Approximately 1 in 7 major surgical procedures in the US is associated with a complication, which totals over 4 million complications each year and costs of at least $80 billion. Furthermore, medical errors are the third leading cause of death in the US.
Different patients with different risk factors experience risk at different steps during the same episode of care. Although numerous institutions collect and manipulate “big data” related to risk, no clinician can keep pace with the constant alarms, perpetually-evolving guidelines, and complex datasets.
In addition, clinical workflow for the same service can vary drastically across institutions (e.g., due to budget, staffing, culture) and patient populations (e.g., due to demographics, rates of poverty and insurance, social determinants of health). This workflow requires optimization in order to increase capacity while reducing costs and improving quality.
Presaj focuses the attention of caregivers and assists them in reducing the risk of complications in major surgical procedures and the treatment of other medical conditions.
Unlike the numerous initiatives that collect and manipulate pre-existing big data, Presaj is generating unique data that directly informs providers of the care steps with the most risk for each individual patient.
The Presaj system adjusts its data to reflect the unique risk profiles of each care facility and positively influences organizational culture in order to combat the taboo surrounding risk reporting.
Presaj utilizes Patient Failure Mode Analysis (PFMA), a novel tool for assessing patient risks at the process level, and a unique machine learning solution that customizes this data for each care facility.
PFMA combines systems-engineering standards with the expertise of specialist clinicians in order to provide clinicians with personalized information for each patient that cuts through the extraneous data and identifies the specific steps with high risk.
Presaj's machine learning solution, which is trained on actuarial and facility-specific datasets, modifies the PFMA data to create customized process-level insights for each institution.