Search

An algorithm derived from machine learning uses the arterial waveform to predict intraoperative hypotension some minutes before episodes, possibly giving clinician’s time to intervene and prevent hypotension. Whether the Hypotension Prediction Index works well with noninvasive arterial pressure waveforms remains unknown. We therefore evaluated sensitivity, specificity, and positive predictive value of the Index based on non-invasive arterial waveform estimates. We used continuous hemodynamic data measured from ClearSight (formerly Nexfin) noninvasive finger blood pressure monitors in surgical patients. We re-evaluated data from a trial that included 320 adults ≥ 45 years old designated ASA physical status 3 or 4 who had moderate-to-high-risk non-cardiac surgery with general anesthesia. We calculated sensitivity and specificity for predicting hypotension, defined as mean arterial pressure ≤ 65 mmHg for at least 1 min, and characterized the relationship with receiver operating characteristics curves. We also evaluated the number of hypotensive events at various ranges of the Hypotension Prediction Index. And finally, we calculated the positive predictive value for hypotension episodes when the Prediction Index threshold was 85. The algorithm predicted hypotension 5 min in advance, with a sensitivity of 0.86 [95% confidence interval 0.82, 0.89] and specificity 0.86 [0.82, 0.89]. At 10 min, the sensitivity was 0.83 [0.79, 0.86] and the specificity was 0.83 [0.79, 0.86]. And at 15 min, the sensitivity was 0.75 [0.71, 0.80] and the specificity was 0.75 [0.71, 0.80]. The positive predictive value of the algorithm prediction at an Index threshold of 85 was 0.83 [0.79, 0.87]. A Hypotension Prediction Index of 80–89 provided a median of 6.0 [95% confidence interval 5.3, 6.7] minutes warning before mean arterial pressure decreased to

Editor’s Perspective What We Already Know about This Topic What This Article Tells Us That Is New Background 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. Methods 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. Results 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]). Conclusions 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.

BACKGROUNDIn 2008, the US Food and Drug Administration (FDA) issued a Guidance for Industry statement formally recognizing (during drug development) the conjoined nature of type 2 diabetes (T2D) and cardiovascular disease (CVD), which has precipitated an urgent need for panels of markers (and means of analysis) that are able to differentiate subtypes of CVD in the context of T2D. Here, we explore the possibility of creating such panels using the working hypothesis that proteins, in addition to carrying time-cumulative marks of hyperglycemia (e.g., protein glycation in the form of Hb A1c), may carry analogous information with regard to systemic oxidative stress and aberrant enzymatic signaling related to underlying pathobiologies involved in T2D and/or CVD.METHODSWe used mass spectrometric immunoassay to quantify, in targeted fashion, relative differences in the glycation, oxidation, and truncation of 11 specific proteins.RESULTSProtein oxidation and truncation (owing to modified enzymatic activity) are able to distinguish between subsets of diabetic patients with or without a history of myocardial infarction and/or congestive heart failure where markers of glycation alone cannot.CONCLUSIONMarkers based on protein modifications aligned with the known pathobiologies of T2D represent a reservoir of potential cardiovascular markers that are needed to develop the next generation of antidiabetes medications.

Cardiovascular disease (CVD) is considered as the leading cause of morbidity and mortality in type 2 diabetes (T2D) patients. In 2008 the US FDA issued a Guidance to Industry statement, recognizing the conjoined nature of CVD and T2D and emphasizing the need to monitor cardiovascular risk during new diabetic drug trials. This led researchers to work towards identifying panels of markers that are able to distinguish subtypes of CVD in the context of T2D. Immunoassays are used to detect and quantify biomolecules in a solution. Mass spectrometric immunoassay analysis of various proteins in the blood serum of 212 subjects belonging to multiple disease groups resulted in the identification of 41 molecular species as potential biomarkers. In this paper, support vector machines are used to measure the effectiveness of using these species as a diagnosis tool. We suggest an any-vs-rest SVM multiclass classification method by dividing the problem into a series of binary SVM classification problems and using a MAP decision rule to predict the correct class. One-vs-rest and discriminant analysis approaches are also evaluated for comparison.