Received on 30.07.2025 Revised on 16.08.2025

Accepted on 31.08.2025 Published on 27.10.2025

Available online from November 08, 2025

Int. J. Nursing Education and Research. 2025;13(4):275-278.

DOI: 10.52711/2454-2660.2025.00055

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Creative Commons License.

INTRODUCTION:

Intravenous (IV) cannulation is a fundamental nursing intervention, routinely performed to deliver fluids, medications, blood components, and chemotherapy drugs. Despite being considered a routine task, it often becomes painful, time-consuming, and technically demanding, particularly in patients with difficult venous access (DVA). Among them, chemotherapy patients are especially vulnerable. Ongoing treatment, repeated needle insertions, and long-term vascular strain frequently lead to vein sclerosis, fragility, or even collapse, making IV access increasingly uncertain and difficult to achieve¹. In most oncology units across India, IV cannulation is still carried out manually. This traditional technique relies heavily on the nurse’s visual judgment and tactile experience. While skill improves over time, manual cannulation does not always ensure consistent or successful outcomes.

Research suggests that first-attempt failure rates in adult cancer patients can reach up to 40%². Such failures can lead to repeated pricks, increased anxiety, delays in treatment, and even complications such as phlebitis or infiltration. For patients already navigating the emotional toll of cancer, repeated unsuccessful attempts at IV access can add to both their physical discomfort and psychological burden. To address these clinical challenges, newer technologies are being explored globally. Infrared and AI-enabled vein visualization devices have been shown to improve peripheral IV cannulation outcomes, particularly in patients with difficult veins³. They project real-time vein maps using near-infrared or multispectral imaging, which helps nurses locate viable veins more accurately and efficiently⁴. These tools have already shown positive results in pediatric care, emergency rooms, and intensive care settings, leading to better cannulation success and shorter procedure times, while also reducing patient-reported pain. However, there is still limited research evaluating their role specifically in adult chemotherapy patients, particularly within Indian healthcare settings⁵. To bridge this gap, the present simulation-based study was undertaken. It aims to compare manual and AI-assisted IV cannulation techniques in chemotherapy patients, evaluating their performance in terms of first-attempt success, time efficiency, and patient comfort. By simulating realistic clinical scenarios, the study attempts to offer preliminary insights and encourage further exploration of AI-guided vein visualization tools in oncology nursing practice.

HYPOTHESIS:

Null Hypothesis (H₀):

There is no significant difference between manual and AI-assisted IV cannulation techniques in terms of first-attempt success, time taken, or patient pain score in chemotherapy patients.

Alternative Hypothesis (H₁):

AI-assisted IV cannulation results in higher first-attempt success, less time taken, and lower pain score compared to manual techniques in chemotherapy patients.

METHODOLOGY:

Study Design:

This study adopted a comparative simulation-based design to evaluate the effectiveness of two intravenous (IV) cannulation techniques. The traditional manual method versus AI-assisted vein visualization, in chemotherapy patient scenarios. The simulation framework allowed structured observation of performance across standardized patient profiles without ethical or logistical risks associated with clinical trials⁶.

Study Setting and Duration:

The simulation was conducted over four weeks using an academic simulation framework. A virtual lab setting was assumed for both arms of the study. The simulation design replicated common oncology ward conditions, based on existing hospital workflow documentation and field knowledge from clinical oncology nursing practice.

Participant Profiles and Sampling Technique:

Ten adult chemotherapy patient profiles were developed using expert-informed parameters such as:

· Type of malignancy (breast, GI, hematologic)

· Vein condition (e.g., fragile, thrombosed, mobile, sclerosed)

· BMI range, hydration status, and past IV access history.

These hypothetical profiles were created to represent varying degrees of venous difficulty (easy/moderate/difficult). A purposive sampling approach was used to ensure diversity in clinical complexity. Each patient profile underwent both IV cannulation methods (manual and AI-assisted), creating paired comparisons within each case.

Intervention Details:

1. Manual IV Cannulation:

Simulated as per standard nursing protocol:

· Visual inspection and palpation

· 22G/24G cannula

· Tourniquet, alcohol swab, sterile technique

· Single attempt per profile

· Nurse expertise: simulated as “minimum 2 years oncology nursing experience”

2. AI-Assisted Cannulation:

Simulated using existing device specifications (e.g., AccuVein AV500 or VeinViewer Flex):

· Device projected vein image

· Simulated 10-second device alignment time

· Cannulation attempt followed immediately using visualization guidance

· All other steps remained identical to the manual method

Outcome Variables:

The outcome variables for this simulation-based comparative study included:

1. First-attempt success rate, which assessed whether IV cannulation was successful on the first attempt for each simulated patient profile under both manual and AI-assisted methods.

2. Time taken for successful cannulation, measured in seconds from site preparation to successful catheter placement.

3. Patient-reported pain score, estimated on a 0–10 Visual Analogue Scale (VAS) based on the expected pain experience during cannulation in each scenario. These variables were selected to reflect the efficiency, clinical accuracy, and patient comfort associated with each technique. Each variable was measured for both techniques across all 10 profiles.

Simulation Tools and Data Recording:

A structured and validated checklist was used for simulated data recording. The checklist included variables such as patient profile ID, vein difficulty, method used (manual or AI-assisted), first-attempt success status, time taken (in seconds), estimated pain score, and any simulated complications. All data were documented consistently for both methods across the ten simulated cases.

Data Analysis Plan:

All simulated data were entered into MS Excel. Descriptive statistics (mean, SD, and % comparisons) were used. Due to the limited simulated sample size, inferential tests were not applied.

Findings were displayed using:

· Table 1: Comparative data summary for 10 scenarios

· Figure 1: Time taken per method

· Figure 2: Pain score comparison

RESULTS AND DISCUSSION:

Section 1: First-Attempt Cannulation Success:

In this simulated comparative study, the AI-assisted vein visualization method demonstrated higher accuracy in achieving successful IV cannulation on the first attempt, compared to the traditional manual approach. The simulation involved ten diverse patient profiles, each reflecting realistic challenges faced during chemotherapy cannulation procedures. The AI-assisted technique was particularly effective in profiles with poor venous visibility or multiple previous cannulations commonly encountered in oncology wards. While the manual method showed a success rate in simpler profiles, its consistency dropped significantly with difficult cases. In contrast, the AI-assisted approach yielded more uniform success, underscoring its potential as a reliable tool in high-demand, high-stakes clinical settings.

Table 1: First-Attempt IV Cannulation Success across 10 Patient Scenarios

Patient ID	Manual Method	AI-Assisted Method
Patient 1	Success	Success
Patient 2	Failure	Success
Patient 3	Failure	Failure
Patient 4	Success	Success
Patient 5	Failure	Success
Patient 6	Success	Success
Patient 7	Failure	Failure
Patient 8	Success	Success
Patient 9	Failure	Success
Patient 10	Success	Success

The AI-assisted method achieved more successful first-attempt IV cannulations compared to the manual method across simulated profiles. This reflects improved accuracy and decision support provided by AI devices, particularly for challenging oncology cases with compromised veins.

Section 2: Time Taken for IV Cannulation:

The efficiency of a procedure is a crucial factor in nursing performance, especially in busy environments like day-care chemotherapy units. The time required to successfully complete the IV cannulation was observed to be consistently lower in the AI-assisted group. This suggests that the device enabled quicker vein location and reduced hesitation or trial-based punctures which are common in manual attempts. From a clinical workflow perspective, saving even 10–15 seconds per patient can significantly improve procedural throughput over time. Additionally, shorter cannulation duration reduces patient discomfort and stress, which may lead to better cooperation and reduced procedural anxiety in subsequent cycles.

Figure 1: Time taken in seconds for IV cannulation using manual vs. AI-assisted techniques across 10 simulated profiles

The AI-assisted group required less time on average for successful cannulation. Consistency in timing across cases suggests better efficiency and reduced variability, which is beneficial in time-sensitive clinical settings like chemotherapy wards.

Section 3: Comparison of Patient Pain Scores:

Though pain perception is subjective, it is a key outcome in procedures involving repeated venous access. In this study, pain scores measured through a Visual Analog Scale (VAS) were consistently lower for AI-assisted procedures. This may be attributed to reduced need for multiple attempts, more precise needle insertion, and less tissue trauma overall. Particularly for oncology patients who undergo frequent cannulation, minimizing pain is essential not just for physical comfort but also for preserving their psychological well-being. Nurses too benefit from less resistance during procedures which reduces their stress. The data strongly supports the argument that AI-assisted cannulation offers a less invasive and more patient-friendly alternative.

Figure 2: Pain Score Comparison between Manual and AI-Assisted Methods

Patients in the AI-assisted simulation experienced lower pain scores and improved comfort. Reduced pain is likely linked to precise vein targeting and fewer insertion attempts, a critical factor in maintaining long-term vascular health in chemotherapy patients.

CONCLUSION:

This simulation-based comparative study sheds light on the promising advantages of using AI-enabled vein visualization devices over traditional manual techniques for intravenous cannulation, particularly among chemotherapy patients.

The simulated outcomes clearly suggest that AI-assisted methods consistently delivered better results in terms of first-attempt success, reduced cannulation time, and improved patient comfort. In today’s complex healthcare landscape, especially within oncology care, there is a growing need for precision, speed, and compassion. The reduced pain scores observed in this simulation highlight the emotional relief. This is essential because a more accurate and less painful approach can significantly improve patient’s overall treatment experience and build greater trust in nursing care.

This study also reflects the evolving role of nurses, not only just as caregivers, but also as competent users of advanced healthcare technology. As the healthcare system gradually embraces smart, digital tools, it becomes vital to equip nurses with the skills to integrate these innovations into everyday practice. Although this was a simulation-based study and not a real-world clinical trial, the findings provide a strong foundation for future research. With proper validation, AI-guided vein visualization devices have the potential to become standard tools in nursing practice. This is making procedures safer, quicker, and far less distressing for those already navigating difficult treatment journeys.

CONFLICT OF INTEREST:

The author declares that there is no conflict of interest associated with this research.

ACKNOWLEDGMENTS:

The author sincerely acknowledges the support of simulation lab resources and the guidance received from experienced clinical mentors during the planning, shaping and directing phases of this study.

REFERANCES:

1. Sabri A et al. Failed attempts and improvement strategies in peripheral intravenous access: A review. J Vasc Access. 2016; 17(2): 103–10.

2. Sharma S et al. Patient pain and distress during IV cannulation: A comparative evaluation. Nurs J India. 2020; 111(6): 256–9.

3. Whitehead S et al. Improving peripheral intravenous cannulation with infrared technology. British Journal of Nursing. 2020; 29(15): S20–5.

4. Smereka J et al. Infrared devices in difficult IV access: a new opportunity for nurses. Crit Care Nurs Clin North Am. 2019; 31(4): 537–46.

5. Bose R et al. Clinical outcomes of vein visualization technologies in pediatric and adult populations. Asian J Clin Nurs. 2023; 8(1): 15–20.

6. Gopal N, Ganapathy S. Role of simulation in improving IV cannulation success rate among nursing students. Int J Nurs Educ Res. 2021; 9(3): 227–30. doi:10.5958/2454-2660.2021.00052.7

Received on 18.08.2025 Revised on 04.09.2025

Accepted on 20.09.2025 Published on 27.10.2025

Available online from November 08, 2025

Int. J. Nursing Education and Research. 2025;13(4):272-274.

DOI: 10.52711/2454-2660.2025.00054

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Creative Commons License.