Clinical Decision Support Module Research Articles

Clinical decision support to enhance venous thromboembolism pharmacoprophylaxis prescribing for pediatric inpatients with COVID-19.

To design and evaluate a clinical decision support (CDS) module to improve guideline concordant venous thromboembolism (VTE) pharmacoprophylaxis prescribing for pediatric inpatients with COVID-19. The proportion of patients who met our institutional clinical practice guideline's (CPG) criteria for VTE prophylaxis was compared to those who triggered a CDS alert, indicating the patient needed VTE prophylaxis, and to those who were prescribed prophylaxis pre and post the launch of a new VTE CDS module to support VTE pharmacoprophylaxis prescribing. The sensitivity, specificity, positive predictive value (PPV), negative predictive value, F1-score and accuracy of the tool were calculated for the pre- and post-intervention periods using the CPG recommendation as the gold standard. Accuracy was defined as the sum of the true positives and true negatives over the sum of the true positives, false positives, true negatives, and false negatives. Logistic regression was used to identify variables associated with correct thromboprophylaxis prescribing. A significant increase in the proportion of patients triggering a CDS alert occurred in the post-intervention period (44.3% vs. 6.9%, p<.001); however, no reciprocal increase in VTE prophylaxis prescribing was achieved (36.6% vs. 40.9%, p=.53). The updated CDS module had an improved sensitivity (55.0% vs. 13.3%), NPV (44.9% vs. 36.3%), F1-score (66.7% vs. 23.5%), and accuracy (62.5% vs. 42.0%), but an inferior specificity (78.6% vs. 100%) and PPV (84.6% vs. 100%). The updated CDS model had an improved accuracy and overall performance in correctly identifying patients requiring VTE prophylaxis. Despite an increase in correct patient identification by the CDS module, the proportion of patients receiving appropriate pharmacologic prophylaxis did not change. CDS tools to support correct VTE prophylaxis prescribing need ongoing refinement and validation to maximize clinical utility.

Blinded-assessment of a solution to evaluate olaparib maintenance treatment efficacy in patients with ovarian cancer from the GINECO/ENGOT PAOLA-1 trial.

5588 Background: SOPHiA DDM Dx HRD Solution (SOPHiA GENETICS, SA) combines analysis of genomic instability with mutational status of HRR genes, including BRCA1/2, generated through a single genomic workflow in order to to predict Homologous Recombination Deficiency (HRD) status in ovarian cancer (OvCa) samples. Previous evaluation of SOPHiA DDM Dx HRD Solution demonstrated its results to be highly concordant with a reference HRD method. As part of the ENGOT HRD initiative, we present updated clinical relevance results of SOPHiA DDM Dx HRD Solution. Methods: GINECO/ENGOT-Ov25 PAOLA-1 trial randomized (2:1) 804 patients (pts) to receive after the end of first-line platinum-based chemotherapy either maintenance olaparib+bevacizumab or placebo+bevacizumab for up to 2 years. DNA from a sub-cohort of 384 formalin-fixed paraffin-embedded (FFPE) OvCa pts samples included in the PAOLA-1 clinical trial were analyzed using SOPHiA DDM Dx HRD Solution(*). We combined SOPHiA DDM Dx HRD Solution genomic instability score, with BRCA mutational status obtained from a Clinical Decision Support module, and clinical interpretation of Variants of Unknown Significance to establish the pts HRD status and investigated differences in progression-free survival (PFS) in the olaparib+bevacizumab and placebo+bevacizumab arms between pts with HRD positive or HRD negative test. Results: We determined the HRD status of 98.4% of pts using SOPHiA DDM Dx HRD Solution. The median PFS time for pts with HRD positive tumors was 35.7 months longer in the olaparib+bevacizumab arm than in the placebo+bevacizumab arm (hazard ratio [HR], 0.36; 95% confidence interval [CI], 0.25-0.51, p&lt; 0.001), confirming the findings of our previous interim analysis. No significant difference in PFS was observed between treatment arms in pts with HRD negative test (HR, 1.02; 95% CI, 0.71-1.48; p= 0.90). Conclusions: These clinical relevance results from the SOPHiA DDM Dx HRD Solution evaluation on the PAOLA-1 samples further support the value of combining low-pass whole genome and targeted sequencing in a unique workflow for reliable and cost-effective HRD testing and future patient stratification. (*) Comparison data generated using the CE-IVD pipeline with Clinical Decision Support module for BRCA status only available in EU, Switzerland, UK.

Breast cancer survival analysis agents for clinical decision support

Personalized support and assistance are essential for cancer survivors, given the physical and psychological consequences they have to suffer after all the treatments and conditions associated with this illness. Digital assistive technologies have proved to be effective in enhancing the quality of life of cancer survivors, for instance, through physical exercise monitoring and recommendation or emotional support and prediction. To maximize the efficacy of these techniques, it is challenging to develop accurate models of patient trajectories, which are typically fed with information acquired from retrospective datasets. This paper presents a Machine Learning-based survival model embedded in a clinical decision system architecture for predicting cancer survivors’ trajectories. The proposed architecture of the system, named PERSIST, integrates the enrichment and pre-processing of clinical datasets coming from different sources and the development of clinical decision support modules. Moreover, the model includes detecting high-risk markers, which have been evaluated in terms of performance using both a third-party dataset of breast cancer patients and a retrospective dataset collected in the context of the PERSIST clinical study.

Usability and the Rapid Deployable Infectious Disease Decision Support System.

Health information technology-guided clinical decision support has demonstrated decreases in patient safety errors in the electronic health record. Unknown and re-emerging infectious diseases are a growing concern for many healthcare facilities. The purpose of this project was to develop a modular approach to integrate rapid deployment of clinical decision support for infectious diseases into the clinical workflow and evaluate the usability of the design. This article reports on the results of a quality improvement project to develop, implement, and evaluate rapid deployment of a clinical decision support module using a tuberculosis use case. Important lessons learned from the electronic health record build with previous Ebola and Zika decision support alert strategy are discussed as foundational in guiding the overall design, implementation, and evaluation of improvement strategies. Subject matter expert feedback was sought throughout the project for electronic health record design and build considerations. Usability evaluation was conducted using the classic Task, User, Representation, and Function unified framework of electronic health record usability. Usability satisfaction for both providers and nurses remained high. Tuberculosis cases pre-alert and post-alert had decreased order times for diagnostic studies. Results suggest satisfied clinicians coupled with usable systems create a more efficient workflow resulting in safer and timelier diagnostic testing.

Enabling Laboratory Medicine in Primary Care Through IT Systems Use

Important problems remain regarding the efficiency and quality of laboratory testing in primary care. In view of this, a significant function of electronic medical record (EMR) systems is to enable the practice of laboratory medicine by primary care physicians. The present study aims to deepen our understanding of the nature and extent of physicians' use of EMR and other laboratory information exchange systems for patient management and care within the laboratory testing process. We conducted a survey of 684 Canadian family physicians. Results indicate that physicians use 84 percent of the laboratory functionalities available in their EMR system. The two most important impacts are the ability to gain time in the post-analytical phase and to take faster action in this same phase as they follow-up on their patients' test results. Physicians who perceive to benefit most from their EMR use are those who make the most extensive use of their system. Extended use of an EMR system allows primary care physicians to better ascertain and monitor the health status of their patients, verify their diagnosis assumptions, and, if their system includes a clinical decision support module, apply evidence-based practices in laboratory medicine.

User-Centered Development of a Behavioral Economics Inspired Electronic Health Record Clinical Decision Support Module.

Changing physician behaviors is difficult. Electronic health record (EHR) clinical decision support (CDS) offers an opportunity to promote guideline adherence. Behavioral economics (BE) has shown success as an approach to supporting evidence-based decision-making with little additional cognitive burden. We applied a user-centered approach to incorporate BE “nudges” into a CDS module in two “vanguard” sites utilizing: (1) semi-structured interviews with key informants (n=8); (2) a design thinking workshop; and (3) semi-structured group interviews with clinicians. In the 133 day development phase at two clinics, the navigator section fired 299 times for 27 unique clinicians. The inbasket refill alert fired 124 times for 22 clinicians. Fifteen prescriptions for metformin were written by 11 clinicians. Our user-centered approach yielded a BE- driven CDS module with relatively high utilization by clinicians. Next steps include the addition of two modules and continued tracking of utilization, and assessment of clinical impact of the module.

Implant Failure Prediction Using Discriminant Analysis.

Electronic dental records (EDR) provide access to a vast repository of clinical information which may be used for analyzing dental care delivery. The goal of this study was identification of determinants of implant survival and development of implant failure prediction model using large data set of intact and failed implant parameters extracted from EDR. A retrospective analysis of 19 variables reflecting patient, surgeon and dental treatment characteristics of 800 dental implants was performed using discriminant analysis to develop a predictive model identifying potential implant failure based on characteristics routinely available in a clinical care setting. The intact and failed implant characteristics were compared using the Goodman and Kruskal's lambda test, the point-biserial test, the chi-square test, and ANOVA test. A stepwise discriminant analysis reduced model dimensionality from 19 to 4 features. The final discriminant analysis model included the following variables: non-temporary implant, pre-op antibiotics, immunocompromised status, and gender. Overall, 72% of implant failure cases and 62% of intact implants were correctly identified by the resulting discriminant function. As the final predictive feature set is readily available in EDR, the resulting algorithm may be implemented as a clinical decision support module embedded into EDR to promote personalized approach in dental implant patients.

Designing for implementation: user-centered development and pilot testing of a behavioral economic-inspired electronic health record clinical decision support module

BackgroundCurrent guidelines recommend less aggressive target hemoglobin A1c (HbA1c) levels based on older age and lower life expectancy for older adults with diabetes. The effectiveness of electronic health record (EHR) clinical decision support (CDS) in promoting guideline adherence is undermined by alert fatigue and poor workflow integration. Integrating behavioral economics (BE) and CDS tools is a novel approach to improving adherence to guidelines while minimizing clinician burden.MethodsWe will apply a systematic, user-centered design approach to incorporate BE “nudges” into a CDS module and will perform user testing in two “vanguard” sites. To accomplish this, we will conduct (1) semi-structured interviews with key informants (n = 8), (2) a 2-h, design-thinking workshop to derive and refine initial module ideas, and (3) semi-structured group interviews at each site with clinic leaders and clinicians to elicit feedback on three proposed nudge module components (navigator section, inbasket refill protocol, medication preference list). Detailed field notes will be summarized by module idea and usability theme for rapid iteration. Frequency of firing and user action taken will be assessed in the first month of implementation via EHR reporting to confirm that module components and related reporting are working as expected as well as assess utilization. To assess the utilization and feasibility of the new tools and generate estimates of clinician compliance with the Choosing Wisely guideline for diabetes management in older adults, a 6-month, single-arm pilot study of the BE-EHR module will be conducted in six outpatient primary care clinics.DiscussionWe hypothesize that a low burden, user-centered approach to design will yield a BE-driven, CDS module with relatively high utilization by clinicians. The resulting module will establish a platform for exploring the ability of BE concepts embedded within the EHR to affect guideline adherence for other use cases.

The Role of Computerized Clinical Decision Support in Reducing Inappropriate Medication Administration During Epidural Therapy

Background: The use of epidural anesthesia has been shown to improve outcomes in the postoperative setting. To minimize risk of complications, avoiding certain medications with epidural anesthesia is advised. Objective: This study sought to determine the role of a computerized clinical decision support module implemented into the computerized physician order entry (CPOE) system on the incidence of administration of medications known to increase complications with epidural anesthesia. Methods: This study was a retrospective cohort chart review in adult patients receiving epidural anesthesia for at least 1 day. Patients were identified retrospectively and divided into 2 cohorts, those receiving an epidural 3 months prior to initiation of the module and those receiving an epidural 3 months following implementation. The primary end point was incidence of inappropriate medication administration before and after implementation. Complications of therapy were collected as secondary end points. Results: There was a reduction in the incidence of inappropriate medication administration in the postimplementation group versus the preimplementation group (6.3% vs 12.8%) although statistical significance was not achieved. In addition, the incidence of enoxaparin administration was significantly lower postimplementation than the preimplementation (0% vs 3.9%). There were no significant differences in other complications of therapy. Conclusions: This study demonstrated that application of decision support for this high-risk procedural population was able to eliminate the incidence of the most common inappropriate medication for epidural analgesia, enoxaparin. A reduction in incidence of other inappropriate medications was also observed; however, statistical significance was not reached. The use of computerized clinical decision support can be a powerful tool in reducing or ameliorating medication errors, and further study will be required to determine the most appropriate and effective implementation strategies.

A federated collaborative care cure cloud architecture for addressing the needs of multi-morbidity and managing poly-pharmacy (c3-cloud project)

A federated collaborative care cure cloud architecture for addressing the needs of multi-morbidity and managing poly-pharmacy (c3-cloud project)

An Introduction to the Centers for Disease Control and Prevention's Efforts to Prevent Older Adult Falls.

An Introduction to the Centers for Disease Control and Prevention's Efforts to Prevent Older Adult Falls.

Design and anticipated outcomes of the eMERGE-PGx project: a multicenter pilot for preemptive pharmacogenomics in electronic health record systems.

We describe here the design and initial implementation of the eMERGE-PGx project. eMERGE-PGx, a partnership of the eMERGE and PGRN consortia, has three objectives : 1) Deploy PGRNseq, a next-generation sequencing platform assessing sequence variation in 84 proposed pharmacogenes, in nearly 9,000 patients likely to be prescribed drugs of interest in a 1–3 year timeframe across several clinical sites; 2) Integrate well-established clinically-validated pharmacogenetic genotypes into the electronic health record with associated clinical decision support and assess process and clinical outcomes of implementation; and 3) Develop a repository of pharmacogenetic variants of unknown significance linked to a repository of EHR-based clinical phenotype data for ongoing pharmacogenomics discovery. We describe site-specific project implementation and anticipated products, including genetic variant and phenotype data repositories, novel variant association studies, clinical decision support modules, clinical and process outcomes, approaches to manage incidental findings, and patient and clinician education methods.

Use of a Computerized Decision Aid for ADHD Diagnosis: A Randomized Controlled Trial

To determine if implementing attention-deficit/hyperactivity disorder (ADHD) diagnosis and treatment guidelines in a clinical decision support system would result in better care, including higher rates of adherence to clinical care guidelines. We conducted a cluster randomized controlled trial in which we compared diagnosis and management of ADHD in 6- to 12-year-olds after implementation of a computer decision support system in 4 practices. Eighty-four charts were reviewed. In the control group, the use of structured diagnostic assessments dropped from 50% in the baseline period to 38% in the intervention period. In the intervention group, however, it rose from 60% to 81%. This difference was statistically significant, even after controlling for age, gender, and race (odds ratio of structured diagnostic assessment in intervention group versus control group = 8.0, 95% confidence interval 1.6-40.6). Significant differences were also seen in the number of ADHD core symptoms noted at the time of diagnosis. Our study was not powered to detect changes in care and management, but the percent of patients who had documented medication adjustments, mental health referrals, and visits to mental health specialists were higher in the intervention group than the control. The introduction of a clinical decision support module resulted in higher quality of care with respect to ADHD diagnosis including a prospect for higher quality of ADHD management in children. Future work will examine how to further develop the ADHD module and add support for other chronic conditions.

An Electronic System to Document Reasons for Medication Discontinuation and to Flag Unwanted Represcriptions in Geriatric Patients

Earlier studies have shown poor documentation of the reasons for medication discontinuation during hospitalization. Communication of reasons for discontinuation, e.g. adverse drug reactions (ADRs), to general practitioners and pharmacists was also found to be insufficient, leading to a rate of represcription after an ADR of 27% during the first 6 months after discharge. The aim of this study was to develop and implement a user-friendly electronic clinical decision support system to document reasons for medication discontinuation in hospitalized geriatric patients and to flag potentially undesirable represcriptions. The electronic clinical decision support module was developed using the Gaston framework. Pop-up windows force physicians to document reasons for medication discontinuation, and the system alerts physicians to the represcription of drugs withdrawn because of an ADR. We interviewed users regarding the acceptability of the system. On a 20-bed geriatric ward, the electronic system documented 2,228 medication discontinuations and the reasons for them over 11.4 months and alerted physicians to represcription of drugs associated with an ADR 20 times. The system was considered to be user-friendly. This clinical decision support system fulfilled its aims of documenting the reasons for medication discontinuation and alerting physicians to potentially undesirable represcription of previously withdrawn drugs. It was found to be user-friendly.

External Validation of Aminoglycoside Models Used in Web Calculators and Clinical Decision Support Systems After Laboratory Conversion to Serum Creatinine Isotope Dilution Mass Spectrometry Assay

BackgroundModels to predict gentamicin t½ from serum creatinine (SCr) estimated creatinine clearance (CrCl) are currently being incorporated into smart-device applications and clinical decision support modules without external validation. ObjectiveThe aim of this study was to determine whether such models remain viable after conversion to isotope dilution mass spectrometry (IDMS) SCr assay. MethodsThis study analyzed data from retrospective reviews of the medical records of nonobese adults receiving the aminoglycoside gentamicin and having ≥2 evaluable serum gentamicin concentrations after laboratory IDMS SCr conversion, from January 2008 to August 2009, at a tertiary care hospital in Florida. A literature search found a number of cited aminoglycoside models. This group of models was classified as group 1. The World Wide Web was also searched for the term aminoglycoside dosing calculators, with 6 models found and referred to as group 2. Predictive performance measures were used to compare the model results with the t½ calculated from gentamicin concentrations using the Nelder-Mead algorithm. ResultsThe records of 39 patients met the inclusion criteria (23 men, 16 women; age range, 18–86 years; range of estimated CrCl, 55–115 mL/min) and provided the “gold standard” aminoglycoside t½. A gentamicin t½ was predicted from several published models (group 1) and from other models used in online smart-device applications (group 2) and clinical decision modules. The median (interquartile range) root mean square errors were 0.48 (0.44 to 0.65) and 0.48 (0.45 to 0.70) hours from group-1 and -2 models, respectively. The median mean relative prediction errors were 9% (−14% to +13%) and 11% (+1% to +21%) from groups 1 and 2. The median mean absolute prediction errors were 21% (19% to 28%) and 21% (20% to 30%) from groups 1 and 2. Adjusting SCr by +20% improved the predictive ability in 3 of 12 cited models and in 5 of 6 models used in applications. ConclusionsModels to predict gentamicin t½ should be externally validated at one's institution before use. The findings from the present study provide a framework for conducting external validation.

Expert System Shells for Rapid Clinical Decision Support Module Development: An ESTA Demonstration of a Simple Rule-Based System for the Diagnosis of Vaginal Discharge

ObjectivesThis study demonstrates the feasibility of using expert system shells for rapid clinical decision support module development.MethodsA readily available expert system shell was used to build a simple rule-based system for the crude diagnosis of vaginal discharge. Pictures and 'canned text explanations' are extensively used throughout the program to enhance its intuitiveness and educational dimension. All the steps involved in developing the system are documented.ResultsThe system runs under Microsoft Windows and is available as a free download at http://healthcybermap.org/vagdisch.zip (the distribution archive includes both the program's executable and the commented knowledge base source as a text document). The limitations of the demonstration system, such as the lack of provisions for assessing uncertainty or various degrees of severity of a sign or symptom, are discussed in detail. Ways of improving the system, such as porting it to the Web and packaging it as an app for smartphones and tablets, are also presented.ConclusionsAn easy-to-use expert system shell enables clinicians to rapidly become their own 'knowledge engineers' and develop concise evidence-based decision support modules of simple to moderate complexity, targeting clinical practitioners, medical and nursing students, as well as patients, their lay carers and the general public (where appropriate). In the spirit of the social Web, it is hoped that an online repository can be created to peer review, share and re-use knowledge base modules covering various clinical problems and algorithms, as a service to the clinical community.

Electronic Health Records and the Management of Women at High Risk of Hereditary Breast and Ovarian Cancer

Currently, management strategies exist that can decrease the morbidity and mortality associated with having a BRCA1 or BRCA2 mutation. Unfortunately, the task of identifying these patients at high risk is a daunting challenge. This problem is intensified because Electronic Health Records (EHRs) today lack the functionality needed to identify these women and to manage those women once they have been identified. Numerous niche software programs have been developed to fill this gap. Unfortunately, these extremely valuable niche programs are prevented from being interoperable with the EHRs, on the premise that each EHR vendor will build their own programs. Effectively, in our efforts to adopt EHRs, we have lost sight of the fact that they can only have a major impact on quality of care if they contain structured data and if they interact with robust Clinical Decision Support (CDS) tools. We are at a cross roads in the development of the health care Information Technology infrastructure. We can choose a path where each EHR vendor develops each CDS module independently. Alternatively, we can choose a path where experts in each field develop external niche software modules that are interoperable with any EHR vendor. We believe that the modular approach to development of niche software programs that are interoperable with current EHRs will markedly increase the speed at which useful and functional EHRs that improve quality of care become a reality. Thus, in order to realize the benefits of CDS, we suggest vendors develop means to become interoperable with external modular niche programs.