HLTH7029_Assessment3_VladimirChudin

1.

QUALITY & SAFETY
INITIATIVE
Rx
Vladimir Chudin
AI
Student ID: 22226249
HLTH7029 Quality and Safety
Assessment 3 Presentation
Western Sydney University
May 2026
✓
AI-Assisted Electronic
Medication Administration
System
Reducing medication errors in Australian hospitals through real-time
alerts, barcode verification, staff training and continuous audit.
AI-EMAS
Medication Safety
Patient Safety
Vladimir Chudin
Student ID: 22226249
HLTH7029 Quality and Safety
Assessment 3 Presentation
Western Sydney University | May 2026
01

2.

Executive Summary
Key strategic overview
Clinical Risk
Digital Intervention
Expected Outcomes
AI
✓
Problem
Solution
Impact
Medication errors remain a
major source of preventable
patient harm and healthcare
risk in Australian hospitals
AI-EMAS enhances medication
safety through barcode
verification, real-time alerts and
clinical decision support
Expected outcomes include
improved patient safety,
reduced medication errors,
increased staff confidence and
enhanced workflow efficiency
!
WHO, 2021; Bates et al., 2021; Sutton et al., 2020
02

3.

Medication Errors: Why This Matters
Patient safety, quality of care and organisational risk
Medication errors can occur
during prescribing, dispensing
or administration.
Error
Harm
System
Burden
• Linked with preventable harm
• Associated with higher morbidity and
mortality
• Increases workload, healthcare costs and
clinical governance pressure
Quality issue → safety risk → system
improvement opportunity
Medication-related harm remains one of the
most common preventable adverse events in
hospitals
World Health Organization, 2021; Australian Commission on Safety and Quality in Health Care, 2026
03

4.

Root Causes: A System-Level Problem
Medication errors arise from workflow and organisational factors
Workload
Communication gaps
Polypharmacy
Medication
Errors
Manual input
System-level contributors
Workflow inefficiencies
Interruptions
Frequent interruptions during medication rounds and time pressure
Weak
decision
support
Human factors
Staff fatigue, cognitive overload and multitasking
Technology limitations
Limited real-time alerts and reliance on manual documentation
Communication failures
Rodziewicz et al., 2024; Tariq et al., 2024; Sutton et al., 2020
Incomplete handovers and prescribing miscommunication
04

5.

Current Workflow Gaps
Where the risk enters the medication process
1
2
3
4
Prescribe
Dispense
Administer
Document
Missing clinical
information
Manual verification
process
Interruptions + time
pressure
Delayed or duplicated
entry
Real-time alerts
Automated documentation
AI verification
Barcode scanning
Key issue: current systems may not provide enough real-time
decision support.
Sutton et al., 2020; Assessment 2 proposal
05

6.

Proposed Initiative: AI-EMAS
A safer electronic medication administration system
AI-enabled medication verification workflow
AI-assisted eMAR
• Real-time medication alerts
Flags high-risk doses and potential
interactions instantly
Medication Safety Dashboard
• Barcode medication
verification
Patient ID matched
Confirms correct patient, medication
Dose checked
Interaction alert
Barcode verified
and dosage before administration
• Clinical decision support
Provides evidence-based prompts
during medication administration
• Automated safety checks
Identifies duplicate therapy and
prescribing inconsistencies
• Reduced manual
documentation
Minimises repetitive data entry and
documentation delays
06
Bates et al., 2021; Sutton et al., 2020

7.

How AI-EMAS Works in Practice
A point-of-care safety workflow
The system adds safety checks before medication reaches the patient
Safety checkpoints integrated throughout the workflow
1
2
3
4
5
Patient ID
Medication
AI screen
Nurse action
Audit trail
barcode scan
barcode check
dose + interaction
alert
confirm or escalate
automatic record
Clinical scenario example
1. Patient wristband and medication barcode are scanned before administration
2. The AI system identifies a potential medication interaction and generates a real-time alert
3. The nurse escalates the concern for clinical review before medication administration proceeds
Bates et al., 2021; Craswell et al., 2021
07

8.

Evidence Supporting the Initiative
Technology can strengthen medication safety when implemented well
Evidence
AI + patient safety
AI-supported systems can
reduce medication-related risk
through real-time clinical alerts
and error detection
Example: interaction alert
generated before administration
of anticoagulants.
Bates et al., 2021
Improves early risk identification
Bates et al., 2021; Sutton et al., 2020; Craswell et al., 2021
Evidence
Evidence
Clinical decision
support
Medication
automation
CDSS can improve care but
requires careful workflow
integration.
Automated medication
technologies can support
nursing and pharmacy
workflows.
Example: dosage warning
displayed for renal impairment
patients.
Example: barcode mismatch
detected before medication
administration.
Sutton et al., 2020
Craswell et al., 2021
Supports safer clinical decisions
Enhances workflow efficiency
08

9.

Stakeholder Engagement
IT team
Implementation depends on collaboration, not technology alone
Nurses
Doctors
Governance
AI-EMAS
Implementation
Pharmacists
Key implementation roles
Nurses
Medication administration, barcode scanning and escalation of safety alerts
Patients
Pharmacists
Medication review, interaction verification and safety monitoring
Doctors
Safe prescribing practices and clinical decision-making
IT team
System integration, technical support and workflow optimisation
Governance
Policy oversight, compliance monitoring and audit processes
Assessment 2 proposal; Craswell et al., 2021
Patients
Identity confirmation and participation in medication safety
09

10.

Change Management Strategy
Using Lewin’s model to reduce resistance and sustain practice change
Phase
Key actions
Expected outcome
Unfreeze
Communicate medication safety Staff recognise the need for practice
risks, explain need for digital change,
improvement
address staff concerns
Change
Pilot AI-EMAS, provide staff training, Staff begin integrating AI-EMAS into
introduce workflow support and
routine workflow
clinical guidance
Embed into policy, conduct audits, AI-EMAS becomes part of standard
monitor compliance and provide
medication safety practice
refresher education
Refreeze
Key implementation principle
Sustainable change requires continuous staff engagement, leadership support and workflow integration
Change management principle applied to Assessment 2 implementation plan
10

11.

Staff Education & Engagement
Training must be role-specific and practical
Workshops
✓
short practical sessions
Simulation
✓
Example: barcode scanning
and medication verification
exercises
Example: responding to AIgenerated interaction alerts
Super users
Feedback loops
ward-level support
✓
safe practice before rollout
Example: experienced staff
assisting colleagues during
rollout
✓
Online modules
✓
flexible refresher learning
Example: short e-learning
updates on AI-EMAS
workflows
staff concerns addressed
Example: workflow
adjustments based on
frontline feedback
Training objective
Education strategies aim to improve staff confidence, reduce resistance and support safe AI-EMAS adoption
Bates et al., 2021; Sutton et al., 2020
11

12.

Six-Month Implementation Timeline
A phased rollout reduces disruption and supports adoption
Start small → adjust workflow → scale safely → evaluate outcomes
M1–2
M3
M4
M5
M6
Planning
Stakeholders
Pilot ward
Training
Workflow fixes
Full rollout
Evaluation
Audit
M1–2 Planning & stakeholder engagement
Workflow mapping, stakeholder consultation, governance approval and identification of medication safety risks before implementation.
M3 Pilot ward rollout
Initial AI-EMAS testing in a pilot ward with frontline staff feedback, workflow observation and early issue identification.
M4 Training & optimisation
Staff education sessions, simulation training, alert refinement and workflow adjustments based on pilot feedback.
M5 Hospital-wide rollout
Expansion of AI-EMAS across clinical areas with ongoing technical support, monitoring and workflow integration.
M6 Evaluation & audit
Review of medication safety outcomes, compliance auditing, staff feedback analysis and sustainability planning for long-term use.
Assessment 2 implementation timeline
12

13.

Risks and Mitigation
Implementation barriers should be managed before full rollout
Risk
Impact
Mitigation
Staff resistance
Low adoption
Early engagement + training
System downtime
Workflow delay
IT support + escalation path
Alert fatigue
Ignored warnings
Optimise alert thresholds
Workflow disruption
Reduced efficiency
Pilot testing before rollout
Sutton et al., 2020; Assessment 2 proposal
13

14.

Evaluation and Monitoring
Success must be measured with practical safety indicators
↓
Medication errors
↑
Compliance
reduction in reported medication incidents
↑
Staff confidence
✓
Audit outcomes
survey results
barcode scan completion
clinical governance review
Monitoring methods and evaluation indicators
Medication errors
Review monthly incident reports and monitor changes in medication-related errors after AI-EMAS rollout
Compliance monitoring
Track barcode scanning compliance and completion of medication verification checks
Staff confidence
Collect staff feedback surveys following training and implementation
Audit outcomes
Conduct routine governance audits to review workflow safety and documentation quality
Continuous improvement
Use monitoring and feedback data to refine workflows and support ongoing patient safety improvement
World Health Organization, 2021; Assessment 2 proposal
14

15.

Conclusion and References
Why the initiative should be adopted
References
Key message
Australian Commission on Safety and Quality in Health Care. (2026). Medication safety
standard. https://www.safetyandquality.gov.au/standards/nsqhs-standards/medicationsafety-standard
• AI-EMAS addresses system-level
Bates, D. W., Levine, D. M., Syrowatka, A., Kuznetsova, M., Craig, K. J. T., Rui, A.,
medication safety risks through real-time
Jackson, G. P., Rhee, K., & Lipsitz, S. R. (2021). The potential of artificial intelligence to
clinical decision support, barcode
improve patient safety: A systematic review. NPJ Digital Medicine, 4, 54.
verification and workflow integration
Craswell, A., Bennett, K., Hanson, J., Dalgliesh, B., & Wallis, M. (2021). Implementation of
distributed automated medication dispensing units in a new hospital: Nursing and pharmacy
• A phased implementation strategy,
experience. Journal of Clinical Nursing, 30(19–20), 2863–2872.
supported by staff training, stakeholder
Rodziewicz, T. L., Houseman, B., & Hipskind, J. E. (2024). Medical error reduction and
engagement and continuous monitoring,
prevention. StatPearls.
can strengthen medication safety and
Sutton, R. T., Pincock, D., Baumgart, D. C., Sadowski, D. C., Fedorak, R. N., & Kroeker, K.
support sustainable quality improvement in
I. (2020). An overview of clinical decision support systems: Benefits, risks, and strategies for
success. NPJ Digital Medicine, 3, 17.
Australian hospitals
Sydney Children’s Hospitals Network. (2025). Robots set to revolutionise medication
management in our new buildings.
Tariq, R. A., Vashisht, R., Sinha, A., & Scherbak, Y. (2024). Medication dispensing errors
and prevention. StatPearls.
World Health Organization. (2021). Global Patient Safety Action Plan 2021–2030.
Full APA 7 reference details based on Assessment 2 source list
15