objective: To build an analytic framework mapping repetitive and high-volume telephone call patterns in a large medical center to their associated clinical units using an enterprise unified communications server log file and to support visualization of specific call patterns using graphical networks. Methods: Consecutive call detail records from the medical center’s unified communications server were parsed to cross-correlate telephone call patterns and map associated phone numbers to a cost center dictionary. Hashed data structures were built to allow construction of edge and node files representing high volume call patterns for display with an open source graph network tool. Results: Summary statistics for an analysis of exactly one week’s call detail records at a large academic medical center showed that 912,386 calls were placed with a total duration of 23,186 hours. Approximately half of all calling called number pairs had an average call duration under 60 seconds and of these the average call duration was 27 seconds. Conclusions: Cross-correlation of phone calls identified by clinical cost center can be used to generate graphical displays of clinical enterprise communications. Many calls are short. The compact data transfers within short calls may serve as automation or re-design targets. The large absolute amount of time medical center employees were engaged in VoIP telecommunications suggests that analysis of telephone call patterns may offer additional insights into core clinical workflows.... D. W. Rucker (1) 27447 2017-04-19 08:16:43 Automating Clinical Score Calculation within the Electronic Health Record Objectives: Evidence-based clinical scores are used frequently in clinical practice, but data collection and data entry can be time consuming and hinder their use. We investigated the programmability of 168 common clinical calculators for automation within electronic health records. Methods: We manually reviewed and categorized variables from 168 clinical calculators as being extractable from structured data, unstructured data, or both. Advanced data retrieval methods from unstructured data sources were tabulated for diagnoses, non-laboratory test results, clinical history, and examination findings. Results: We identified 534 unique variables, of which 203/534 (37.8%) were extractable from structured data and 269/534 (50.4.7%) were potentially extractable using advanced techniques. Nearly half (265/534, 49.6%) of all variables were not retrievable. Only 26/168 (15.5%) of scores were completely programmable using only structured data and 43/168 (25.6%) could potentially be programmable using widely available advanced information retrieval techniques. Scores relying on clinical examination findings or clinical judgments were most often not completely programmable. Conclusion: Complete automation is not possible for most clinical scores because of the high prevalence of clinical examination findings or clinical judgments – partial automation is the most that can be achieved. The effect of fully or partially automated score calculation on clinical efficiency and clinical guideline adherence requires further study.... C. Aakre (1), M. Dziadzko (2), M. T. Keegan (2), V. Herasevich (2, 3) 27420 2017-04-12 08:22:31 Technology-Mediated Interventions and Quality of Life for Persons Living with HIV/AIDS Background: As HIV/AIDS is considered a chronic disease; quality of life (QoL) has become an important focus for researchers and healthcare providers. Technology-mediated interventions have demonstrated improved clinical effectiveness in outcomes, such as viral suppression, for persons living with HIV/AIDS (PLWH). However, the evidence to support the impact of these interventions on QoL is lacking. Objectives: The aim of this paper was to assess the impact of technology-mediated interventions on QoL and to identify the instruments used to measure the QoL of PLWH. Methods: For this review we followed the PRISMA guidelines. A literature search was conducted in PubMed, CINAHL, Cochrane, and EMBASE databases in April 2016. Inclusion criteria limited articles to those with technology-mediated interventions as compared to usual care; articles with the population defined as HIV-infected patients; and articles with QoL measured as a health outcome in randomized controlled trials. The Cochrane Collaboration Risk of Bias Tool was used to assess study quality. Results: Of the 1,554 peer-reviewed articles returned in the searches, 10 met the inclusion criteria. This systematic review identified four types of technology-mediated interventions and two types of QoL instruments used to examine the impact of technology-mediated interventions on PLWH. Four studies of technology-mediated interventions resulted in improvement in QoL. Four studies considered QoL as a secondary outcome and resulted in a negative or neutral impact on QoL. Overall, four studies had a low risk of bias, one study had a moderate risk of bias, and the other five studies had a high risk of bias. Conclusions: The evidence to support the improvement of QoL using technology-mediated interventions is insufficient. This lack of research highlights the need for increased study of QoL as an outcome measure and the need for consistent measures to better understand the role of technology-mediated interventions in improving QoL for PLWH.... H. Cho (1), S. Iribarren (2), R. Schnall (1) 27419 2017-04-12 08:19:03 Examining Perceptions of Computerized Physician Order Entry in a Neonatal Intensive Care Unit Background: Computerized provider order entry (CPOE) is a technology with potential to transform care delivery. While CPOE systems have been studied in adult populations, less is known about the implementation of CPOE in the neonatal intensive care unit (NICU) and perceptions of nurses and physicians using the system. Objective: To examine perceptions of clinicians before and after CPOE implementation in the NICU of a pediatric hospital. Methods: A cross-sectional survey of clinicians working in a Level III NICU was conducted. The survey was distributed before and after CPOE implementation. Participants were asked about their perception of CPOE on patient care delivery, implementation of the system, and effect on job satisfaction. A qualitative section inquired about additional concerns surrounding implementation. Responses were tabulated and analyzed using the Chi-square test. Results: The survey was distributed to 158 clinicians with a 47% response rate for pre-implementation and 45% for post-implementation. Clinicians understood why CPOE was implemented, but felt there was incomplete technical training. The expectation for increased job satisfaction and ability to recruit high-quality staff was high. However, there was concern about the ability to deliver appropriate treatments before and after implementation. Physicians were more optimistic about CPOE implementation than nurses who remained concerned that workflow may be altered. Conclusions: Introducing CPOE is a potentially risky endeavor and must be done carefully to mitigate harm. Although high expectations of the system can be met, it is important to attend to differing expectations among clinicians with varied levels of comfort with technology. Interdisciplinary collaboration is critical in planning a functioning CPOE to ensure that efficient workflow is maintained and appropriate supports for individuals with a lower degree of technical literacy is available.... K. S. Beam (1), M. Cardoso (1), M. Sweeney (2), G. Binney (3), S. N. Weingart (2) 27384 2017-04-05 08:49:51 Open Access: The Building Blocks of Interoperability Background: Patient matching is a key barrier to achieving interoperability. Patient demographic elements must be consistently collected over time and region to be valuable elements for patient matching. Objectives: We sought to determine what patient demographic attributes are collected at multiple institutions in the United States and see how their availability changes over time and across clinical sites. Methods: We compiled a list of 36 demographic elements that stakeholders previously identified as essential patient demographic attributes that should be collected for the purpose of linking patient records. We studied a convenience sample of 9 health care systems from geographically distinct sites around the country. We identified changes in the availability of individual patient demographic attributes over time and across clinical sites. Results: Several attributes were consistently available over the study period (2005–2014) including last name (99.96%), first name (99.95%), date of birth (98.82%), gender/sex (99.73%), postal code (94.71%), and full street address (94.65%). Other attributes changed significantly from 2005–2014: Social security number (SSN) availability declined from 83.3% to 50.44% (p<0.0001). Email address availability increased from 8.94% up to 54% availability (p<0.0001). Work phone number increased from 20.61% to 52.33% (p<0.0001). Conclusions: Overall, first name, last name, date of birth, gender/sex and address were widely collected across institutional sites and over time. Availability of emerging attributes such as email and phone numbers are increasing while SSN use is declining. Understanding the relative availability of patient attributes can inform strategies for optimal matching in healthcare.... A. Culbertson (1), S. Goel (2), M. B. Madden (2), N. Safaeinili (2), K. L. Jackson (2), T. Carton (3), R. Waitman (4), M. Liu (4), A. Krishnamurthy (5), L. Hall (6), N. Cappella (7), S. Visweswaran (7), M. J. Becich (7), R. Applegate (8), E. Bernstam (8), R. Rothman (9), M. Matheny (9), G. Lipori (10), J. Bian (10), W. Hogan (10), D. Bell (11), A. Martin (12), S. Grannis (12), J. Klann (13), R. Sutphen (14), A. B. O’Hara (15), A. Kho (2) 27383 2017-04-05 08:44:23 The effect of requesting a reason for non-adherence to a guideline in a long running automated... Background: Automated reminders are employed frequently to improve guideline adherence, but limitations of automated reminders are becoming more apparent. We studied the reasons for non-adherence in the setting of automated reminders to test the hypothesis that a separate request for a reason in itself may further improve guideline adherence. Methods: In a previously implemented automated reminder system on prophylaxis for postoperative nausea and vomiting (PONV), we included additional automated reminders requesting a reason for non-adherence. We recorded these reasons in the pre-operative screening clinic, the OR and the PACU. We compared adherence to our PONV guideline in two study groups with a historical control group. Results: Guideline adherence on prescribing and administering PONV prophylaxis (dexamethasone and granisetron) all improved compared to the historical control group (89 vs. 82% (p< 0.0001), 96 vs 95% (not significant) and 90 vs 82% (p<0.0001)) while decreasing unwarranted prescription for PONV prophylaxis (10 vs. 13 %). In the pre-operative screening clinic, the main reason for not prescribing PONV prophylaxis was disagreement with the risk estimate by the decision support system. In the OR/PACU, the main reasons for not administering PONV prophylaxis were: ‘unintended non-adherence’ and ‘failure to document’. Conclusions: In this study requesting a reason for non-adherence is associated with improved guideline adherence. The effect seems to depend on the underlying reason for non-adherence. It also illustrates the importance of human factors principles in the design of decision support. Some reasons for non-adherence may not be influenced by automated reminders.... F. O. Kooij (1), T. Klok (2), B. Preckel (1), M. W. Hollmann (1), J. E. Kal (2) 27368 2017-03-29 08:26:38