Computer-based Clinical Decision Support System Research Articles

Nursing Diagnosis Accuracy in Nursing Education: Clinical Decision Support System Compared With Paper-Based Documentation-A Before and After Study.

Computer-based technologies have been widely used in nursing education, although the best educational modality to improve documentation and nursing diagnostic accuracy using electronic health records is still under investigation. It is important to address this gap and seek an effective way to address increased accuracy around nursing diagnoses identification. Nursing diagnoses are judgments that represent a synthesis of data collected by the nurse and used to guide interventions and to achieve desirable patients' outcomes. This current investigation is aimed at comparing the nursing diagnostic accuracy, satisfaction, and usability of a computerized system versus a traditional paper-based approach. A total of 66 nursing students solved three validated clinical scenarios using the NANDA-International terminologies traditional paper-based approach and then the computer-based Clinical Decision Support System. Study findings indicated a significantly higher nursing diagnostic accuracy ( P < .001) in solving cancer and stroke clinical scenarios, whereas there was no significant difference in acute myocardial infarction scenario. The use of the electronic system increased the number of correct diagnostic indicators ( P < .05); however, the level of students' satisfaction was similar. The usability scores highlighted the need to make the electronic documentation systems more user-friendly.

Effect on thromboprophylaxis among hospitalized patients using a system-wide multifaceted quality improvement intervention: Rationale and design for a multicenter cluster randomized clinical trial in China

BackgroundVenous thromboembolism (VTE) is a life-threatening disease that can affect each hospitalized patient. But the current in-hospital thromboprophylaxis remains suboptimal and there exists a large gap between clinical practice and guideline-recommended care in China.MethodsTo facilitate implementation of guideline recommendations, we conduct a multicenter, adjudicator-blinded, cluster-randomized clinical trial, aiming to assess the effectiveness of a system-wide multifaceted quality improvement (QI) strategy on VTE prophylaxis improvement and thromboembolism reduction in clinical setting. Hospitals are randomized into intervention or control group. In intervention group, hospitals receive the concept of appropriate in-hospital thromboprophylaxis plus a multifaceted QI which encompasses four components: (1) an electronic alert combining computer-based clinical decision support system and electronic reminders, (2) appropriate prophylaxis based on dynamic VTE and bleeding risk assessments, (3) periodical audit and interactive feedback on performance, (4) strengthened training and patient education. In control, hospitals receive the concept of recommended prophylaxis alone without QI. Thromboprophylaxis will be at the discretion of hospitals and conducted as usual. With a final sample size of 5760 hospitalized patients in 32 hospitals on mainland China, this trial will examine the effect of QI on improvement in thromboprophylaxis and patient-centered outcomes. This is an open-label trial that patients and healthcare professionals will know group allocation after enrollment, but endpoint adjudicators and statisticians will be blinded. RCT# NCT04211181ConclusionsThe system-wide multifaceted QI intervention is expected to facilitate implementation of recommended VTE prophylaxis in hospital, thereafter reducing VTE incidence and relevant adverse events among hospitalized patients in China.

Computational modeling of bicuspid aortopathy: Towards personalized risk strategies

This paper describes current advances on the application of in-silico for the understanding of bicuspid aortopathy and future perspectives of this technology on routine clinical care. This includes the impact that artificial intelligence can provide to develop computer-based clinical decision support system and that wearable sensors can offer to remotely monitor high-risk bicuspid aortic valve (BAV) patients. First, we discussed the benefit of computational modeling by providing tangible examples of in-silico software products based on computational fluid-dynamic (CFD) and finite-element method (FEM) that are currently transforming the way we diagnose and treat cardiovascular diseases. Then, we presented recent findings on computational hemodynamic and structural mechanics of BAV to highlight the potentiality of patient-specific metrics (not-based on aortic size) to support the clinical-decision making process of BAV-associated aneurysms. Examples of BAV-related personalized healthcare solutions are illustrated.

Simple and Elaborated Clinician Reminder Prompts for Human Papillomavirus Vaccination: A Randomized Clinical Trial

ObjectiveTo evaluate the effects of simple and elaborated health care provider (HCP) reminder prompts on human papillomavirus (HPV) vaccine initiation rates. MethodsTwenty-nine pediatric HCPs serving 5 pediatric clinics were randomized to 1 of 3 arms: 1) usual practice control, 2) simple reminder prompt, and 3) elaborated reminder prompt, which included suggested language for recommending the early adolescent platform vaccines. Prompts were delivered via a computer-based clinical decision support system deployed in the 5 clinics. Eligible patients were ages 11 to 13 years, had not received HPV vaccine, and were due for meningococcal ACWY (MenACWY) vaccine and/or the tetanus, diphtheria, and pertussis booster (Tdap). Receipt of HPV vaccine was determined via automated queries sent to the Indiana immunization registry. Data were analyzed via logistic regression models, with generalized estimating equations used to account for the clustering of patients within HCPs. ResultsTen HCPs in the control group saw 301 patients, 8 HCPs in the simple prompt group saw 124, and 11 HCPs in the elaborated prompt group saw 223. The elaborated prompt arm had a higher rate of HPV vaccination (62%) than the control arm (45%): adjusted odds ratio, 2.76; 95% confidence interval, 1.07 to 7.14. The simple prompt arm did not differ significantly from the control arm with respect to HPV vaccine initiation, which might have been because of the small sample size for this arm. MenACWY and Tdap rates did not vary across the 3 arms. ConclusionsResults suggest that an elaborated HCP-targeted reminder prompt, with suggested recommendation language, might improve rates of HPV vaccine initiation.

Barriers and Facilitators to Clinical Decision Support Systems Adoption: A Systematic Review

The objective of the study was to identify potential barriers and facilitators to improve clinical practice using computer-based Clinical Decision Support System (CDSS). Studies published since 2000 were found using PubMed database, PsychInfo, CINAHL, EBSCO host database, and Google scholar. Twenty-six relevant publications were examined. Thirty-five unique barriers and twenty-five unique facilitators were identified in the literature as important determinants of CDSS’s adoption in clinical practice. The list of barriers and facilitators collected from each study were then organized under the four dimensions of The Unified Theory of Acceptance and Use of Technology (UTAUT) model: performance expectancy, effort expectancy, social influence, and facilitating conditions. Some of the important barriers to CDSS use include; lack of time or time constraints, economic constraints (e.g., finance and resources), lack of knowledge of system or content, reluctance to use system in front of patients, obscure workflow issues, less authenticity or reliability of information, lack of agreement with the system, and physician or user attitude toward the system. The study contributes immensely to the literature by identifying the important barriers and facilitators of CDSS.

Improving Recognition, Diagnosis, and Management Of Heparin Induced Thrombocytopenia By Implementing a Computer-Based Clinical Decision Support System

IntroductionHeparin induced thrombocytopenia (HIT) is often not considered as a potential etiology of thrombocytopenia. The gradual 5 to 14 day decline in platelet count (PC) may not be easily recognized by busy clinicians. The life-threatening complications of HIT are potentially preventable with prompt recognition and management. Implementation of computer-based clinical decision support systems (CDSS) may aid in addressing these issues. Such systems have shown promise in increasing provider recognition, appropriate testing, and management of a variety of conditions. MethodsWe developed, implemented and evaluated a CDSS designed to identify patients at risk for HIT. The CDSS was integrated into the electronic medical record (Centricity Enterprise, GE) at Mayo Clinic Rochester. The CDSS identified inpatients with recent or active use of heparin medications, who experienced a 50% PC drop. For such patients, the system generated an electronic message alerting their care team of the 50% PC drop and asked them to consider the possibility of HIT. A link to a website with recommendations for the diagnosis and management of HIT was included with the alert. Providers were encouraged to assess for HIT using the 4Ts Score and, if indicated, the anti-heparin/platelet factor 4 (PF4) antibody assay.We performed a retrospective chart review of consecutive patients identified by the system and equal number of randomly generated controls that did not trigger alerts. The accuracy of the algorithm was assessed and errors were analyzed for clinical significance. Patient risk of HIT was evaluated by using the 4Ts Score and the HIT Expert Probability (HEP) Score. Alert effect was classified as:1) Objective an action (discontinuing heparin, testing for HIT antibodies, subspecialty consult for HIT) and/or documentation (discussing the possibility of HIT) within three days after the alert had been received.2) Probable: new documentation of an explanation for thrombocytopenia without mention of HIT or documentation or action more than three days after the alert.3) None: no clear action or change in documentation. ResultsOver the study period, 2,785 patients had a total of 37,060 PC (13.31 PC/patient) and the CDSS triggered a total of 124 alerts. About 10% of alerted clinicians reviewed the website with recommendations on the management of HIT. A total of 117 patients generating alerts were compared to 124 controls. Demographics between the two groups were similar. The CDSS had a 95% sensitivity for accurately detecting a 50% platelet drop for inpatients on heparin. The specificity was 74%.The Objective alert effect was found in 21% of the cases (16% of providers changed their management and 5% documented that HIT was felt to be unlikely). The most common actions taken after receiving the alert were obtaining a HIT antibody assay, withholding heparin, consulting a subspecialty service, and/or changing anticoagulants. The Probable alert effect was 14% of the cases. HIT had been considered before the alert was sent in 11% of patients. Alert effect was classified as None for the remaining 54% of patients.Anti-heparin/PF4 testing for HIT was ordered for 25% of the intervention patients compared to 3% of controls. For the intervention group, PF4 was negative for 86% of tested patients, equivocal for 10%, and positive in 3%. All PF4 tests were negative in the control group.4Ts score was greater than or equal to 4 in 38% of patients and averaged 3.1 (range 7 to 0). HEP score averaged 4 (range 14 to -4). Risk calculations showed a trend to higher risk with therapeutic heparin compared to prophylactic heparin preparations. HIT risk scores were comparable by admitting service and diagnosis. ConclusionsOur CDSS successfully identified upwards of 95% of inpatients at risk for HIT. However, approximately 26% of the alerts were false positives. Only a small proportion of clinicians accessed the website with recommendations for the diagnosis and management of HIT but patients with a suspected HIT were managed appropriately. Of the patients triggering a HIT alert, 38% had an intermediate or high clinical probability of HIT based on the 4Ts Score that would be an indication for further testing. This result highlights the success of the CDSS in identifying patients needing further evaluation but also the difficulties of a computer-based CDSS in representing all the important clinical criteria for the diagnosis of HIT. Disclosures:No relevant conflicts of interest to declare.

Pilot study to validate a computer-based clinical decision support system for dyslipidemia treatment (HTE-DLP)

Pilot study to validate a Computerized Decision Support Systems (CDS) (HTE-DLP) for improving treatment of hyperlipidemia. MethodsHTE-DLP was programmed to offer automatic specific reminders for lipid treatment. Seventy-seven patients with high cardiovascular risk were randomized. 10 expert physicians in cardiovascular-risk management were recruited. We assessed number of patients at LDL <70 mg/dl after 12 weeks of treatment. ResultsA greater proportion of intervention group reached the LDL-C <70 mg/ml [55.0% vs12.5%, p = 0.003; OR: 3.26 IC (1.16–9.15)]. “High potency statins” and combined therapy were used more frequently in the intervention group than the control group (p = 0.001). Seven adverse effects were documented in the intervention group and two in the control group. An acceptable relationship was observed with regard to costeffectiveness in the intervention group. Physicians expressed good agreement with HTE-DLP (86.1%) and comfortable ease-of-use (85%). ConclusionsUse of a CDSS in high-risk cardiovascular patients resulted in a significant reduction in LDL-C levels.

Clinical Decision Support System and Incidence of Delirium in Cognitively Impaired Older Adults Transferred to Intensive Care

Elderly patients with cognitive impairment are at increased risk of developing delirium, especially in the intensive care unit. To evaluate the efficacy of a computer-based clinical decision support system that recommends consulting a geriatrician and discontinuing use of urinary catheters, physical restraints, and unnecessary anticholinergic drugs in reducing the incidence of delirium. Data for a subgroup of patients enrolled in a large clinical trial who were transferred to the intensive care units of a tertiary-care, urban public hospital in Indianapolis were analyzed. Data were collected on frequency of orders for consultation with a geriatrician; discontinuation of urinary catheterization, physical restraints, or anticholinergic drugs; and the incidence of delirium. The sample consisted of 60 adults with cognitive impairment. Mean age was 74.6 years; 45% were African American, and 52% were women. No differences were detected between the intervention and the control groups in orders for consultation with a geriatrician (33% vs 40%; P = .79) or for discontinuation of urinary catheters (72% vs 76%; P = .99), physical restraints (12% vs 0%; P=.47), or anticholinergic drugs (67% vs 36%; P=.37). The 2 groups did not differ in the incidence of delirium (27% vs 29%; P = .85). Use of a computer-based clinical decision support system may not be effective in changing prescribing patterns or in decreasing the incidence of delirium.

A clinical decision support system for venous thromboembolism prophylaxis at a general hospital in a middle-income country

OBJECTIVE: To determine the impact that implementing a combination of a computer-based clinical decision support system and a program of training seminars has on the use of appropriate prophylaxis for venous thromboembolism (VTE). METHODS: We conducted a cross-sectional study in two phases (prior to and after the implementation of the new VTE prophylaxis protocol) in order to evaluate the impact that the combined strategy had on the use of appropriate VTE prophylaxis. The study was conducted at Nossa Senhora da Conceição Hospital, a general hospital in the city of Porto Alegre, Brazil. We included clinical and surgical patients over 18 years of age who were hospitalized for ≥ 48 h. The pre-implementation and post-implementation phase samples comprised 262 and 261 patients, respectively. RESULTS: The baseline characteristics of the two samples were similar, including the distribution of patients by risk level. Comparing the pre-implementation and post-implementation periods, we found that the overall use of appropriate VTE prophylaxis increased from 46.2% to 57.9% (p = 0.01). Looking at specific patient populations, we observed that the use of appropriate VTE prophylaxis increased more dramatically among cancer patients (from 18.1% to 44.1%; p = 0.002) and among patients with three or more risk factors (from 25.0% to 42.9%; p = 0.008), two populations that benefit most from prophylaxis. CONCLUSIONS: It is possible to increase the use of appropriate VTE prophylaxis in economically constrained settings through the use of a computerized protocol adhered to by trained professionals. The underutilization of prophylaxis continues to be a major problem, indicative of the need for ongoing improvement in the quality of inpatient care.

System Design of a Computer-Based Clinical Decision Support System Management by Using Radial Basis Function Approach

Effective corporate governance mechanisms and strategies are commonly referred to as the area of management that deals with getting the best performance from employees within the organization at hand. Whilst the activities involved in the management of people for their optimal performance have been carried out for generations, it is only relatively recently that attempts have been made to identify, describe and refine the practices of effective corporate governance mechanisms and strategies. The present paper introduces and outlines the framework of modern Optimal Human Resource Management of hospital with using Neural Network (NN) and its crucial connectivity to Optimal Performance of people within the organization at hand and what the organization needs to do in order to achieve such well sought after connectivity. The NN is described in the present paper identifying its basic structures, unique characteristics, advantages and. Hospital as the most well known organization provides this type of service that plays an important role in maintaining the health of patients. Improving the quality of health care and reducing medical errors seems to be essential that available strategies should be used to achieve this goal. One of the strategies is to design System that in the present study, the modeling of this system is based on decision support systems using RBF.

Screening for Obstructive Sleep Apnea in Veterans With Ischemic Heart Disease Using a Computer-Based Clinical Decision Support System

Screening for Obstructive Sleep Apnea in Veterans With Ischemic Heart Disease Using a Computer-Based Clinical Decision Support System

Screening for obstructive sleep apnea in veterans with ischemic heart disease using a computer-based clinical decision-support system

To assess the validity of a handheld clinical decision-support system (CDSS) in detecting obstructive sleep apnea (OSA) in veterans with ischemic heart disease against polysomnography (PSG) and to compare the diagnostic accuracy of the CDSS versus the Berlin questionnaire. We enrolled prospectively 143 patients with underlying ischemic heart disease. Veterans with history of neurologic disease, systolic congestive heart failure, or receiving opiates were excluded from participation. Participants were asked to complete the Berlin Questionnaire and to answer all eight questions of CDSS-software. At the end of the interview, veterans were scheduled for an in-laboratory polysomnogram. Ninety one patients completed the study. The prevalence of OSA (AHI ≥5/h) was 74.7% with a median AHI of 11.5/h (range 0-90). When compared to PSG, the CDSS and the Berlin questionnaire achieved a sensitivity of 98.5% [95% confidence interval (CI) 92.1-100] and 80.9% (95% CI 69.5-89.4) and a specificity of 86.9% (95% CI 66.4-97.2) and 39.1% (95% CI 19.7-61.5) at a threshold value of AHI ≥5 with a corresponding area under the curve of 0.93 (95% CI 0.85-0.97) and 0.60 (95% CI 0.49-0.70); respectively. CDSS is a superior screening tool for identifying cardiac veterans with undiagnosed OSA than the BQ.

Clinical decision support to improve blood pressure control in hemodialysis patients: a nonrandomized controlled trial

Computer-based clinical decision support aims to improve the quality of patient care. The utility of decision support for improving blood pressure control in hemodialysis patients is unknown. This was a nonrandomized controlled trial of adult patients receiving chronic in-center hemodialysis during the period of April 1, 2005, to September 30, 2006, in 1 of the 2 major university-based renal programs in Alberta, Canada. Physicians in the intervention center were provided with twice-monthly audits and printed management suggestions based on guideline-recommended blood pressure targets. The same data were available to physicians in the control group but without audit and feedback decision support. Eight hundred and thirty hemodialysis patients were receiving dialysis treatment at the time the study was initiated. Preintervention and postintervention blood pressure data were available for 361 patients. The primary outcome, the proportion of postdialysis systolic blood pressures at target over 12 months, did not differ between the intervention and the control programs (unadjusted odds ratio 0.59; 95% confidence interval [95% CI], 0.34-1.02, p = 0.06; adjusted odds ratio 0.62; 95% CI, 0.35-1.11, p = 0.11). There was no significant difference between the intervention and control groups in other measures of blood pressure such as the mean change in postdialysis systolic blood pressures (unadjusted mean difference 4 mm Hg, 95% CI, -1 to 9, p = 0.36; adjusted mean difference 2 mm Hg, 95% CI, -1 to 5, p = 0.19). In this population of chronic hemodialysis patients, a computer-based clinical decision support system was not associated with improved blood pressure control.

407 Impact of an Emergency Department Transient Ischemic Attack Clinical Pathway: Preliminary Results of a Prospective Study

Patients with transient ischemic attack are a challenge to appropriately diagnose and disposition in the emergency department (ED). It is known that transient ischemic attack patients are at elevated risk of stroke and that most of that risk occurs in the first few days following their TIA event. This knowledge has led to recommendations for earlier and more aggressive diagnostic evaluations for these patients. This is often a difficult task in the outpatient setting. The purpose of this study is to describe the design and impact of an ED-based TIA clinical pathway to assist clinicians in obtaining recommended diagnostic studies and initiating secondary prevention measures. This is an ongoing prospective, observational study examining the impact of a newly developed ED-based transient ischemic attack clinical pathway. Patients who present to the ED within 24 hours of a transient ischemic attack event are eligible for enrollment. The pathway represents a multi-disciplinary effort between emergency medicine, stroke neurology, and neuro-radiology specialists and incorporates recent American Stroke Association (ASA) recommendations into a computer-based clinical decision support system integrated with computerized physician order entry. The pathway favors magnetic resonance diffusion-weighted imaging of the brain over CT scans, in keeping with those recommendations. Patients with suspected transient ischemic attack undergo an abbreviated workup in the ED. Those who meet specific “low risk” criteria are admitted to the ED observation unit where they undergo diffusion-weighted imaging along with carotid vessel imaging and, if deemed appropriate, echocardiography. Patients are observed for occult atrial fibrillation or any neurologic deterioration. Secondary prevention measures are initiated for discharged patients based on the results of their evaluation: anti-platelet therapy, statins, blood pressure or diabetic control, or anticoagulation. Patients are admitted if further observation or intervention is warranted. Telephone follow-up and electronic medical record review are performed to assess 30- and 90-day outcomes. Since the study period began in September, 2010, 42 patients have been enrolled. Average age at enrollment was 64.8 (SD 17.9). Subjects were predominantly female (59.5%) and Caucasian (85%). Medical comorbidities most commonly included hypertension (52.4%), dyslipidemia (33.3%), prior stroke or transient ischemic attack (26.2%) and diabetes (19.5%). Average ABCD2 score was 3.4 (SD 1.3). One-third of patients were on antiplatelet agents prior to presentation. Atrial fibrillation was identified in 3 patients, all of whom had been diagnosed with atrial fibrillation in the past. Diffusion-weighted imaging was obtained for 36 (86%) of patients while only 11 (26.2%) received CT scans. Diffusion-weighted imaging revealed acute ischemia in 6 patients (16.7%), subacute ischemia in 1 (2.8%), and chronic/old ischemia in 8 (22.2%). Carotid imaging was performed on 40 patients (95.2%) and revealed stenosis >50% in 3 (7.5%). Thirty-two patients (76.2%) were discharged home from the EDOU, 80% on anti-platelet agents and 23.3% on statins. No subsequent stroke events occurred in discharged patients. Expedited transient ischemic attack evaluation in an ED observation unit setting incorporating diffusion-weighted imaging allows for rapid performance of recommended diagnostic studies and safe discharge for a majority of ED transient ischemic attack patients.

Recurrent Neural Networks in Computer-Based Clinical Decision Support for Laryngopathies: An Experimental Study

The main goal of this paper is to give the basis for creating a computer-based clinical decision support (CDS) system for laryngopathies. One of approaches which can be used in the proposed CDS is based on the speech signal analysis using recurrent neural networks (RNNs). RNNs can be used for pattern recognition in time series data due to their ability of memorizing some information from the past. The Elman networks (ENs) are a classical representative of RNNs. To improve learning ability of ENs, we may modify and combine them with another kind of RNNs, namely, with the Jordan networks. The modified Elman-Jordan networks (EJNs) manifest a faster and more exact achievement of the target pattern. Validation experiments were carried out on speech signals of patients from the control group and with two kinds of laryngopathies.

Prescribers' Responses to Alerts During Medication Ordering in the Long Term Care Setting

Computerized physician order entry with clinical decision support has been shown to improve medication safety in adult inpatients, but few data are available regarding its usefulness in the long-term care setting. The objective of this study was to examine opportunities for improving medication safety in that clinical setting by determining the proportion of medication orders that would generate a warning message to the prescriber via a computerized clinical decision support system and assessing the extent to which these alerts would affect prescribers' actions. The study was set within a randomized controlled trial of computerized clinical decision support conducted in the long-stay units of a large, academically-affiliated long-term care facility. In March 2002, a computer-based clinical decision support system (CDSS) was added to an existing computerized physician order entry (CPOE) system. Over a subsequent one-year study period, prescribers ordering drugs for residents on three resident-care units of the facility were presented with alerts; these alerts were not displayed to prescribers in the four control units. We assessed the frequency of drug orders associated with various categories of alerts across all participating units of the facility. To assess the impact of actually receiving an alert on prescriber behavior during drug ordering, we calculated separately for the intervention and control units the proportion of the alerts, within each category, that were followed by an appropriate action and estimated the relative risk of an appropriate action in the intervention units compared to the control units. During the 12 months of the study, there were 445 residents on the participating units of the facility, contributing 3,726 resident-months of observation time. During this period, 47,997 medication orders were entered through the CPOE system-approximately 9 medication orders per resident per month. 9,414 alerts were triggered (2.5 alerts per resident-month). The alert categories most often triggered were related to risks of central nervous system side-effects such as over-sedation (20%). Alerts for risk of drug-associated constipation (13%) or renal insufficiency/electrolyte imbalance (12%) were also common. Twelve percent of the alerts were related to orders for warfarin. Overall, prescribers who received alerts were only slightly more likely to take an appropriate action (relative risk 1.11, 95% confidence interval 1.00, 1.22). Alerts related to orders for warfarin or central nervous system side effects were most likely to engender an appropriate action, such as ordering a recommended laboratory test or canceling an ordered drug. Long-term care facilities must implement new system-level approaches with the potential to improve medication safety for their residents. The number of medication orders that triggered a warning message in this study suggests that CPOE with a clinical decision support system may represent one such tool. However, the relatively low rate of response to these alerts suggests that further refinements to such systems are required, and that their impact on medication errors and adverse drug events must be carefully assessed.

Evaluation of CaDet, a computer-based clinical decision support system for early cancer detection: a comparison with the performance of clinicians

Based on an analysis of the epidemiologic and clinical attributes of individual patients, the CaDet computer program presents physicians with data patterns that may require clinical attention with regard to early cancer detection. This study evaluated the performance of the program as a possible tool to aid clinicians in the latter. Patient data were obtained by a questionnaire from 160 healthy volunteers. Scored cancer alerts generated by the computer program in response to this data were evaluated in comparison to similar alerts provided by five expert internists who reviewed the same information in blinded fashion. The alert profiles generated by the computer for each of the patients examined were highly correlated to those provided by the clinicians. The computer's alert rate increased with the number of physicians who raised corresponding alerts (20%, 32%, 54%, 73% and 91%, respectively, for 1, 2, 3, 4 and 5 physicians, p < 0.0001) and with the overall weight assigned by the physicians to these alerts (22%, 56%, 84% and 90% for cumulative scores of 1–4, 5–8, 9–12 and 13 or more points, respectively, p < 0.0001). It is concluded that the CaDet computer program may have a role in improving early detection, pending the results of further clinical research.

Risk Stratification and Prevention in Chronic Coronary Artery Disease: Use of a Novel Prognostic and Computer-Based Clinical Decision Support System in a Large Primary Managed-Care Group Practice

Current therapy for chronic coronary artery disease (CAD) is extremely variable and under-utilizes preventive measures that have demonstrated benefit. Therefore, we sought to determine whether a novel hybrid prognostic and computer-based clinical decision support system (ohms|cad®; Interactive Heart Management Corporation, Laurence Harbor, New Jersey), that provides the treating physician with real-time, patient-specific recommendations, could improve outcomes, decrease utilization of services, and lower the costs of CAD. This was an observational study in a managed-care group practice with 39,565 members. A subpopulation of 1,628 patients participated in the study after being identified as being at increased risk for CAD. Over the 21 months after introduction of ohms|cad, utilization of cardiovascular services, coronary disease outcomes, and costs were compared with a baseline year by computing the relative risks of discrete CAD-related events. The use of ohms|cad significantly reduced adverse CAD outcomes in the entire population of members. Acute myocardial infarctions were reduced by 30% [relative risk (RR), 0.70; 95% confidence interval (CI), 0.59-0.81] and hospitalizations for angina or suspected infarction by 32% (RR, 0.68; 95% CI, 0.62-0.75). Stress tests decreased by 62% (RR, 0.38; 95% CI, 0.35-0.40), cardiac catheterizations by 20% (RR, 0.80; 95% CI, 0.71-0.89), and coronary angioplasties by 22% (RR, 0.78; 95% CI, 0.62-0.96). The rate of coronary artery bypass grafting was unchanged (RR, 1.06; 95% CI, 0.88-1.26). In addition, there were significant improvements in ambulatory ischemia, most monitored risk factors, and use of aspirin. Net CAD-associated costs in the population were reduced by 17%. Thus, an automated system that provides patient-specific prognostic information and clinical decision support for the treatment of chronic CAD can help increase the use of preventive strategies, and lower the morbidity and cost of chronic CAD.

Users' Guides to the Medical Literature: XVIII. How to use an article evaluating the clinical impact of a computer-based clinical decision support system.

Users' Guides to the Medical Literature: XVIII. How to use an article evaluating the clinical impact of a computer-based clinical decision support system.

Implementing clinical guidelines in the treatment of hypertension in general practice: Evaluation of patient outcome related to implementation of a computer-based clinical decision support system

Objective - To evaluate the implementation of clinical guidelines for hypertension in general practice by use of a computer-based clinical decision support system (CDSS) and a specific implementation strategy. Evaluation of patient outcome. Design - Randomised study with health centres as units. The intervention group had the CDSS installed and made ready for use, doctors and assistants were trained and received a user-manual, the doctors were offered telephone repetitions, a seminar in risk intervention and, at the same seminar, further demonstration of the CDSS. The doctors received baseline registrations with information of how they treated their own hypertensive patients, and use of the CDSS was checked repeatedly. Setting - General practice in Sør- and Nord-Trø