Clinical Decision Support Tool Research Articles

Individual and System Level Factors Contributing to Guideline Non-Adherent Surgical Antibiotic Prophylaxis at a Tertiary Health Care System: A Qualitative Analysis

Background Antibiotics play a crucial role in preventing surgical site infections, yet adherence to Infectious Disease Society of America (IDSA) guidelines varies widely. This qualitative study aimed to explore factors influencing perioperative antibiotic administration and assess the potential impact of a clinical decision support (CDS) tool on guideline adherence. Methods In this qualitative study, perioperative personnel with diverse roles (surgeons, anesthesiologists, certified nurse anesthetists, trainees, and pharmacists) were interviewed using a semi-structured interview format from September 2023 through April 2024. Interviews were then analyzed for codes which were assigned to concepts using the constant comparison method for assessment of factors that were described as barriers or facilitators of guideline adherence. Results After piloting with three interviews, we conducted nine sessions with a total of 17 participants: 7 attending anesthesiologists, 3 resident trainees, 2 perioperative pharmacists, 3 Certified Registered Nurse Anesthetists (CRNAs), and 2 attending surgeons. Key themes emerged: (1) Limited familiarity with Infectious Disease Society of America (IDSA) antibiotic guidelines, (2) Lack of standardization and optimization of antibiotic decision-making process, (3) Challenges with managing beta-lactam allergies, (4) Difficulty optimizing vancomycin timing, and (5) Perceived benefit of a Clinical Decision Support (CDS) tool in enhancing workflow and guideline adherence. Conclusions Non-adherence to antibiotic guidelines in the perioperative setting often results from a lack of structured workflow. Our interviews provide a foundation for developing a clinical decision support tool tailored to provider needs, aiming to improve user satisfaction and promote better adherence to perioperative antibiotic guidelines.

CTN-0138: adaptation, implementation, and cluster randomized trial of a Community Pharmacy-Based Prescription Drug Monitoring Program Opioid Risk Assessment Tool—a protocol paper

Abstract Background As the opioid epidemic continues to have a major negative impact across the US, community pharmacies have come under scrutiny from legal systems attempting to hold them accountable for their role in over dispensing and lack of patient intervention. While the most available tool for monitoring patients’ opioid use is Prescription Drug Monitoring Programs (PDMP), these do not provide pharmacists with actionable information and decision support. Our study addresses this gap through three objectives: [1] incorporate validated opioid risk metric thresholds into a PDMP platform to create the Opioid Risk Reduction Clinical Decision Support (ORRCDS) tool; [2] assess ORRCDS’ ability to reduce patient opioid risk; [3] assess ORRCDS’ sustainability and viability for broader dissemination in community pharmacy. Methods For objective 1, our team is partnering with leadership from the largest US PDMP organization and a top-five pharmacy chain to implement ORRCDS into the pharmacy chain’s workflow following the Guideline Implementation with Decision Support (GUIDES) framework. For objective 2, our team will conduct a type-1 implementation mixed methods study using a 2-arm parallel group clustered randomized design. We anticipate enrolling ~ 6,600 patients with moderate and high opioid use risk during the 6-month enrollment phase across 80 pharmacies. This sample size will provide 96.3% power to detect a 5% or greater difference in responder rate between the intervention and control arm. Responders are patients with moderate-risk at baseline who reduce to low-risk or those with high-risk at baseline who reduce to moderate or low-risk at 180 days post last intervention. To accomplish objective 3, we will use the Consolidated Framework for Implementation Research (CFIR) to develop and execute cross-sectional qualitative interviews with pharmacists (n = 15), pharmacy leaders (n = 15), and PDMP leaders (n = 15) regarding long term adoption and sustainability of the ORRCDS tool. Conclusions A PDMP tool that addresses moderate- and high-risk opioid use is not available in community pharmacy. This study will implement ORRCDS in a large retail pharmacy chain that will include additional screening and guidance to pharmacy staff to address risky opioid medication use. Our results will make critical advancements for protecting patient health and addressing the opioid epidemic.

Evaluation of a clinical decision support alert to identify hepatic dysfunction and need for medication therapy adjustment in hospitalized patients.

In an effort to expedite the publication of articles, AJHP is posting manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. To optimize the hepatic dysfunction alert tool at our institution to identify appropriate patients and minimize irrelevant alerts. This single-center, retrospective review included adults hospitalized over a 1-month period for whom a hepatic dysfunction alert fired for a medication order placed in the electronic health record. The existing alert determines hepatic dysfunction based on laboratory tests. The primary objective was to determine the proportion of patients with an alert that was deemed to be clinically relevant. Alerts were considered relevant if the patient had a Child-Pugh score in class B or C and were ordered a medication with a hepatic warning from FDA or LiverTox. The performance of 14 alternative models was evaluated. A total of 1,541 alerts fired for 309 patients. Of these patients, 155 were randomly selected for the analysis, and the alert was deemed relevant in 86 patients (55%). Patients with relevant alerts were more likely to have documented liver disease and worsening measures on liver function tests. Of the alternative models evaluated, a model that excluded INR and albumin resulted in a 27% decrease in the number of alerts fired, of which 73% were relevant; however, it failed to identify 30% of patients with relevant hepatic dysfunction. None of the other models performed better. The existing hepatic dysfunction clinical decision support tool correctly identifies patients with relevant hepatic dysfunction only 55% of the time. Alternative models were able to improve the rate of relevant results, but not without missing patients with relevant hepatic dysfunction.

The intelligent diabetes telemonitoring using decision support to treat patients on insulin therapy (DiaTRUST) trial: study protocol for a randomized controlled trial

BackgroundDiabetes affects 10.5% of adults globally, with type 2 diabetes accounting for 90–95% of cases. Achieving optimal glycemic control is crucial yet challenging, particularly with insulin therapy, where 30–50% of patients fail to meet treatment targets. Telemedicine can improve diabetes management but generates vast amounts of data, burdening healthcare professionals. Integrating clinical decision support tools into telemonitoring systems may enhance care efficiency and glycemic control.MethodsThe trial is a multicenter 3-month, three-arm, open-label, randomized controlled trial. The trial aims to enroll 51 participants with type 2 diabetes on insulin therapy. Participants will be divided with a 3:1:1 ratio into telemonitoring with decision support, telemonitoring without decision support, and usual care groups. The study employs connected insulin pens, continuous glucose monitors (CGMs), and activity trackers to enable telemonitoring. Outcomes measured include CGM time in range, HbA1c, hypo- and hyperglycemia incidents, total daily insulin dose, body weight, treatment satisfaction, and adherence.DiscussionTelemonitoring with decision support has the potential to revolutionize diabetes management by offering personalized treatment suggestions, thereby reducing the burden on healthcare professionals, and improving patient outcomes. This study will provide valuable insights into the effectiveness of such an approach in achieving glycemic control in people with type 2 diabetes on insulin therapy. By evaluating both clinical outcomes and patient and healthcare professionals’ satisfaction, the study aims to contribute to the development of efficient, scalable telehealth solutions for diabetes care.Trial registrationClinicalTrials.gov NCT06185296. Registered on December 14, 2023.

Developing a clinical decision support framework for integrating predictive models into routine nursing practices in home health care for patients with heart failure.

The healthcare industry increasingly values high-quality and personalized care. Patients with heart failure (HF) receiving home health care (HHC) often experience hospitalizations due to worsening symptoms and comorbidities. Therefore, close symptom monitoring and timely intervention based on risk prediction could help HHC clinicians prevent emergency department (ED) visits and hospitalizations. This study aims to (1) describe important variables associated with a higher risk of ED visits and hospitalizations in HF patients receiving HHC; (2) map data requirements of a clinical decision support (CDS) tool to the exchangeable data standard for integrating a CDS tool into the care of patients with HF; (3) outline a pipeline for developing a real-time artificial intelligence (AI)-based CDS tool. We used patient data from a large HHC organization in the Northeastern US to determine the factors that can predict ED visits and hospitalizations among patients with HF in HHC (9362 patients in 12,223 care episodes). We examined vital signs, HHC visit details (e.g., the purpose of the visit), and clinical note-derived variables. The study identified critical factors that can predict ED visits and hospitalizations and used these findings to suggest a practical CDS tool for nurses. The tool's proposed design includes a system that can analyze data quickly to offer timely advice to healthcare clinicians. Our research showed that the length of time since a patient was admitted to HHC and how recently they have shown symptoms of HF were significant factors predicting an adverse event. Additionally, we found this information from the last few HHC visits before the occurrence of an ED visit or hospitalization were particularly important in the prediction. One hundred percent of clinical demographic profiles from the Outcome and Assessment Information Set variables were mapped to the exchangeable data standard, while natural language processing-driven variables couldn't be mapped due to their nature, as they are generated from unstructured data. The suggested CDS tool alerts nurses about newly emerging or rising risks, helping them make informed decisions. This study discusses the creation of a time-series risk prediction model and its potential CDS applications within HHC, aiming to enhance patient outcomes, streamline resource utilization, and improve the quality of care for individuals with HF. This study provides a detailed plan for a CDS tool that uses the latest AI technology designed to aid nurses in their day-to-day HHC service. Our proposed CDS tool includes an alert system that serves as a guard rail to prevent ED visits and hospitalizations. This tool can potentially improve how nurses make decisions and improve patient outcomes by providing early warnings about ED visits and hospitalizations.

Cost-effectiveness of clinical decision support to improve CKD outcomes among First Nations Australians

IntroductionThe Northern Territory (NT) is a hotspot for chronic kidney disease (CKD) and has a high incidence of kidney replacement therapy (KRT). The Territory Kidney Care clinical decision support tool (CDS) aims to improve diagnosis and management of CKD in remote NT, particularly amongst First Nations Australians. We model the cost-effectiveness of the CDS versus usual care. MethodsTaking a healthcare funder perspective, we modelled a cohort of people from remote NT at risk of or with CKD, as of 1 January 2017. A Markov cohort model was developed using 6 years of observed patient-level data (2017 to 2023), extrapolated to a 15-year time horizon. The CDS tool was modelled to improve CKD diagnosis (scenario 1), improve management (scenario 2), or improve both diagnosis and management (scenario 3). ResultsThe remote NT cohort consisted of 23,195 people, predominantly (89%) First Nations, with a mean age of 42. Scenario 3 (improved diagnosis and management) was most cost-effective at an incremental cost-effectiveness ratio (ICER) of $96,684 per patient avoiding KRT, $30,086 per patient avoiding death. Scenario 1 (improved diagnosis) was less cost-effective, and scenario 2 (improved management) was least cost-effective. The ICER per quality adjusted life years gained ranged from $3,427 (scenario 3) to $63,486 (scenario 2). ConclusionTerritory Kidney Care is highly cost-effective when it supports early diagnosis of CKD and increases optimal management in diagnosed patients. These results support investing in CDS tools, implemented in strong partnerships, to improve outcomes in settings with a high burden of CKD.

Widespread Adoption of Precision Anticancer Therapies After Implementation of Pathologist-Directed Comprehensive Genomic Profiling Across a Large US Health System.

Precision therapies and immunotherapies have revolutionized cancer care, with novel genomic biomarker-associated therapies being introduced into clinical practice rapidly, resulting in notable gains in patient survival. Despite this, there is significant variability in the utilization of tumor molecular profiling that spans the timing of test ordering, comprehensiveness of gene panels, and clinical decision support through therapy and trial recommendations. To standardize testing, we designed a pathologist-directed test ordering system at the time of diagnosis using a 523-gene DNA/RNA hybrid comprehensive genomic profiling (CGP) panel and extensive clinical decision support tools. To comprehensively characterize the clinical impact of this protocol, we developed a novel natural language processing (NLP)-based approach to extract clinical features from physician chart notes. We assessed test actionability rates, therapy choice, and outcomes across a set of 3,216 patients with advanced cancer. We observed 49% of patients had at least one actionable genomic biomarker-driven-approved and/or guideline-recommended targeted or immunotherapy (IO) and 53% of patients would have been eligible for a precision therapy clinical trial from three large basket trials. When assessing CGP versus an in silico 50-gene panel, 67% of tumors compared with 33% harbored actionable alterations including clinical trials. Among patients with 6 months or more of follow-up, over 52% received a targeted therapy (TT) or IO, versus 32% who received conventional chemotherapy alone. Furthermore, patients receiving TT had significantly improved overall survival compared with patients receiving chemotherapy alone (P < .001). Overall, these data represent a major shift in standard clinical practice toward molecularly guided treatments (targeted and immunotherapies) over conventional systemic chemotherapy. As guidelines continue to evolve and more precision therapeutics gain approval, we expect this gap to continue to widen.

Creating Perinatal Nursing Care Plans Using ChatGPT: A Pathway to Improve Nursing Care Plans and Reduce Documentation Burden.

Extensive time spent on documentation in electronic health records (EHRs) impedes patient care and contributes to nurse burnout. Artificial intelligence-based clinical decision support tools within the EHR, such as ChatGPT, can provide care plan recommendations to the perinatal nurse. The lack of explicit methodologies for effectively integrating ChatGPT led to our initiative to build and demonstrate our ChatGPT-4 prompt to support nurse care planning. We employed our process model, previously tested with 22 diverse medical-surgical patient scenarios, to generate a tailored prompt for ChatGPT-4 to produce care plan suggestions for an exemplar patient presenting with preterm labor and gestational diabetes. A comparative analysis was conducted by evaluating the output against a "nurse-generated care plan" developed by our team of nurses on content alignment, accuracy of standardized nursing terminology, and prioritization of care. ChatGPT-4 delivered suggestions for nursing diagnoses, interventions, and outcomes comparable to the "nurse-generated care plan." It accurately identified major care areas, avoided irrelevant or unnecessary recommendations, and identified top priority care. Of the 24 labels generated by ChatGPT-4, 16 correctly utilized standardized nursing terminology. This demonstration of the use of our ChatGPT-4 prompt illustrates the potential of leveraging a large language model to assist perinatal nurses in creating care plans. The next steps are improving the accuracy of ChatGPT-4-generated standardized nursing terminology and integrating our prompt into EHRs. This work supports our broader goal of enhancing patient outcomes while mitigating the burden of documentation that contributes to nurse burnout.

Health Care Professionals' Experience of Using AI: Systematic Review With Narrative Synthesis.

There has been a substantial increase in the development of artificial intelligence (AI) tools for clinical decision support. Historically, these were mostly knowledge-based systems, but recent advances include non-knowledge-based systems using some form of machine learning. The ability of health care professionals to trust technology and understand how it benefits patients or improves care delivery is known to be important for their adoption of that technology. For non-knowledge-based AI tools for clinical decision support, these issues are poorly understood. The aim of this study is to qualitatively synthesize evidence on the experiences of health care professionals in routinely using non-knowledge-based AI tools to support their clinical decision-making. In June 2023, we searched 4 electronic databases, MEDLINE, Embase, CINAHL, and Web of Science, with no language or date limit. We also contacted relevant experts and searched reference lists of the included studies. We included studies of any design that reported the experiences of health care professionals using non-knowledge-based systems for clinical decision support in their work settings. We completed double independent quality assessment for all included studies using the Mixed Methods Appraisal Tool. We used a theoretically informed thematic approach to synthesize the findings. After screening 7552 titles and 182 full-text articles, we included 25 studies conducted in 9 different countries. Most of the included studies were qualitative (n=13), and the remaining were quantitative (n=9) and mixed methods (n=3). Overall, we identified 7 themes: health care professionals' understanding of AI applications, level of trust and confidence in AI tools, judging the value added by AI, data availability and limitations of AI, time and competing priorities, concern about governance, and collaboration to facilitate the implementation and use of AI. The most frequently occurring are the first 3 themes. For example, many studies reported that health care professionals were concerned about not understanding the AI outputs or the rationale behind them. There were issues with confidence in the accuracy of the AI applications and their recommendations. Some health care professionals believed that AI provided added value and improved decision-making, and some reported that it only served as a confirmation of their clinical judgment, while others did not find it useful at all. Our review identified several important issues documented in various studies on health care professionals' use of AI tools in real-world health care settings. Opinions of health care professionals regarding the added value of AI tools for supporting clinical decision-making varied widely, and many professionals had concerns about their understanding of and trust in this technology. The findings of this review emphasize the need for concerted efforts to optimize the integration of AI tools in real-world health care settings. PROSPERO CRD42022336359; https://tinyurl.com/2yunvkmb.

Prevalence and prediction of masked uncontrolled hypertension in patients recently hospitalised for an acute coronary syndrome

Abstract Background Masked uncontrolled hypertension (MUCH) is defined as normal office blood pressure (BP) but elevated out-of-office BP in patients on antihypertensive treatment. MUCH is associated with similar cardiovascular risk as sustained hypertension and is clinically challenging since this often remains undetected without out-of-office BP measurements. Purpose To study the prevalence of MUCH following an acute coronary syndrome and to utilise machine learning methods to develop prediction models for identifying MUCH. Methods Ambulatory 24-h BP measurement (ABPM) was performed in 100 patients attending the cardiology outpatient clinic at a Swedish university hospital following an acute coronary syndrome, as part of a study which screened for co-morbidities. From the SWEDEHEART registry, 106 variables during the hospital care period and subsequent follow-up visit (after 6-10 weeks) were pre-processed including filtering on 5 or more missing values and zero or near-zero variance. Variable importance for the prediction of MUCH (office BP &amp;lt; 140/90 mm Hg at ABPM start but mean 24-h BP ≥ 130/80 mm Hg) was assessed using the Boruta and least absolute shrinkage and selection operator (LASSO) machine learning algorithms. Subsequently, logistic regression, LASSO and random forest models using different variable subsets were evaluated by receiver operating characteristic area under the curve (AUC) in repeated cross-validation. Results Age was 62.0±8.4 years, 74% male, 54% had NSTEMI and 46% STEMI. The follow-up visit and ABPM were performed at median 7 and 11 weeks, respectively, after hospital discharge. Among 90 patients with complete data and ABPM recordings, 31 had mean 24-h BP above target levels, of which 18 were identified with MUCH. Patients with MUCH had lower eGFR (68±11 vs 76±12 ml/min/1.73m², P=0.009), and more often a history of hypertension (89 vs 53%, P=0.005) and diabetes mellitus (44 vs 11%, P=0.003). In total, 65 variables where eligible for machine learning after filtering. Boruta and LASSO identified pulse pressure at the follow-up visit, serum creatinine, diabetes mellitus and history of hypertension as important predictors. Random forest, logistic regression and LASSO showed mean AUC 0.826, 0.822, and 822, respectively, in cross validation using these predictors. Conclusions In this small trial, one in five had MUCH at follow-up after an acute coronary syndrome, which highlights the importance of out-of-office BP measurements. The easily accessible measures of pulse pressure at the follow-up visit, serum creatinine, diabetes mellitus and history of hypertension were identified as important predictors of MUCH. A simple prediction model may be used as a clinical decision support tool after appropriate external validation.

Pharmacologic treatment of hypertension guided by non-invasive haemodynamics in primary care improves blood pressure control

Abstract Background Current guidelines on hypertension (HTN) provide blood pressure (BP) targets and therapeutic algorithms but ignore the potential to treat individual patients according to their haemodynamic profile. We have shown that use of non-invasive haemodynamic information obtained by impedance cardiography (ICG) can improve BP control in the primary care setting. Purpose To investigate whether improved rates of BP control by matching patients’ non-invasive haemodynamics to specific pharmacologic treatments and increasing patient engagement translates into improved clinical outcome measures. Methods Electronic medical records (EMR) were obtained for 14,698 patients from two US primary care groups between 2014 and 2023. ICG was done when BP exceeded 140/90 mmHg. Haemodynamic measurements included mean arterial pressure (MAP), cardiac index (CI), cardiac power index (CPI), total peripheral resistance index (TPRI), stroke index (SI) and heart rate (HR) (Figure 1). Haemodynamic ICG profiles were classified as: Vasoconstriction, Hyperdynamic, or Mixed pattern. Printed clinical decision support (CDS) tools and later an EMR integrated CDS application were used to communicate recommendations to physicians. Printed reports were shared with patients to increase their engagement. Pharmacological therapy was tailored based on haemodynamic information. Rates of successful BP treatment and the occurrence of myocardial infarction (MI) or stroke were tracked through the EMR. Results Of 14,698 patients, 50% were women, 17% were Black and 17% were aged 18-49 years, 45% aged 50-69 years, and 38% age ≥ 70 years. A total of 21,246 ICGs were performed classifying patients as Vasoconstriction 47%, Hyperdynamic with high heart rate (HR) or high stroke index (SI) 24%, and Mixed Haemodynamic (combination of Vasoconstriction and Hyperdynamic) 29% (Figure 1). Demographic features were not strongly associated with haemodynamic classification. Within 2-3 years of inclusion, &amp;gt;85% of patient achieved BP control (&amp;lt;140/90 mmHg), which was sustained during follow-up. Over a median (IQR) follow-up of 8 (2016-2023) years, there were 14 (5) MI and 34 (16) strokes. These event rates appear to be lower than those reported in other large cohorts of patients with HTN. Conclusions Treating patients with HTN according to their individual haemodynamic profile is associated with high rates of BP control. Further analysis will determine whether the rates of MI, stroke and death are lower than expected based on the patients baseline risk profile.Haemodynamic Status (ICG Test Results)

Comorbidity neural network model for personalised recommendations in cardiometabolic risk factor management: towards early precision medicine in routine clinical practice

Abstract Background and Aims Hypertension and hypercholesterolaemia often develop in tandem to confer a risk of cardiovascular disease that may be more than additive. The present study explored early comorbid therapeutic intervention, i.e., beyond individual disease silos, while minimising data bias to provide clinical decision support tools that are portable across clinics. Methods A neural network was created to reproduce UK national clinical guidelines with an accuracy higher than 95%. Relying on real-world evidence from the UK primary care Clinical Practice Research Datalink electronic health record resource, a transfer learning methodology was then applied to achieve recommended risk factor goal attainment after two years. Shapley values derived from game theory were used to define similar digital twin cohorts, and to evaluate individualised recommendations that deviated from national clinical guidelines by rejecting a no-benefit hypothesis retrospectively in a classical proportion test. The methodology was ported to an independent hold-out dataset with anonymized records from six primary care clinics in the South of England. Results The adult patient population (n=469,496, mean+SD age 61+11yr; M 56% vs F 44%; primary 84% vs secondary prevention 16%) included 101,255 diagnosed for hypertension and 112,180 for cholesterol management. While a majority of the 52,504 therapeutic decisions in a test set agree with single morbidity guidelines, for 4639 deviations from the guidance, a significant minority was identified for whom alternative therapy was recommended. Rejecting a no-clinical benefit hypothesis at the 95% confidence level in a retrospective analysis, 1367 decisions showed statistically significant better outcomes over guidelines, for example by escalating anti-hypertensive therapies for patients receiving statin therapy (1085) or by complementing anti-hypertensive therapy with a statin (158). Similar findings were obtained when tested in a hold-out dataset with 13,725 decisions for 6531 patients. Conclusions The results support the contention that machine learning can identify patient subgroups for whom comorbid intervention deviating from clinical guidelines may be appropriate. A novel aspect of the study is the demonstration of clinically portable and actionable application of machine learning in the context of comorbid cardiometabolic diseases. The results represent practical steps towards personalised precision medicine for cardiovascular comorbidity in routine clinical practice.

Iterative Development of a Clinical Decision Support Tool to Enhance Naloxone Co-Prescribing.

Background Opioid overdoses have contributed significantly to mortality in the United States. Despite long-standing recommendations from the Centers for Disease Control and Prevention to co-prescribe naloxone for patients receiving opioids who are at high risk of overdose, compliance with these guidelines has remained low. Objectives The objective of this study was to develop and evaluate a hospital-wide electronic health record (EHR)-based clinical decision support (CDS) tool designed to promote naloxone co-prescription for high-risk opioids. Methods We employed an iterative approach to develop a point-of-order, interruptive EHR alert as the primary intervention and assessed naloxone prescription rates, EHR efficiency metrics, and barriers to adoption. Data was obtained from our EHR's clinical data warehouse and analyzed using statistical process control and Chi-square analyses to assess statistically significant differences in prescribing rates during the intervention periods. Results The initial implementation phase of the intervention, spanning from April 2019 to May 2022, yielded a nearly 3-fold increase in the proportion of high-risk patients receiving naloxone, rising from 13.4% [95% CI, 12.9% - 13.8%] to 36.4% [95% CI, 35.2% - 37.5%; p = 1 x 10-38]. Enhancements to the CDS design and logic during the subsequent iteration's study period, June 2022 and December 2023, reduced the number of CDS triggers by more than 30-fold while simultaneously driving an additional increase in naloxone receipt to 42.7% [95% CI, 40.6% - 44.8%; p = 2 x 10-5]. The efficiency of the CDS demonstrated marked improvement, with prescribers accepting the naloxone co-prescription recommendation provided by the CDS in 41.1% of the encounters in version two, compared to 6.2% in version one (p = 6 x 10-9). Conclusion This study offers a sustainable and scalable model to address low rates of naloxone co-prescription and may also be used to target other opportunities for improving guideline-concordant prescribing practices.

Extubation Advisor: Implementation and Evaluation of A Novel Extubation Clinical Decision Support Tool.

Extubation Advisor (EA) is a novel software tool that generates a synoptic report for each Spontaneous Breathing Trial (SBT) conducted to inform extubation decision-making. To assess bedside EA implementation, perceptions of utility, and identify barriers and facilitators of use. We conducted a phase I mixed-methods interventional study in three mixed intensive care unit (ICUs) in two academic hospitals. We interviewed critical care physicians (MDs) and respiratory therapists (RTs) regarding user-centered design principles and usability. We evaluated our ability to consent participants (feasibility threshold 50%), capture complete data (threshold 90%), generate and review EA reports in real-time (thresholds 75% and 80%, respectively), and MD perception of tool usefulness (6-point Likert scale). We analyzed interview transcripts using inductive coding to identify facilitators and barriers to EA implementation and perceived benefit of tool use. We enrolled 31 patients who underwent 70 SBTs. Although consent rates [31/31 (100%], complete data capture [68/68 (100%)], and EA report generation [68/70 (97.1%)] exceeded feasibility thresholds, reports were reviewed by MDs for [55/70 (78.6%)] SBTs. Mean MD usefulness score was 4.0/6. Based on feedback obtained from 36 interviews (15 MDs, 21 RTs), we revised the EA report twice and identified facilitators (ability to track patient progress, enhance extubation decision-making, and provide support in resource-limited settings) and barriers (resource constraints, need for education) to tool implementation. Half of respondents (9 MDs, 9 RTs; combined 50%) perceived definite or potential benefit to EA tool use. This is the first study of a waveform-based variability-derived, predictive clinical decision support tool evaluated in adult ICUs. Our findings support the feasibility of integrating the EA tool into bedside workflow. Clinical trials are needed to assess the utility of the EA tool in practice and its impact on extubation decision-making and outcomes. NCT04708509.

Calibration, Clinical Utility and Specificity of Clinical Decision Support Tools in Inflammatory Bowel Disease

Background and AimsClinical decision support tools (CDSTs) have been developed to predict response to vedolizumab (VDZ) and ustekinumab (UST) in Crohn’s disease (CD) and ulcerative colitis (UC). In addition to assessing their discrimination performance, our study aimed to evaluate their calibration, clinical utility and specificity. MethodsWe included 280 CD and 218 UC patients initiating VDZ, and 194 CD patients initiating UST. We assessed discrimination by comparing rates of effectiveness outcomes between response probability groups forecasted by CDSTs. Calibration curves and decision curve analysis evaluated the calibration and clinical utility of VDZ-CDSTs. Additionally, we examined the agreement between UST-CDST and VDZ-CDST in assigning response probability groups among CD patients starting UST. ResultsIn the overall cohort, CDSTs allocated 7.2%, 50.0% and 42.8% of the patients to the low, intermediate and high response probability groups, respectively. VDZ-CDSTs groups demonstrated significant differences in the rates of clinical and endoscopic response and remission, while UST-CDST groups showed significant discrimination only for clinical remission. Although VDZ-CDSTs overestimated clinical remission rates, they more accurately predicted rates of VDZ persistence without need for surgery or dose escalation. Compared to empirically treating all patients with VDZ, VDZ-CDSTs yielded higher net benefits in selecting patients who would continue VDZ without need for surgery or dose escalation. Finally, the agreement between UST-CDST and VDZ-CDST in predicting response was 73.7%. ConclusionVDZ-CDSTs significantly discriminated response to VDZ and were more beneficial in identifying patients who would continue therapy without requiring surgery or dose escalation, compared to treating all patients empirically.

Design and development of a machine-learning-driven opioid overdose risk prediction tool integrated in electronic health records in primary care settings

BackgroundIntegrating advanced machine-learning (ML) algorithms into clinical practice is challenging and requires interdisciplinary collaboration to develop transparent, interpretable, and ethically sound clinical decision support (CDS) tools. We aimed to design a ML-driven CDS tool to predict opioid overdose risk and gather feedback for its integration into the University of Florida Health (UFHealth) electronic health record (EHR) system.MethodsWe used user-centered design methods to integrate the ML algorithm into the EHR system. The backend and UI design sub-teams collaborated closely, both informed by user feedback sessions. We conducted seven user feedback sessions with five UF Health primary care physicians (PCPs) to explore aspects of CDS tools, including workflow, risk display, and risk mitigation strategies. After customizing the tool based on PCPs’ feedback, we held two rounds of one-on-one usability testing sessions with 8 additional PCPs to gather feedback on prototype alerts. These sessions informed iterative UI design and backend processes, including alert frequency and reappearance circumstances.ResultsThe backend process development identified needs and requirements from our team, information technology, UFHealth, and PCPs. Thirteen PCPs (male = 62%, White = 85%) participated across 7 user feedback sessions and 8 usability testing sessions. During the user feedback sessions, PCPs (n = 5) identified flaws such as the term “high risk” of overdose potentially leading to unintended consequences (e.g., immediate addiction services referrals), offered suggestions, and expressed trust in the tool. In the first usability testing session, PCPs (n = 4) emphasized the need for natural risk presentation (e.g., 1 in 200) and suggested displaying the alert multiple times yearly for at-risk patients. Another 4 PCPs in the second usability testing session valued the UFHealth-specific alert for managing new or unfamiliar patients, expressed concerns about PCPs’ workload when prescribing to high-risk patients, and recommended incorporating the details page into training sessions to enhance usability.ConclusionsThe final backend process for our CDS alert aligns with PCP needs and UFHealth standards. Integrating feedback from PCPs in the early development phase of our ML-driven CDS tool helped identify barriers and facilitators in the CDS integration process. This collaborative approach yielded a refined prototype aimed at minimizing unintended consequences and enhancing usability.

Potential for an Electronic Clinical Decision Support Tool to Support Appropriate Antibiotic Use for Pediatric Diarrhea Among Village Doctors in Bangladesh.

Potential for an Electronic Clinical Decision Support Tool to Support Appropriate Antibiotic Use for Pediatric Diarrhea Among Village Doctors in Bangladesh.

Competing and Noncompeting Risk Models for Predicting Kidney Allograft Failure.

Prognostic models are becoming increasingly relevant in clinical trials as potential surrogate endpoints, and for patient management as clinical decision support tools. However, the impact of competing risks on model performance remains poorly investigated. We aimed to carefully assess the performance of competing risk and noncompeting risk models in the context of kidney transplantation, where allograft failure and death with a functioning graft are two competing outcomes. We included 11,046 kidney transplant recipients enrolled in 10 countries. We developed prediction models for long-term kidney graft failure prediction, without accounting (i.e., censoring) and accounting for the competing risk of death with a functioning graft, using Cox, Fine-Gray, and cause-specific Cox regression models. To this aim, we followed a detailed and transparent analytical framework for competing and noncompeting risk modelling, and carefully assessed the models' development, stability, discrimination, calibration, overall fit, clinical utility, and generalizability in external validation cohorts and subpopulations. More than 15 metrics were used to provide an exhaustive assessment of model performance. Among 11,046 recipients in the derivation and validation cohorts, 1,497 (14%) lost their graft and 1,003 (9%) died with a functioning graft after a median follow-up post-risk evaluation of 4.7 years (IQR 2.7-7.0). The cumulative incidence of graft loss was similarly estimated by Kaplan-Meier and Aalen-Johansen methods (17% versus 16% in the derivation cohort). Cox and competing risk models showed similar and stable risk estimates for predicting long-term graft failure (average mean absolute prediction error of 0.0140, 0.0138 and 0.0135 for Cox, Fine-Gray, and cause-specific Cox models, respectively). Discrimination and overall fit were comparable in the validation cohorts, with concordance index ranging from 0.76 to 0.87. Across various subpopulations and clinical scenarios, the models performed well and similarly, although in some high-risk groups (such as donors over 65 years old), the findings suggest a trend towards moderately improved calibration when using a competing risk approach. Competing and noncompeting risk models performed similarly in predicting long-term kidney graft failure.

Ordering and Utilization of Peripheral Blood Flow Cytometry in an Academic Medical Center

Abstract Introduction/Objective The American Society for Clinical Pathology and the American Board of Internal Medicine’s Choosing Wisely campaign have developed best practice utilization guidelines for laboratory testing. Wisconsin Diagnostic Laboratories and Medical College of Wisconsin leadership noticed an increase in inappropriate peripheral blood flow cytometry testing in the last two years. An intervention was developed to help reduce inappropriate testing requests. Methods/Case Report The laboratory implemented a clinical decision support tool in the electronic medical record system that looked at patient diagnosis, history of stem cell transplant, and recommendations from pathology to help improve utilization of peripheral blood flow cytometry testing. Based on patient history, flow cytometry testing would move forward, or an alternative order of a peripheral blood pathology smear review with reflex to flow cytometry was offered. Pathologists would reflex flow cytometry if abnormalities were present by light microscopy or predetermined reflexing criteria were met. Results (if a Case Study enter NA) 314 cases were included for analysis. The intervention reduced volumes of peripheral blood flow cytometry in patients without a history of hematologic malignancy by 49.1% (p=&amp;lt;0.001). Appropriate utilization increased from 47.0% in the pre-intervention period to 80.4% in the post intervention period (p=&amp;lt;0.001). Significant diagnosis rate increased from 42.5% to 50.0% (p=.261). This resulted in a cost savings of $12,232 for the health system during the intervention period. Conclusion Clinical decision support based utilization efforts provide strong and consistent interventions to reduce the unnecessary and inappropriate ordering of peripheral blood flow cytometry.

Barriers and facilitators of the use of clinical informatics resources to facilitate pharmacogenomic implementation in resource-limited settings.

Understand perceived barriers to and facilitators of using clinical informatics applications for pharmacogenomic (PGx) implementation in resource-limited settings. We conducted a qualitative research study using a semi-structured interview guide informed by the Consolidated Framework for Implementation Research (CFIR). Interview questions assessed CFIR contextual determinants related to: electronic health record (EHR) infrastructure; clinical informatics personnel and resources; EHR integration of PGx test results; PGx clinical decision support (CDS) tools; institutional resources; and partner receptivity. Transcripts were coded and analyzed to identify themes. We interviewed 24 clinical informaticists and executive leaders working in rural or underserved health care settings in Montana (n = 15) and Colorado (n = 9) and identified three major themes: (1) EHR infrastructure limitations, (2) insufficient supporting resources, and (3) unique contextual considerations for resource-limited settings. EHR infrastructure limitations included limited agency related to EHR build and interoperability concerns. Theme 1 highlighted challenges associated with integrating structured data into the EHR and inadequate vendor support. Theme 2 included limited familiarity with PGx across the care team, cost concerns, and allocation of non-financial resources. Theme 3 highlighted perceptions about the clinical utility of PGx within rural and underrepresented populations. Potential facilitators, such as being able to act nimbly, were found to coexist among the reported barriers. Our results provide insight into the clinical informatics infrastructure in resource-limited settings and identify unique considerations for clinical informatics-facilitated PGx implementation. Future efforts in these settings should consider innovative partnerships and strategies to leverage facilitators and minimize barriers associated with integrating PGx CDS applications.