17
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      Explainable machine-learning predictions for the prevention of hypoxaemia during surgery

      research-article

      Read this article at

      ScienceOpenPublisherPMC
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Although anaesthesiologists strive to avoid hypoxemia during surgery, reliably predicting future intraoperative hypoxemia is not currently possible. Here, we report the development and testing of a machine-learning-based system that, in real time during general anaesthesia, predicts the risk of hypoxemia and provides explanations of the risk factors. The system, which was trained on minute-by-minute data from the electronic medical records of over fifty thousand surgeries, improved the performance of anaesthesiologists when providing interpretable hypoxemia risks and contributing factors. The explanations for the predictions are broadly consistent with the literature and with prior knowledge from anaesthesiologists. Our results suggest that if anaesthesiologists currently anticipate 15% of hypoxemia events, with this system’s assistance they would anticipate 30% of them, a large portion of which may benefit from early intervention because they are associated with modifiable factors. The system can help improve the clinical understanding of hypoxemia risk during anaesthesia care by providing general insights into the exact changes in risk induced by certain patient or procedure characteristics.

          Related collections

          Most cited references26

          • Record: found
          • Abstract: found
          • Article: not found

          Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review.

          Developers of health care software have attributed improvements in patient care to these applications. As with any health care intervention, such claims require confirmation in clinical trials. To review controlled trials assessing the effects of computerized clinical decision support systems (CDSSs) and to identify study characteristics predicting benefit. We updated our earlier reviews by searching the MEDLINE, EMBASE, Cochrane Library, Inspec, and ISI databases and consulting reference lists through September 2004. Authors of 64 primary studies confirmed data or provided additional information. We included randomized and nonrandomized controlled trials that evaluated the effect of a CDSS compared with care provided without a CDSS on practitioner performance or patient outcomes. Teams of 2 reviewers independently abstracted data on methods, setting, CDSS and patient characteristics, and outcomes. One hundred studies met our inclusion criteria. The number and methodologic quality of studies improved over time. The CDSS improved practitioner performance in 62 (64%) of the 97 studies assessing this outcome, including 4 (40%) of 10 diagnostic systems, 16 (76%) of 21 reminder systems, 23 (62%) of 37 disease management systems, and 19 (66%) of 29 drug-dosing or prescribing systems. Fifty-two trials assessed 1 or more patient outcomes, of which 7 trials (13%) reported improvements. Improved practitioner performance was associated with CDSSs that automatically prompted users compared with requiring users to activate the system (success in 73% of trials vs 47%; P = .02) and studies in which the authors also developed the CDSS software compared with studies in which the authors were not the developers (74% success vs 28%; respectively, P = .001). Many CDSSs improve practitioner performance. To date, the effects on patient outcomes remain understudied and, when studied, inconsistent.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Estimate of the global volume of surgery in 2012: an assessment supporting improved health outcomes.

            It was previously estimated that 234·2 million operations were performed worldwide in 2004. The association between surgical rates and population health outcomes is not clear. We re-estimated global surgical volume to track changes over time and assess rates associated with healthy populations.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: not found

              Anesthesia awareness and the bispectral index.

              Awareness during anesthesia is a serious complication with potential long-term psychological consequences. Use of the bispectral index (BIS), developed from a processed electroencephalogram, has been reported to decrease the incidence of anesthesia awareness when the BIS value is maintained below 60. In this trial, we sought to determine whether a BIS-based protocol is better than a protocol based on a measurement of end-tidal anesthetic gas (ETAG) for decreasing anesthesia awareness in patients at high risk for this complication. We randomly assigned 2000 patients to BIS-guided anesthesia (target BIS range, 40 to 60) or ETAG-guided anesthesia (target ETAG range, 0.7 to 1.3 minimum alveolar concentration [MAC]). Postoperatively, patients were assessed for anesthesia awareness at three intervals (0 to 24 hours, 24 to 72 hours, and 30 days after extubation). We assessed 967 and 974 patients from the BIS and ETAG groups, respectively. Two cases of definite anesthesia awareness occurred in each group (absolute difference, 0%; 95% confidence interval [CI], -0.56 to 0.57%). The BIS value was greater than 60 in one case of definite anesthesia awareness, and the ETAG concentrations were less than 0.7 MAC in three cases. For all patients, the mean (+/-SD) time-averaged ETAG concentration was 0.81+/-0.25 MAC in the BIS group and 0.82+/-0.23 MAC in the ETAG group (P=0.10; 95% CI for the difference between the BIS and ETAG groups, -0.04 to 0.01 MAC). We did not reproduce the results of previous studies that reported a lower incidence of anesthesia awareness with BIS monitoring, and the use of the BIS protocol was not associated with reduced administration of volatile anesthetic gases. Anesthesia awareness occurred even when BIS values and ETAG concentrations were within the target ranges. Our findings do not support routine BIS monitoring as part of standard practice. (ClinicalTrials.gov number, NCT00281489 [ClinicalTrials.gov].). Copyright 2008 Massachusetts Medical Society.
                Bookmark

                Author and article information

                Journal
                101696896
                45929
                Nat Biomed Eng
                Nat Biomed Eng
                Nature biomedical engineering
                2157-846X
                9 January 2019
                10 October 2018
                October 2018
                16 April 2019
                : 2
                : 10
                : 749-760
                Affiliations
                [1 ]Paul G. Allen School of Computer Science and Engineering, University of Washington, Seattle, WA, USA.
                [2 ]Department of Anesthesiology and Pain Medicine, University of Washington, Seattle, WA, USA.
                [3 ]Seattle Children’s Hospital, Seattle, WA, USA.
                [4 ]Veterans Affairs Puget Sound Health Care System, Seattle, WA, USA.
                [5 ]Center for Perioperative and Pain initiatives in Quality Safety Outcome, University of Washington, Seattle, WA, USA.
                [6 ]Harborview Injury Prevention and Research Center, University of Washington, Seattle, WA, USA Seattle, WA, USA
                Author notes

                Author contributions

                S.-I.L., S.M.L., B.N., and J.K. initiated the study. S.-I.L. and S.M.L. developed the Prescience algorithms and designed data analyses and experiments. S.M.L. performed data analyses, experiments, and data preprocessing. B.N., and S.-F. N. provided the electronic medical record data. J.K. recruited anaesthesiologists and helped design the anaesthesiologist test and survey. M.H., M.J.E., T.A., D.E.L., D.K.-W.L. performed the web-based anaesthesiologist experiments and provided survey data. M.H. provided manuscript feedback. M.S.V. provided clinical assessment, interpretation of feature importances, and connections with anaesthesiologists’ workflow. S.-I L., S.M.L. wrote the paper in conjunction with B.N., J.K., and M.S.V. who wrote sections on clinical interpretation and integration with current practices.

                [* ]To whom correspondence should be addressed: suinlee@ 123456cs.washington.edu
                Article
                NIHMS1505578
                10.1038/s41551-018-0304-0
                6467492
                31001455
                7c54bdc1-f58e-4fb8-a6a2-3874827e532d

                <license-p>Users may view, print, copy, and download text and data-mine the content in such documents, for the purposes of academic research, subject always to the full Conditions of use:<uri xlink:href="http://www.nature.com/authors/editorial_policies/license.html#terms">http://www.nature.com/authors/editorial_policies/license.html#terms</uri></license-p>

                History
                Categories
                Article

                Comments

                Comment on this article