Machine learning of physiological waveforms and electronic health record data to predict, diagnose and treat haemodynamic instability in surgical patients: protocol for a retrospective study

Abstract

IntroductionAbout 42 million surgeries are performed annually in the USA. While the postoperative mortality is less than 2%, 12% of all patients in the high-risk surgery group account for 80% of postoperative deaths. New onset of haemodynamic instability is common in surgical patients and its delayed treatment leads to increased morbidity and mortality. The goal of this proposal is to develop, validate and test real-time intraoperative risk prediction tools based on clinical data and high-fidelity physiological waveforms to predict haemodynamic instability during surgery.Methods and analysisWe will initiate our work using an existing annotated intraoperative database from the University of California Irvine, including clinical and high-fidelity waveform data. These data will be used for the training and development of the machine learning model (Carnegie Mellon University) that will then be tested on prospectively collected database (University of California Los Angeles). Simultaneously, we will use existing knowledge of haemodynamic instability patterns derived from our intensive care unit cohorts, medical information mart for intensive care II data, University of California Irvine data and animal studies to create smart alarms and graphical user interface for a clinical decision support. Using machine learning, we will extract a core dataset, which characterises the signatures of normal intraoperative variability, various haemodynamic instability aetiologies and variable responses to resuscitation. We will then employ clinician-driven iterative design to create a clinical decision support user interface, and evaluate its effect in simulated high-risk surgeries.Ethics and disseminationWe will publish the results in a peer-reviewed publication and will present this work at professional conferences for the anaesthesiology and computer science communities. Patient-level data will be made available within 6 months after publication of the primary manuscript. The study has been approved by University of California, Los Angeles Institutional review board. (IRB #19–0 00 354).

Patient Perceptions of Audio and Video Recording in the Operating Room

“…Continuous audio-video recording in the operating room has the potential to benefit both surgeons and patients through surgeon 13,14 and patient 15,16 education; surgeon 17,18 and surgical team 19,20 performance evaluation; and Al-driven quality improvement. 21,22,23,24 Despite these potential benefits, there is minimal understanding of how these devices are viewed by patients. In the current study, we interviewed 49 surgical patients set to undergo varying procedures and found that they independently identified some of the intended benefits of ORR including education, QI, and patient safety.…”

MOVER: Medical Informatics Operating Room Vitals and Events Repository

“…The increased adoption of EHR systems and subsequent rise in digitally available healthcare data has resulted in a newfound ability to perform predictive modeling on healthcare data using artificial intelligence (AI), primarily in the form of machine learning. Applications of AI in a healthcare setting include providing more accurate diagnoses, recommending treatment plans, predicting patient outcomes, tracking patient e ngagement and adherence, reducing the burden of administrative tasks, among others [3,4,5,6,7,8,9,10,11,12,13 ]. Despite many publications showing AI algorithms to be very successful in retrospective healthcare studies, there is a very limited amount of freely and publicly available medical data for researchers to work with, to develop and benchmark predictive and other methods in a reproducible manner.. To address this issue, we present and release a new repository we have constructed over the years called MOVER: Medical Informatics Operating Room Vitals and Events Repository.…”

Differentiation of Bone Metastasis in Elderly Patients With Lung Adenocarcinoma Using Multiple Machine Learning Algorithms

“… 17 Other studies have shown that machine learning can predict and diagnose hemodynamic instability in surgery patients by physiological waveforms and electronic health records. 18 Additionally, it has been reported that a new machine learning technique for accurate diagnosis of coronary artery disease has been developed. Moreover, studies have shown that machine learning algorithms based on medical data can diagnose patients with ankylosing spondylitis.…”