Researchers present at the 2023 ANESTHESIOLOGY meeting have demonstrated that an automated system for pain recognition which uses artificial intelligence (AI), is effective and can serve as an impartial method for detecting pains in patients before, during, and after surgery.
The researchers provided the AI model with 143,293 facial images from 115 pain episodes and 159 non-pain episodes in 69 patients undergoing a variety of elective surgical procedures.
With enough examples, it made accurate pain predictions. The AI-automated pain recognition system aligned with CPOT results 88% of the time and with VAS results 66% of the time.
The AI system learned to identify patterns by analyzing raw facial images, with a focus on facial expressions and muscles in specific facial areas like the eyebrows, lips, and nose.
This approach aims at alleviating the workload of nurses and healthcare professionals who periodically evaluate patients’ pain, and it will personnel them to concentrate on other aspects of care.
The automated pain recognition system, combining the two AI techniques, computer vision and deep learning, allows it to interpret visual cues to assess patients’ pain.
The research team intends to further expand the model by incorporating additional variables like patient movement and sound.
Subjective methods like the Visual Analog Scale (VAS) and the Critical-Care Pain Observation Tool (CPOT) are employed to assess level of pains in patients.
With this System, early recognition and effective management of pain will reduce hospital stays and prevent long-term health conditions like chronic pain, anxiety, and depression.
One of the researchers at the meeting Heintz, said that he VAS is less accurate compared to CPOT because VAS is a subjective measurement that can be more heavily influenced by emotions and behaviors than CPOT might be.
Researchers present at the 2023 ANESTHESIOLOGY meeting have demonstrated that an automated system for pain recognition which uses artificial intelligence (AI), is effective and can serve as an impartial method for detecting pains in patients before, during, and after surgery.
The researchers provided the AI model with 143,293 facial images from 115 pain episodes and 159 non-pain episodes in 69 patients undergoing a variety of elective surgical procedures.
With enough examples, it made accurate pain predictions. The AI-automated pain recognition system aligned with CPOT results 88% of the time and with VAS results 66% of the time.
The AI system learned to identify patterns by analyzing raw facial images, with a focus on facial expressions and muscles in specific facial areas like the eyebrows, lips, and nose.
This approach aims at alleviating the workload of nurses and healthcare professionals who periodically evaluate patients’ pain, and it will personnel them to concentrate on other aspects of care.
The automated pain recognition system, combining the two AI techniques, computer vision and deep learning, allows it to interpret visual cues to assess patients’ pain.
The research team intends to further expand the model by incorporating additional variables like patient movement and sound.
Subjective methods like the Visual Analog Scale (VAS) and the Critical-Care Pain Observation Tool (CPOT) are employed to assess level of pains in patients.
With this System, early recognition and effective management of pain will reduce hospital stays and prevent long-term health conditions like chronic pain, anxiety, and depression.
One of the researchers at the meeting Heintz, said that he VAS is less accurate compared to CPOT because VAS is a subjective measurement that can be more heavily influenced by emotions and behaviors than CPOT might be.