Intelligent video analytics in healthcare
Esteban Rubens
You would think that the question of handwashing as a simple and effective means of controlling intrahospital infections would be completely settled in 2021. After all, it has been over 170 years since Ignaz Semmelweis argued that handwashing before each patient examination was necessary to control widespread maternal mortality in hospital settings. Even though that simple intervention virtually eliminated postpartum infections and deaths, the medical establishment rejected his ideas and ridiculed him, which hastened his early death at age 47. Joseph Lister, the father of modern antisepsis, said this about Semmelweis: “I think with the greatest admiration of him and his achievement and it fills me with joy that at last he is given the respect due to him.”
Handwashing in healthcare today
As clear and exhaustive as the data is on the effectiveness of handwashing to prevent healthcare-acquired infections, the U.S. Centers for Disease Control says that “on average, healthcare providers clean their hands less than half of the times they should.” In Japan, studies have demonstrated that hand hygiene rates were suboptimal and lower than reported adherence rates from other international studies. There’s similar worrying evidence from global studies that found baseline hand hygiene compliance was below 50%. As a result of these observations, global campaigns have tried to improve handwashing in healthcare. There’s also an international organization dedicated to fighting nosocomial infections—the International Nosocomial Infection Control Consortium—that focuses on hand hygiene and has sponsored multidimensional interventions to improve handwashing adherence around the world. As necessary as these interventions are, the problem of hand hygiene in healthcare settings is still a widespread global problem.How can technology help?
In many parts of the world, video cameras are widely used for security purposes in healthcare. The video feeds captured by those cameras are largely monitored by human beings, as opposed to being fed to analytics tools. At the same time, machine-learning methods excel at computer vision tasks such as identification and segmentation. Bringing these two strands together seems like a logical approach. It can harness the advancements in AI and computer hardware to help solve a problem that negatively affects patients and healthcare institutions around the world.With that in mind, NetApp has combined our experience in video data management with NetApp® E-Series systems and our partner NVIDIA’s Clara Guardian application framework for multimodal AI deployment in healthcare. Our objective is simple: Bring together outstanding technology to help solve the handwashing problem in healthcare. By harnessing the existing video camera infrastructure in a healthcare institution and directing the live video streams to appropriately trained neural networks, we can identify handwashing noncompliance. That data can be aggregated and used to shape not only general campaigns, but also specific interventions focused on those people who might need more training and attention.
Improving hand hygiene in healthcare benefits patients, clinicians, and all other stakeholders alike. By automating the detection of opportunities for improvement, we hope to add a valuable tool to healthcare worldwide. Are you interested? Contact me at Esteban.Rubens@NetApp.com.
Esteban Rubens
Esteban joined NetApp to build a Healthcare AI practice leveraging our full portfolio to help create ML-based solutions that improve patient care, and reduce provider burnout. Esteban has been in the Healthcare IT industry for 15 years, having gone from a being storage geek at various startups to spending 12 years as a healthcare-storage geek at FUJIFILM Medical Systems. He's a visible participant in the AI-in-Healthcare conversation, speaking and writing at length on the subject. He is particularly interested in the translation of Machine Learning research into clinical practice, and the integration of AI tools into existing workflows. He is a competitive powerlifter in the USAPL federation so he will try to sneak early-morning training in wherever he's traveling.
