Machine-learning Algorithm to Predict Hypotension Based on High-fidelity Arterial Pressure Waveform Analysis
Tóm tắt
With appropriate algorithms, computers can learn to detect patterns and associations in large data sets. The authors’ goal was to apply machine learning to arterial pressure waveforms and create an algorithm to predict hypotension. The algorithm detects early alteration in waveforms that can herald the weakening of cardiovascular compensatory mechanisms affecting preload, afterload, and contractility.
The algorithm was developed with two different data sources: (1) a retrospective cohort, used for training, consisting of 1,334 patients’ records with 545,959 min of arterial waveform recording and 25,461 episodes of hypotension; and (2) a prospective, local hospital cohort used for external validation, consisting of 204 patients’ records with 33,236 min of arterial waveform recording and 1,923 episodes of hypotension. The algorithm relates a large set of features calculated from the high-fidelity arterial pressure waveform to the prediction of an upcoming hypotensive event (mean arterial pressure < 65 mmHg). Receiver-operating characteristic curve analysis evaluated the algorithm’s success in predicting hypotension, defined as mean arterial pressure less than 65 mmHg.
Using 3,022 individual features per cardiac cycle, the algorithm predicted arterial hypotension with a sensitivity and specificity of 88% (85 to 90%) and 87% (85 to 90%) 15 min before a hypotensive event (area under the curve, 0.95 [0.94 to 0.95]); 89% (87 to 91%) and 90% (87 to 92%) 10 min before (area under the curve, 0.95 [0.95 to 0.96]); 92% (90 to 94%) and 92% (90 to 94%) 5 min before (area under the curve, 0.97 [0.97 to 0.98]).
The results demonstrate that a machine-learning algorithm can be trained, with large data sets of high-fidelity arterial waveforms, to predict hypotension in surgical patients’ records.
Từ khóa
Tài liệu tham khảo
2017, Relationship between intraoperative hypotension, defined by either reduction from baseline or absolute thresholds, and acute kidney and myocardial injury after noncardiac surgery: A retrospective cohort analysis., Anesthesiology, 126, 47, 10.1097/ALN.0000000000001432
2016, Association between intraoperative hypotension and myocardial injury after vascular surgery., Anesthesiology, 124, 35, 10.1097/ALN.0000000000000922
2013, Relationship between intraoperative mean arterial pressure and clinical outcomes after noncardiac surgery: Toward an empirical definition of hypotension., Anesthesiology, 119, 507, 10.1097/ALN.0b013e3182a10e26
1997, The impact of complications after vascular surgery in Veterans Affairs Medical Centers., J Surg Res, 67, 62, 10.1006/jsre.1996.4946
Vascular Events In Noncardiac Surgery Patients Cohort Evaluation Study I, 2012, Association between postoperative troponin levels and 30-day mortality among patients undergoing noncardiac surgery., JAMA, 307, 2295, 10.1001/jama.2012.5502
2016, Early-phase cumulative hypotension duration and severe-stage progression in oliguric acute kidney injury with and without sepsis: An observational study., Crit Care, 20, 405, 10.1186/s13054-016-1564-2
Medicine, 2003, NUa: New opportunities, new challenges: The changing nature of biomedical science, Enhancing the Vitality of the National Institutes of Health: Organizational Change to Meet New Challenges
2007, A novel two-dimensional echocardiographic image analysis system using artificial intelligence-learned pattern recognition for rapid automated ejection fraction., J Am Coll Cardiol, 49, 217, 10.1016/j.jacc.2006.08.045
2017, Prediction of 30-day all-cause readmissions in patients hospitalized for heart failure: Comparison of machine learning and other statistical approaches., JAMA Cardiol, 2, 204, 10.1001/jamacardio.2016.3956
2016, Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs., JAMA, 316, 2402, 10.1001/jama.2016.17216
2011, Open-Access MIMIC-II Database for Intensive Care Research, 2011 Annual International Conference of the Ieee Engineering in Medicine and Biology Society (Embc), 8315
2011, Multiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database., Crit Care Med, 39, 952, 10.1097/CCM.0b013e31820a92c6
2017, Trends and challenges in clinical monitoring: Papers from the 2015 IAMPOV symposium., Anesth Analg, 124, 2, 10.1213/ANE.0000000000001495
2014, “Off-label” use of clinical monitors: What happens when new physiologic understanding meets state-of-the-art technology., Anesth Analg, 119, 1241, 10.1213/ANE.0000000000000479
PhysioNet and Computers in Cardiology Challenge: Predicting acute hypotensive episodes. Available at: https://physionet.org/challenge/2009/. Accessed November 7, 2017
2014, Gleaning knowledge from data in the intensive care unit., Am J Respir Crit Care Med, 190, 606, 10.1164/rccm.201404-0716CP
2010, Complexity modeling: Identify instability early., Crit Care Med, 38, S649, 10.1097/CCM.0b013e3181f24484
2016, Using supervised machine learning to classify real alerts and artifact in online multisignal vital sign monitoring data., Crit Care Med, 44, e456, 10.1097/CCM.0000000000001660
2013, Automatic identification of artifacts in monitoring critically ill patients., Intensive Care Med, 39, S470
2017, Learning temporal rules to forecast instability in continuously monitored patients., J Am Med Inform Assoc, 24, 47, 10.1093/jamia/ocw048
2013, Artifact patterns in continuous noninvasive monitoring of patients., Intensive Care Med, 39, S405
2016, Guidelines for developing and reporting machine learning predictive models in biomedical research: A multidisciplinary view., J Med Internet Res, 18, e323, 10.2196/jmir.5870
2013, Accessing the public MIMIC-II intensive care relational database for clinical research., BMC Med Inform Decis Mak, 13, 9, 10.1186/1472-6947-13-9
PhysioNet: MIMIC II Waveform Database Matched Subset. Available at: https://www.physionet.org/physiobank/database/mimic2wdb/matched/. (Accessed November 7, 2017
2000, PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals., Circulation, 101, E215
2007, Calculating arterial pressure-based cardiac output using a novel measurement and analysis method., Biomed Instrum Technol, 41, 403, 10.2345/0899-8205(2007)41[403:CAPCOU]2.0.CO;2
1984, The static elastic properties of 45 human thoracic and 20 abdominal aortas in vitro and the parameters of a new model., J Biomech, 17, 425, 10.1016/0021-9290(84)90034-4
2009, The ability of stroke volume variations obtained with Vigileo/FloTrac system to monitor fluid responsiveness in mechanically ventilated patients., Anesth Analg, 108, 513, 10.1213/ane.0b013e318192a36b
2010, Statistical evaluation of a biomarker., Anesthesiology, 112, 1023, 10.1097/ALN.0b013e3181d47604
2017, Evaluating performance of early warning indices to predict physiological instabilities., J Biomed Inform, 75, 14, 10.1016/j.jbi.2017.09.008
2013, Learning temporal rules to forecast instability in intensive care patients., Intensive Care Med, 39, S470
2015, Temporal distribution of instability events in continuously monitored step-down unit patients: Implications for rapid response systems., Resuscitation, 89, 99, 10.1016/j.resuscitation.2015.01.015
2011, Use of advanced machine-learning techniques for noninvasive monitoring of hemorrhage., J Trauma, 71, S25
2013, Estimation of individual-specific progression to impending cardiovascular instability using arterial waveforms., J Appl Physiol (1985), 115, 1196, 10.1152/japplphysiol.00668.2013
2014, Risk prediction for acute hypotensive patients by using gap constrained sequential contrast patterns., AMIA Annu Symp Proc, 2014, 1748