Overview of Clinical Decision Support Systems

Application of artificial neural networks in reproductive medicine

With the emergence of the age of information, the data on reproductive medicine has improved immensely. Nonetheless, healthcare workers who wish to utilise the relevance and implied value of the various data available to aid clinical decision-making encounter the difficulty of statistically analysing such large data. The application of artificial intelligence becoming widespread in recent years has emerged as a turning point in this regard. Artificial neural networks (ANNs) exhibit beneficial characteristics of comprehensive analysis and autonomous learning, owing to which these are being applied to disease diagnosis, embryo quality assessment, and prediction of pregnancy outcomes. The present report aims to summarise the application of ANNs in the field of reproduction and analyse its further application potential.

Machine learning techniques for periodontitis and dental caries detection: A narrative review

OBJECTIVES

In recent years, periodontitis, and dental caries have become common in humans and need to be diagnosed in the early stage to prevent severe complications and tooth loss. These dental issues are diagnosed by visual inspection, measuring pocket probing depth, and radiographs findings from experienced dentists. Though a glut of machine learning (ML) algorithms has been proposed for the automated detection of periodontitis, and dental caries, determining which ML techniques are suitable for clinical practice remains under debate. This review aims to identify the research challenges by analyzing the limitations of current methods and how to address these to obtain robust systems suitable for clinical use or point-of-care testing.

METHODS

An extensive search of the literature published from 2015 to 2022 written in English, related to the subject of study was sought by searching the electronic databases: PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, and ScienceDirect.

RESULTS

The initial electronic search yielded 1743 titles, and 55 studies were eventually included based on the selection criteria adopted in this review. Studies selected were on ML applications for the automatic detection of periodontitis and dental caries and related dental issues: Apical lessons, Periodontal bone loss, and Vertical root fracture.

CONCLUSION

While most of the ML-based studies use radiograph images for the detection of periodontitis and dental caries, few pieces of the literature revealed that good diagnostic accuracy could be achieved by training the ML model even with mobile photos representing the images of dental issues. Nowadays smartphones are used in every sector for different applications. Training the ML model with as many images of dental issues captured by the smartphone can achieve good accuracy, reduce the cost of clinical diagnosis, and provide user interaction.

Perceptions of Artificial Intelligence-Assisted Care for Children With a Respiratory Complaint

OBJECTIVES

To evaluate caregiver opinions on the use of artificial intelligence (AI)-assisted medical decision-making for children with a respiratory complaint in the emergency department (ED).

METHODS

We surveyed a sample of caregivers of children presenting to a pediatric ED with a respiratory complaint. We assessed caregiver opinions with respect to AI, defined as "specialized computer programs" that "help make decisions about the best way to care for children." We performed multivariable logistic regression to identify factors associated with discomfort with AI-assisted decision-making.

RESULTS

Of 279 caregivers who were approached, 254 (91.0%) participated. Most indicated they would want to know if AI was being used for their child's health care (93.5%) and were extremely or somewhat comfortable with the use of AI in deciding the need for blood (87.9%) and viral testing (87.6%), interpreting chest radiography (84.6%), and determining need for hospitalization (78.9%). In multivariable analysis, caregiver age of 30 to 37 years (adjusted odds ratio [aOR] 3.67, 95% confidence interval [CI] 1.43-9.38; relative to 18-29 years) and a diagnosis of bronchospasm (aOR 5.77, 95% CI 1.24-30.28 relative to asthma) were associated with greater discomfort with AI. Caregivers with children being admitted to the hospital (aOR 0.23, 95% CI 0.09-0.50) had less discomfort with AI.

CONCLUSIONS

Caregivers were receptive toward the use of AI-assisted decision-making. Some subgroups (caregivers aged 30-37 years with children discharged from the ED) demonstrated greater discomfort with AI. Engaging with these subgroups should be considered when developing AI applications for acute care.

Artificial intelligence-based clinical decision support in pediatrics

Machine learning models may be integrated into clinical decision support (CDS) systems to identify children at risk of specific diagnoses or clinical deterioration to provide evidence-based recommendations. This use of artificial intelligence models in clinical decision support (AI-CDS) may have several advantages over traditional "rule-based" CDS models in pediatric care through increased model accuracy, with fewer false alerts and missed patients. AI-CDS tools must be appropriately developed, provide insight into the rationale behind decisions, be seamlessly integrated into care pathways, be intuitive to use, answer clinically relevant questions, respect the content expertise of the healthcare provider, and be scientifically sound. While numerous machine learning models have been reported in pediatric care, their integration into AI-CDS remains incompletely realized to date. Important challenges in the application of AI models in pediatric care include the relatively lower rates of clinically significant outcomes compared to adults, and the lack of sufficiently large datasets available necessary for the development of machine learning models. In this review article, we summarize key concepts related to AI-CDS, its current application to pediatric care, and its potential benefits and risks. IMPACT: The performance of clinical decision support may be enhanced by the utilization of machine learning-based algorithms to improve the predictive performance of underlying models. Artificial intelligence-based clinical decision support (AI-CDS) uses models that are experientially improved through training and are particularly well suited toward high-dimensional data. The application of AI-CDS toward pediatric care remains limited currently but represents an important area of future research.

Conformity assessment of a computer vision-based posture analysis system for the screening of postural deformation

Background

This study evaluates the conformity of using a computer vision-based posture analysis system as a screening assessment for postural deformity detection in the spine that is easily applicable to clinical practice.

Methods

One hundred forty participants were enrolled for screening of the postural deformation. Factors that determine the presence or absence of spinal deformation, such as shoulder height difference (SHD), pelvic height difference (PHD), and leg length mismatch (LLD), were used as parameters for the clinical decision support system (CDSS) using a commercial computer vision-based posture analysis system. For conformity analysis, the probability of postural deformation provided by CDSS, the Cobb angle, the PHD, and the SHD was compared and analyzed between the system and radiographic parameters. A principal component analysis (PCA) of the CDSS and correlation analysis were conducted.

Results

The Cobb angles of the 140 participants ranged from 0° to 61°, with an average of 6.16° ± 8.50°. The postural deformation of CDSS showed 94% conformity correlated with radiographic assessment. The conformity assessment results were more accurate in the participants of postural deformation with normal (0–9°) and mild (10–25°) ranges of scoliosis. The referenced SHD and the SHD of the CDSS showed statistical significance (p < 0.001) on a paired t-test. SHD and PHD for PCA were the predominant factors (PC1 SHD for 79.97%, PC2 PHD for 19.86%).

Conclusion

The CDSS showed 94% conformity for the screening of postural spinal deformity. The main factors determining diagnostic suitability were two main variables: SHD and PHD. In conclusion, a computer vision-based posture analysis system can be utilized as a safe, efficient, and convenient CDSS for early diagnosis of spinal posture deformation, including scoliosis.

Irrational prescription of surfactant replacement therapy in neonatal respiratory distress

Purpose

Respiratory distress is known as one of the leading causes of neonatal death. In recent decades, surfactant therapy has revolutionized respiratory failure. Since the implementation of the health system reform plan as well as the allocation of new financial resources for health system in Iran, the rate of irrational prescription has increased and prescription of surfactant for neonates, has raised unexpectedly, which is thought to be due to irrational prescriptions partly. The present study aimed to determine the rate of irrational prescription of surfactant for neonates with respiratory distress.

Methods

This research was a cross-sectional descriptive study, which was conducted retrospectively. In the current study, determining the rate of irrational prescription was done in terms of the surfactant prescription guideline. Finally, the medical data of 846 neonates who underwent surfactant therapy in Iran in 2018, were extracted from the information system of the Ministry of Health and the neonatal medical records.

Results

The results show that drug selection index, dose index, and time index were irrational for 14.30%, 27.42%, and 1.06% of neonates, respectively. Moreover, the total index of drug prescription, which is a combination of the above-mentioned three components, was found to be irrational for 31.47% of neonates.

Conclusions

The results of the present study are considered as a warning to providers and decision makers in the field of neonatal health to reduce irrational prescriptions of surfactant for neonates. This study suggests the use of educational interventions in order to reduce irrational prescriptions due to drug selection as well as the use of computer alert approaches in order to reduce irrational prescriptions due to wrong dose.

Evaluating a Prototype Clinical Decision Support Tool for Chronic Pain Treatment in Primary Care

OBJECTIVES

 The Chronic Pain Treatment Tracker (Tx Tracker) is a prototype decision support tool to aid primary care clinicians when caring for patients with chronic noncancer pain. This study evaluated clinicians' perceived utility of Tx Tracker in meeting information needs and identifying treatment options, and preferences for visual design.

METHODS

 We conducted 12 semi-structured interviews with primary care clinicians from four health systems in Indiana. The interviews were conducted in two waves, with prototype and interview guide revisions after the first six interviews. The interviews included exploration of Tx Tracker using a think-aloud approach and a clinical scenario. Clinicians were presented with a patient scenario and asked to use Tx Tracker to make a treatment recommendation. Last, participants answered several evaluation questions. Detailed field notes were collected, coded, and thematically analyzed by four analysts.

RESULTS

 We identified several themes: the need for clinicians to be presented with a comprehensive patient history, the usefulness of Tx Tracker in patient discussions about treatment planning, potential usefulness of Tx Tracker for patients with high uncertainty or risk, potential usefulness of Tx Tracker in aggregating scattered information, variability in expectations about workflows, skepticism about underlying electronic health record data quality, interest in using Tx Tracker to annotate or update information, interest in using Tx Tracker to translate information to clinical action, desire for interface with visual cues for risks, warnings, or treatment options, and desire for interactive functionality.

CONCLUSION

 Tools like Tx Tracker, by aggregating key information about past, current, and potential future treatments, may help clinicians collaborate with their patients in choosing the best pain treatments. Still, the use and usefulness of Tx Tracker likely relies on continued improvement of its functionality, accurate and complete underlying data, and tailored integration with varying workflows, care team roles, and user preferences.

Implementation of pharmacogenomic clinical decision support for health systems: a cost-utility analysis

We constructed a cost-effectiveness model to assess the clinical and economic value of a CDS alert program that provides pharmacogenomic (PGx) testing results, compared to no alert program in acute coronary syndrome (ACS) and atrial fibrillation (AF), from a health system perspective. We defaulted that 20% of 500,000 health-system members between the ages of 55 and 65 received PGx testing for CYP2C19 (ACS-clopidogrel) and CYP2C9, CYP4F2 and VKORC1 (AF-warfarin) annually. Clinical events, costs, and quality-adjusted life years (QALYs) were calculated over 20 years with an annual discount rate of 3%. In total, 3169 alerts would be fired. The CDS alert program would help avoid 16 major clinical events and 6 deaths for ACS; and 2 clinical events and 0.9 deaths for AF. The incremental cost-effectiveness ratio was $39,477/QALY. A PGx-CDS alert program was cost-effective, under a willingness-to-pay threshold of $100,000/QALY gained, compared to no alert program.

A treatment recommender clinical decision support system for personalized medicine: method development and proof-of-concept for drug resistant tuberculosis

Background

Personalized medicine tailors care based on the patient’s or pathogen’s genotypic and phenotypic characteristics. An automated Clinical Decision Support System (CDSS) could help translate the genotypic and phenotypic characteristics into optimal treatment and thus facilitate implementation of individualized treatment by less experienced physicians.

Methods

We developed a hybrid knowledge- and data-driven treatment recommender CDSS. Stakeholders and experts first define the knowledge base by identifying and quantifying drug and regimen features for the prototype model input. In an iterative manner, feedback from experts is harvested to generate model training datasets, machine learning methods are applied to identify complex relations and patterns in the data, and model performance is assessed by estimating the precision at one, mean reciprocal rank and mean average precision. Once the model performance no longer iteratively increases, a validation dataset is used to assess model overfitting.

Results

We applied the novel methodology to develop a treatment recommender CDSS for individualized treatment of drug resistant tuberculosis as a proof of concept. Using input from stakeholders and three rounds of expert feedback on a dataset of 355 patients with 129 unique drug resistance profiles, the model had a 95% precision at 1 indicating that the highest ranked treatment regimen was considered appropriate by the experts in 95% of cases. Use of a validation data set however suggested substantial model overfitting, with a reduction in precision at 1 to 78%.

Conclusion

Our novel and flexible hybrid knowledge- and data-driven treatment recommender CDSS is a first step towards the automation of individualized treatment for personalized medicine. Further research should assess its value in fields other than drug resistant tuberculosis, develop solid statistical approaches to assess model performance, and evaluate their accuracy in real-life clinical settings.

Big data and predictive analytics in neurocritical care

PURPOSE OF REVIEW

To describe predictive data and workflow in the intensive care unit when managing neurologically ill patients.

RECENT FINDINGS

In the era of Big Data in medicine, intensive critical care units are data-rich environments. Neurocritical care adds another layer of data with advanced multimodal monitoring to prevent secondary brain injury from ischemia, tissue hypoxia, and a cascade of ongoing metabolic events. A step closer toward personalized medicine is the application of multimodal monitoring of cerebral hemodynamics, bran oxygenation, brain metabolism, and electrophysiologic indices, all of which have complex and dynamic interactions. These data are acquired and visualized using different tools and monitors facing multiple challenges toward the goal of the optimal decision support system. In this review, we highlight some of the predictive data used to diagnose, treat, and prognosticate the neurologically ill patients. We describe information management in neurocritical care units including data acquisition, wrangling, analysis, and visualization.

Hybrid Method Incorporating a Rule-Based Approach and Deep Learning for Prescription Error Prediction

INTRODUCTION

Recently, automated detection has been a new approach to address the risks posed by prescribing errors. This study focused on prescription errors and utilized real medical data to supplement the Drug Utilization Review (DUR)-based rules, the current prescription error detection method. We developed a new hybrid method through artificial intelligence for prescription error prediction by utilizing actual detection accuracy improvement to reduce 'warning fatigue' for doctors and improve medical care quality.

OBJECT

This study was conducted in the Department of Pediatrics, targeting children sensitive to drugs to develop a prescription error detection system. Based on the DUR prescription history, 15,281 patient-level observations of children from Konyang University Hospital (KYUH)'s common data model (CDM) and DUR were collected and analyzed retrospectively.

METHOD

Among the CDM data, inspection information was interlocked with DUR and reflected as standard information for model development; this included outpatient prescriptions from January 1 to December 31, 2018. Through consultation with pediatric clinicians, rule definitions and model development were conducted for 35 drugs, with 137,802 normal and 1609 prescription errors.

RESULTS

We developed a novel hybrid method of error detection in the form of an advanced rule-based deep neural network (ARDNN), which showed the expected performance (precision: 72.86, recall: 81.01, F1 score: 76.72) and reduced alarm pop-up alert fatigue to below 10%. We also created an ARDNN-based comprehensive dashboard that allows doctors to monitor prescription errors with alarm pop-ups when prescribing medications.

CONCLUSION

These results can advance the existing rule-based model by developing a prescription error detection model using deep learning. This method can improve overall medical efficiency and service quality by reducing doctors' fatigue.

Effect of Computerized Physician Order Entry and Clinical Decision Support System on Adverse Drug Events Prevention in the Emergency Department: A Systematic Review

Objective: An adverse drug event (ADE) is an injury resulting from a medical intervention related to a drug. The emergency department (ED) is a ward vulnerable to more ADEs because of overcrowding. Information technologies such as computerized physician order entry (CPOE) and clinical decision support system (CDSS) may decrease the occurrence of ADEs. This study aims to review research that reported the evaluation of the effectiveness of CPOE and CDSS on lowering the occurrence of ADEs in the ED. Data Sources: PubMed, EMBASE, and Web of Science databases were used to find studies published from 2003 to 2018. The search was conducted in November 2018. Study Selection and Data Extraction: The search resulted in 1700 retrieved articles. After applying inclusion and exclusion criteria, 11 articles were included. Data on the date, country, type of system, medication process stages, study design, participants, sample size, and outcomes were extracted. Data Synthesis: Results showed that CPOE and CDSS may prevent ADEs in the ED through significantly decreasing the rate of errors, ADEs, excessive dose, and inappropriate prescribing (in 54.5% of articles); furthermore, CPOE and CDSS may significantly increase the rate of appropriate prescribing and dosing in compliance with established guidelines (45.5% of articles). Conclusion: This study revealed that the use of CPOE and CDSS can lower the occurrence of ADEs in the ED; however, further randomized controlled trials are needed to address the effect of a CDSS, with basic or advanced features, on the occurrence of ADEs in the ED.

Effect of Having, but Not Consulting, a Computerized Diagnostic Aid

Previous research has described physicians' reluctance to use computerized diagnostic aids (CDAs) but has never experimentally examined the effects of not consulting an aid that was readily available. Experiment 1. Participants read about a diagnosis made either by a physician or an auto mechanic (to control for perceived expertise). Half read that a CDA was available but never actually consulted; no mention of a CDA was made for the remaining half. For the physician, failure to consult the CDA had no significant effect on competence ratings for either the positive or negative outcome. For the auto mechanic, failure to consult the CDA actually increased competence ratings following a negative but not a positive outcome. Negligence judgments were greater for the mechanic than for the physician overall. Experiment 2. Using only a negative outcome, we included 2 different reasons for not consulting the aid and provided accuracy information highlighting the superiority of the CDA over the physician. In neither condition was the physician rated lower than when no aid was mentioned. Ratings were lower when the physician did not trust the CDA and, surprisingly, higher when the physician believed he or she already knew what the CDA would say. Finally, consistent with our previous research, ratings were also high when the physician consulted and then followed the advice of a CDA and low when the CDA was consulted but ignored. Individual differences in numeracy did not qualify these results. Implications for the literature on algorithm aversion and clinical practice are discussed.

A novel method to retrieve alerts from a homegrown Computerized Physician Order Entry (CPOE) system of an academic medical center: Comprehensive alert characteristic analysis

Background

The collection and analysis of alert logs are necessary for hospital administrators to understand the types and distribution of alert categories within the organization and reduce alert fatigue. However, this is not readily available in most homegrown Computerized Physician Order Entry (CPOE) systems.

Objective

To present a novel method that can collect alert information from a homegrown CPOE system (at an academic medical center in Taiwan) and conduct a comprehensive analysis of the number of alerts triggered and alert characteristics.

Methods

An alert log collector was developed using the Golang programming language and was implemented to collect all triggered interruptive alerts from a homegrown CPOE system of a 726-bed academic medical center from November 2017 to June 2018. Two physicians categorized the alerts from the log collector as either clinical or non-clinical (administrative).

Results

Overall, 1,625,341 interruptive alerts were collected and classified into 1,474 different categories based on message content. The sum of the top 20, 50, and 100 categories of most frequently triggered alerts accounted for approximately 80, 90 and 97 percent of the total triggered alerts, respectively. Among alerts from the 100 most frequently triggered categories, 1,266,818 (80.2%) were administrative and 312,593 (19.8%) were clinical alerts.

Conclusion

We have successfully developed an alert log collector that can serve as an extended function to retrieve alerts from a homegrown CPOE system. The insight generated from the present study could also potentially bring value to hospital system designers and hospital administrators when redesigning their CPOE system.

Reducing Alert Fatigue by Sharing Low-Level Alerts With Patients and Enhancing Collaborative Decision Making Using Blockchain Technology: Scoping Review and Proposed Framework (MedAlert)

Background

Clinical decision support (CDS) is a tool that helps clinicians in decision making by generating clinical alerts to supplement their previous knowledge and experience. However, CDS generates a high volume of irrelevant alerts, resulting in alert fatigue among clinicians. Alert fatigue is the mental state of alerts consuming too much time and mental energy, which often results in relevant alerts being overridden unjustifiably, along with clinically irrelevant ones. Consequently, clinicians become less responsive to important alerts, which opens the door to medication errors.

Objective

This study aims to explore how a blockchain-based solution can reduce alert fatigue through collaborative alert sharing in the health sector, thus improving overall health care quality for both patients and clinicians.

Methods

We have designed a 4-step approach to answer this research question. First, we identified five potential challenges based on the published literature through a scoping review. Second, a framework is designed to reduce alert fatigue by addressing the identified challenges with different digital components. Third, an evaluation is made by comparing MedAlert with other proposed solutions. Finally, the limitations and future work are also discussed.

Results

Of the 341 academic papers collected, 8 were selected and analyzed. MedAlert securely distributes low-level (nonlife-threatening) clinical alerts to patients, enabling a collaborative clinical decision. Among the solutions in our framework, Hyperledger (private permissioned blockchain) and BankID (federated digital identity management) have been selected to overcome challenges such as data integrity, user identity, and privacy issues.

Conclusions

MedAlert can reduce alert fatigue by attracting the attention of patients and clinicians, instead of solely reducing the total number of alerts. MedAlert offers other advantages, such as ensuring a higher degree of patient privacy and faster transaction times compared with other frameworks. This framework may not be suitable for elderly patients who are not technology savvy or in-patients. Future work in validating this framework based on real health care scenarios is needed to provide the performance evaluations of MedAlert and thus gain support for the better development of this idea.

A data-driven approach to a chemotherapy recommendation model based on deep learning for patients with colorectal cancer in Korea

BACKGROUND

Clinical Decision Support Systems (CDSSs) have recently attracted attention as a method for minimizing medical errors. Existing CDSSs are limited in that they do not reflect actual data. To overcome this limitation, we propose a CDSS based on deep learning.

METHODS

We propose the Colorectal Cancer Chemotherapy Recommender (C3R), which is a deep learning-based chemotherapy recommendation model. Our model improves on existing CDSSs in which data-based decision making is not well supported. C3R is configured to study the clinical data collected at the Gachon Gil Medical Center and to recommend appropriate chemotherapy based on the data. To validate the model, we compared the treatment concordance rate with the National Comprehensive Cancer Network (NCCN) Guidelines, a representative set of cancer treatment guidelines, and with the results of the Gachon Gil Medical Center's Colorectal Cancer Treatment Protocol (GCCTP).

RESULTS

For the C3R model, the treatment concordance rates with the NCCN guidelines were 70.5% for Top-1 Accuracy and 84% for Top-2 Accuracy. The treatment concordance rates with the GCCTP were 57.9% for Top-1 Accuracy and 77.8% for Top-2 Accuracy.

CONCLUSIONS

This model is significant, i.e., it is the first colon cancer treatment clinical decision support system in Korea that reflects actual data. In the future, if sufficient data can be secured through cooperation among multiple organizations, more reliable results can be obtained.

Comparative Effectiveness of Best Practice Alerts with Active and Passive Presentations: A Retrospective Study

We assess the relationship of active or passive presentation of Best Practice Advisories (BPAs) for hospital clinicians with compliance rates of recommended actions. We identify the design characteristics of alerts that can be used to assess the effectiveness of design choices with superior usability. Alerts in Electronic Health Records (EHRs) are frequently overridden by healthcare providers. Identifying characteristics of effective alerts can increase the frequency that actions recommended in evidence-based care guidelines are done, reduce user frustration, and improve interface usability along with the willingness to use alerts. We conducted a retrospective analysis of data for 11 BPAs between June 2014 and May 2015. The outcome measure was the percent correspondence with recommended actions. A repeated measures regression model was used for the correlation of the BPA presentation type with the outcome measure. The BPA presentation type was significant such that the odds are 7.7 times greater that a recommended action would be taken by a provider with an active BPA presentation type after adjusting for whether an action was required. Active presentation alerts achieve higher compliance rates. CDS alerts that actively interrupted the provider’s workflow were associated with a higher compliance rate with recommended actions.

Leveraging IoTs and Machine Learning for Patient Diagnosis and Ventilation Management in the Intensive Care Unit

Future healthcare systems will rely heavily on clinical decision support systems (CDSS) to improve the decision-making processes of clinicians. To explore the design of future CDSS, we developed a research-focused CDSS for the management of patients in the intensive care unit that leverages Internet of Things (IoT) devices capable of collecting streaming physiologic data from ventilators and other medical devices. We then created machine learning (ML) models that could analyze the collected physiologic data to determine if the ventilator was delivering potentially harmful therapy and if a deadly respiratory condition, acute respiratory distress syndrome (ARDS), was present. We also present work to aggregate these models into a mobile application that can provide responsive, real-time alerts of changes in ventilation to providers. As illustrated in the recent COVID-19 pandemic, being able to accurately predict ARDS in newly infected patients can assist in prioritizing care. We show that CDSS may be used to analyze physiologic data for clinical event recognition and automated diagnosis, and we also highlight future research avenues for hospital CDSS.

Using clinical reasoning ontologies to make smarter clinical decision support systems: a systematic review and data synthesis

OBJECTIVE

The study sought to describe the literature describing clinical reasoning ontology (CRO)-based clinical decision support systems (CDSSs) and identify and classify the medical knowledge and reasoning concepts and their properties within these ontologies to guide future research.

METHODS

MEDLINE, Scopus, and Google Scholar were searched through January 30, 2019, for studies describing CRO-based CDSSs. Articles that explored the development or application of CROs or terminology were selected. Eligible articles were assessed for quality features of both CDSSs and CROs to determine the current practices. We then compiled concepts and properties used within the articles.

RESULTS

We included 38 CRO-based CDSSs for the analysis. Diversity of the purpose and scope of their ontologies was seen, with a variety of knowledge sources were used for ontology development. We found 126 unique medical knowledge concepts, 38 unique reasoning concepts, and 240 unique properties (137 relationships and 103 attributes). Although there is a great diversity among the terms used across CROs, there is a significant overlap based on their descriptions. Only 5 studies described high quality assessment.

CONCLUSION

We identified current practices used in CRO development and provided lists of medical knowledge concepts, reasoning concepts, and properties (relationships and attributes) used by CRO-based CDSSs. CRO developers reason that the inclusion of concepts used by clinicians' during medical decision making has the potential to improve CDSS performance. However, at present, few CROs have been used for CDSSs, and high-quality studies describing CROs are sparse. Further research is required in developing high-quality CDSSs based on CROs.

The Role of Artificial Intelligence in Clinical Decision Support Systems and a Classification Framework

Clinical decision support systems are meant to improve the quality of decision-making in healthcare. Artificial intelligence is the science of creating intelligent systems that solve complex problems at the level of or better than human experts. Combining artificial intelligence methods into clinical decision support will enable the utilization of large quantities of data to produce relevant decision-making information to practitioners. This article examines various artificial intelligence methodologies and shows how they may be incorporated into clinical decision-making systems. A framework for describing artificial intelligence applications in clinical decision support systems is presented.

Reasons For Physicians Not Adopting Clinical Decision Support Systems: Critical Analysis

Background

Clinical decision support systems (CDSSs) are an integral component of today’s health information technologies. They assist with interpretation, diagnosis, and treatment. A CDSS can be embedded throughout the patient safety continuum providing reminders, recommendations, and alerts to health care providers. Although CDSSs have been shown to reduce medical errors and improve patient outcomes, they have fallen short of their full potential. User acceptance has been identified as one of the potential reasons for this shortfall.

Objective

The purpose of this paper was to conduct a critical review and task analysis of CDSS research and to develop a new framework for CDSS design in order to achieve user acceptance.

Methods

A critical review of CDSS papers was conducted with a focus on user acceptance. To gain a greater understanding of the problems associated with CDSS acceptance, we conducted a task analysis to identify and describe the goals, user input, system output, knowledge requirements, and constraints from two different perspectives: the machine (ie, the CDSS engine) and the user (ie, the physician).

Results

Favorability of CDSSs was based on user acceptance of clinical guidelines, reminders, alerts, and diagnostic suggestions. We propose two models: (1) the user acceptance and system adaptation design model, which includes optimizing CDSS design based on user needs/expectations, and (2) the input-process-output-engagemodel, which reveals to users the processes that govern CDSS outputs.

Conclusions

This research demonstrates that the incorporation of the proposed models will improve user acceptance to support the beneficial effects of CDSSs adoption. Ultimately, if a user does not accept technology, this not only poses a threat to the use of the technology but can also pose a threat to the health and well-being of patients.

Neuromyelitis optica: Application of computer diagnostics to historical case reports

The retrospective diagnosis of illnesses by medical historians can often be difficult and prone to bias, although knowledge of the medical disorders of historical figures is key to the understanding of their behavior and reactions. The recent application of computer diagnostics to historical figures allows an objective differential diagnosis to be accomplished. Taking an example from clinical neurology, we analyzed the earliest reported cases of Devic's disease (neuromyelitis optica) that commonly affects the optic nerve and spinal cord and was previously often confused with multiple sclerosis. We conclude that in most identified cases the software concurred with the contemporary physicians' interpretation, but some claimed cases either had insufficient data to provide a diagnosis or other possible diagnoses were suggested that had not been considered. Computational methods may, therefore, help historians to diagnose the ailments of historical figures with greater objectivity.

An ontology-driven, case-based clinical decision support model for removable partial denture design

We present the initial work toward developing a clinical decision support model for specific design of removable partial dentures (RPDs) in dentistry. We developed an ontological paradigm to represent knowledge of a patient’s oral conditions and denture component parts. During the case-based reasoning process, a cosine similarity algorithm was applied to calculate similarity values between input patients and standard ontology cases. A group of designs from the most similar cases were output as the final results. To evaluate this model, the output designs of RPDs for 104 randomly selected patients were compared with those selected by professionals. An area under the curve of the receiver operating characteristic (AUC-ROC) was created by plotting true-positive rates against the false-positive rate at various threshold settings. The precision at position 5 of the retrieved cases was 0.67 and at the top of the curve it was 0.96, both of which are very high. The mean average of precision (MAP) was 0.61 and the normalized discounted cumulative gain (NDCG) was 0.74 both of which confirmed the efficient performance of our model. All the metrics demonstrated the efficiency of our model. This methodology merits further research development to match clinical applications for designing RPDs. This paper is organized as follows. After the introduction and description of the basis for the paper, the evaluation and results are presented in Section 2. Section 3 provides a discussion of the methodology and results. Section 4 describes the details of the ontology, similarity algorithm, and application.

Effectiveness of a Clinical Decision Support System for Pointing Device Prescription

OBJECTIVE

We present a novel, knowledge-driven approach to prescription of pointing devices that uses the Ontology-Supported Computerized Assistive Technology Recommender (OSCAR), a clinical decision support system (CDSS).

METHOD

Fifty-five occupational therapists were divided into four groups: two assistive technology (AT) expert groups and two novice groups. Novice Group 1 used the OSCAR CDSS for the prescription process, and Novice Group 2 used the conventional method. OSCAR's effectiveness and its impact on users were evaluated.

RESULTS

The ability of Novice Group 1 to make suitable pointing device prescriptions was similar to that of the two expert groups and was significantly better than that of Novice Group 2. The system positively affected Novice Group 1's learning of the prescription process.

CONCLUSION

The structure and organized framework for clinical reasoning of the OSCAR CDSS appear to enable occupational therapy practitioners inexperienced in AT to achieve performance levels comparable to those of experts.

Assessment of readiness for clinical decision support to aid laboratory monitoring of immunosuppressive care at U.S. liver transplant centers

BACKGROUND

Following liver transplantation, patients require lifelong immunosuppressive care and monitoring. Computerized clinical decision support (CDS) has been shown to improve post-transplant immunosuppressive care processes and outcomes. The readiness of transplant information systems to implement computerized CDS to support post-transplant care is unknown.

OBJECTIVES

a) Describe the current clinical information system functionality and manual and automated processes for laboratory monitoring of immunosuppressive care, b) describe the use of guidelines that may be used to produce computable logic and the use of computerized alerts to support guideline adherence, and c) explore barriers to implementation of CDS in U.S. liver transplant centers.

METHODS

We developed a web-based survey using cognitive interviewing techniques. We surveyed 119 U.S. transplant programs that performed at least five liver transplantations per year during 2010-2012. Responses were summarized using descriptive analyses; barriers were identified using qualitative methods.

RESULTS

Respondents from 80 programs (67% response rate) completed the survey. While 98% of programs reported having an electronic health record (EHR), all programs used paper-based manual processes to receive or track immunosuppressive laboratory results. Most programs (85%) reported that 30% or more of their patients used external laboratories for routine testing. Few programs (19%) received most external laboratory results as discrete data via electronic interfaces while most (80%) manually entered laboratory results into the EHR; less than half (42%) could integrate internal and external laboratory results. Nearly all programs had guidelines regarding pre-specified target ranges (92%) or testing schedules (97%) for managing immunosuppressive care. Few programs used computerized alerting to notify transplant coordinators of out-of-range (27%) or overdue laboratory results (20%).

CONCLUSIONS

Use of EHRs is common, yet all liver transplant programs were largely dependent on manual paper-based processes to monitor immunosuppression for post-liver transplant patients. Similar immunosuppression guidelines provide opportunities for sharing CDS once integrated laboratory data are available.

A retrospective analysis of interruptive versus non-interruptive clinical decision support for identification of patients needing contact isolation

BACKGROUND

In determining whether clinical decision support (CDS) should be interruptive or non-interruptive, CDS designers need more guidance to balance the potential for interruptive CDS to overburden clinicians and the potential for non-interruptive CDS to be overlooked by clinicians.

OBJECTIVE

(1)To compare performance achieved by clinicians using interruptive CDS versus using similar, non-interruptive CDS. (2)To compare performance achieved using non-interruptive CDS among clinicians exposed to interruptive CDS versus clinicians not exposed to interruptive CDS.

METHODS

We studied 42 emergency medicine physicians working in a large hospital where an interruptive CDS to help identify patients requiring contact isolation was replaced by a similar, but non-interruptive CDS. The first primary outcome was the change in sensitivity in identifying these patients associated with the conversion from an interruptive to a non-interruptive CDS. The second primary outcome was the difference in sensitivities yielded by the non-interruptive CDS when used by providers who had and who had not been exposed to the interruptive CDS. The reference standard was an epidemiologist-designed, structured, objective assessment.

RESULTS

In identifying patients needing contact isolation, the interruptive CDS-physician dyad had sensitivity of 24% (95% CI: 17%-32%), versus sensitivity of 14% (95% CI: 9%-21%) for the non-interruptive CDS-physician dyad (p = 0.04). Users of the non-interruptive CDS with prior exposure to the interruptive CDS were more sensitive than those without exposure (14% [95% CI: 9%-21%] versus 7% [95% CI: 3%-13%], p = 0.05).

LIMITATIONS

As with all observational studies, we cannot confirm that our analysis controlled for every important difference between time periods and physician groups.

CONCLUSIONS

Interruptive CDS affected clinicians more than non-interruptive CDS. Designers of CDS might explicitly weigh the benefits of interruptive CDS versus its associated increased clinician burden. Further research should study longer term effects of clinician exposure to interruptive CDS, including whether it may improve clinician performance when using a similar, subsequent non-interruptive CDS.

Effects of a computerized feedback intervention on safety performance by junior doctors: results from a randomized mixed method study

Background

The behaviour of doctors and their responses to warnings can inform the effective design of Clinical Decision Support Systems. We used data from a University hospital electronic prescribing and laboratory reporting system with hierarchical warnings and alerts to explore junior doctors’ behaviour. The objective of this trial was to establish whether a Junior Doctor Dashboard providing feedback on prescription warning information and laboratory alerting acceptance rates was effective in changing junior doctors’ behaviour.

Methods

A mixed methods approach was employed which included a parallel group randomised controlled trial, and individual and focus group interviews. Junior doctors below the specialty trainee level 3 grade were recruited and randomised to two groups. Every doctor (N = 42) in the intervention group was e-mailed a link to a personal dashboard every week for 4 months. Nineteen participated in interviews. The 44 control doctors did not receive any automated feedback. The outcome measures were the difference in responses to prescribing warnings (of two severities) and laboratory alerting (of two severities) between the months before and the months during the intervention, analysed as the difference in performance between the intervention and the control groups.

Results

No significant differences were observed in the rates of generating prescription warnings, or in the acceptance of laboratory alarms. However, responses to laboratory alerts differed between the pre-intervention and intervention periods. For the doctors of Foundation Year 1 grade, this improvement was significantly (p = 0.002) greater in the group with access to the dashboard (53.6% ignored pre-intervention compared to 29.2% post intervention) than in the control group (47.9% ignored pre-intervention compared to 47.0% post intervention). Qualitative interview data indicated that while junior doctors were positive about the electronic prescribing functions, they were discriminating in the way they responded to other alerts and warnings given that from their perspective these were not always immediately clinically relevant or within the scope of their responsibility.

Conclusions

We have only been able to provide weak evidence that a clinical dashboard providing individualized feedback data has the potential to improve safety behaviour and only in one of several domains. The construction of metrics used in clinical dashboards must take account of actual work processes.

Trial registration

ISRCTN: ISRCTN72253051