CloudMedx is working with with the UCSF Department of Orthopaedic Surgery to create artificial intelligence (AI) models for enhancing patient outcomes following joint replacement surgery.
The research collaboration will study how patient-generated health care data collected from consumer-grade wearable sensors may predict clinical outcomes after hip and knee replacement surgery.
Based on structured and unstructured data from patient medical records and wearable devices, the UCSF research team intends to develop new class of algorithms, which can predict a patient’s individual outcome and recovery following surgery.
UCSF Health orthopedic surgeon and project leader Dr Stefano Bini said: “We want to combine patient-reported outcomes, data from electronic medical records and sensor data to predict how patients will recover following joint replacement surgery.
“To give us a perspective on how patients are doing with predictive analytics, we partnered with CloudMedx to handle the large data sets that will be needed.”
Bini noted that current gold standard for patient evaluations are validated patient reported outcome surveys, which are secured prior to surgery.
The data points collected in the interim have not been validated and are generally discouraged, said Bini.
Bini further said: “By using CloudMedx’s robust AI to read clinical notes using machine-assisted natural language processing, we aim to surface insights in real time to improve patient outcomes.”
CloudMedx is a clinical artificial intelligence platform, which offers real time clinical insights to the healthcare industry to help improve clinical and operational outcomes.
The firm uses evidence-based algorithms, machine learning and natural language to analyze both unstructured data and structured data, enabling providers and health systems enhanced care delivery, reduce costs, and optimize workflows.
CloudMedx’s clinical analyzer studies patient’s record to offer clinicians, nurses, and front line staff with insights to improve patient outcomes.
The firm’s coding analyzer will enhance the efficiency of coders and billers, which offers the required alerts to manage medical coding. Its studies both structured and unstructured data, and uses NLP and machine learning to gain insights from data.