Abstract

This review describes the steps and conclusions from the development and validation of an artificial intelligence algorithm (the Hypotension Prediction Index), one of the first machine learning predictive algorithms used in the operating room environment. The algorithm has been demonstrated to reduce intraoperative hypotension in two randomized controlled trials via real-time prediction of upcoming hypotensive events prompting anesthesiologists to act earlier, more often, and differently in managing impending hypotension. However, the algorithm entails no dynamic learning process that evolves from use in clinical patient care, meaning the algorithm is fixed, and furthermore provides no insight into the decisional process that leads to an early warning for intraoperative hypotension, which makes the algorithm a ”black box.” Many other artificial intelligence machine learning algorithms have these same disadvantages. Clinical validation of such algorithms is relatively new and requires more standardization, as guidelines are lacking or only now start to be drafted. Before adaptation in clinical practice, impact of artificial intelligence algorithms on clinical behavior, outcomes and economic advantages should be studied too.

Highlights

  • W.H. van der Ven et al / Surgery 169 (2021) 1300e1303 cognitive tasks from humans

  • First attempts to use algorithms as an aid in anesthesiology practice date back to the 1950s, where maintenance of general anesthesia was controlled in an electroencephalographic activity-guided closed-loop setting.4e6 Despite receiving broad interest and additional research underlining the potential of these automated systems,[7,8] they were never implemented in routine care

  • We describe the steps from development to clinical implementation of the Hypotension Prediction Index (HPI) as one of the first Machine learning (ML)-derived predictive algorithms used in the operating room environment

Read more

Summary

Contents lists available at ScienceDirect

One of the first validations of an artificial intelligence algorithm for clinical use: The impact on intraoperative hypotension prediction and clinical decision-making. The algorithm entails no dynamic learning process that evolves from use in clinical patient care, meaning the algorithm is fixed, and provides no insight into the decisional process that leads to an early warning for intraoperative hypotension, which makes the algorithm a ”black box.”. Technology Gaps: The Hypotension Prediction Index entails no dynamic learning process that evolves from use in clinical patient care, meaning the algorithm is fixed, and provides no insight in the decisional process that leads to an early warning for intraoperative hypotension, which makes the algorithm a “black box”; it shares these disadvantages with many other machine learning algorithms. Future research with machine learning algorithms such as the Hypotension Prediction Index should focus on perioperative hemodynamic improvement with regard to reduction of postoperative morbidity and mortality

Introduction
Aim
Developmental process of the HPI
Validation process
Internal and external validation
DATA COLLECTION
CLINICAL VALIDATION
Clinical validation
Results
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call