Creating a Medication Therapy Observational Research Database from an Electronic Medical Record: Challenges and Data Curation.

BACKGROUND: Observational research has shown its potential to complement experimental research and clinical trials by secondary use of treatment data from hospital care processes. It can also be applied to better understand pediatric drug utilization for establishing safer drug therapy. Clinical documentation processes often limit data quality in pediatric medical records requiring data curation steps, which are mostly underestimated. OBJECTIVES: The objectives of this study were to transform and curate data from a departmental electronic medical record into an observational research database. We particularly aim at identifying data quality problems, illustrating reasons for such problems and describing the systematic data curation process established to create high-quality data for observational research. METHODS: Data were extracted from an electronic medical record used by four wards of a German university children's hospital from April 2012 to June 2020. A four-step data preparation, mapping, and curation process was established. Data quality of the generated dataset was firstly assessed following an established 3 × 3 Data Quality Assessment guideline and secondly by comparing a sample subset of the database with an existing gold standard. RESULTS: The generated dataset consists of 770,158 medication dispensations associated with 89,955 different drug exposures from 21,285 clinical encounters. A total of 6,840 different narrative drug therapy descriptions were mapped to 1,139 standard terms for drug exposures. Regarding the quality criterion correctness, the database was consistent and had overall a high agreement with our gold standard. CONCLUSION: Despite large amounts of freetext descriptions and contextual knowledge implicitly included in the electronic medical record, we were able to identify relevant data quality issues and to establish a semi-automated data curation process leading to a high-quality observational research database. Because of inconsistent dosage information in the original documentation this database is limited to a drug utilization database without detailed dosage information.

Machine learning in medication prescription: A systematic review.

BACKGROUND: Medication prescription is a complex process that could benefit from current research and development in machine learning through decision support systems. Particularly pediatricians are forced to prescribe medications "off-label" as children are still underrepresented in clinical studies, which leads to a high risk of an incorrect dose and adverse drug effects. METHODS: PubMed, IEEE Xplore and PROSPERO were searched for relevant studies that developed and evaluated well-performing machine learning algorithms following the PRISMA statement. Quality assessment was conducted in accordance with the IJMEDI checklist. Identified studies were reviewed in detail, including the required variables for predicting the correct dose, especially of pediatric medication prescription. RESULTS: The search identified 656 studies, of which 64 were reviewed in detail and 36 met the inclusion criteria. According to the IJMEDI checklist, five studies were considered to be of high quality. 19 of the 36 studies dealt with the active substance warfarin. Overall, machine learning algorithms based on decision trees or regression methods performed superior regarding their predictive power than algorithms based on neural networks, support vector machines or other methods. The use of ensemble methods like bagging or boosting generally enhanced the accuracy of the dose predictions. The required input and output variables of the algorithms were considerably heterogeneous and differ strongly among the respective substance. CONCLUSIONS: By using machine learning algorithms, the prescription process could be simplified and dosing correctness could be enhanced. Despite the heterogenous results among the different substances and cases and the lack of pediatric use cases, the identified approaches and required variables can serve as an excellent starting point for further development of algorithms predicting drug doses, particularly for children. Especially the combination of physiologically-based pharmacokinetic models with machine learning algorithms represents a great opportunity to enhance the predictive power and accuracy of the developed algorithms.

Demand Analysis of a German Emergency Medical Service Feedback System.

BACKGROUND: The number of emergency medical service (EMS) calls in Germany is continuously increasing. The initial assessment, the pre-hospital care and the choice of hospital for further care by the EMS influences the patient's outcome and are the basis for further care in hospital. However, the EMS does not receive any official feedback on its decisions. OBJECTIVES: This study evaluates the demand for a feedback system from the emergency department (ED) to the EMS, what it should contain, and how it could be integrated in the electronic clinical systems. METHODS: A semi-structured interview guideline for expert interviews with members of EMS staff (n = 6) and ED staff (n = 17) was developed. A mockup to visualise a possible implementation was designed and included in the interview. RESULTS: There is a significant demand for feedback on pre-diagnosis, pre-hospital care and handover of patients from the EMS to the ED. The EDs are very interested in improving the collaboration with the paramedic services through feedback. CONCLUSION: A feedback system is strongly desired by various EMS stakeholders and, according to them, could improve both EMS and ED collaboration and overall patient care.

Usability Analysis of a Medication Visualization Tool for Decision Support.

BACKGROUND: In Germany, patients are entitled to a medication plan. While the overview is useful, it does not contain explicit information on various potential adverse drug events (ADEs). Therefore, physicians must continue to seek information from various sources to ensure medication safety. OBJECTIVE: In this project a first functional prototype of a medication therapy tool was developed that focuses on visualizing and highlighting potential ADEs. A usability analysis about the tool's functionality, design and usability was conducted. METHODS: A web application tool was developed using the MMI Pharmindex as database. ADEs are color coded and can be displayed in three different ways - as a list, a table, or a graph. To test the tool, an online survey was conducted amongst healthcare professionals (n = 9). The test included two real medication plans to check ADEs through the tool. RESULTS: The survey results indicated that the web tool was clear and self-explanatory. It scored overall "good" (score: 76.5) on the System Usability Scale questionnaire. Due to the free-text information of the database used, there were some inconsistencies in the visualized ADEs. CONCLUSION: There is a demand for a visualization tool for medications. The high quality of the database is crucial in order to correctly visualize all necessary information, such as drug-drug interactions and inclusion of patient data. This is essential to provide a trustworthy tool for medical professionals.

Attitudes and Acceptance Towards Artificial Intelligence in Medical Care.

BACKGROUND: Artificial intelligence (AI) in medicine is a very topical issue. As far as the attitudes and perspectives of the different stakeholders in healthcare are concerned, there is still much to be explored. OBJECTIVE: Our aim was to determine attitudes and aspects towards acceptance of AI applications from the perspective of physicians in university hospitals. METHODS: We conducted individual exploratory expert interviews. Low fidelity mockups were used to show interviewees potential application areas of AI in clinical care. RESULTS: In principle, physicians are open to the use of AI in medical care. However, they are critical of some aspects such as data protection or the lack of explainability of the systems. CONCLUSION: Although some trends in attitudes e.g., on the challenges or benefits of using AI became clear, it is necessary to conduct further research as intended by the subsequent PEAK project.

Metamizole Use in Children: Analysis of Drug Utilisation and Adverse Drug Reactions at a German University Hospital between 2015 and 2020.

BACKGROUND: Metamizole use is controversially discussed due to its potentially serious adverse drug reactions (ADRs). In Germany, however, it remains a popular analgesic and antipyretic drug. OBJECTIVE: The aim of this study was to discuss the safety profile of metamizole in children by analysing the inpatient prescription patterns and presenting the metamizole-related ADRs at a paediatric hospital between 2015 and 2020. METHODS: Metamizole utilisation data were retrospectively analysed from electronic medical records. ADRs were prospectively recorded via the hospital's stimulated reporting system and analysed accordingly. Patients aged < 18 years admitted to one of the general wards of the department of paediatrics and adolescent medicine of a German university hospital between June 2015 and May 2020 who received at least one drug therapy within their inpatient stay were included in the analysis. Causality of ADRs was rated according to the World Health Organisation causality assessment. RESULTS: In 31.7% (3759/11,857) of the inpatient stays of 7809 patients, metamizole was administered. Metamizole exposure was highest in adolescents (37.9%) and lowest in newborns (9.9%). Overall, metamizole was administered parenterally in about 90%. Three cases of agranulocytosis, one allergic shock and one rash with possible or higher causality to metamizole treatment were reported. Three of these occurred prior to hospitalisation. All patients recovered without remaining harm. DISCUSSION: Metamizole is commonly used in paediatric inpatients in Germany. Serious ADRs occur but rarely. Continuous monitoring of drug therapy through, for example, stimulated reporting systems ensures that serious ADRs are detected, and appropriate interventions can be introduced.

Development and Evaluation of a Web-Based Paediatric Drug Information System for Germany.

Background: Off-label use is frequent in paediatrics but that does not necessarily mean that the risk-benefit ratio is negative. Nevertheless, evidence-based data is essential for safe drug therapy. In Germany, there is no publicly available compendium providing transparent, evidence-based information for paediatric pharmacotherapy to date. This work describes the development of a web-based paediatric drug information system (PDIS) for Germany and its evaluation by health care professionals (HCP). Methods: Since 2012, a PDIS is being developed by the authors and is supported by the Federal Ministry of Health since 2016. Dosing recommendations were established based on systematic literature reviews and subsequent evaluation by clinical experts. The prototype was evaluated by HCP. Based on the results, the further development was concluded. Results: 92% of HCP believed that the PDIS could improve the quality of prescribing, as currently available information is deficient. Besides the license and formulations, dosing recommendations were the most relevant modules. A dosage calculator was the most wanted improvement. To facilitate sustainability of future development, a collaboration with the Dutch Kinderformularium was established. As of 2021, the database will be available to German HCP. Conclusion: The fundamentals for a German PDIS were established, and vital steps were taken towards successful continuation.

Evaluation of Different Learning Algorithms of Neural Networks for Drug Dosing Recommendations in Pediatrics.

Publicly accessible databases with evidence-based information on drug dosages for children and adolescents are not available in Germany. In previous work a prototypical web-based online platform for pediatric dosing recommendation has been developed. Quality assured maintenance of such a database is a time consuming effort. Recent work has shown that it is possible to use routinely documented data for machine learning approaches in order to create models for future decision support tools. This work describes the development of a prototype for pediatric dosing recommendations on the basis of routine drug prescriptions. Since they are structured for daily clinical use, not for machine learning, they include a substantial proportion of narrative text that requires preprocessing with consideration of medical and pharmaceutical knowledge. Three different learning algorithms have been applied and compared. The genetic algorithm with backpropagation has achieved the highest accuracy in the predictions. Our study constitutes a first step towards pediatric dosing recommendations, but there are multiple additional steps to be taken before a routine use might be considered, such as an evaluation by experienced physicians.

Mapping the Entire Record-An Alternative Approach to Data Access from Medical Logic Modules.

OBJECTIVES: This study aimed to describe an alternative approach for accessing electronic medical records (EMRs) from clinical decision support (CDS) functions based on Arden Syntax Medical Logic Modules, which can be paraphrased as "map the entire record." METHODS: Based on an experimental Arden Syntax processor, we implemented a method to transform patient data from a commercial patient data management system (PDMS) to tree-structured documents termed CDS EMRs. They are encoded in a specific XML format that can be directly transformed to Arden Syntax data types by a mapper natively integrated into the processor. The internal structure of a CDS EMR reflects the tabbed view of an EMR in the graphical user interface of the PDMS. RESULTS: The study resulted in an architecture that provides CDS EMRs in the form of a network service. The approach enables uniform data access from all Medical Logic Modules and requires no mapping parameters except a case number. Measurements within a CDS EMR can be addressed with straightforward path expressions. The approach is in routine use at a German university hospital for more than 2 years. CONCLUSION: This practical approach facilitates the use of CDS functions in the clinical routine at our local hospital. It is transferrable to standard-compliant Arden Syntax processors with moderate effort. Its comprehensibility can also facilitate teaching and development. Moreover, it may lower the entry barrier for the application of the Arden Syntax standard and could therefore promote its dissemination.

Pan-European Data Harmonization for Biobanks in ADOPT BBMRI-ERIC.

BACKGROUND: High-quality clinical data and biological specimens are key for medical research and personalized medicine. The Biobanking and Biomolecular Resources Research Infrastructure-European Research Infrastructure Consortium (BBMRI-ERIC) aims to facilitate access to such biological resources. The accompanying ADOPT BBMRI-ERIC project kick-started BBMRI-ERIC by collecting colorectal cancer data from European biobanks. OBJECTIVES: To transform these data into a common representation, a uniform approach for data integration and harmonization had to be developed. This article describes the design and the implementation of a toolset for this task. METHODS: Based on the semantics of a metadata repository, we developed a lexical bag-of-words matcher, capable of semiautomatically mapping local biobank terms to the central ADOPT BBMRI-ERIC terminology. Its algorithm supports fuzzy matching, utilization of synonyms, and sentiment tagging. To process the anonymized instance data based on these mappings, we also developed a data transformation application. RESULTS: The implementation was used to process the data from 10 European biobanks. The lexical matcher automatically and correctly mapped 78.48% of the 1,492 local biobank terms, and human experts were able to complete the remaining mappings. We used the expert-curated mappings to successfully process 147,608 data records from 3,415 patients. CONCLUSION: A generic harmonization approach was created and successfully used for cross-institutional data harmonization across 10 European biobanks. The software tools were made available as open source.

User-Centered Development of an Online Platform for Drug Dosing Recommendations in Pediatrics.

BACKGROUND: Drug therapy in pediatric patients is a complex process. Children are subject to continuous growth and variation in drug-metabolizing enzyme activity, requiring continuous adaption of dosages. In Germany, currently no publicly available database exists that provides evidence-based information on drug dosages in pediatrics. For local drug dosing support, a prototype database has been developed within the Children's Hospital, Erlangen. A user-centered development process was initiated to establish an online platform for evidence-based dosing recommendations, as well as pharmacological and pharmaceutical drug information in pediatrics. OBJECTIVES: The objectives of the study were to survey the demand for such a platform and to assess the usability of the different versions of the developed system. METHODS: The developed prototype was evaluated in a pluralistic walkthrough with prospective end users. After a redesign, the second prototype of the online platform underwent an online usability testing based on a tailored questionnaire and the System Usability Scale (SUS) (n = 12). RESULTS: Eleven of 12 participants expressed a demand for an online platform for pediatric dosing recommendations. The majority of the participants requested the integration of extended features, such as drug-drug interaction alerts, or information on adverse effects, pharmacokinetics, and pharmacodynamics. Particularly noteworthy is the demand for an online calculator; 5 of a total of 15 participants explicitly requested a calculator for dosages (based on age, weight, body surface) and glomerular filtration rate. The usability of the second prototype was rated "good to excellent" with a median SUS of 81.25. CONCLUSION: Local domain experts demand an online platform for pediatric dosing recommendations. The application of the user-centered design approach enabled the development of a prototype suitable for practical use. Multiple additional required functionalities have been identified, whereby the importance of an online calculator for patient-individual dosing recommendations was particularly emphasized.