Uncovering healthcare practitioners' information processing using the think-aloud method: From paper-based guideline to clinical decision support system

Artificial Intelligence and Machine Learning for Inborn Errors of Immunity: Current State and Future Promise

Artificial intelligence (AI) and machine learning (ML) research within medicine has exponentially increased over the last decade, with studies showcasing the potential of AI/ML algorithms to improve clinical practice and outcomes. Ongoing research and efforts to develop AI-based models have expanded to aid in the identification of inborn errors of immunity (IEI). The use of larger electronic health record data sets, coupled with advances in phenotyping precision and enhancements in ML techniques, has the potential to significantly improve the early recognition of IEI, thereby increasing access to equitable care. In this review, we provide a comprehensive examination of AI/ML for IEI, covering the spectrum from data preprocessing for AI/ML analysis to current applications within immunology, and address the challenges associated with implementing clinical decision support systems to refine the diagnosis and management of IEI.

Factors clinicians consider when providing pediatric wheelchair skills training: a modified think aloud study

PURPOSE

Children who use a manual wheelchair (WC) or a power WC may not receive adequate WC skills training. Clinicians report knowledge as a barrier to the provision of paediatric WC skills training. The purpose of this study was to explore the breadth and depth of specific factors clinicians consider when providing WC skills training for children.

METHODS

Data in this modified Think Aloud study were gathered via one-on-one, Zoom-based, audio-recorded Think Aloud Sessions. Sessions consisted of participants viewing four videos, each of different children performing a different WC skill while thinking aloud (verbally expressing) about the factors they recognized, observed, and considered while watching the video. After each video, participants also responded to questions regarding the specific WC skill and the provision of WC skills training for the child in the video. Factors participants reported were independently identified by three researchers through a deductive process of directed content analysis and categorized using the International Classification of Functioning, Disability and Health (ICF) coding system.

RESULTS

Twenty-eight English-speaking clinicians participated in the study. A total of 1246 distinct factors were mapped to 352 unique ICF codes spanning all four ICF Domains. The largest number of identified factors mapped to codes within the Activities and participation Domain (42.25%).

CONCLUSION

Participants reported considering multiple factors across the ICF in the provision of WC skills training for children. Providing paediatric WC skills training is a complex activity requiring clinicians to consider a wide range of factors that go beyond a child's motor abilities.

Examining explainable clinical decision support systems with think aloud protocols

Machine learning tools are increasingly used to improve the quality of care and the soundness of a treatment plan. Explainable AI (XAI) helps users in understanding the inner mechanisms of opaque machine learning models and is a driver of trust and adoption. Explanation methods for black-box models exist, but there is a lack of user studies on the interpretability of the provided explanations. We used a Think Aloud Protocol (TAP) to explore oncologists' assessment of a lung cancer relapse prediction system with the aim of refining the purpose-built explanation model for better credibility and utility. Novel to this context, TAP is used as a neutral methodology to elicit experts' thought processes and judgements of the AI system, without explicit prompts. TAP aims to elicit the factors which influenced clinicians' perception of credibility and usefulness of the system. Ten oncologists took part in the study. We conducted a thematic analysis of their verbalized responses, generating five themes that help us to understand the context within which oncologists' may (or may not) integrate an explainable AI system into their working day.

Using the think aloud protocol in health professions education: an interview method for exploring thought processes: AMEE Guide No. 151

The think aloud protocol (TAP) has two components, the think aloud interview, a technique for verbal data collection, and protocol analysis, a technique for predicting and analyzing verbal data. TAP is a useful method for those attempting to observe, explore, and understand individuals' thoughts, which remain among the most difficult research areas in health professions education. Notably, the long, complex history and heterogeneous implementation of variations of TAP can make it difficult to understand and implement rigorously. In this Guide, we define the TAP and related concepts, describe the origins, outline applications, offer a detailed roadmap for rigorous implementation as a technique for data collection and/or data analysis, and suggest opportunities for adaptation of the traditional TAP. We aim to arm researchers with the tools to implement a rigorous think aloud interview, while explaining its origins to empower them to adapt the traditional TAP intentionally and justifiably to modern health professions education research.

"What brought you in today?": Modeling patient-provider clinic visits to characterize rural providers' antibiotic treatment decisions

BACKGROUND

Designing clinical decision support (CDS) tools is challenging because clinical decision-making must account for an invisible task load: incorporating non-linear objective and subjective factors to make an assessment and treatment plan. This calls for a cognitive task analysis approach.

OBJECTIVES

The objectives of this study were to 1.) understand healthcare providers' decision making during a typical clinic visit, and 2.) explore how antibiotic treatment decisions are made when they arise.

METHODS

Two cognitive task analysis methods were applied - Hierarchical Task Analysis (HTA) and Operations Sequence Diagramming (OSD) - to 39 h of observational data collected at family medicine, urgent care, and emergency medicine clinical sites.

RESULTS

The resulting HTA models included a coding taxonomy detailing ten cognitive goals and associated sub-goals and demonstrated how the goals occur as interactions between the provider and electronic health record, the patient, and the physical clinic environment. Although the HTA detailed resources for antibiotic treatment decisions, antibiotics were a minority of drug classes ordered. The OSD shows the sequence of events and when decisions are made solely at the provider level and when shared decision making occurs with the patient. Qualitative data from the observations informed a constructed vignette case example portraying select tasks from the HTA.

CONCLUSIONS

These findings emphasize that the scope of disease states presenting to a generalist clinical setting is broad and could include acute exacerbations of rare diseases within a time-pressured environment. CDS must be accessible, time efficient, and fit within the resource gathering task before treatment decisions are made.

Human-Centered Design of a Clinical Decision Support for Anemia Screening in Children with Inflammatory Bowel Disease

BACKGROUND

Inflammatory bowel disease (IBD) commonly leads to iron deficiency anemia (IDA). Rates of screening and treatment of IDA are often low. A clinical decision support system (CDSS) embedded in an electronic health record could improve adherence to evidence-based care. Rates of CDSS adoption are often low due to poor usability and fit with work processes. One solution is to use human-centered design (HCD), which designs CDSS based on identified user needs and context of use and evaluates prototypes for usefulness and usability.

OBJECTIVES

this study aimed to use HCD to design a CDSS tool called the IBD Anemia Diagnosis Tool, IADx.

METHODS

Interviews with IBD practitioners informed creation of a process map of anemia care that was used by an interdisciplinary team that used HCD principles to create a prototype CDSS. The prototype was iteratively tested with "Think Aloud" usability evaluation with clinicians as well as semi-structured interviews, a survey, and observations. Feedback was coded and informed redesign.

RESULTS

Process mapping showed that IADx should function at in-person encounters and asynchronous laboratory review. Clinicians desired full automation of clinical information acquisition such as laboratory trends and analysis such as calculation of iron deficit, less automation of clinical decision selection such as laboratory ordering, and no automation of action implementation such as signing medication orders. Providers preferred an interruptive alert over a noninterruptive reminder.

CONCLUSION

Providers preferred an interruptive alert, perhaps due to the low likelihood of noticing a noninterruptive advisory. High levels of desire for automation of information acquisition and analysis with less automation of decision selection and action may be generalizable to other CDSSs designed for chronic disease management. This underlines the ways in which CDSSs have the potential to augment rather than replace provider cognitive work.

Usability of the IDDEAS prototype in child and adolescent mental health services: A qualitative study for clinical decision support system development

Introduction

Child and adolescent mental health services (CAMHS) clinical decision support system (CDSS) provides clinicians with real-time support as they assess and treat patients. CDSS can integrate diverse clinical data for identifying child and adolescent mental health needs earlier and more comprehensively. Individualized Digital Decision Assist System (IDDEAS) has the potential to improve quality of care with enhanced efficiency and effectiveness.

Methods

We examined IDDEAS usability and functionality in a prototype for attention deficit hyperactivity disorder (ADHD), using a user-centered design process and qualitative methods with child and adolescent psychiatrists and clinical psychologists. Participants were recruited from Norwegian CAMHS and were randomly assigned patient case vignettes for clinical evaluation, with and without IDDEAS. Semi-structured interviews were conducted as one part of testing the usability of the prototype following a five-question interview guide. All interviews were recorded, transcribed, and analyzed following qualitative content analysis.

Results

Participants were the first 20 individuals from the larger IDDEAS prototype usability study. Seven participants explicitly stated a need for integration with the patient electronic health record system. Three participants commended the step-by-step guidance as potentially helpful for novice clinicians. One participant did not like the aesthetics of the IDDEAS at this stage. All participants were pleased about the display of the patient information along with guidelines and suggested that wider guideline coverage will make IDDEAS much more useful. Overall, participants emphasized the importance of maintaining the clinician as the decision-maker in the clinical process, and the overall potential utility of IDDEAS within Norwegian CAMHS.

Conclusion

Child and adolescent mental health services psychiatrists and psychologists expressed strong support for the IDDEAS clinical decision support system if better integrated in daily workflow. Further usability assessments and identification of additional IDDEAS requirements are necessary. A fully functioning, integrated version of IDDEAS has the potential to be an important support for clinicians in the early identification of risks for youth mental disorders and contribute to improved assessment and treatment of children and adolescents.

Improved guideline adherence in oncology through clinical decision-support systems: still hindered by current health IT infrastructures?

PURPOSE OF REVIEW

Despite several efforts to enhance guideline adherence in cancer management, the rate of adherence remains often dissatisfactory in clinical routine. Clinical decision-support systems (CDSS) have been developed to support the management of cancer patients by providing evidence-based recommendations. In this review, we focus on both current evidence supporting the beneficial effects of CDSS on guideline adherence as well as technical and structural requirements for CDSS implementation in clinical routine.

RECENT FINDINGS

Some studies have demonstrated a significant improvement of guideline adherence by CDSSs in oncologic diseases such as breast cancer, colon cancer, cervical cancer, prostate cancer, and hepatocellular carcinoma as well as in the management of cancer pain. However, most of these studies were rather small and designs rather simple. One reason for this limited evidence might be that CDSSs are only occasionally implemented in clinical routine. The main limitations for a broader implementation might lie in the currently existing clinical data infrastructures that do not sufficiently allow CDSS interoperability as well as in some CDSS tools themselves, if handling is hampered by poor usability.

SUMMARY

In principle, CDSSs improve guideline adherence in clinical cancer management. However, there are some technical und structural obstacles to overcome to fully implement CDSSs in clinical routine.

Performance and usability testing of an automated tool for detection of peripheral artery disease using electronic health records

Peripheral artery disease (PAD) is a common cardiovascular disorder that is frequently underdiagnosed, which can lead to poorer outcomes due to lower rates of medical optimization. We aimed to develop an automated tool to identify undiagnosed PAD and evaluate physician acceptance of a dashboard representation of risk assessment. Data were derived from electronic health records (EHR). We developed and compared traditional risk score models to novel machine learning models. For usability testing, primary and specialty care physicians were recruited and interviewed until thematic saturation. Data from 3168 patients with PAD and 16,863 controls were utilized. Results showed a deep learning model that utilized time engineered features outperformed random forest and traditional logistic regression models (average AUCs 0.96, 0.91 and 0.81, respectively), P < 0.0001. Of interviewed physicians, 75% were receptive to an EHR-based automated PAD model. Feedback emphasized workflow optimization, including integrating risk assessments directly into the EHR, using dashboard designs that minimize clicks, and providing risk assessments for clinically complex patients. In conclusion, we demonstrate that EHR-based machine learning models can accurately detect risk of PAD and that physicians are receptive to automated risk detection for PAD. Future research aims to prospectively validate model performance and impact on patient outcomes.

A Clinical Decision Support System for Increasing Compliance with Protocols in Chemotherapy of Children with Acute Lymphoblastic Leukemia

Objective:

In this survey, a protocol-based Chemotherapy Prescription Decision Support System (CPDSS) was designed and evaluated to reduce medication errors in the chemotherapy process of children with ALL.

Methods:

The CPDSS algorithm was extracted by the software development team based on the protocol used by doctors to treat children with ALL. The ASP.Net MVC and SQL Server 2016 programming languages were used to develop the system. A 3-step evaluation (technical, retrospective, and user satisfaction) was performed on CPDSS designed at 2 children’s hospitals in Tehran. The data were analyzed using descriptive statistics. At the technical evaluation step, users provided recommendations included in the system.

Results:

In the retrospective CPDSS evaluation step, 1281 prescribed doses of the drugs related to 30 patients were entered into the system. CPDSS detected 735 cases of protocol deviations and 57 (95%, CI = 1.25-2.55) errors in prescribed chemotherapy for children with ALL. In the user satisfaction evaluation, the users approved two dimensions of the user interface and functionality of the system.

Conclusions:

With the provision of alerts, the CPDSS can help increase compliance with chemotherapy protocols and decrease the chemotherapy prescribing errors that can improve patient safety.

Enhancing System Acceptance through User-Centred Design: Integrating Patient Generated Wellness Data

Gestational diabetes mellitus (GDM) is a condition that appears during pregnancy and is expected to be a temporary one. While patients are encouraged to manage it themselves, research findings indicate that GDM may negatively affect the foetus; in addition, there is an increased risk of women with GDM subsequently developing Type 2 diabetes. To alleviate the risks, women with GDM are advised to maintain a record of their diet and blood glucose levels and to attend regular clinical reviews. Rather than using a paper diary, women with GDM can maintain a record of their blood glucose level readings and other relevant data using a wellness mobile application (app). However, such apps are developed for general use and may not meet the specific needs of clinical staff (physicians, dietitians, obstetricians and midwives) involved in managing GDM; for example, an app may record glucose readings but not the details of a meal taken before or after the glucose reading. Second, the apps do not permanently store the data generated by the patient and do not support the transfer of these data to a clinical system or information portal. The mobile health (mHealth) system designed and developed in this research allows one to integrate different types of user generated wellness data into a centralised database. A user-centered design (UCD) approach informed by the technology acceptance model (TAM) was adopted. This paper investigates and evaluates the effectiveness of the approach with regard to facilitating system acceptance and future adoption through an early focus on enhancing system usefulness and ease of use. The functional system requirements of the proposed system were refined through a series of interviews with the perspective of clinical users; ease-of-use and usability issues were resolved through 'think aloud' sessions with clinicians and GDM patients.

Contradictions and Interventions in Health IS

The study analyzes data collected in two case studies in the healthcare industry, which is characterized by a variety of social and technical elements forming an activity system where all elements interact with each other. The findings indicate that many problems emerging during the implementation of a health information system can be traced back to contradictions between elements of the activity systems that are created or amplified by the new IS. The authors find that some contradictions are latent and become salient when introducing a new IS, while other contradictions are (unintentionally) newly created. Also, the study shows that contradictions are more complex than hitherto assumed and often concern more than two elements of a healthcare activity system. In a similar vein, effective interventions geared toward countering these contradictions are found to account for additional complexity while not always achieving their goal. Drawing on activity theory, the authors develop a framework to coherently synthesize the findings. The study can help increase the understanding of the IS’s role within an activity system and help guide IS implementation projects aimed at avoiding unintended consequences.

Values of Importance to Patients With Cardiovascular Disease as a Foundation for eHealth Design and Evaluation: Mixed Methods Study

BACKGROUND

eHealth interventions are developed to support and facilitate patients with lifestyle changes and self-care tasks after being diagnosed with a cardiovascular disease (CVD). Creating long-lasting effects on lifestyle change and health outcomes with eHealth interventions is challenging and requires good understanding of patient values.

OBJECTIVE

The aim of the study was to identify values of importance to patients with CVD to aid in designing a technological lifestyle platform.

METHODS

A mixed method design was applied, combining data from usability testing with an additional online survey study, to validate the outcomes of the usability tests.

RESULTS

A total of 11 relevant patient values were identified, including the need for security, support, not wanting to feel anxious, tailoring of treatment, and personalized, accessible care. The validation survey shows that all values but one (value 9: To have extrinsic motivation to accomplish goals or activities [related to health/lifestyle]) were regarded as important/very important. A rating of very unimportant or unimportant was given by less than 2% of the respondents (value 1: 4/641, 0.6%; value 2: 10/641, 1.6%; value 3: 9/641, 1.4%; value 4: 5/641, 0.8%; value 5: 10/641, 1.6%; value 6: 4/641, 0.6%; value 7: 10/639, 1.6%; value 8: 4/639, 0.6%; value 10: 3/636, 0.5%; value 11: 4/636, 0.6%) to all values except but one (value 9: 56/636, 8.8%).

CONCLUSIONS

There is a high consensus among patients regarding the identified values reflecting goals and themes central to their lives, while living with or managing their CVD. The identified values can serve as a foundation for future research to translate and integrate these values into the design of the eHealth technology. This may call for prioritization of values, as not all values can be met equally.

Nurse Cognition, Decision Support, and Barcode Medication Administration: A Conceptual Framework for Research, Practice, and Education

This article synthesizes theoretical perspectives related to nurse cognition. We present a conceptual model that can be used by multiple stakeholders to study and contemplate how nurses use clinical decision support systems, and specifically, Barcode-Assisted Medication Administration, to make decisions during the delivery of care. Theoretical perspectives integrated into the model include dual process theory, the Cognitive Continuum Theory, human factors engineering, and the Recognition-Primed Decision model. The resulting framework illustrates the process of nurse cognition during Barcode-Assisted Medication Administration. Additionally, the model includes individual or human and environmental factors that may influence nurse cognition and decision making. It is important to consider the influence of individual, human, and environmental factors on the process of nurse cognition and decision making. Specifically, it is necessary to explore the impact of heuristics and biases on clinician decision making, particularly related to the development of alarm and alert fatigue. Aided by the proposed framework, stakeholders may begin to identify heuristics and cognitive biases that influence the decision of clinicians to accept or override a clinical decision support system alert and whether heuristics and biases are associated with inappropriate alert override.

Testing a mobile app for child abuse treatment: A mixed methods study

Objective

This study provides a preliminary evaluation of the usability and acceptability of a mobile application (sexual assault care algorithm, SACA).

Methods

An explanatory sequential mixed methods research was used. A quantitative survey was followed up by a qualitative study. A convenience sample of participants (n = 4) was recruited. The research was conducted on a one-on-one basis. In the quantitative phase, a random assignment technique was used to divide four participants into two groups of two participants each. Post-Study System Usability Questionnaire(PSSUQ) and Acceptability e-Scale were used to collect quantitative data. In the qualitative phase, interview, observation, and documentation were used to collect qualitative data. Data were analyzed both quantitative and qualitatively. The qualitative data were linked with the initial quantitative data to determine how the follow-up qualitative data helped explain the initial quantitative results.

Results

The quantitative results suggested that SACA has high usability (5.05 ± 1.83) and acceptability (3.81 ± 1.22). The qualitative results further indicate that the participants thought SACA was easy to use and useful, and most of them would recommend it to others. Areas of improvement include adding features that would calculate and validate the elapsed time since the sexual assault, adding explanations to some buttons, and providing training.

Conclusions

Our findings highlight the value of using a mixed methods research design to conduct a usability and acceptability test. Nurses are more likely to adopt a new technology for their evidence-based practice when the technology is easy to use and useful and requires less time to find the right piece of guideline evidence. Individualized training needs to be designed based on users’ characteristics.

Using a think-aloud methodology to understand online physical activity information search experiences and preferences of parents of children and youth with disabilities

BACKGROUND

The Internet is a preferred source of physical activity (PA) information. However, limited research exists regarding the experiences of parents of children and youth with disabilities (CYWD) in searching for PA programme information online. This research examined the experiences and preferences of parents of CYWD in searching for PA programme information online.

METHOD

Parents of CYWD (n = 10) participated in a think-aloud exercise while searching for PA programme information online. Following the think-aloud exercise, semi-structured interviews were used to further understand parents' experiences and preferences in searching for PA programme information online.

RESULTS

Parents identified key features that contributed to a positive online search experience. Additionally, parents noted challenges and resulting negative affect that was experienced.

CONCLUSIONS

This research can inform the development and dissemination of online PA programme information that is accessible and relevant to the preferences of parents of CYWD and can facilitate positive search experiences.

An overview of clinical decision support systems: benefits, risks, and strategies for success

Computerized clinical decision support systems, or CDSS, represent a paradigm shift in healthcare today. CDSS are used to augment clinicians in their complex decision-making processes. Since their first use in the 1980s, CDSS have seen a rapid evolution. They are now commonly administered through electronic medical records and other computerized clinical workflows, which has been facilitated by increasing global adoption of electronic medical records with advanced capabilities. Despite these advances, there remain unknowns regarding the effect CDSS have on the providers who use them, patient outcomes, and costs. There have been numerous published examples in the past decade(s) of CDSS success stories, but notable setbacks have also shown us that CDSS are not without risks. In this paper, we provide a state-of-the-art overview on the use of clinical decision support systems in medicine, including the different types, current use cases with proven efficacy, common pitfalls, and potential harms. We conclude with evidence-based recommendations for minimizing risk in CDSS design, implementation, evaluation, and maintenance.

Bridging the Gap Between Academic Research and Pragmatic Needs in Usability: A Hybrid Approach to Usability Evaluation of Health Care Information Systems

BACKGROUND

Technology is increasingly embedded into the full spectrum of health care. This movement has benefited from the application of software development practices such as usability testing and agile development processes. These practices are frequently applied in both commercial or operational and academic settings. However, the relative importance placed on rapid iteration, validity, reproducibility, generalizability, and efficiency differs between the 2 settings and the needs and objectives of academic versus pragmatic usability evaluations.

OBJECTIVE

This paper explores how usability evaluation typically varies on key dimensions in pragmatic versus academic settings that impact the rapidity, validity, and reproducibility of findings and proposes a hybrid approach aimed at satisfying both pragmatic and academic objectives.

METHODS

We outline the characteristics of pragmatic versus academically oriented usability testing in health care, describe the tensions and gaps resulting from differing contexts and goals, and present a model of this hybrid process along with 2 case studies of digital development projects in which we demonstrate this integrated approach to usability evaluation.

RESULTS

The case studies presented illustrate design choices characteristic of our hybrid approach to usability evaluation.

CONCLUSIONS

Designed to leverage the strengths of both pragmatically and academically focused usability studies, a hybrid approach allows new development projects to efficiently iterate and optimize from usability data as well as preserves the ability of these projects to produce deeper insights via thorough qualitative analysis to inform further tool development and usability research by way of academically focused dissemination.

Development of a Tailored Intervention With Computerized Clinical Decision Support to Improve Quality of Care for Patients With Knee Osteoarthritis: Multi-Method Study

BACKGROUND

Clinical practice patterns greatly diverge from evidence-based recommendations to manage knee osteoarthritis conservatively before resorting to surgery.

OBJECTIVE

This study aimed to tailor a guideline-based computerized decision support (CDS) intervention that facilitates the conservative management of knee osteoarthritis.

METHODS

Experts with backgrounds in clinical medicine, research, implementation, or health informatics suggested the most important recommendations for implementation, how to develop an implementation strategy, and how to form the CDS algorithms. In 6 focus group sessions, 8 general practitioners and 22 patients from Norway, Belgium, and Finland discussed the suggested CDS intervention and identified factors that would be most critical for the success of the intervention. The focus group moderators used the GUideline Implementation with DEcision Support checklist, which we developed to support consideration of CDS success factors.

RESULTS

The experts prioritized 9 out of 22 recommendations for implementation. We formed the concept for 6 CDS algorithms to support implementation of these recommendations. The focus group suggested 59 unique factors that could affect the success of the presented CDS intervention. Five factors (out of the 59) were prioritized by focus group participants in every country, including the perceived potential to address the information needs of both patients and general practitioners; the credibility of CDS information; the timing of CDS for patients; and the need for personal dialogue about CDS between the general practitioner and the patient.

CONCLUSIONS

The focus group participants supported the CDS intervention as a tool to improve the quality of care for patients with knee osteoarthritis through shared, evidence-based decision making. We aim to develop and implement the CDS based on these study results. Future research should address optimal ways to (1) provide patient-directed CDS, (2) enable more patient-specific CDS within the context of patient complexity, and (3) maintain user engagement with CDS over time.

Integration of Hospital Information and Clinical Decision Support Systems to Enable the Reuse of Electronic Health Record Data

Background: The efficiency and acceptance of clinical decision support systems (CDSS) can increase if they reuse medical data captured during health care delivery. High heterogeneity of the existing legacy data formats has become the main barrier for the reuse of data. Thus, we need to apply data modeling mechanisms that provide standardization, transformation, accumulation and querying medical data to allow its reuse.

Objectives: In this paper, we focus on the interoperability issues of the hospital information systems (HIS) and CDSS data integration.

Materials and Methods: Our study is based on the approach proposed by Marcos et al. where archetypes are used as a standardized mechanism for the interaction of a CDSS with an electronic health record (EHR). We build an integration tool to enable CDSSs collect data from various institutions without a need for modifications in the implementation. The approach implies development of a conceptual level as a set of archetypes representing concepts required by a CDSS.

Results: Treatment case data from Regional Clinical Hospital in Tomsk, Russia was extracted, transformed and loaded to the archetype database of a clinical decision support system. Test records’ normalization has been performed by defining transformation and aggregation rules between the EHR data and the archetypes. These mapping rules were used to automatically generate openEHR compliant data. After the transformation, archetype data instances were loaded into the CDSS archetype based data storage. The performance times showed acceptable performance for the extraction stage with a mean of 17.428 s per year (3436 case records). The transformation times were also acceptable with 136.954 s per year (0.039 s per one instance). The accuracy evaluation showed the correctness and applicability of the method for the wide range of HISes. These operations were performed without interrupting the HIS workflow to prevent the HISes from disturbing the service provision to the users.

Conclusions: The project results have proven that archetype based technologies are mature enough to be applied in routine operations that require extraction, transformation, loading and querying medical data from heterogeneous EHR systems. Inference models in clinical research and CDSS can benefit from this by defining queries to a valid data set with known structure and constraints. The standard based nature of the archetype approach allows an easy integration of CDSSs with existing EHR systems.

The use of computer-interpretable clinical guidelines to manage care complexities of patients with multimorbid conditions: A review

Clinical practice guidelines (CPGs) document evidence-based information and recommendations on treatment and management of conditions. CPGs usually focus on management of a single condition; however, in many cases a patient will be at the centre of multiple health conditions (multimorbidity). Multiple CPGs need to be followed in parallel, each managing a separate condition, which often results in instructions that may interact with each other, such as conflicts in medication. Furthermore, the impetus to deliver customised care based on patient-specific information, results in the need to be able to offer guidelines in an integrated manner, identifying and managing their interactions. In recent years, CPGs have been formatted as computer-interpretable guidelines (CIGs). This enables developing CIG-driven clinical decision support systems (CDSSs), which allow the development of IT applications that contribute to the systematic and reliable management of multiple guidelines. This study focuses on understanding the use of CIG-based CDSSs, in order to manage care complexities of patients with multimorbidity. The literature between 2011 and 2017 is reviewed, which covers: (a) the challenges and barriers in the care of multimorbid patients, (b) the role of CIGs in CDSS augmented delivery of care, and (c) the approaches to alleviating care complexities of multimorbid patients. Generating integrated care plans, detecting and resolving adverse interactions between treatments and medications, dealing with temporal constraints in care steps, supporting patient-caregiver shared decision making and maintaining the continuity of care are some of the approaches that are enabled using a CIG-based CDSS.