DNP 805 Using the clinical question you identified in the previous discussion question, determine the individual components to that question and pinpoint the location in the hypothetical database where the information you require will be extracted

Having elements of a discharge record being uploaded into a database provides useful information. Providers being able to review discharge plans, medications and history of a patient can guide clinical decisions for the best outcomes possible. Specific items such as discharge instructions, medications or prescriptions, and diagnosis could be available to every medical provider via a communal database. “Health Current is the health information exchange (HIE) that helps partners transform care by bringing together communities and information across Arizona. The HIE, provides secure access to patient health information as well as the secure exchange of patient health information between the HIE and its participating organizations and providers. More complete information is more meaningful and leads to better care and better outcomes. It makes healthcare transformation possible” (HIE, 2022).

Healthcurrent. HIE. 2022. https://healthcurrent.org/hie/

REPLY

The clinical problem from the previous discussion was chronic heart failure and the clinical question is if they will continue to use standardized medication treatments that may not be working with the complexity of chronic heart failure (Bai, Yao, Jiang, Bian, Zhou, Sun, Hu, Sun, Xie, & He, 2022). The Individual components to this question would be located in the electronic health records (EHR) of the patient within the database of the healthcare system. The individual components would be the patient demographics which includes the name of the patient, account number, sex, date of birth, race, religion, address, and insurance information, admission history and physical, the medication list, the laboratory results, the nursing records and the physician records. EHRs are designed to hold many types and ranges of patient data such as listed above and it has an endless capability for being customized to the particular needs of the patient and the HCP as well as the organization (Alexander, Hoy, & Frith, 2019).

References:

Alexander, S., Hoy, H., & Frith, K. (2019). Applied clinical informatics for nurses (2nd ed.). Jones & Bartlett Learning.

Bai, Y., Yao, H., Jiang, X., Bian, S., Zhou, J., Sun, X., Hu, G., Sun, L., Xie, G., & He, K. (2022). Construction of a non-mutually exclusive decision tree for medication recommendation of chronic heart failure. Frontiers in Pharmacology, 12. https://doi.org/10.3389/fphar.2021.758573

The clinical question proposed was, what interventions are impactful in improving decreasing nursing turnover among nurses? To do this you look at the nursing turnover rate and comparing it to leapfrog rating, CMS Stars, Magnet status, mandated patient ratios, workplace violence incidents, employee injuries, and union hospitals. This would allow for correlations of what makes facilities more appealing to nurses. This data could also be regionalized, because what is more important to nurses in California may be very different for those in Mississippi. They allows for targeted recruiting and retaining techniques. Some of these have already been studied on a smaller scale. For example, one study determined a correlation with workplace violence and turnover in two large teaching hospitals (Yeh et al., 2020). Another example is Magnet units have lower turnover than units a non-Magnet facilities (Park et al., 2016). What we don’t know is how widespread this is and if it varies across regions. This will add to that ability. Also, how has this changed post pandemic. Have the priories on what is keeping nursing from turning over the same? All are things that can be answered by this database.

DNP 805 Using the clinical question you identified in the previous discussion question

Reference

Park, S. H., Gass, S., & Boyle, D. K. (2016). Comparison of Reasons for Nurse Turnover in Magnet ® and Non-Magnet Hospitals. The Journal of Nursing Administration, 46(5), 284–290.

Yeh, T.-F., Chang, Y.-C., Feng, W.-H., Sclerosis, M., & Yang, C.-C. (2020). Effect of Workplace Violence on Turnover Intention: The Mediating Roles of Job Control, Psychological Demands, and Social Support. Inquiry : A Journal of Medical Care Organization, Provision and Financing, 57, 46958020969313. https://doi-org.lopes.idm.oclc.org/10.1177/0046958020969313

Click here to ORDER an A++ paper from our Verified MASTERS and DOCTORATE WRITERS DNP 805 Using the clinical question you identified in the previous discussion question, determine the individual components to that question and pinpoint the location in the hypothetical database where the information you require will be extracted:

There are many valid points for consideration in data mining related to nursing turnover. Considering the nursing shortage we are in, it is a hot topic and one worth investigating. There are two vital sides to this topic one concerns the nurse and the other concerns care for the patient. I appreciate your data mining considerations have variables that relate to both sides of this issue. In addition to considering the impact on the patient and nurse, the locality is another important factor that you addressed. Because this information can vary from location to location, it would be interesting to compare one region to another. Different factors help to keep staff at the bedside, and compensation is one of those factors (Halim, et al., 2020). With proper data mining techniques, this can be analyzed to entice nurses to stay. With the cost to replace a nurse, the current shortage, and patients who depend on nursing care, this data mining would be fruitful to the nursing profession.

Reference

Halim, Z., Muhammad M. W. Edwin, C. & Shah, A. (2020). Identifying factors for employee retention using computational techniques; An approach to assist the decision-making. SN Applied Sciences, 2, 1612.

Interesting topic and question Alicia, One that pulls at my emotions dearly when i see how much the bedside nurses are pulled in so many different directions. The early nursing turnover which is now a critical issue that has received worldwide attention and it has a lot of mitigating factors like some of the ones you have mentioned such as the mandated nurse-patient ratios, workplace violence, employee injuries. The aging population has added and increased pressure on the health care system with the increasing need for healthcare services which has continued to increase the need for nurses (Hu, Wang, Lan, & Wu, 2022). Personally, for me, what I consider the biggest issue is the non-standardized nurse-patient ratios nationally. Hence states like California and some have set ratios of 6 patients per RN while states like NJ base it on acuity so that they could continue to increase the number of patients per RN even when they are not short of RNs. Another issue I have is the incessant rush within healthcare. The rush to get things done especially in the medical units when it is not an emergency. This rush to get things done, does not afford the nurses the time to calmly critically think things through and because of the lack of staff especially the ancillary staff like the nursing assistants to support the nursing work, the nurses, have to do all things which increases the pressure and stress upon the nurses. A study reported that 22% of hospital nurses plan to leave their profession in less than a year because of workplace stress. The stress reduces nursing quality care, increases the re-recruitment costs, and the associated decrease in patient safety and positive outcomes (Hu, Wang, Lan, & Wu, 2022). There is also the negative feeling of the nurses when they have to keep training new staff constantly. These states and facilities forget to realize that, one, they are dealing with human lives and the nurses need to pay attention to the patients to avert any adverse events but when they are pulled in different directions, they are not able to focus on all their patients in a safe manner. An article points to three possible interventions of hope, career identity, job satisfaction that may help to reduce early nurse turnover (Hu, Wang, Lan, & Wu, 2022). The Nurses’ career identity affects their work enthusiasm and is positively associated to their job satisfaction which eventually affects the quality of their work. This is their understanding of the social impact of their profession on their work which is characterized by their feelings, values and their attitude to their work (Hu, Wang, Lan, & Wu, 2022). Hope is a concept that portrays positive motivation based on one’s sense of success from the will power and energy to achieve a set goal. Scholars have shown that hope is particularly important in the face of the intense competition and uncertainty that characterize the present work and career environment. Having high level of hope helps the nurses to appropriately deal with the psychological stress and be able to cope with the difficulties and perhaps decrease the negative impact of dissatisfaction with the job that generates intention to leave. So, when hope is lost or diminished, it becomes difficult to retain the nurse (Hu, Wang, Lan, & Wu, 2022). Likewise, job satisfaction is also a positive emotional reaction that is generated by the nurse individual assessment of their work. It is a negative association and an antecedent to nurse turnover intention (Hu, Wang, Lan, & Wu, 2022). Nurses particularly feel job dissatisfaction when they are constantly overwhelmed and overworked, leaving work 2-3 hours late to catch up on documentation which is worse when they have to come back the next day. This causes extreme lack of adequate sleep, stress and decreased mental cognition when they need it. This affects patient safety and outcome and it is not safe for the nurses either. When they feel that the safety of their nursing license is constantly being placed on the line, they will have the intention to leave. Job satisfaction has a negative association with turnover intention which suggests that improving the job satisfaction of nurses is an important strategy to retain nurses (Hu, Wang, Lan, & Wu, 2022).

References:

Hu, H., Wang, C., Lan, Y., & Wu, X. (2022). Nurses’ turnover intention, hope and career identity: The mediating role of job satisfaction. BMC Nursing, 21(1). https://doi.org/10.1186/s12912-022-00821-5

As a case manager, we are in constant contact with this issue of trying our best to encourage patients to make and maintain their medical appointments to avoid the less than 30 days hospital readmission rates for Heart failure (HF), which affecte the payments to hospitals. Like you have mentioned the 30-day readmission rate, there is also a medical spending for HF that is bound to rise to $53 billion and HF also contributing to the increased mortality rates with only about 30-40% of patients surviving after one year of HF admission. HF has also continued to impact post-discharge course hence the 30-day readmission rate of 27% like you mentioned. To prevent this situation, the Centers for Medicare & Medicaid Services (CMS) initiated the Hospital Readmissions Reduction Program (HRRP) in 2012 which will reduce payments to hospitals with higher readmission rates following admissions with HF. Though the rate has reduced for some hospitals but for others it still remains high (Nair, Lak, Hasan, Gunasekaran, Babar, & Gopalakrishna, 2020). Some of the other interventions that could be added to your individual component would be having a list of their medications to know what they are taking and to make sure that the patient knows what they are taking and how to take it. Also, patient education and stressing the need for lifestyle adjustments and care management which includes keeping their appointments and following the care regimen is an integral part of preventing readmissions. HF education must start on the day of admission and continue in small portions till they leave, so that they are able to understand and grasp the teaching (Nair, Lak, Hasan, Gunasekaran, Babar, & Gopalakrishna, 2020). Another component that can be looked at is a weekly or biweekly phone call, and home visits can be used to increase follow-up visits and thereby decrease readmission rates. Though these may not be documented in the patient electronic health record (EHR). Perhaps maybe they should start including it in the EHR as part of the process for reducing hospital readmission rates (Nair, Lak, Hasan, Gunasekaran, Babar, & Gopalakrishna, 2020).

References:

Nair, R., Lak, H., Hasan, S., Gunasekaran, D., Babar, A., & Gopalakrishna, K. V. (2020). Reducing all-cause 30-day hospital readmissions for patients presenting with acute heart failure exacerbations: A quality improvement initiative. Cureus. https://doi.org/10.7759/cureus.7420

Hospital re-admissions have become a healthcare nightmare. Undoubtedly, its prevention has the potential of delivering better quality care while saving healthcare costs. There are lots of research studies being conducted on the key factors that contribute to preventable hospital readmissions. Interestingly, there’s increased awareness regarding the prediction of readmission risks that may assist physicians and hospital management to develop early interventions that identify and treat patients at high risk of readmissions and enhance both quality of care and financial outcomes. (Ben-Assuli & Padman, 2018). I believe telehealth medicine may be helpful in preventing readmissions or reducing the rate of readmissions. However, different mining techniques to predict readmission risks have been explored and compared. A comparative analysis of data mining techniques by Hon, et al, (2016), on patients specifically with Congestive Heart Failure (CHF), could identify higher readmission risks in patients with an anticipated lengthy and expensive 30-day readmission (Ben-Assuli & Padman, 2018).

References

Ben-Assuli, O. and Padman, R. (2018). Analysing repeated hospital readmissions using data mining …

https://www.ncbi.nlm.nih.gov › articles › PMC6452839

Hon C. P., Pereira M., Sushmita S., Teredesai A., & De Cock M. (2016). Risk stratification for hospital readmission of heart failure patients: A machine learning approach. In Proceedings of the 7th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics (pp. 491–492). ACM. [Google Scholar]

Patients who suffer from COPD are at a higher risk for hospital readmission. Using data mining techniques, clinicians, case managers, and researchers can create predictive analytic tools to help determine readmission risk based on personal characteristics, labs, medications, and severity of disease progression. At times, healthcare providers know some patients are inherently at higher risk for readmission. Data mining techniques can help identify those patients who are at an increased risk for readmission but would otherwise, fall through the cracks and might not be identified. Regardless, patients with a diagnosis of COPD have been identified as a high risk for readmission, and hospitals are penalized if these patients have a readmission within 30 days (Agarwal et al., 2018).

Hospital administrators and providers would benefit from having data mining information on COPD readmissions in order to equip patients with the right information and resources. Using predictive analytics, this information is compiled and anticipates those who are at an increased risk for readmission. Mohamed et al. (2022) compared data for patients who were readmitted with COPD. A decrease in physical activity, comorbidities, and Beck Depression Inventory were important variables relating to readmissions for patients with COPD (Mohamed et al., 2022). Comorbidities are easily extracted from the electronic medical record, either in past medical history or through the history and physical. The actual inventory would need to be completed for the Beck Depression Inventory results to be available. A decrease in physical activity seems more objective, however, there may be a scoring system available that a trained physical therapist could perform to gather data regarding changes in activity level.

Huang et al. (2020) found smoking history and current smoking status to be a piece of useful information when it comes to predicting readmission risks. Additionally, Huang et al. (2020) found medications the patient was prescribed to be a factor as well. This information is easily extrapolated from the electronic medical record. In using these key risk factors, which can be pulled from the electronic medical record through the medication administration record, past and current medical history, scoring from the therapy team and through the history and physical, patients can more easily be identified as a higher readmission risk.

References

Agarwal, A., Baechle, C., Behara, R., Zhu, X. (2018). A natural language processing framework for assessing hospital readmissions for patients with COPD. IEEE Journal of Biomedical & Health Informatics, 22(2), 588-596.

Huang C. D., Goo, J., Behara, R. & Agarwal, A. (2020). Clinical decision support system for managing COPD-related readmission risk. Information Systems Frontier, 22, 735-747. Doi: https://doi.org/10.1007/s10796-018-9881-4

Mohamed, I., Fouda, M. M. & Hosny, K. M. (2022). Machine learning algorithms for COPD patients readmission prediction: A data analytics approach. IEEE Access, 10, 15279 – 15287. Doi: 10.1109/ACCESS.2022.3148600

Unread

The previously identified clinical question was; what is the impact of oral care using oral chlorhexidine on the incidence of ventilator-associated pneumonia (VAP) among critically ill patients under mechanical intubation? Intensive care patients under mechanical intubation are at a high risk of developing healthcare associated infections (HAIs), particularly VAP. VAP is associated with high rates of mortality and morbidity, and prolonged hospital stays that negatively impact healthcare costs (Kocaçal & Türk, 2019). VAP has been associated with colonization of the oropharynx by gram negative pathogens and dental plaque while the endotracheal tube conducts the pathogens from the oral cavity to the lower respiratory tract. There are various strategies recommended to decrease the colonization of the oral cavity by pathogens such as oral care using chlorhexidine, a broad-spectrum antiseptic.

The individual components to this clinical question during data mining should include; sex, age, underlying medical conditions (pre-existing pulmonary disease, organ failure, head trauma, AIDS, and coma), intubation, duration of mechanical intubation, nutrition (enteral nutrition and nutritional status), aspiration of oropharyngeal/gastric contents, prophylaxis for stress ulcers, and use of systemic antibiotics. The demographics category will provide important data about the patient’s sex and age, the laboratory category will provide essential microbiology data, under the physiologic data, information captured should include the vital signs, the procedural notes should highlight the duration of mechanical ventilation, whether the patient is under mechanical intubation, nutrition, and whether the patient aspirated gastric/oropharyngeal contents. The medication category should capture information about current prescriptions, timing, and dosing. In such a case, Chen, Lin & Yang (2020) suggest that, demographic attributes such as age and sex can be used as predictors to recognize patients at high risk of developing VAP by identifying hidden patterns and important information.

References

Chen, C. Y., Lin, W. C., & Yang, H. Y. (2020). Diagnosis of ventilator-associated pneumonia using electronic nose sensor array signals: solutions to improve the application of machine learning in respiratory research. Respiratory research, 21(1), 1-12.

Kocaçal Güler, E., & Türk, G. (2019). Oral chlorhexidine against ventilator-associated pneumonia and microbial colonization in intensive care patients. Western Journal of Nursing Research, 41(6), 901-919. https://doi.org/10.1177%2F0193945918781531

A heart disease prediction model, which implements data mining technique, can help the medical practitioners in detecting the heart disease status based on the patient’s clinical data. Data mining classification techniques for good decision making in the field of health care addressed are namely Decision trees, Naive Bayes, Neural Networks and Support Vector Machines. Combining any of these algorithms helps to make decisions quicker and more precise (Sayad AT, Halkarnikar PP. 2014).

A major challenge faced by health care organizations, such as hospitals and medical centers, is the provision of quality services at affordable costs. The quality service implies diagnosing patients properly and administering effective treatments. The available heart disease database consists of both numerical and categorical data. Before further processing, cleaning, and filtering are applied on these records in order to filter the irrelevant data from the database. The proposed system can determine an exact hidden knowledge, patterns and relationships associated with heart disease from a historical heart disease database. It can also answer the complex queries for diagnosing heart disease; therefore, it can be helpful to health care practitioners to make intelligent clinical decisions (Go AS, Mozaffarian D, Roger VL, et al, 2014).

Information extraction refers to the task of automatically extracting structured information from unstructured documents. Sub-tasks like named entity, relationship, and terminology extraction are extremely useful to characterize the content of large text corpora and give data analysts a sense of what information might be present in such corpora (Roger VL, Weston SA, Redfield MM, et al, 2014).

Structured Data: Structured data is information that can be stored and displayed in a consistent, organized manner. This type of data can be validated against expected or biologically plausible ranges and easily analyzed over time. Examples of health data that would fall into this category include numerical values like height, weight, and blood pressure, as well as categorical values like blood type or ordinal values like the stages of a disease diagnosis.

Clinical diagnosis: Cardiac disorder

Clinical Measures: Pulse, Systolic blood pressure

Labs: Electrocardiogram, Cardiac computerized tomography, Cholesterol, Serum glucose and Troponin level

Medication reconciliation: Beta Blockers, Loop diuretics

Prescription order: Furosemide, digoxin

Imaging order: Echo orders

Hospitalization

Unstructured data: Unstructured data, on the other hand, lacks the organization and precision of structured data. Examples in this category include physician notes, x-ray images and even faxed copies of structured data. In most cases, unstructured data must be manually analyzed and interpreted.

References

Go AS, Mozaffarian D, Roger VL, et al. heart disease and stroke statistics–2014 update: a report from the American Heart Association. Circulation. 2014 Jan 21;129(3):e28–e292.

Roger VL, Weston SA, Redfield MM, et al. Trends in heart failure incidence and survival in a community-based population. JAMA. 2014 Jul 21;292(3):344–50.

Sayad AT, Halkarnikar PP. (2014). Diagnosis of heart disease using neural network approach. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5863635/ Int J Adv Sci Eng Technol. 2014;2:88–92.

DNP 805 Using the clinical question you identified in the previous discussion question, determine the individual components to that question and pinpoint the location in the hypothetical database where the information you require will be extracted