Machine learning and artificial intelligence can help healthcare providers predict wound healing time frames and risks, according to a report in Advances in Wound Care.
Clinicians and data scientists used information from a wound care EHR to predict the likelihood of a patient’s wound healing over four, eight and 12 weeks of treatment. The study examined more than 1.2 million wounds to understand the effect of 187 variables, including patient demographics, comorbidities such as weight, smoking status and other conditions, wound characteristics and time between treatments.
The study is one of the first to prove the value of AI to predict wound healing and support the use of such tools in real-time clinical decision-making. An algorithm within the EHR significantly outperformed other models, providing a high level of confidence in predictions. It was also able to identify comorbidities, such as diabetes and hypertension, impacting the trajectory of healing.
“Through these insights, clinicians can make more timely decisions that will help improve treatment and reduce the costs of care,” said first author Matt Berezo, a data scientist with Net Health, which provided the EHR data.
From the December 2021 Issue of McKnight's Long-Term Care News
