Patient Safety in Surgery is calling for submissions to our collection on machine learning approach for improvement of patient safety in surgery. Over the past several years, there has been a paradigm shift across healthcare systems to understand the causes leading up to patient safety events including, but not limited to: surgical site infections, hospital acquired infections, falls, medication errors, and hospital acquired pressure injuries. Healthcare systems managed these events by counting the occurrence after it was reported. This data was then used to drive continuous improvement efforts to support patient outcomes and operational efficiency. Going forward, healthcare systems are shifting focus from counting patient safety related events after they have occurred, to using machine-learning algorithms to predict the patient safety event and prevent harm.
The goal of the special issue in the journal is to provide novel insights into the understanding of machine learning and the impact on preventing patient safety events. We predict machine learning will allow health systems to improve patient safety surveillance programs by identifying patients “at risk” of sustaining preventable harm and thereby enabling the healthcare team to mitigate adverse events before they occur.
All submissions will undergo a formal peer review by at least two qualified referees.
The scope of the special issue of the journal includes, but is not limited to, the following article types and areas of research:
- Basic predictive algorithms to identify patient safety events
- Investigation of novel multi-regression predictive analytics to identify patient safety events
- Patient safety risk factors, indications, and complication elements that are used to identify safety events before the occurrence
- Case reports that describe unusual experiences and important lessons learned while preventing patient harm
- Review articles that cover pertinent areas of research described above
