The healthcare workers were not consonant of the study being conducted. Bias was not a factor.



Article: Nearest-Neighbor and Logistic Regression Analyses of Clinical and Heart Rate

The goal and purposes of the research study and the article was to test the concept that the nearest-neighbor adds to logistic regression in the early diagnosis of late-onset of neonatal sepsis (Xiao et al., 2010). The study population was all admissions to the University of Virginia NICU from July 1999 to July 2003 of patients who were 7 r more days of age (Xiao et al., 2010). Laboratory teste were available to archive and review. The analysis was limited to the time that the data was available, or 92% of the total time (Xiao et al., 2010). Infants were followed to identify sepsis; however, health care personnel were not consonant of the monitoring. Sepsis was defined to be present when a physician suspected the diagnosis, obtained a blood culture that grew bacteria, and antibiotic therapy was initiated of 5 days or more (Xiao et al., 2010).

The data sets were from both the nearest-neighbor and logistic regression analyses call for training data set and a test data set (Xiao et al., 2010). Each data point in the test would be evaluated. The duration of the test result was 12 hours (Xiao et al., 2010). The selection criteria were based on work using the regression modeling that was indicative of epoch in which most of the diagnostic test results were available (Xiao et al., 2010). Cases of sepsis were individually reviewed for data accuracy, the health care personnel were blinded to the results (Xiao et al., 2010). The logistic regression model used was an induvial nearest-neighbor model with HRC and laboratory models were combined, so that 1 or more laboratory values available, the maximum of the prediction was made final in the final prediction of the combined model (Xiao et al., 2010).

Logistic regression is used in the study, the results of the study concluded that both neareest-neighbor and regression models using heart rate characteristics and available laboratory results were notably associated with impending sepsis, and each model added dependent information to the other (Xiao et al., 2010).

The study was not biased. The healthcare workers were not consonant of the study being conducted. Bias was not a factor. The weaknesses of the study resulted in the HRC data not being available for online inspection by the physician, and results are likely skewed (Xiao et al., 2010).  To mitigate or solve for the weaknesses the HRC data is required. Otherwise, the data collected is not an accurate summary.

Findings can contribute to nursing as it adds to existing logistic regression methods for early detection and diagnosis of neonatal sepsis. The nearest-neighbor analysis is a new approach to predicting impending illness, and both logistic regression and nearest-neighbor analysis models based on the HRC and laboratory test results contribute the independent information (Xiao et al., 2010). The best predictions indicated that both models were driven by the single most abnormal finding (Xiao et al., 2010). The approach can predict and prevent illness resulting in decreased hospitalization and improved quality of life.


Xiao, Y., Griffin, M. P., Lake, D. E., & Moorman, J. R. (2010). Nearest-Neighbor and Logistic

Regression Analyses of Clinical and Heart Rate Characteristics in the Early Diagnosis

of Neonatal Sepsis. Medical Decision Making, 30(2), 258-266.




Article: Prediction of influenza vaccination outcome by neural networks and logistic regression

What are the goals and purposes of the research study the article describes?

The purpose is to design a model to enable successful prediction of outcome of influenza vaccination based on a real historical medical data (Trictica-Majnaric & et al., 2010). In addition, to design a computer based neural network model that will enable successful prediction of the outcome of influenza vaccine efficacy based on data related to influenza viruses and influenza vaccination in combination with historical medical data (Trictica-Majnaric & et al., 2010).

How is logistic regression used in the study? What are the results of its use?

In this study the logistic regression was used to estimate risk of reaction to influenza vaccine and to extract variables which are found to be an importance in risk prediction (Trictica-Majnaric & et al., 2010). The logistic regression model is used with the same initial set of input variables as the NN model with the forward selection procedure (selection criteria was p <0.05) (Trictica-Majnaric & et al., 2010). With the output, a binary variable was used with one category, representing a patient with a negative influenza vaccine outcome (0) and the other representing a patient with a positive influenza vaccine outcome (1). Essentially c 0 accounts for the number of patients predicted to have a negative vaccine outcome; whereas, t 0 are the actual (target) negative vaccine outcomes, c 1 is the number of predicted to have a positive vaccine outcome, and t 1 are the actual positive vaccine outcomes (Trictica-Majnaric & et al., 2010).

What other quantitative and statistical methods could be used to address the research issue discussed in the article?

There are several other methods that could have been used to address the issue discussed in the article. According to Gray, Grove, and Sutherland (2016), there are four types of quantitative research of which include descriptive, correlational, causal comparative/quasi-experimental, and experimental. Many of the quantitative methods and designs are to develop the body of knowledge needed for evidenced based practice (Gray & et al., 2013). Whereas the statistical approach is most often used as a prediction regression analysis (Gray & et al., 2013). The purpose of a regression analysis was to identify which factor or factors to predict or explain the value of a dependent (outcome) variable (Gray & et al., 2013). Additionally, these methods include simple linear regression, multiple regression, logistic regression, and cox proportional hazard regression (Gray & et al., 2013).

What are the strengths and weakness of the study?

Due to the small sample size, it serves as a limitation, it was necessary to perform a 10-fold cross validation procedure to estimate the generalization ability of the model (Trictica-Majnaric & et al., 2010). The procedure showed that the multilayer perceptron algorithm had the highest average performance obtained on 10 samples, therefore can be proposed as the model that generalizes better (Trictica-Majnaric & et al., 2010). Subsequently, the sensitivity and specificity ratios of the NN model were also higher than those ratios of the LR model (Trictica-Majnaric & et al., 2010). The model was able to balance the false positives and false negative hit rates and determine important features that were necessary to correctly classify patients with negative vaccine outcome between those with positive vaccine outcome (Trictica-Majnaric & et al., 2010).

How could the weaknesses of the study be remedied?

I would have to suggest using a larger sample size and random controlled trial to eliminate any bias.

How could findings from this study contribute to evidence-based practice, the nursing profession, or society?

Although the study presented preliminary findings, its’ potential of the methodology in this field was found to have been quite evident and showed to have promising primary health care benefits associated with influenza vaccination (Trictica-Majnaric & et al., 2010). Therefore, the research study confirms improved patient outcomes when practiced in an evidenced based approach.


Gray, J.R., Grove, S.K., & Sutherland, S. (2017). Burns and Grove’s the practice of nursing

research: Appraisal, synthesis, and generation of evidence (8th ed). St Louis, MO: Saunders Elsevier

Tritica-Majnaric, L., Zekic-Susak, M., Sarlija, N., & Vitale, B. (2010). Prediction of influenza

vaccination outcome by neural networks a logistic regression. Journal of Biomedical Informatics, 43(5), 774-781. Doi: 10.1016/j.jbi.2010.04.011



Describe your selected technology, including when it was first introduced into the health care industry

The selected technological innovation for this assignment is mHealth. mHealth also referred to mobile health is the use of mobile devices to provide treatment and management to the patients. The technology relies on the use of communication devices such as personal digital assistants, tablet computers and mobile phones. mHealth is considered the sub-segment of eHealth that entails the use of information and communication technologies (Sort, 2017). The history of mHealth dates back to the period of emergence of mobile phone technologies.

Assess the applications of the technology, noting the benefits and potential challenges of the innovation

Health has a number of applications in psychiatric practice. Firstly, the technology is utilized in the provision of health education to patients with mental health problems. Patients with mental health problems can receive short-messages about the effective management of their conditions and the required lifestyle and behavioral interventions that they should embrace. mHealth is also used in psychiatric practice to improve the level of treatment adherence among patients. Patients receive reminders about medication use and importance of adhering to the prescribed treatments for the realization of optimum outcomes of care. mHealth also addresses barriers to care such as geographical location and cost (Grossman et al., 2020). Patients with mental health problems can receive the care that they need irrespective of their distance from the healthcare providers.

Appraise the potential of the innovation to improve health care practice and related outcomes.
Read a selection of your colleagues’ postings

mHealth is however associated with some challenges. Firstly, it does not address all the care needs of the patients in entirety. The technology does not provide the physical interaction of the patients and providers, which is essential in provision of quality and safe care. The technology also has the limitation of high cost of acquisition as well as ownership. Health organizations have to spend a significant amount of their financial resources to establish it. Lastly, mhealth is associated with the increased risk of data loss due to its reliance on mobile phones (Sort, 2017). Despite these weaknesses, the technology has the potential of improving the healthcare practices and related outcomes in psychiatry.


Grossman, J. T., Frumkin, M. R., Rodebaugh, T. L., & Lenze, E. J. (2020). MHealth Assessment and Intervention of Depression and Anxiety in Older Adults. Harvard Review of Psychiatry28(3), 203–214.

Sort, A. (2017). The role of mHealth in mental health. MHealth3.



Decision Support and Innovative Informatics Tools

                       Decision Support Systems

Decision support systems (DSS) is an information system that aids a business in decision-making activities that require judgment, determination, and a sequence of actions. In healthcare, the DSS is known as the clinical decision support (CDS). CDS system is a healthcare technology tool that helps to improve patient care by assisting healthcare providers with decision making by analyzing patient data.  The CDS provides clinicians, staff, patients or other individuals with knowledge and person-specific information, intelligently filtered, or presented at appropriate times, to enhance health and health care. CDS encompasses a variety of tools to enhance decision-making in the clinical workflow. These tools include computerized alerts and reminders to care providers and patients; clinical guidelines; condition-specific order sets; focused patient data reports and summaries; documentation templates; diagnostic support, and contextually relevant reference information, among other tools. CDS was included by congress as a centerpiece of the Medicare and Medicaid electronic health record (EHR) incentive programs Meaningful Use. CDS is a key tool for improving the quality of healthcare. CDS system helps with condition diagnosis and improves care by eliminating unnecessary testing thereby enhancing patient safety (HealthIT,2018). CDS is vital for health information technology (HIT) and EHR functionality because it contributes to increased quality of care, and enhanced health outcomes, improved efficiency, and enhances provider and patient satisfaction. CDS works by providing clinicians with knowledge and patient- specific information that are presented at appropriate times to enhance health and healthcare (Saba, and McCormick,2015). CDS systems improves the quality of health care in the United States because the use of CDS systems increases the practice of evidence-based practice as well as adherence as it provides clinicians and caregivers with the clinical knowledge and patient-specific information that will help in decision making (HealthIT,2018).

When Introduced into the Healthcare Industry

Since their first use in the 1980s, CDSS have seen a rapid evolution. They are now commonly administered through electronic medical records and other computerized clinical workflows, which has been facilitated by increasing global adoption of electronic medical records with advanced capabilities (Abderrazak et al., 2017).

Applications of the Technology, Benefits and Potential Challenges

Based on the information the patient provided, recommendations and patient-specific assessments are generated from a clinical knowledgebase and communicated effectively at appropriate times during patient care. CDS systems establishes a standard knowledge structure that aligns with written evidence-based guidelines (Eichner,2010).


A DSS increases the speed and efficiency of decision-making activities, a DSS can collect and analyze real-time data, increased quality of care and enhanced health helps with avoidance of errors and adverse events, improved efficiency, cost-benefit, and provider and patient satisfaction (Reed et al., 2020).

Potential Challenges

The cost to develop and implement a DSS is a huge capital investment, which makes it less accessible to smaller organizations.

Appraise the Potential of the Innovation to Improve Health Care Practice and Related Outcomes.

Computerized clinical decision support systems, or CDSS, represent a paradigm shift in healthcare today. CDSS are used to augment clinicians in their complex decision-making processes. Since their first use in the 1980s, they are now commonly administered through electronic medical records and other computerized clinical workflows, which has been facilitated by increasing global adoption of electronic medical records with advanced capabilities. A clinical decision support system (CDSS) is intended to improve healthcare delivery by enhancing medical decisions with targeted clinical knowledge, patient information, and other health information as a  traditional CDSS is comprised of software designed to be a direct aid to clinical-decision making, in which the characteristics of an individual patient are matched to a computerized clinical knowledge base and patient-specific assessments or recommendations are then presented to the clinician for a decision (Reed et al., 2020).


Abderrazak, S., Amina, N., AbdelKamel, T., Ramtani, T., & Ouhab, A. (2017). Decision support system for health care resources allocation. Electronic Physician, 9(6), 4661–4668.

Eichner, J. (2010). Challenges and barriers to Clinical Decision Support design. Retrieved from

Health IT. (2018). Clinical decision support.

Reed T. Sutton, David Pincock, Daniel C. Baumgart, Daniel C. Sadowski, Richard N. Fedorak, & Karen I. Kroeker. (2020). An overview of clinical decision support systems: benefits, risks, and strategies for success. Npj Digital Medicine, 3(1), 1–10.

Saba, V. K., & McCormick, K. A. (2015). Essentials of nursing informatics (6th ed.). New York, NY: McGraw-Hill.