Informatics Nursing and Big Data

Introduction

A major component of nursing informatics is the study and use of clinical decision support systems. The clinical decision support systems seek to provide healthcare practitioners with whatever they require at the time and place of decision-making with an aim of delivering the best possible patient care. Informatics is a common phenomenon within the healthcare sector. The advancements in nursing informatics have been facilitated by changing technological advances. Application of nursing informatics has facilitated the reduction of medication errors. The integration of informatics and evidence-based practice facilitates the improvement of care provided in healthcare facilities. This paper seeks to review the benefits accrued from informatic nursing, review the use of clinical decision system, and evaluate the use of big data analytics and big data mining in enhancing the delivery of healthcare services.

Benefits of Informatics Nursing

Among the successes that have been acquired from the use of informatics nursing to healthcare is a reduction in medication error. Medication error refers to a preventable event that may lead to inappropriate medication use and cause patients harm at a point when medication is in being administered the healthcare professional. The use of electronic health record (EHR) and barcode medication administration (BCMA) have assisted nurses to provide safer patient care, efficiently manage patient information, and enhance the documentation. The use of informatics systems such as BCMA technology with an electronic medication administration (eMAR) leads to improvement in medication administration safety on a universal level. This technology works better when incorporated with EHR.

The informatics system starts with the computerized order entry by the provider. This capability is essential in minimizing the probability of occurrence of a transcription error. The pharmacist then verifies the order and dispenses the medication. The RN notes the active medication order in the patient’s medical record. After the verification of the medication, the nurse then scans the patient’s bar-coded wristband to facilitate positive identification. The nurse then clarifies the medication order in the eMAR and scans the bar-coded medication. The system issues an alert in case one of the five rights (right patient, medication, dose, time, and route) is not adhered to. The success rate of the BCMA technology has been found to minimize medication errors by 65%-86% (Gann, 2015). Other studies have added evidence to support this attributed success in the reduction of medication errors. It has been indicated that the BCMA system minimized the absolute rate of non-timing errors by 4.6%. It has also been indicated that the inclusion of BCMA system into CPOE and ADD system minimizes medication administration errors in the medical-surgical units from 8% to 3.4% (Shah, Lo, Babich, Tsao, & Bansback, 2016).

Clinical Decision Support System

Clinical decision support systems (CDSS) refers to a computerized program that offers clinical knowledge and patient-related data, intelligently filtered and provided at an appropriate time to facilitate patient care. The variables included in the CDSS include function, user, setting, and desired outcome. The clinical decision support system is used to carry out functions such as alerting, reminding, critiquing, interpreting, predicting, diagnosing, assisting, and suggesting (Lyerla, Lerounge, Cooke, Turpin, & Wilson, 2010). Decision support involves the integration of evidence with specifications from individual patients to offer advice or guidance in the process of decision making. Decision support allows health professionals to search for information concerning individual patients stored in the system, seek evidence-based guidance, provide advice on the treatment, and management that is ideal for the patient (Dowding, 2013).  

An example in the application of nursing clinical decision support system is on its application to assist the nurses to improve positioning of patients receiving mechanical ventilation. In this case, the CDD system offers a pop-up alert window on the computer screen after a nurse electronically documents the HBO angle for a patient receiving mechanical ventilation. The nursing clinical decision support system in such a case is integrated into a patient’s electronic flow sheet with an aim of enhancing the nurse’s adherence to guidelines (Lyerla, 2010).

Big Data Mining and Analytics in Healthcare

Big data in healthcare refers to the large and complex data that is generated from the electronic health records in different data formats. The nature of this data poses challenges to analyze and manage with normal systems. This calls for big data analytics, which involves the integration of heterogeneous data, quality controls, analysis, modeling, interpretation, and validation process. The use of big data analytics offers comprehensive knowledge mined from the available huge amount of data. The new knowledge acquired from big data analytics offers comprehensive benefits to the patients, clinicians, and health policy makers (Ristevski & Chen, 2018). The application of analytics such as data mining, text mining, and big data analytics assist healthcare professionals in disease prediction and treatment. This has impacted the healthcare sector by improving the delivery of care and reduced costs.  

An emerging trend in the big data analytics is on healthcare internet of things (IoT). The internet of things refers to the increasing smart, interconnected devices, and sensors that allow sharing of tidal volumes of data that is generated and shared between devices. The data arising from the healthcare IoT is largely unstructured. This leads to the creation of a dire need of Hadoop and other advanced big data analytics. In healthcare sectors, there are numerous devices with each monitoring a different aspect of patient behavior such as glucose level, fetal status, electrocardiograms, and blood pressure. Traditionally the readings on these factors would require a follow-up visit to a physician. However, the presence of smarter monitoring device refines the process thereby, reducing the need for direct intervention by the healthcare provider. The rise in wearable devices continues to play a critical role in facilitating continuous health monitoring of people (Manogaran at al., 2017). Some devices facilitate the adherence of medication regimen at home using smart dispensers and allow healthcare providers to get patients to resume proper medication. It is clear that the possibility presented by healthcare IoT is likely to reduce costs and improve patient care.

Big data analytics and data mining allow the processing of crude data and meaningful information. This process is likely to detect instances of fraud and falsehood. Big data analytics and data mining analyzes data from different sources and formats and identifies anomalies that might warrant further investigation (Lambrou, 2014).

Conclusion

The discussion above discusses how informatics nursing affects the provision of healthcare services, how clinical decision support system influences clinical decisions, and also evaluate the implication of big data analytics to healthcare sector. The success that have been acquired from the use of nursing informatics to healthcare is reduction of medication error. This is through the reliance on electronic health record (EHR) and bar code medication administration (BCMA). The clinical decision support system is used to carry out functions such as alerting, reminding, critiquing, interpreting, predicting, diagnosing, assisting, and suggesting. Big data analytics has been noted to involve the integration of heterogenous data, quality controls, analysis, modelling, interpretation and validation process

References

Dowding, D. (2013). Using computerised decision-support systems. Nursing times, 109(36), 23-25.

Gann, M. (2015). How informatics nurses use barcode technology to reduce medication errors. Nursing2018, 45(3), 60-66.

Lambrou, N. (2014). Big data, false data, smart data, dumb data: measuring the human condition. ARPA journal, 2.

Lyerla, F., LeRouge, C., Cooke, D. A., Turpin, D., & Wilson, L. (2010). A nursing clinical decision support system and potential predictors of head-of-bed position for patients receiving mechanical ventilation. American Journal of Critical Care, 19(1), 39-47.

Manogaran, G., Lopez, D., Thota, C., Abbas, K. M., Pyne, S., & Sundarasekar, R. (2017). Big data analytics in healthcare Internet of Things. In Innovative healthcare systems for the 21st century(pp. 263-284). Springer, Cham.

Ristevski, B., & Chen, M. (2018). Big Data Analytics in Medicine and Healthcare. Journal of integrative bioinformatics, 15(6), 1-5.

Shah, K., Lo, C., Babich, M., Tsao, N. W., & Bansback, N. J. (2016). Barcode medication administration technology: a systematic review of impact on patient safety when used with computerized prescriber order entry and automated dispensing devices. The Canadian journal of hospital pharmacy, 69(5), 394.