Title |
Building an automated, machine learning-enabled platform for predicting post-operative complications
|
---|---|
Published in |
Physiological Measurement, February 2023
|
DOI | 10.1088/1361-6579/acb4db |
Pubmed ID | |
Authors |
Jeremy A Balch, Matthew M Ruppert, Benjamin Shickel, Tezcan Ozrazgat-Baslanti, Patrick J Tighe, Philip A Efron, Gilbert R Upchurch, Parisa Rashidi, Azra Bihorac, Tyler J Loftus |
Abstract |
In 2019, the University of Florida College of Medicine launched the MySurgeryRisk algorithm to predict eight major post-operative complications using automatically extracted data from the electronic health record. This project was developed in parallel with our Intelligent Critical Care Center and represents a culmination of efforts to build an efficient and accurate model for data processing and predictive analytics. This paper discusses how our model was constructed and improved upon. We highlight the consolidation of the database, processing of fixed and time-series physiologic measurements, development and training of predictive models, and expansion of those models into different aspects of patient assessment and treatment. We end by discussing future directions of the model. |
X Demographics
Geographical breakdown
Country | Count | As % |
---|---|---|
United States | 1 | 33% |
Unknown | 2 | 67% |
Demographic breakdown
Type | Count | As % |
---|---|---|
Members of the public | 3 | 100% |
Mendeley readers
Geographical breakdown
Country | Count | As % |
---|---|---|
Unknown | 19 | 100% |
Demographic breakdown
Readers by professional status | Count | As % |
---|---|---|
Researcher | 3 | 16% |
Student > Ph. D. Student | 1 | 5% |
Student > Bachelor | 1 | 5% |
Student > Doctoral Student | 1 | 5% |
Student > Master | 1 | 5% |
Other | 0 | 0% |
Unknown | 12 | 63% |
Readers by discipline | Count | As % |
---|---|---|
Computer Science | 2 | 11% |
Medicine and Dentistry | 2 | 11% |
Engineering | 2 | 11% |
Unknown | 13 | 68% |