Dennis Toddenroth

A scoping review of cloud computing in healthcare

BackgroundCloud computing is a recent and fast growing area of development in healthcare. Ubiquitous, on-demand access to virtually endless resources in combination with a pay-per-use model allow for new ways of developing, delivering and using services. Cloud computing is often used in an “OMICS-context”, e.g. for computing in genomics, proteomics and molecular medicine, while other field of application still seem to be underrepresented. Thus, the objective of this scoping review was to identify the current state and hot topics in research on cloud computing in healthcare beyond this traditional domain.MethodsMEDLINE was searched in July 2013 and in December 2014 for publications containing the terms “cloud computing” and “cloud-based”. Each journal and conference article was categorized and summarized independently by two researchers who consolidated their findings.Results102 publications have been analyzed and 6 main topics have been found: telemedicine/teleconsultation, medical imaging, public health and patient self-management, hospital management and information systems, therapy, and secondary use of data. Commonly used features are broad network access for sharing and accessing data and rapid elasticity to dynamically adapt to computing demands. Eight articles favor the pay-for-use characteristics of cloud-based services avoiding upfront investments. Nevertheless, while 22 articles present very general potentials of cloud computing in the medical domain and 66 articles describe conceptual or prototypic projects, only 14 articles report from successful implementations. Further, in many articles cloud computing is seen as an analogy to internet-/web-based data sharing and the characteristics of the particular cloud computing approach are unfortunately not really illustrated.ConclusionsEven though cloud computing in healthcare is of growing interest only few successful implementations yet exist and many papers just use the term “cloud” synonymously for “using virtual machines” or “web-based” with no described benefit of the cloud paradigm. The biggest threat to the adoption in the healthcare domain is caused by involving external cloud partners: many issues of data safety and security are still to be solved. Until then, cloud computing is favored more for singular, individual features such as elasticity, pay-per-use and broad network access, rather than as cloud paradigm on its own.

Ontology-Based Data Integration between Clinical and Research Systems

Data from the electronic medical record comprise numerous structured but uncoded ele-ments, which are not linked to standard terminologies. Reuse of such data for secondary research purposes has gained in importance recently. However, the identification of rele-vant data elements and the creation of database jobs for extraction, transformation and loading (ETL) are challenging: With current methods such as data warehousing, it is not feasible to efficiently maintain and reuse semantically complex data extraction and trans-formation routines. We present an ontology-supported approach to overcome this challenge by making use of abstraction: Instead of defining ETL procedures at the database level, we use ontologies to organize and describe the medical concepts of both the source system and the target system. Instead of using unique, specifically developed SQL statements or ETL jobs, we define declarative transformation rules within ontologies and illustrate how these constructs can then be used to automatically generate SQL code to perform the desired ETL procedures. This demonstrates how a suitable level of abstraction may not only aid the interpretation of clinical data, but can also foster the reutilization of methods for un-locking it.

Evaluating predictive modeling algorithms to assess patient eligibility for clinical trials from routine data

BackgroundThe necessity to translate eligibility criteria from free text into decision rules that are compatible with data from the electronic health record (EHR) constitutes the main challenge when developing and deploying clinical trial recruitment support systems. Recruitment decisions based on case-based reasoning, i.e. using past cases rather than explicit rules, could dispense with the need for translating eligibility criteria and could also be implemented largely independently from the terminology of the EHR’s database. We evaluated the feasibility of predictive modeling to assess the eligibility of patients for clinical trials and report on a prototype’s performance for different system configurations.MethodsThe prototype worked by using existing basic patient data of manually assessed eligible and ineligible patients to induce prediction models. Performance was measured retrospectively for three clinical trials by plotting receiver operating characteristic curves and comparing the area under the curve (ROC-AUC) for different prediction algorithms, different sizes of the learning set and different numbers and aggregation levels of the patient attributes.ResultsRandom forests were generally among the best performing models with a maximum ROC-AUC of 0.81 (CI: 0.72-0.88) for trial A, 0.96 (CI: 0.95-0.97) for trial B and 0.99 (CI: 0.98-0.99) for trial C. The full potential of this algorithm was reached after learning from approximately 200 manually screened patients (eligible and ineligible). Neither block- nor category-level aggregation of diagnosis and procedure codes influenced the algorithms’ performance substantially.ConclusionsOur results indicate that predictive modeling is a feasible approach to support patient recruitment into clinical trials. Its major advantages over the commonly applied rule-based systems are its independency from the concrete representation of eligibility criteria and EHR data and its potential for automation.

Secure Secondary Use of Clinical Data with Cloud-based NLP Services. Towards a Highly Scalable Research Infrastructure.

OBJECTIVES The secondary use of clinical data provides large opportunities for clinical and translational research as well as quality assurance projects. For such purposes, it is necessary to provide a flexible and scalable infrastructure that is compliant with privacy requirements. The major goals of the cloud4health project are to define such an architecture, to implement a technical prototype that fulfills these requirements and to evaluate it with three use cases. METHODS The architecture provides components for multiple data provider sites such as hospitals to extract free text as well as structured data from local sources and de-identify such data for further anonymous or pseudonymous processing. Free text documentation is analyzed and transformed into structured information by text-mining services, which are provided within a cloud-computing environment. Thus, newly gained annotations can be integrated along with the already available structured data items and the resulting data sets can be uploaded to a central study portal for further analysis. RESULTS Based on the architecture design, a prototype has been implemented and is under evaluation in three clinical use cases. Data from several hundred patients provided by a University Hospital and a private hospital chain have already been processed. CONCLUSIONS Cloud4health has shown how existing components for secondary use of structured data can be complemented with text-mining in a privacy compliant manner. The cloud-computing paradigm allows a flexible and dynamically adaptable service provision that facilitates the adoption of services by data providers without own investments in respective hardware resources and software tools.

Integrating Arden-Syntax-based clinical decision support with extended presentation formats into a commercial patient data management system

The purpose of this study was to introduce clinical decision support (CDS) that exceeds conventional alerting at tertiary care intensive care units. We investigated physicians’ functional CDS requirements in periodic interviews, and analyzed technical interfaces of the existing commercial patient data management system (PDMS). Building on these assessments, we adapted a platform that processes Arden Syntax medical logic modules (MLMs). Clinicians demanded data-driven, user-driven and time-driven execution of MLMs, as well as multiple presentation formats such as tables and graphics. The used PDMS represented a black box insofar as it did not provide standardized interfaces for event notification and external access to patient data; enabling CDS thus required periodically exporting datasets for making them accessible to the invoked Arden engine. A client–server-architecture with a simple browser-based viewer allows users to activate MLM execution and to access CDS results, while an MLM library generates hypertext for diverse presentation targets. The workaround that involves a periodic data replication entails a trade-off between the necessary computational resources and a delay of generated alert messages. Web technologies proved serviceable for reconciling Arden-based CDS functions with alternative presentation formats, including tables, text formatting, graphical outputs, as well as list-based overviews of data from several patients that the native PDMS did not support.

Using Arden Syntax for the creation of a multi-patient surveillance dashboard

OBJECTIVE Most practically deployed Arden-Syntax-based clinical decision support (CDS) modules process data from individual patients. The specification of Arden Syntax, however, would in principle also support multi-patient CDS. The patient data management system (PDMS) at our local intensive care units does not natively support patient overviews from customizable CDS routines, but local physicians indicated a demand for multi-patient tabular overviews of important clinical parameters such as key laboratory measurements. As our PDMS installation provides Arden Syntax support, we set out to explore the capability of Arden Syntax for multi-patient CDS by implementing a prototypical dashboard for visualizing laboratory findings from patient sets. METHODS AND MATERIAL Our implementation leveraged the object data type, supported by later versions of Arden, which turned out to be serviceable for representing complex input data from several patients. For our prototype, we designed a modularized architecture that separates the definition of technical operations, in particular the control of the patient context, from the actual clinical knowledge. Individual Medical Logic Modules (MLMs) for processing single patient attributes could then be developed according to well-tried Arden Syntax conventions. RESULTS We successfully implemented a working dashboard prototype entirely in Arden Syntax. The architecture consists of a controller MLM to handle the patient context, a presenter MLM to generate a dashboard view, and a set of traditional MLMs containing the clinical decision logic. Our prototype could be integrated into the graphical user interface of the local PDMS. We observed that with realistic input data the average execution time of about 200ms for generating dashboard views attained applicable performance. CONCLUSION Our study demonstrated the general feasibility of creating multi-patient CDS routines in Arden Syntax. We believe that our prototypical dashboard also suggests that such implementations can be relatively easy, and may simultaneously hold promise for sharing dashboards between institutions and reusing elementary components for additional dashboards.

Concept and implementation of a study dashboard module for a continuous monitoring of trial recruitment and documentation

BACKGROUND The difficulty of managing patient recruitment and documentation for clinical trials prompts a demand for instruments for closely monitoring these critical but unpredictable processes. Increasingly adopted Electronic Data Capture (EDC) applications provide novel opportunities to reutilize stored information for an efficient management of traceable trial workflows. In related clinical and administrative settings, so-called digital dashboards that continuously visualize time-dependent parameters have recently met a growing acceptance. To investigate the technical feasibility of a study dashboard for monitoring the progress of patient recruitment and trial documentation, we set out to develop a propositional prototype in the form of a separate software module. METHODS After narrowing down functional requirements in semi-structured interviews with study coordinators, we analyzed available interfaces of a locally deployed EDC application, and designed the prototypical study dashboard based on previous findings. The module thereby leveraged a standardized export format in order to extract and import relevant trial data into a clinical data warehouse. Web-based reporting tools then facilitated the definition of diverse views, including diagrams of the progress of patient accrual and form completion at different granularity levels. To estimate the utility of the dashboard and its compatibility with current workflows, we interviewed study coordinators after a demonstration of sample outputs from ongoing trials. RESULTS The employed tools promoted a rapid development. Displays of the implemented dashboard are organized around an entry page that integrates key metrics for available studies, and which links to more detailed information such as study-specific enrollment per center. The interviewed experts commented that the included graphical summaries appeared suitable for detecting that something was generally amiss, although practical remedies would mostly depend on additional information such as access to the original patient-specific data. The dependency on a separate application was seen as a downside. Interestingly, the prospective users warned that in some situations knowledge of specific accrual statistics might undermine blinding in a subtle yet intricate fashion, so ignorance of certain patient features was seen as sometimes preferable for reproducibility. DISCUSSION Our proposed study dashboard graphically recaps key progress indicators of patient accrual and trial documentation. The modular implementation illustrates the technical feasibility of the approach. The use of a study dashboard might introduce certain technical requirements as well as subtle interpretative complexities, which may have to be weighed against potential efficiency gains.

Employing heat maps to mine associations in structured routine care data

OBJECTIVE Mining the electronic medical record (EMR) has the potential to deliver new medical knowledge about causal effects, which are hidden in statistical associations between different patient attributes. It is our goal to detect such causal mechanisms within current research projects which include e.g. the detection of determinants of imminent ICU readmission. An iterative statistical approach to examine each set of considered attribute pairs delivers potential answers but is difficult to interpret. Therefore, we aimed to improve the interpretation of the resulting matrices by the use of heat maps. We propose strategies to adapt heat maps for the search for associations and causal effects within routine EMR data. METHODS Heat maps visualize tabulated metric datasets as grid-like choropleth maps, and thus present measures of association between numerous attribute pairs clearly arranged. Basic assumptions about plausible exposures and outcomes are used to allocate distinct attribute sets to both matrix dimensions. The image then avoids certain redundant graphical elements and provides a clearer picture of the supposed associations. Specific color schemes have been chosen to incorporate preexisting information about similarities between attributes. The use of measures of association as a clustering input has been taken as a trigger to apply transformations which ensure that distance metrics always assume finite values and treat positive and negative associations in the same way. To evaluate the general capability of the approach, we conducted analyses of simulated datasets and assessed diagnostic and procedural codes in a large routine care dataset. RESULTS Simulation results demonstrate that the proposed clustering procedure rearranges attributes similar to simulated statistical associations. Thus, heat maps are an excellent tool to indicate whether associations concern the same attributes or different ones, and whether affected attribute sets conform to any preexisting relationship between attributes. The dendrograms help in deciding if contiguous sequences of attributes effectively correspond to homogeneous attribute associations. The exemplary analysis of a routine care dataset revealed patterns of associations that follow plausible medical constellations for several diseases and the associated medical procedures and activities. Cases with breast cancer (ICD C50), for example, appeared to be associated with radiation therapy (8-52). In cross check, approximately 60 percent of the attribute pairs in this dataset showed a strong negative association, which can be explained by diseases treated in a medical specialty which routinely does not perform the respective procedures in these cases. The corresponding diagram clearly reflects these relationships in the shape of coherent subareas. CONCLUSION We could demonstrate that heat maps of measures of association are effective for the visualization of patterns in routine care EMRs. The adjustable method for the assignment of attributes to image dimensions permits a balance between the display of ample information and a favorable level of graphical complexity. The scope of the search can be adapted by the use of pre-existing assumptions about plausible effects to select exposure and outcome attributes. Thus, the proposed method promises to simplify the detection of undiscovered causal effects within routine EMR data.

Using Arden Syntax Medical Logic Modules to reduce overutilization of laboratory tests for detection of bacterial infections—Success or failure?

OBJECTIVE Bacterial infections frequently cause prolonged intensive care unit (ICU) stays. Repeated measurements of the procalcitonin (PCT) biomarker are typically used for early detection and follow up of bacterial infections and sepsis, but those PCT measurements are costly. To avoid overutilization, we developed and evaluated a clinical decision support system (CDSS) in Arden Syntax which computes necessary and preventable PCT orders. METHODS The CDSS implements a rule set based on the latest PCT value, the time period since this measurement, and the PCT trend scenario. We assessed the CDSS effects on the daily rate of ordered PCT tests within a prospective study having two ON and two OFF phases in a surgical ICU. In addition, we performed interviews with the participating physicians to investigate their experience with the CDSS advice. RESULTS Prior to the deployment of the CDSS, 22% of the performed PCT tests were potentially preventable according to the rule set. During the first ON phase the daily rate of ordered PCT tests per patient decreased significantly from 0.807 to 0.662. In subsequent OFF, ON and OFF phases, however, PCT utilization reached again daily rates of 0.733, 0.803, and 0.792, respectively. The interviews demonstrated that the physicians were aware of the problem of PCT overutilization, which they primarily attributed to acute time constraints. The responders assumed that the majority of preventable measurements are indiscriminately ordered for patients during longer ICU stays. CONCLUSION We observed an 18% reduction of PCT tests within the first four weeks of CDSS support in the investigated ICU. This reduction may have been influenced by raised awareness of the overutilization problem; the extent of this influence cannot be determined in our study design. No reduction of PCT tests could be observed during the second ON phase. The physician interviews indicated that time critical ICU situations can prevent extensive reflection about the necessity of individual tests. In order to achieve an enduring effect on PCT utilization, we will have to proceed to electronic order entry.

Effects of staff training and electronic event monitoring on long-term adherence to lung-protective ventilation recommendations

Purpose: To investigate long‐term effects of staff training and electronic clinical decision support (CDS) on adherence to lung‐protective ventilation recommendations. Materials and methods: In 2012, group instructions and workshops at two surgical intensive care units (ICUs) started, focusing on standardized protocols for mechanical ventilation and volutrauma prevention. Subsequently implemented CDS functions continuously monitor ventilation parameters, and from 2015 triggered graphical notifications when tidal volume (VT) violated individual thresholds. To estimate the effects of these educational and technical interventions, we retrospectively analyzed nine years of VT records from routine care. As outcome measures, we calculated relative frequencies of settings that conform to recommendations, case‐specific mean excess VT, and total ICU survival. Results: Assessing 571,478 VT records from 10,241 ICU cases indicated that adherence during pressure‐controlled ventilation improved significantly after both interventions; the share of conforming VT records increased from 61.6% to 83.0% and then 86.0%. Despite increasing case severity, ICU survival remained nearly constant over time. Conclusions: Staff training effectively improves adherence to lung‐protective ventilation strategies. The observed CDS effect seemed less pronounced, although it can easily be adapted to new recommendations. Both interventions, which futures studies could deploy in combination, promise to improve the precision of mechanical ventilation. Highlights:Recommended lung‐protective ventilation regimens depend on personalized settingsStaff training and electronic notifications can facilitate recommendation adherenceWe studied their effects on tidal volumes at two surgical intensive care unitsAfter both interventions, tidal volumes moderately converged towards targetsStaff training and electronic notifications can improve the precision of ventilation