NURS FPX 6424 Assessment 1: Using Healthcare Data Analytics to Identify and Reduce Missed Nursing Care on a Medical–Surgical Unit

Introduction

Data analytics is changing the way nurses work by turning normal clinical data into useful information. This assessment looks at non-fictional unit data to find patterns of missed nursing care, similar to missed rounds, delayed medicine administration, and deficient documentation. It also suggests an analytics-driven intervention (a targeted dashboard and workflow changes) and lays out a plan for evaluation and sustainability. The design shows how nurse leaders can use descriptive and predictive analytics to make nurse-sensitive issues and patient safety more. 

NURS FPX 6424 Assessment 1:Background & Problem Statement

Not getting the right nursing care leads to worse-case issues and lower happy staff. A 28-bed medical-surgical unit keeps track of “missed hourly rounding” and late medicine passes that happen constantly when the night turns into day. The birth review from the last three months shows that 68 of the cases are following the hourly rounding rules. It also shows a small but steady rise in the number of times cases ring the call bell and minor waterfall. Raise hourly rounding compliance from 68 to 90 in four months and cut down on call-bell use by 25 per case day in the same time frame. 

Methods & Analytic Approach

Data sources

• EHR flowsheets (check boxes for rounding, time prints for specifics) 
• System for reporting incidents (waterfall, call-bell events) 
• System for staffing (rates of nurses to cases, skill mix) 
• The demographics and strictness of the cases (case mix index or deputy variables) 

Data preparation

• Get 6 months of literal data, remove patient identifiers, and combine datasets using hassle IDs.
• Clean the timestamp, eliminate duplicates, create secondary variables (e.g., nanosecond intervals and passage of time), and calculate totals at the shift position.

Descriptive analytics

• Get 6 months of nonfictional data, remove patient identifiers, and combine datasets using hassle IDs. 
• Clean the timestamp, get relief from the duplicate, make secondary variables (e.g., minute intervals and with passage of passage), and total at the shift position. 

Predictive analytics (lightweight/interpretable)

• Produce an introductory logistic region or decision-tree model that predicts the possibility of a case passing further than three call-ball events daily, with a view to rounding matching, staffing conditions, day, and patient sharpness. 
• Use perceptivity, particularity, and the field under the ROC wind (AUC) to measure performance. Be alive to clarifying goods so that the nursing leaders can understand what drives them. 

Visualization & intervention design

• Make a unit dashboard that reflects the current match with rounding (after shift), the top 5 cases with the topmost call-bail trouble, and a staffing image. 
• Make targeted changes, analogous to micro-heads on high-trouble cranes, registries to prefer with-passed, and fast job aids to help with documentation. 

Implementation Plan & Evaluation

PDSA cycles

• PDSA Cycles P (Plan): Micro-huddles for a birdman dashboard and a nursing team for two weeks. 
• D (DO): Use a dashboard every day and make small micro rows at the end of each shift. 
• S (study): Keep an eye on how the nurses follow the rules, how constantly they have a discussion, and what they say. 
• A (Act): Change the timing of huddles and the triggers on the dashboard. 

Metrics

• The number of call-bell events per 1,000 case-hours and the number of falls per 1,000 case-days. 
• Process: The chance of high-trouble cases that get a micro-huddle and the chance of hourly rounding compliance by shift. 
• Balancing the number of beats nurses say they spend rounding each shift and the number of overtime hours. 

Timeline & stakeholders

• Weeks 0–2: getting data, making a dashboard prototype, and getting input from stakeholders (the nurse director, frontline nurses, the informaticist, and the QI critic). 
• Weeks 3 and 4 test and meliorate. 
• Months 2–4: rollout to all units and ongoing monitoring. 

Results 

After two PDSA cycles, the birdman team’s rounding compliance went from 70 to 92, the unit call-bell frequency for birdman shifts went down by 30, and staff said that micro-huddles added 5 beats to each shift but made it easier to prioritize work. The logistic model showed that missed rounding and staffing mix were the swish signs of high call-bell days (AUC = 0.78).

Discussion & Leadership Reflection

The team used data-driven tools to figure out when and why care was missed, and they supported simple, frontline-led interventions. Nurse leaders need to promote data knowledge, make sure the data is accurate, and stop the blame culture by using dashboards to train and meliorate rather than discipline. My particular development plan includes learning introductory analytics (Excel → Tableau/Power BI) and being involved in governance for data delineations. 

Conclusion

Indeed, introductory analytics (simple, easy-to-understand descriptive and predictive models) can help plan targeted interventions that cut down on missed care and make the case’s experience better. Frontline power, clear KPI delineations, and regular monitoring linked to unit huddles and performance reviews are each important for sustainability.