Computer clinical decision support that automates personalized clinical care: a challenging but needed healthcare delivery strategy.

How to deliver best care in various clinical settings remains a vexing problem. All pertinent healthcare-related questions have not, cannot, and will not be addressable with costly time- and resource-consuming controlled clinical trials. At present, evidence-based guidelines can address only a small fraction of the types of care that clinicians deliver. Furthermore, underserved areas rarely can access state-of-the-art evidence-based guidelines in real-time, and often lack the wherewithal to implement advanced guidelines. Care providers in such settings frequently do not have sufficient training to undertake advanced guideline implementation. Nevertheless, in advanced modern healthcare delivery environments, use of eActions (validated clinical decision support systems) could help overcome the cognitive limitations of overburdened clinicians. Widespread use of eActions will require surmounting current healthcare technical and cultural barriers and installing clinical evidence/data curation systems. The authors expect that increased numbers of evidence-based guidelines will result from future comparative effectiveness clinical research carried out during routine healthcare delivery within learning healthcare systems.

Enabling a learning healthcare system with automated computer protocols that produce replicable and personalized clinician actions.

Clinical decision-making is based on knowledge, expertise, and authority, with clinicians approving almost every intervention-the starting point for delivery of "All the right care, but only the right care," an unachieved healthcare quality improvement goal. Unaided clinicians suffer from human cognitive limitations and biases when decisions are based only on their training, expertise, and experience. Electronic health records (EHRs) could improve healthcare with robust decision-support tools that reduce unwarranted variation of clinician decisions and actions. Current EHRs, focused on results review, documentation, and accounting, are awkward, time-consuming, and contribute to clinician stress and burnout. Decision-support tools could reduce clinician burden and enable replicable clinician decisions and actions that personalize patient care. Most current clinical decision-support tools or aids lack detail and neither reduce burden nor enable replicable actions. Clinicians must provide subjective interpretation and missing logic, thus introducing personal biases and mindless, unwarranted, variation from evidence-based practice. Replicability occurs when different clinicians, with the same patient information and context, come to the same decision and action. We propose a feasible subset of therapeutic decision-support tools based on credible clinical outcome evidence: computer protocols leading to replicable clinician actions (eActions). eActions enable different clinicians to make consistent decisions and actions when faced with the same patient input data. eActions embrace good everyday decision-making informed by evidence, experience, EHR data, and individual patient status. eActions can reduce unwarranted variation, increase quality of clinical care and research, reduce EHR noise, and could enable a learning healthcare system.

Evaluating How Post-Bronchodilator Vital Capacities Affect the Diagnosis of Obstruction in Pulmonary Function Tests.

BACKGROUND: Although the ratio of FEV1 to the vital capacity (VC) is universally accepted as the cornerstone of pulmonary function test (PFT) interpretation, FVC remains in common use. We sought to determine what the differences in PFT interpretation were when the largest measured vital capacity (VCmax) was used instead of the FVC. METHODS: We included 12,238 consecutive PFTs obtained for routine clinical care. We interpreted all PFTs first using FVC in the interpretation algorithm and then again using the VCmax, obtained either before or after administration of inhaled bronchodilator. RESULTS: Six percent of PFTs had an interpretive change when VCmax was used instead of FVC. The most common changes were: new diagnosis of obstruction and exclusion of restriction (previously suggested by low FVC without total lung capacity measured by body plethysmography). A nonspecific pattern occurred in 3% of all PFT interpretations with FVC. One fifth of these 3% produced a new diagnosis of obstruction with VCmax. The largest factors predicting a change in PFT interpretation with VCmax were a positive bronchodilator response and the administration of a bronchodilator. Larger FVCs decreased the odds of PFT interpretation change. Surprisingly, the increased numbers of PFT tests did not increase odds of PFT interpretation change. CONCLUSIONS: Six percent of PFTs have a different interpretation when VCmax is used instead of FVC. Evaluating borderline or ambiguous PFTs using the VCmax may be informative in diagnosing obstruction and excluding restriction.

The evolution of eProtocols that enable reproducible clinical research and care methods.

Unnecessary variation in clinical care and clinical research reduces our ability to determine what healthcare interventions are effective. Reducing this unnecessary variation could lead to further healthcare quality improvement and more effective clinical research. We have developed and used electronic decision support tools (eProtocols) to reduce unnecessary variation. Our eProtocols have progressed from a locally developed mainframe computer application in one clinical site (LDS Hospital) to web-based applications available in multiple languages and used internationally. We use eProtocol-insulin as an example to illustrate this evolution. We initially developed eProtocol-insulin as a local quality improvement effort to manage stress hyperglycemia in the adult intensive care unit (ICU). We extended eProtocol-insulin use to translate our quality improvement results into usual clinical care at Intermountain Healthcare ICUs. We exported eProtocol-insulin to support research in other US and international institutions, and extended our work to the pediatric ICU. We iteratively refined eProtocol-insulin throughout these transitions, and incorporated new knowledge about managing stress hyperglycemia in the ICU. Based on our experience in the development and clinical use of eProtocols, we outline remaining challenges to eProtocol development, widespread distribution and use, and suggest a process for eProtocol development. Technical and regulatory issues, as well as standardization of protocol development, validation and maintenance, need to be addressed. Resolution of these issues should facilitate general use of eProtocols to improve patient care.

A replicable method for blood glucose control in critically Ill patients.

CONTEXT: To ensure interpretability and replicability of clinical experiments, methods must be adequately explicit and should elicit the same decision from different clinicians who comply with the study protocol. OBJECTIVE: The objective of this study was to determine whether clinician compliance with protocol recommendations exceeds 90%. DESIGN: We developed an adequately explicit computerized protocol (eProtocol-insulin) for managing critically ill adult patient blood glucose. We monitored clinician compliance with eProtocol-insulin recommendations in four intensive care units in four hospitals and compared blood glucose distributions with those of a simple clinical guideline at one hospital and a paper-based protocol at another. All protocols and the guideline used intravenous insulin and 80 to 110 mg/dL (4.4-6.1 mmol/L) blood glucose targets. SETTING: The setting for this study was four academic hospital intensive care units. PATIENTS: This study included critically ill adults requiring intravenous insulin. INTERVENTION: Intervention used in this study was a bedside computerized protocol for managing blood glucose. MAIN OUTCOME MEASURE: The main outcome measure was clinician compliance with eProtocol-insulin recommendations. RESULTS: The number of patients was 31 to 458 and the number of blood glucose measurements was 2,226 to 19,925 among the four intensive care units. Clinician compliance with eProtocol-insulin recommendations was 91% to 98%. Blood glucose distributions were similar in the four hospitals (generalized linear model p = .18). Compared with the simple guideline, eProtocol-insulin glucose measurements within target increased from 21% to 39%, and mean blood glucose decreased from 142 to 115 mg/dL (generalized linear model p < .001). Compared with the paper-based protocol, eProtocol-insulin glucose measurements within target increased from 28% to 42%, and mean blood glucose decreased from 134 to 116 mg/dL (generalized linear model p = .001). CONCLUSIONS: The 91% to 98% clinician compliance indicates eProtocol-insulin is an exportable instrument that can establish a replicable experimental method for clinical trials of blood glucose management in critically ill adults. Control of blood glucose was better with eProtocol-insulin than with a simple clinical guideline or a paper-based protocol.

Multicenter validation of a computer-based clinical decision support tool for glucose control in adult and pediatric intensive care units.

INTRODUCTION: Hyperglycemia during critical illness is common, and intravenous insulin therapy (IIT) to normalize blood glucose improves outcomes in selected populations. Methods differ widely in complexity, insulin dosing approaches, efficacy, and rates of hypoglycemia. We developed a simple bedside-computerized decision support protocol (eProtocol-insulin) that yields promising results in the development center. We examined the effectiveness and safety of this tool in six adult and five pediatric intensive care units (ICUs) in other centers. METHODS: We required attending physicians of eligible patients to independently intend to use intravenous insulin to normalize blood glucose. We used eProtocol-insulin for glucose control for a duration determined by the clinical caregivers. Adults had an anticipated length of stay of 3 or more days. In pediatric ICUs, we also required support or intended support with mechanical ventilation for greater than 24 hours or with a vasoactive infusion. We recorded all instances in which eProtocol-insulin instructions were not accepted and all blood glucose values. An independent data safety and monitoring board monitored study results and subject safety. Bedside nurses were selected randomly to complete a paper survey describing their perceptions of quality of care and workload related to eProtocol-insulin use. RESULTS: Clinicians accepted 93% of eProtocol-insulin instructions (11,773/12,645) in 100 adult and 48 pediatric subjects. Forty-eight percent of glucose values were in the target range. Both of these results met a priori-defined efficacy thresholds. Only 0.18% of glucose values were < or =40 mg/dl. This is lower than values reported in prior IIT studies. Although nurses reported eProtocol-insulin required as much work as managing a mechanical ventilator, most nurses felt eProtocol-insulin had a low impact on their ability to complete non-IIT nursing activities. CONCLUSIONS: A multicenter validation demonstrated that eProtocol-insulin is a valid, exportable tool that can assist clinicians in achieving control of glucose in critically ill adults and children.

An electronic protocol for translation of research results to clinical practice: a preliminary report.

INTRODUCTION: We evaluated the feasibility of using an electronic protocol developed for research use (Research-eProtocol-insulin) for blood glucose management in usual intensive care unit clinical practice. METHODS: We implemented the rules of Research-eProtocol-insulin in the electronic medical record of the Intermountain Healthcare hospital system (Clinical-eProtocol-insulin) for use in usual clinical practice. We evaluated the performance of Clinical-eProtocol-insulin rules in the intensive care units of seven Intermountain Healthcare hospitals and compared this performance with the performance of Research-eProtocol-insulin at the LDS Hospital Shock/Trauma/Respiratory Intensive Care Unit. RESULTS: Clinician (nurse or physician) compliance with computerized protocol recommendations was 95% (of 21,325 recommendations) with Research-eProtocol-insulin and 92% (of 109,458 recommendations) with Clinical-eProtocol-insulin. The blood glucose distribution in clinical practice (Clinical-eProtocol-insulin) was similar to the research use distribution (Research-eProtocol-insulin); however, the mean values (119 mg/dl vs 113 mg/dl) were statistically different (P = 0.0001). Hypoglycemia rates in the research and practice settings did not differ: the percentage of measurements < or =40 mg/dl (0.11% vs 0.1%, P = 0.65) and the percentage of patients with at least one blood glucose < or =40 mg/dl (4.2% vs 3%, P = 0.23) were not statistically significantly different. CONCLUSION: Our electronic blood glucose protocol enabled translation of a research decision-support tool (Research-eProtocol-insulin) to usual clinical practice (Clinical-eProtocol-insulin).