Skip to main content
PMC home page
NIHPA Author Manuscripts logoLink to NIHPA Author Manuscripts
. Author manuscript; available in PMC: 2019 Jun 1.
Published in final edited form as: Crit Care Nurs Clin North Am. 2018 Apr 4;30(2):237–246. doi: 10.1016/j.cnc.2018.02.006

Informatics Solutions for Application of Decision-Making Skills

Christine W Nibbelink 1, Janay R Young 1, Jane M Carrington 1, Barbara B Brewer 1
PMCID: PMC5941940  NIHMSID: NIHMS957692  PMID: 29724442

Abstract

Objective

To discuss the use of Electronic Health Record (EHR), clinical data, that informs Clinical Databases and Clinical Decision Support Systems (CDSS) tools in critical care nursing practice to guide patient care.

Background

Critical care nurses practice in a challenging environment that requires responses to patients with complex, often unstable health conditions. EHR, access to clinical data, and CDSS informed by data from Clinical Databases are informatics tools designed to work together to facilitate decision-making in nursing practice.

Informatics Tools in Critical Care

EHR incorporates many levels of clinical data and includes CDSS. Together, these informatics tools are designed to support nursing practice. Critical care nurses care for patients with a broad number of diseases. EHR, clinical data, and CDSS are informatics tools that can provide important support for critical care nurses’ decision-making.

Conclusions

The complex decision-making environment of critical care requires informatics tools that support nursing practice through integration of current evidence with clinical data. Future research recommendations include continuing efforts towards the development of clinical decision support tools based on patient data that include predictive models to support increased patient safety.

Keywords: Nursing Informatics, Electronic Health Record, Clinical Data, Clinical Databases, Clinical Decision Support Systems, Nursing Practice, Critical Care Nursing

INTRODUCTION

Poor decision-making has been linked with up to 98,000 deaths in hospitals each year.1 Research indicates that critical care nurses make 238 decisions per hour.2 Nursing informatics solutions represent one important effort to improve patient outcomes and support nursing practice. Nursing informatics is a field of science that combines the sciences of nursing, information, computers, and cognition to provide better access to patient information and support nursing practice.3 The goal of nursing informatics is to facilitate progression of patient data to information and wisdom to improve the patient condition.3 Nursing informatics currently includes many tools aimed at facilitation of these efforts. The purpose of this paper is to discuss the utilization of Electronic Health Record (EHR), Clinical Data, and Clinical Decision Support Systems (CDSS) tools to support decision-making in critical care nursing practice.

BACKGROUND

Critical care nurses coordinate care for patients with highly complex and potentially unstable illnesses.4 This requires critical care nurses to work within health care teams to maintain awareness of a patient’s current status in order to limit and respond to complications with an end goal of improved patient outcomes.4 This high level of nursing care requires specialized education, knowledge and skills for effective response to changes in patient status.4 Despite experience and training of nurses caring for complex patients, memory and rapid data processing can interfere with timely and correct decision-making. The electronic health record (EHR) can assist in decision-making. In part due to Meaningful Use promoted by Health Information Technology for Economic and Clinical Health (HITECH) Acts as part of the American Recovery and Reinvestment Act of 2009, CDSS is required to facilitate effective use of EHR in healthcare to improve patient outcomes.5

INFORMATICS TOOLS IN CRITICAL CARE

Electronic Health Record

The EHR serves as the core technology within the healthcare setting. The EHR functions to collect, store, and make available important patient information to support decision-making and care planning. Nurses manage thousands of data points each shift reflective of the complex nature of critically ill patients.5 This is successful in part due to two characteristics of the EHR. First, embedded within the EHR are other technologies such as CDSS, algorithms as alerts and early warning systems, and interfaces connecting, for example, infusion pump, hospital bed, and hemodynamic monitor data. Data from these devices have the potential of triggering an early warning alert (a problem is likely) or CDSS an actual problem (critical value). Second, the EHR supports data entry of patient information, which is a critical element for other embedded applications such as acuity scale, pressure ulcer risk scale, and pain scale.6

Despite these characteristics of the EHR, effectiveness of the EHR as a technology to guide clinical decision-making is inconclusive. The current EHR is effective as a data entry system, it falls short with data retrieval threatening decision-making.6 Despite this, the federal mandate, Meaningful Use, sought to increase effective use of the EHR for improved patient outcomes.7 This mandate sought to attach reimbursement to effective use of the EHR that includes use of embedded technologies to enhance decision-making.8 Meaningful Use guidelines seek to enhance accessibility of information in EHR for better patient outcomes.7 Unfortunately, nursing research finds that while EHR is effective as a data entry tool, data retrieval is limited.6

Clinical Databases

Clinical Databases are a collection of clinical data that exist “behind” the front facing screens of the EHR and allow for data to be captured from basic and advanced hemodynamic monitoring devices and then integrated with the EHR. Monitoring devices used in the ICU, such as arterial pressure or pulmonary artery catheters, capture semi-continuous values that allow for nurse-driven monitoring and evaluation of the therapeutic effect of interventions.9 The monitoring devices communicate with the EHR over a secure network, wirelessly or directly with an Ethernet converter.10 The ICU nurse determines the frequency that the data are captured, validates that the data collected are accurate, and then saves them to the patient’s permanent EHR. Examples of patient data that can be mined for use in decision support are broad. Patients requiring ICU care may experience circulatory failure requiring immediate nursing assessment of basic and advanced hemodynamics for minute-to-minute assessment. These data could be combined with evidence for best practice. Clinical data that are directly from the EHR inform specific CDSSs.

There are some larger healthcare systems where patient data from the EHR are populated and stored in databases stored in a clinical data warehouse, which is used for data analysis and reporting.11 Clinical data enter the warehouse in a de-identified state. An interested clinician or scientist can obtain clinical data sets (based on specific International Classification of Diseases [ICD]9 or 10 codes, demographic information, and so forth and then process, transform, mine and evaluate the data to answer clinical or research questions.11 The data in the clinical data warehouse are used primarily for research at this time point, however, holds great potential for using statistical techniques to model patients who share characteristics towards the development of more informed CDSSs that are data driven to deliver specific nurse care.

The clinical data stored in clinical data warehouse can be analyzed and studied to identify patterns and relationships in a method called data mining.11,12 Data mining is the process of extracting data from large datasets to determine relationships and patterns which can be used for formulating predictive models.12 The knowledge generated from data mining can inform and enhance the decision-making process and to develop CDSS, which could eventually be used for immediate clinical feedback.11 Nursing practice includes determination of appropriate pharmacologic and non-pharmacologic interventions.9 Nursing decision support could provide recommendations that include assessment of mixed venous oxygen saturation (SvO2), through repeated blood withdrawal from the pulmonary artery catheter, as an indicator of the oxygen supply/demand balance.13 SvO2<50% requires the ICU nurse to perform a rapid patient assessment and to provide physiologic optimization which may include oxygen administration, fluid infusion, diuretics, vasopressors, and/or inotropes.13 Through the integration of evidence with clinical data, nurse decision-making may be more effectively supported. For example, clinical data including measurement of fluid intake and output, daily weight, vital signs, and SVO2, can be used to develop a CDSS to titrate diuretics to improve diuresis.

Clinical Decision Support Systems

CDSS are computer software tools designed to facilitate decision-making through connecting evidence with patient status.14 Use of CDSS can improve guideline compliance through warnings, alerts, and advice.14,15 CDSS is an increasingly important tool in nursing practice. Research identifies CDSS as supporting decision-making in time limited circumstances leading to improved patient outcomes. Nursing research is inconclusive in demonstrating effectiveness of CDSS in nursing practice.16 However, Meaningful Use requirements and the demanding nature of decision-making in nursing practice, require that CDSS will continue to to be developed as an important part of nursing practice. Barriers to CDSS use must be better understood and addressed. Examples of CDSS tools, factors associated with nurse use of CDSS, suggestions for CDSS improvement, and CDSS and nursing care of ICU patients will be addressed.

CDSS tools

No all-inclusive list of CDSS exists.17,18 Many tools that support decision-making may not be commonly thought of as CDSS.17,18 Many examples of CDSS exist including, paper decision support tools, order sets, parameters for patient care, patient data, and patient monitors.16–18 Nursing literature does describe examples of tools that are more commonly thought of as CDSS. Examples of CDSS tools identified in literature include information management, focusing attention, and patient-specific consultation.19 Information management CDSS includes patient education material, info buttons, or guidelines for practice.19 Another type of CDSS focuses the attention of nurses. Examples of focusing attention include drug-to-drug interaction warnings and fall risk warnings.19 The final type of CDSS is patient-specific consultation. Ideal patient-specific consultation CDSS provides the healthcare professional with a broad array of patient information combined with guidelines to support decision-making.19 Thus, effective and comprehensive nurse documentation in the EHR is essential for patient specific decision support. Elements such as depression scoring, patient goals, and body mass index provide information that could enhance patient specific decision support.19

Factors associated with CDSS use

Nurses’ interaction with CDSS as a decision support tool is influenced by a variety of factors. Some research indicates nurses describe CDSS as supportive of decision-making.14 Inexperienced nurses do find CDSS supportive of their decisions.20 However, more experienced nurses use CDSS less frequently than inexperienced nurses.20–22

Many barriers to nurse use of CDSS in practice exist including problems with usability and support of nursing knowledge.14 In addition, nurses may ignore evidence-based recommendations made by the CDSS indicating a failure in the design of the system.23,24 Nurses also may bypass recommendations provided by the CDSS if they believe that their own or a colleague’s advice is more appropriate for the patient care situation.14,16 An impediment to nurse interaction with CDSS could be associated with a lack of trust in CDSS effectiveness.15,25 Nurses must believe that the CDSS will support their practice in order to regard it as an important device that provides evidence with which to base decision-making. Excessive alerts also diminish nurses’ willingness to interact with CDSS when decision-making.15,26 Frequent alerts, rather than keeping the nurse focused on evidence-based guidelines, create a negative use experience for nurses leading to decreased interaction with this tool. While CDSS does provide support for nurse decision-making in some circumstances (such as reminders to check heart rate when administering beta blockers), many areas for advancement need to be addressed.

Improvement of CDSS

Several suggestions for CDSS improvement are described in nursing literature. To begin with, the design of CDSS must be user focused for enhanced usability for the nurse end user.25,27,28 User focus would include CDSS design and identification of the end users’ physical, perceptual, and cognitive needs.25,29 Timing of CDSS information is essential. Research identifies that nurse use of CDSS increased when the CDSS information fit with nursing workflow.16 CDSS must fit the nurse user role. For example, charge nurse workflow and bedside nurse workflow present different CDSS user needs.30 Excessive alerts sent to nurses using CDSS lead to ignored messages.31 CDSS tools that do not meet end user needs lead to reduced access to evidence for decision-making.

To better support acute care nurse decision-making, the end user should participate in design. One study designed nurse role specific CDSS with characteristics identified by the participating acute care nurses as important for CDSS.30 Nurses described the predominant needs of CDSS for acute care nursing practice: provide a picture of the patient’s status over the course of time, support nurse autonomy, and align with the individual needs of the patient.30 Through inclusion of the end user in the development of CDSS, specific decision support needs can be addressed potentially resulting in a more effectively implemented CDSS in acute care.

Use of CDSS in acute care nursing practice

Effective CDSS could support decision-making with many patient populations. A logic model exists in the background of the EHR system, connecting evidence-based practice to the CDSS alert and recommendations. The highly complex nature of ICU nursing care requires excellent decision-making skills in conjunction with the data that exists in the EHR and experience of the clinician. The CDSS with evidence-based logic guide nurses towards effective decision making in anticipation of medication side effects. Evidence based clinical decision support tools are also effective towards determining best diagnostic tests. CDSSs could be constructed to include alerts to test for laboratory studies specific to patient diagnoses.32

It is important to point out that at this time point, CDSSs are patient specific, such as with recommendations to check vital signs when administering a particular medication, and are not designed for a specific diagnosis. For example, a message from the CDSS could read “Patient heart rate <50 and consider hold Digitalis is due” or “Patient’s K is <3.5 and patient on diuretic consider potassium supplement.” Rather, designers, nursing informatics scientists, and those in advance practice, work together using best evidence to analyze connections within data. For example, data collection for patients in the ICU, can include abnormal values in pressure monitoring, medications, laboratory values, and so forth, that tell a story about the patient and are applied to specific patients with particular diagnosis to provide the nurse with more information on which to base decisions. As we move forward with data driven care and predictive modeling, CDSSs will provide enhanced information for improved decision support.

Research indicates that improved guideline use in the provision of acute care is needed.15 Despite this, healthcare professionals continue to resist use of CDSS in the care of complex ICU patients believing that CDSS may make mistakes and that their own experience is more valuable than CDSS advice.15 In addition, in a study surveying 36 cardiologists and 126 heart failure specialty nurses on the use of CDSS in patient care, seventy percent of study participants stated that they would not miss significant changes, such as assessment or laboratory values, in patient status.15 Nurses and cardiologists identify that CDSS adds knowledge to their provision of care, but believe that CDSS advice must always be confirmed by the healthcare professional.15 Use of the Internet, number of years using email, and number of years using computers enhanced trust of CDSS with participants of this study.15 Alerts, while designed to increase adoption of guidelines in practice, may lead to resistance to CDSS use.15 Authors theorized that alerts led users to feel less autonomous in their practice.15 Understanding how CDSS systems work reduced barriers to use of CDSS leading authors to emphasize the importance of user attitude toward CDSS for best patient outcomes.15

Clearly, CDSS must be improved to better support nursing practice. Nurse users of CDSS must be involved in design of CDSS to ensure that decision support needs will be met. CDSS advice must include patient specific advice and be provided in accordance with nursing workflow for greater acceptance. Development of CDSS with recognition of the specific end user needs in terms of nursing role and experience level to guide user focused alerts could increase CDSS acceptance.

Predictive Analytics

Within the umbrella of precision health, predictive analytics has emerged. The concepts of precision medicine and nursing are gaining momentum in our data rich healthcare system. Predictive analytics are used to analyze genomic, environment, and lifestyle (precision medicine)33 and evidence-based and personalized patient care (precision nursing)34 towards quality outcomes and patient safety.33,34 Both concepts are evolving as we gain access to and understanding of patient data within the EHR. It is here that we find patterns emerge with patient characteristics and outcomes to inform predictive analytics.

Predictive analytics employs strategies with machine learning or teaching the computer to think and process data. CDSSs developed using this approach are generally referred to as “data driven” and can be applied to several patient conditions such as sepsis.35 Using data from the EHR and database and the logic from CDSS, models can be created that provide “predictions” of patient outcomes based on patient characteristics. And, with these predictions, specify the care the patient requires for a quality outcome.

Imagine nurses admitting a patient into the intensive care unit and once the data are entered in the EHR, algorithms are working in the background to find key characteristics of the patient to determine their precise care needs and predictions of the patient risks for complications or delays in discharge.

Application to Practice

Patients in the ICU are monitored and managed using many devices that collect an enormous amount of data that could, in the near future, be used to develop an algorithm in the background of the EHR and uses predictive models to determine the patient risk for complications. Techniques in computer science, natural language processing, and machine learning teach the computer to mine EHR data to predict patient outcomes or risk for increased morbidity or mortality. Specific to cardiac disease and intensive care, predictive analystics could be applied to predict patient outcomes with acute coronary syndrome and heart failure.36–39 Furthermore, similar models are being tested to determine acuity from EHR data.40 These examples, and no doubt many more that have yet to be published, remain in the development and test environment and will surely become embedded within the EHR in the near future. Another key point to these algorithms and clinical impact is that these will improve the decision-making process. Rather than an alert informing the nurse that their patient has an abnormal laboratory value or vital sign, these advanced CDSSs systems can provide a risk estimate of the patient for morbidity or mortality and acuity, providing a higher level of decision support for the nurse. While this is a developing science, future applications of this technology applied to cardiovascular patients could predict risk and medication survellence, precision medicine and nursing decision-support, and population health.41

Applications for big data could include important considerations associated with population health including quality of care factors and phenotyping for to more precisely diagnose and treat patients with cardiovascular disease.41 While prescriptive analytics that could support medical decision making for care of patients with cardiovascular disease do not currently exist, the possibilities for future applications is strong.41 Therefore, applications designed for nursing practice could also include predictive analytics.

DISCUSSION AND RECOMMENDATIONS

From the information above, we present recommendations for effective use of technology to increase patient safety. A number of technologies are used to monitor patient status and assist in decision-making for example data from technologies (telemetry monitor, pulse oximetry, to glucometer) provide the EHR with data that could then trigger an alert from the CDSS to assist in decision-making. An abundance of data are collected each shift, and when organized, can be used to learn more about our patients and inform care for populations, beyond the current patient. Based on this we propose the following recommendations. First, training new staff to use patient monitoring technology and the EHR should include content that explains nurses’ contribution to the data collected and value of the data toward decision-making. Second, unit and organization administration should work together to design information systems that employ data within the EHR to increase decision-making support and understanding of patients and populations. Third, build interdisciplinary teams for the purpose of discovering best practice from the clinical data and literature. Finally, exploit big data and databases for information that improves care for the patient, guiding all aspects of patient care and teaching.

Clinical data can be applied to develop predictive models and CDSS to inform clinical decisions and tailor clinical management of patients with critical illness.41 Use of predictive models and CDSS in nursing can allow for individualized therapeutic decisions and guidance of effective use of limited health-care resources to improve both quality and efficiency in care, leading to improved patient outcomes.41 The savings from use of big data in health care are estimated to be in the billions per year in the US, due to waste reduction and improved outcomes.42 To date, there are few examples in the literature on predictive and prescriptive analytics to inform medical therapeutic decisions or guide ICU nurses decisions and interventions.41,43 Rather, general CDSSs alerts are available for general care whereby patients in the ICU patients still benefit, such as diet, medications, laboratory assays, for example. With the development of predictive analytics and advances of precision medicine and nursing, CDSSs will become more focused.

CONCLUSION

Nursing science is behind medical science in understanding CDSS use in nursing practice.14 Better understanding of factors associated with nurse use of CDSS in patient care could facilitate use of CDSS in nursing practice. The complex, time limited care of critically ill patients decisions must be made based on evidence for best outcomes.44 EHR, clinical data, and CDSS are important informatics tools that can facilitate integration of evidence in nursing practice. Future research that explores experienced nurses’ use of CDSS, facilitation of decision-making in time limited situations at the appropriate time in the nurses’ workflow, and incorporation of nurse user needs in CDSS design could enhance nurse use of CDSS and lead to better patient outcomes.

Key Points.

  • Decision-making in critical care nursing practice is highly demanding and is essential to quality patient outcomes.

  • Nursing practice in critical care environments involves caring for patients with complex disease processes and requires in-depth, evidence-based understanding of pathophysiology and treatments to provide effective patient care.

  • Informatics tools provide important support for nurse decision-making through integration of patient information with evidence.

Acknowledgments

Source of Funding

This publication was supported by the National Library of Medicine of the National Institutes of Health under Award Number T15LM011271. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

Footnotes

Publisher's Disclaimer: This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo copyediting, typesetting, and review of the resulting proof before it is published in its final citable form. Please note that during the production process errors may be discovered which could affect the content, and all legal disclaimers that apply to the journal pertain.

Conflicts of Interest

The authors declare that they have no conflicts of interest associated with this article.

References

  • 1.Kohn LT, Corrigan JM, Donaldson MS. Errors in health care: A leading cause of death and injury. To err is human: Building a safer health system. 1999 http://www.nap.edu/download.php?record_id=9728#. [PubMed]
  • 2.Bucknall T. Critical care nurses' decision-making activities in the natural clinical setting. J. Clin. Nurs. 2000;9(1):25–35. [PubMed] [Google Scholar]
  • 3.McGonigle D, Hunter K, Sipes C, Hebda T. Why Nurses Need to Understand Nursing Informatics. AORN J. 2014;100(3):324–327. doi: 10.1016/j.aorn.2014.06.012. [DOI] [PubMed] [Google Scholar]
  • 4.Lakanmaa R-L, Suominen T, Perttilä J, Puukka P, Leino-Kilpi H. Competence requirements in intensive and critical care nursing – Still in need of definition? A Delphi study. Intensive Crit. Care Nurs. 2012;28(6):329–336. doi: 10.1016/j.iccn.2012.03.002. [DOI] [PubMed] [Google Scholar]
  • 5.McCormick K. Intensive care unit, emergency room, and operating room. In: Saba V, McCormick K, editors. Essentials of Computers for Nurses. Philadelphia, PA: Lippincott; 1986. [Google Scholar]
  • 6.Carrington JME, J A. Strengths and limitations of the electronic health record for documenting clinical events. Comput. Inform. Nurs. 2011;29(6):360–367. doi: 10.1097/NCN.0b013e3181fc4139. [DOI] [PubMed] [Google Scholar]
  • 7.Fife CE, Walker D, Thomson B. Electronic Health Records, Registries, and Quality Measures: What? Why? How? Adv Wound Care (New Rochelle) 2013;2(10):598–604. doi: 10.1089/wound.2013.0476. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 8.Blumenthal D, Tavenner M. The "meaningful use" regulation for electronic health records. N. Engl. J. Med. 2010;363(6):501–504. doi: 10.1056/NEJMp1006114. [DOI] [PubMed] [Google Scholar]
  • 9.De Backer D. Is there a role for invasive hemodynamic monitoring in acute heart failure management? Curr. Heart Fail. Rep. 2015;12(3):197–204. doi: 10.1007/s11897-015-0256-6. [DOI] [PubMed] [Google Scholar]
  • 10.Zaleski J. Integrating device data into the electronic medical record. Erlangen, Germany: Publicis Publishing; 2008. [Google Scholar]
  • 11.Chen ES, Sarkar IN. Mining the electronic health record for disease knowledge. Methods Mol. Biol. 2014;1159:269–286. doi: 10.1007/978-1-4939-0709-0_15. [DOI] [PubMed] [Google Scholar]
  • 12.Zaki M, Meira W. Data mining and analysis: Fundamental concepts and algorithms. New York, NY: Cambridge University Press; 2014. [Google Scholar]
  • 13.Booker KJ. Hemodynamic monitoring in critical care, in Critical Care Nursing: Monitoring and Treatment for Advanced Nursing Practice. Hoboken, NJ: John Wiley & Sons, Inc.; [Google Scholar]
  • 14.Anderson JA, Willson P. Clinical decision support systems in nursing: synthesis of the science for evidence-based practice. Comput. Inform. Nurs. 2008;26(3):151–158. doi: 10.1097/01.NCN.0000304783.72811.8e. [DOI] [PubMed] [Google Scholar]
  • 15.de Vries AE, van der Wal MH, Nieuwenhuis MM, et al. Perceived barriers of heart failure nurses and cardiologists in using clinical decision support systems in the treatment of heart failure patients. BMC Med. Inform. Decis. Mak. 2013;13:54. doi: 10.1186/1472-6947-13-54. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 16.Piscotty R, Kalisch B. Nurses' use of clinical decision support: a literature review. Comput. Inform. Nurs. 2014;32(12):562–568. doi: 10.1097/CIN.0000000000000110. [DOI] [PubMed] [Google Scholar]
  • 17.Clinical Decision Support. [Accessed June 16, 2017];How to Implement EHRs. 2017 https://www.healthit.gov/providers-professionals/clinical-decision-support-cds.
  • 18. [Accessed June 16, 2017];Clinical Decision Support: More than Just 'Alerts' Tipsheet. 2014. 2017 https://www.healthit.gov/sites/default/files/clinicaldecisionsupport_tipsheet.pdf.
  • 19.Bakken S, Currie LM, Lee NJ, Roberts WD, Collins SA, Cimino JJ. Integrating evidence into clinical information systems for nursing decision support. Int. J. Med. Inform. 2008;77(6):413–420. doi: 10.1016/j.ijmedinf.2007.08.006. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 20.Dowding D, Randell R, Mitchell N, et al. Experience and nurses use of computerised decision support systems. Stud. Health Technol. Inform. 2009;146:506–510. [PubMed] [Google Scholar]
  • 21.Harrison RL, Lyerla F. Using nursing clinical decision support systems to achieve meaningful use. Comput. Inform. Nurs. 2012;30(7):380–385. doi: 10.1097/NCN.0b013e31823eb813. [DOI] [PubMed] [Google Scholar]
  • 22.Yuan MJ, Finley GM, Long J, Mills C, Johnson RK. Evaluation of user interface and workflow design of a bedside nursing clinical decision support system. Interact J Med Res. 2013;2(1):e4. doi: 10.2196/ijmr.2402. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 23.Lyerla F, LeRouge C, Cooke DA, Turpin D, Wilson L. A nursing clinical decision support system and potential predictors of head-of-bed position for patients receiving mechanical ventilation. Am. J. Crit. Care. 2010;19(1):39–47. doi: 10.4037/ajcc2010836. [DOI] [PubMed] [Google Scholar]
  • 24.Boston-Fleischhauer C. Enhancing healthcare process design with human factors engineering and reliability science, part 2: applying the knowledge to clinical documentation systems. J. Nurs. Adm. 2008;38(2):84–89. doi: 10.1097/01.NNA.0000295637.03216.26. [DOI] [PubMed] [Google Scholar]
  • 25.Boy GA. The handbook of human-machine interaction: A human-centered design approach. Burlington, VT: Ashgate; 2011. [Google Scholar]
  • 26.Campion TR, Jr, May AK, Waitman LR, Ozdas A, Lorenzi NM, Gadd CS. Characteristics and effects of nurse dosing over-rides on computer-based intensive insulin therapy protocol performance. J. Am. Med. Inform. Assoc. 2011;18(3):251–258. doi: 10.1136/amiajnl-2011-000129. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 27.Effken J, McGonigle D, Mastrian KG. The human-technology interface. In: McGonigle D, Mastrian KG, editors. Nursing informatics and the foundation of knowledge. 3. Burlington, MA: Ashgate; 2015. pp. 201–216. [Google Scholar]
  • 28.Johnson CM, Johnson TR, Zhang J. A user-centered framework for redesigning health care interfaces. J Biomed Inform. 2005;38(1):75–87. doi: 10.1016/j.jbi.2004.11.005. [DOI] [PubMed] [Google Scholar]
  • 29.Staggers N, Parks PL. Description and initial applications of the Staggers & Parks Nurse-Computer Interaction Framework. Comput. Nurs. 1993;11(6):282–290. [PubMed] [Google Scholar]
  • 30.Jeffery AD, Novak LL, Kennedy B, Dietrich MS, Mion LC. Participatory design of probability-based decision support tools for in-hospital nurses. J. Am. Med. Inform. Assoc. 2017 doi: 10.1093/jamia/ocx060. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 31.Campion TR, Jr, Waitman LR, Lorenzi NM, May AK, Gadd CS. Barriers and facilitators to the use of computer-based intensive insulin therapy. Int. J. Med. Inform. 2011;80(12):863–871. doi: 10.1016/j.ijmedinf.2011.10.003. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 32.Paul S, Hice A. Role of the acute care nurse in managing patients with heart failure using evidence-based care. Crit. Care Nurs. Q. 2014;37(4):357–376. doi: 10.1097/CNQ.0000000000000036. [DOI] [PubMed] [Google Scholar]
  • 33.National Library of Medicine. What is precision medicine? Your guide to understanding gentoc conditions. 2018 https://ghr.nlm.nih.gov/primer/precisionmedicine/definition.
  • 34.Nursing Knowledge 2016; Paper presented at: Big Data Science Conference2016; Minneapolis, MN. [Google Scholar]
  • 35.Tsoukalas A, Albertson T, Tagkopoulos I. From data to optimal decision making: a datadriven, probabilistic machine learning approach to decision support for patients with sepsis. JMIR medical informatics. 2015;3(1):e11. doi: 10.2196/medinform.3445. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 36.Churpek MM, Yuen TC, Park SY, Gibbons R, Edelson DP. Using Electronic Health Record Data to Develop and Validate a Prediction Model for Adverse Outcomes on the Wards. Crit. Care Med. 2014;42(4):841–848. doi: 10.1097/CCM.0000000000000038. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 37.Escobar GJ, LaGuardia JC, Turk BJ, Ragins A, Kipnis P, D D. Early detection of impending physiologic deterioration among patients who are not in intensive care: development of predictive models using data from an automated electronic medical record. J. Hosp. Med. 2012;7(5):388–395. doi: 10.1002/jhm.1929. [DOI] [PubMed] [Google Scholar]
  • 38.Panahiazar M, Taslimitehrani V, Pereira N, Pathak J. Using EHRs and Machine Learning for Heart Failure Survival Analysis. Studies in Health Technology and Informatics. 2015;216:40–44. [PMC free article] [PubMed] [Google Scholar]
  • 39.Sladojević M, Čanković M, Čemerlić S, Mihajlović B, Ađić F, M J. Data mining approach for in-hospital treatment outcome in patients with acute coronary syndrome. Med Pregl. 2015;68(5–6):157–161. doi: 10.2298/mpns1506157s. [DOI] [PubMed] [Google Scholar]
  • 40.Lee J, Maslove DM. Customization of a Severity of Illness Score Using Local Electronic Medical Record Data. J. Intensive Care Med. 2015;32(1):38–47. doi: 10.1177/0885066615585951. [DOI] [PubMed] [Google Scholar]
  • 41.Rumsfeld JS, Joynt KE, Maddox TM. Big data analytics to improve cardiovascular care: promise and challenges. Nature Reviews Cardiology. 2016;13(6):350–359. doi: 10.1038/nrcardio.2016.42. [DOI] [PubMed] [Google Scholar]
  • 42.Raghupathi W, Raghupathi V. Big data analytics in healthcare: promise and potential. Health information science and systems. 2014;2(1):3. doi: 10.1186/2047-2501-2-3. [DOI] [PMC free article] [PubMed] [Google Scholar]
  • 43.Jeffery AD. Methodological Challenges in Examining the Impact of Healthcare Predictive Analytics on Nursing-Sensitive Patient Outcomes. Computers, informatics, nursing : CIN. 2015;33(6):258–264. doi: 10.1097/CIN.0000000000000154. [DOI] [PubMed] [Google Scholar]
  • 44.Yancy CW, Jessup M, Bozkurt B, et al. 2013 ACCF/AHA guideline for the management of heart failure: A report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guidelines. 2013 [Google Scholar]

RESOURCES