Testing Machine Learning-Based Pain Assessment for Postoperative Geriatric Patients.

Area of Science:

• Geriatric Medicine
• Artificial Intelligence in Healthcare
• Surgical Nursing

Background:

• The global population is aging, leading to increased surgeries in elderly individuals.
• Accurate postoperative pain assessment in geriatric patients is challenging, impacting care quality and nurse workload.
• Technological solutions are needed for reliable and efficient pain evaluation in older surgical patients.

Purpose of the Study:

• To develop and evaluate a machine learning-based application for automatic pain assessment in postoperative geriatric patients.
• To provide a more reliable and rapid tool for assessing surgical pain in the elderly.
• To support nursing staff by offering an objective pain measurement method.

Main Methods:

• A methodological study involving 68 geriatric patients undergoing general surgery.
• Data collection using demographic forms, Numeric Rating Scale, and Wong-Baker FACES Pain Scale.
• Application of machine learning algorithms for pain assessment and analysis of agreement with patient self-reports.

Main Results:

• Machine learning models demonstrated a high level of agreement with patient-reported pain scores.
• Nurses tended to assign lower pain scores compared to patient self-assessments.
• The developed application proved effective in objective pain measurement post-geriatric surgery.

Conclusions:

• A machine learning-based pain assessment application is an effective tool for postoperative geriatric patients.
• This technology can enhance the accuracy of pain assessment, alleviate nurse workload, and improve geriatric nursing care.
• The application supports advancements in evidence-based geriatric nursing practices.