Machine Learning | Wireless Patient Monitors

The use of machine learning techniques in monitoring vital signs of patients in hospital wards offers a more accurate and efficient method compared to traditional manual recording methods. In many cases, vital signs are manually recorded in the patient’s  electronic health record (EHR) sometimes hours after they were taken. However, utilizing machine learning, data can be collected and sent to a patient's EHR directly from the monitor and alert caregivers  through the use of integrated vital sign monitors. 

Need for Automated Solutions: Machine Learning Device

The increasing demand for accurate and consistent vital sign monitoring, combined with the strain on overworked and aging medical staff, has led to a need for an automated solution. Several companies have developed devices such as patches that can measure various vital signs, but there is a need for a machine learning system that can analyze the data for accuracy, consistency, and viability. This approach has the potential to significantly reduce hospital mortality. If any of the vital signs exceed a predefined threshold, an automatic warning can be issued to medical practitioners, allowing them to administer timely treatment and prescriptions. This can help in reducing hospital mortality and improving the overall patient outcome.[1]

Development of Machine Learning Devices in IoT

With the advancement of the Internet of Things (IoT), vital sign collection can be partially or fully automated, reducing the workload on medical staff. The use of IoT allows for data storage on a distributed platform such as cloud computing, which opens the possibility of building machine learning algorithms to predict patient health deterioration and manage hospital resources. The IoT has greatly impacted the healthcare industry, providing benefits such as improved patient health and safety, improved medical care delivery, and improved doctor-patient engagement

The increasing demand for accurate and consistent vital sign monitoring, combined with the strain on the overworked and aging medical staff, has led to the need for an automated solution. Companies have already developed devices such as patches that can measure various vital signs. Still, there is a need for a machine learning system that can analyze the data for accuracy and consistency. This approach has the potential to reduce hospital mortality significantly. With the development of the Internet of Things (IoT), vital sign collection can be partially or fully automated, reducing the workload on medical staff.  [2]

Additionally, the use of IoT allows for data storage on a distributed platform, such as cloud computing, which opens the possibility of building machine learning algorithms to predict patient health deterioration and manage hospital resources.[3]

Despite the advancements in the field, the healthcare industry faces some fundamental issues. Some of the main challenges include: [3]

• Limited data availability;
• Lack of provider education and training;
• Poor technological integration. Machine learning and clinical decision support techniques are most effective when they are trained on accurate, clean, and comprehensive data. However, obtaining large amounts of data is significant challenge in this field.

The ViSi Mobile aims to resolve some of these said issues.

ViSi Mobile: Monitoring Vital Signs with Machine Learning

The ViSi Mobile Vital Signs Monitoring System monitors vital signs accurately, continuously, and non-invasively for patients in care units designed for patient recovery and the prevention of physiological deterioration. This device employs powerful machine learning to improve clinical staff efficiency while treating patients.

• The latest ViSi Mobile software minimizes setup time and shortens calibration of its innovative, continuous non-invasive blood pressure sensor by utilizing advanced machine learning algorithms to improve data classification. Sotera provides device manuals, demos and training on how to use the device.
• ViSi Mobile also enhances the automated vital sign collection procedure by seamlessly transcribing data into a patient's electronic medical records through more efficient coding algorithms. By removing the administrative load of active charting, clinical teams may concentrate on treatment plans, the patient's rehabilitation, and the "patient experience" in the recovery unit.
• ViSi Mobile can accomplish these things even better since it uses a database of over 20 million hours of patient data to help healthcare personnel identify potential issues more precisely.
  
  

Sources:

https://scholar.uwindsor.ca/cgi/viewcontent.cgi?article=8997&context=etd

https://pubmed.ncbi.nlm.nih.gov/29871778/

https://healthitanalytics.com/features/how-machine-learning-is-transforming-clinical-decision-support-tools