Machine Learning-Based prediction of Post-Treatment ambulatory blood pressure in patients with hypertension.

Purpose. Pre-treatment prediction of individual blood pressure (BP) response to anti-hypertensive medication is important to determine the specific regimen for promptly and safely achieving a target BP. This study aimed to develop supervised machine learning (ML) models for predicting patient-specific treatment effects using 24-hour ambulatory BP monitoring (ABPM) data.Materials and Methods. A total of 1,129 patients who had both baseline and follow-up ABPM data were randomly assigned into training, validation and test sets in a 3:1:1 ratio. Utilising the features including clinical and laboratory findings, initial ABPM data, and anti-hypertensive medication at baseline and at follow-up, ML models were developed to predict post-treatment individual BP response. Each case was labelled by the mean 24-hour and daytime BPs derived from the follow-up ABPM.Results. At baseline, 616 (55%) patients had been treated using mono or combination therapy with 45 anti-hypertensive drugs and the remaining 513 (45%) patients had been untreated (drug-naïve). By using CatBoost, the difference between predicted vs. measured mean 24-hour systolic BP at follow-up was 8.4 ± 7.0 mm Hg (% difference of 6.6% ± 5.7%). The difference between predicted vs. measured mean 24-hour diastolic BP was 5.3 ± 4.3 mm Hg (% difference of 6.8% ± 5.5%). There were significant correlations between the CatBoost-predicted vs. the ABPM-measured changes in the mean 24-hour Systolic (r = 0.74) and diastolic (r = 0.68) BPs from baseline to follow-up. Even in the patients with renal insufficiency or diabetes, the correlations between CatBoost-predicted vs. ABPM-measured BP changes were significant.Conclusion. ML algorithms accurately predict the post-treatment ambulatory BP levels, which may assist clinicians in personalising anti-hypertensive treatment.

The prediction of post-treatment BP response is essential to plan the appropriate optimal treatment strategy for achieving the target BP level.The poor predictability of the post-treatment BP level is due to the complex pathophysiology of individual BP response, which can partly explain the poor rate to achieve the target systolic BP.In this current study including both treated and untreated patients with hypertension, machine leaning models predicted the post-treatment mean BP levels on 24-hr ABPM even in high-risk patients and patients with a high BP variability.Model-derived selection and optimisation of anti-hypertension drugs may facilitate prompt achievement of adequate BP control without drug-related complications and avoiding repeating 24-hour ABPM or multiple visits for drug readjustment.

Intravascular ultrasound-based machine learning for predicting fractional flow reserve in intermediate coronary artery lesions.

BACKGROUND AND AIMS: Intravascular ultrasound (IVUS)-derived morphological criteria are poor predictors of the functional significance of intermediate coronary stenosis. IVUS-based supervised machine learning (ML) algorithms were developed to identify lesions with a fractional flow reserve (FFR) ≤0.80 (vs. >0.80). METHODS: A total of 1328 patients with 1328 non-left main coronary lesions were randomized into training and test sets in a 4:1 ratio. Masked IVUS images were generated by an automatic segmentation model, and 99 computed IVUS features and six clinical variables (age, gender, body surface area, vessel type, involved segment, and involvement of the proximal left anterior descending artery) were used for ML training with 5-fold cross-validation. Diagnostic performances of the binary classifiers (L2 penalized logistic regression, artificial neural network, random forest, AdaBoost, CatBoost, and support vector machine) for detecting ischemia-producing lesions were evaluated using the non-overlapping test samples. RESULTS: In the classification of test set lesions into those with an FFR ≤0.80 vs. >0.80, the overall diagnostic accuracies for predicting an FFR ≤0.80 were 82% with L2 penalized logistic regression, 80% with artificial neural network, 83% with random forest, 83% with AdaBoost, 81% with CatBoost, and 81% with support vector machine (AUCs: 0.84-0.87). With exclusion of the 28 lesions with borderline FFR of 0.75-0.80, the overall accuracies for the test set were 86% with L2 penalized logistic regression, 85% with an artificial neural network, 87% with random forest, 87% with AdaBoost, 85% with CatBoost, and 85% with support vector machine. CONCLUSIONS: The IVUS-based ML algorithms showed good diagnostic performance for identifying ischemia-producing lesions, and may reduce the need for pressure wires.

Machine learning assessment of myocardial ischemia using angiography: Development and retrospective validation.

BACKGROUND: Invasive fractional flow reserve (FFR) is a standard tool for identifying ischemia-producing coronary stenosis. However, in clinical practice, over 70% of treatment decisions still rely on visual estimation of angiographic stenosis, which has limited accuracy (about 60%-65%) for the prediction of FFR < 0.80. One of the reasons for the visual-functional mismatch is that myocardial ischemia can be affected by the supplied myocardial size, which is not always evident by coronary angiography. The aims of this study were to develop an angiography-based machine learning (ML) algorithm for predicting the supplied myocardial volume for a stenosis, as measured using coronary computed tomography angiography (CCTA), and then to build an angiography-based classifier for the lesions with an FFR < 0.80 versus ≥ 0.80. METHODS AND FINDINGS: A retrospective study was conducted using data from 1,132 stable and unstable angina patients with 1,132 intermediate lesions who underwent invasive coronary angiography, FFR, and CCTA at the Asan Medical Center, Seoul, Korea, between 1 May 2012 and 30 November 2015. The mean age was 63 ± 10 years, 76% were men, and 72% of the patients presented with stable angina. Of these, 932 patients (assessed before 31 January 2015) constituted the training set for the algorithm, and 200 patients (assessed after 1 February 2015) served as a test cohort to validate its diagnostic performance. Additionally, external validation with 79 patients from two centers (CHA University, Seongnam, Korea, and Ajou University, Suwon, Korea) was conducted. After automatic contour calibration using the caliber of guiding catheter, quantitative coronary angiography was performed using the edge-detection algorithms (CAAS-5, Pie-Medical). Clinical information was provided by the Asan BiomedicaL Research Environment (ABLE) system. The CCTA-based myocardial segmentation (CAMS)-derived myocardial volume supplied by each vessel (right coronary artery [RCA], left anterior descending [LAD], left circumflex [LCX]) and the myocardial volume subtended to a stenotic segment (CAMS-%Vsub) were measured for labeling. The ML for (1) predicting vessel territories (CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA) and CAMS-%Vsub and (2) identifying the lesions with an FFR < 0.80 was constructed. Angiography-based ML, employing a light gradient boosting machine (GBM), showed mean absolute errors (MAEs) of 5.42%, 8.57%, and 4.54% for predicting CAMS-%LAD, CAMS-%LCX, and CAMS-%RCA, respectively. The percent myocardial volumes predicted by ML were used to predict the CAMS-%Vsub. With 5-fold cross validation, the MAEs between ML-predicted percent myocardial volume subtended to a stenotic segment (ML-%Vsub) and CAMS-%Vsub were minimized by the elastic net (6.26% ± 0.55% for LAD, 5.79% ± 0.68% for LCX, and 2.95% ± 0.14% for RCA lesions). Using all attributes (age, sex, involved vessel segment, and angiographic features affecting the myocardial territory and stenosis degree), the ML classifiers (L2 penalized logistic regression, support vector machine, and random forest) predicted an FFR < 0.80 with an accuracy of approximately 80% (area under the curve [AUC] = 0.84-0.87, 95% confidence intervals 0.71-0.94) in the test set, which was greater than that of diameter stenosis (DS) > 53% (66%, AUC = 0.71, 95% confidence intervals 0.65-0.78). The external validation showed 84% accuracy (AUC = 0.89, 95% confidence intervals 0.83-0.95). The retrospective design, single ethnicity, and the lack of clinical outcomes may limit this prediction model's generalized application. CONCLUSION: We found that angiography-based ML is useful to predict subtended myocardial territories and ischemia-producing lesions by mitigating the visual-functional mismatch between angiographic and FFR. Assessment of clinical utility requires further validation in a large, prospective cohort study.