Predicting Future Incidences of Cardiac Arrhythmias Using Discrete Heartbeats from Normal Sinus Rhythm ECG Signals via Deep Learning Methods.

This study aims to compare the effectiveness of using discrete heartbeats versus an entire 12-lead electrocardiogram (ECG) as the input for predicting future occurrences of arrhythmia and atrial fibrillation using deep learning models. Experiments were conducted using two types of inputs: a combination of discrete heartbeats extracted from 12-lead ECG and an entire 12-lead ECG signal of 10 s. This study utilized 326,904 ECG signals from 134,447 patients and categorized them into three groups: true-normal sinus rhythm (T-NSR), atrial fibrillation-normal sinus rhythm (AF-NSR), and clinically important arrhythmia-normal sinus rhythm (CIA-NSR). The T-NSR group comprised patients with at least three normal rhythms in a year and no atrial fibrillation or arrhythmias history. Clinically important arrhythmia included atrial fibrillation, atrial flutter, atrial premature contraction, atrial tachycardia, ventricular premature contraction, ventricular tachycardia, right and left bundle branch block, and atrioventricular block over the second degree. The AF-NSR group included normal sinus rhythm paired with atrial fibrillation or atrial flutter within 14 days, and the CIA-NSR group comprised normal sinus rhythm paired with CIA occurring within 14 days. Three deep learning models, ResNet-18, LSTM, and Transformer-based models, were utilized to distinguish T-NSR from AF-NSR and T-NSR from CIA-NSR. The experiments demonstrated the potential of using discrete heartbeats in predicting future arrhythmia and atrial fibrillation incidences extracted from 12-lead electrocardiogram (ECG) signals alone, without any additional patient information. The analysis reveals that these discrete heartbeats contain subtle patterns that deep learning models can identify. Focusing on discrete heartbeats may lead to more timely and accurate diagnoses of these conditions, improving patient outcomes and enabling automated diagnosis using ECG signals as a biomarker.

Prediction of Postoperative Creatinine Levels by Artificial Intelligence after Partial Nephrectomy.

Background and Objectives: Multiple factors are associated with postoperative functional outcomes, such as acute kidney injury (AKI), following partial nephrectomy (PN). The pre-, peri-, and postoperative factors are heavily intertwined and change dynamically, making it difficult to predict postoperative renal function. Therefore, we aimed to build an artificial intelligence (AI) model that utilizes perioperative factors to predict residual renal function and incidence of AKI following PN. Methods and Materials: This retrospective study included 785 patients (training set 706, test set 79) from six tertiary referral centers who underwent open or robotic PN. Forty-four perioperative features were used as inputs to train the AI prediction model. XG-Boost and genetic algorithms were used for the final model selection and to determine feature importance. The primary outcome measure was immediate postoperative serum creatinine (Cr) level. The secondary outcome was the incidence of AKI (estimated glomerular filtration rate (eGFR) < 60 mL/h). The average difference between the true and predicted serum Cr levels was considered the mean absolute error (MAE) and was used as a model evaluation parameter. Results: An AI model for predicting immediate postoperative serum Cr levels was selected from 2000 candidates by providing the lowest MAE (0.03 mg/dL). The model-predicted immediate postoperative serum Cr levels correlated closely with the measured values (R2 = 0.9669). The sensitivity and specificity of the model for predicting AKI were 85.5% and 99.7% in the training set, and 100.0% and 100.0% in the test set, respectively. The limitations of this study included its retrospective design. Conclusions: Our AI model successfully predicted accurate serum Cr levels and the likelihood of AKI. The accuracy of our model suggests that personalized guidelines to optimize multidisciplinary plans involving pre- and postoperative care need to be developed.

Feasibility of artificial intelligence-based decision supporting system in tolvaptan prescription for autosomal dominant polycystic kidney disease.

PURPOSE: Total kidney volume (TKV) measurement is crucial for selecting treatment candidates in autosomal dominant polycystic kidney disease (ADPKD). We developed and investigated the performance of fully-automated 3D-volumetry model and applied it to software as a service (SaaS) for clinical support on tolvaptan prescription in ADPKD patients. MATERIALS AND METHODS: Computed tomography scans of ADPKD patients taken between January 2000 and June 2022 were acquired from seven institutions. The quality of the images was manually reviewed in advance. The acquired dataset was split into training, validation, and test datasets at a ratio of 8.5:1:0.5. Convolutional, neural network-based automatic segmentation model was trained to obtain 3D segment mask for TKV measurement. The algorithm consisted of three steps: data preprocessing, ADPKD area extraction, and post-processing. After performance validation with the Dice score, 3D-volumetry model was applied to SaaS which is based on Mayo imaging classification for ADPKD. RESULTS: A total of 753 cases with 95,117 slices were included. The differences between the ground-truth ADPKD kidney mask and the predicted ADPKD kidney mask were negligible, with intersection over union >0.95. The post-process filter successfully removed false alarms. The test-set performance was homogeneously equal and the Dice score of the model was 0.971; after post-processing, it improved to 0.979. The SaaS calculated TKV from uploaded Digital Imaging and Communications in Medicine images and classified patients according to height-adjusted TKV for age. CONCLUSIONS: Our artificial intelligence-3D volumetry model exhibited effective, feasible, and non-inferior performance compared with that of human experts and successfully predicted the rapid ADPKD progressor.

An Intra-Body Power Transfer System With 1-mW Power Delivered to the Load and 3.3-V DC Output at 160-cm of on-Body Distance.

This paper presents an intra-body power transfer (IBPT) system that can deliver power greater than 1 mW across an on-body distance of 160 cm. A system simulation model is built for the characterization of the channel and optimization of the power transfer. Our system analysis and experimental validation demonstrate that 1 MHz is an optimal carrier frequency for IBPT in terms of power delivered to the load (PDL) and power efficiency (PE). Prototype TX and RX boards were built, and an IC was fabricated in a 180-nm CMOS process for the RX. The proposed RX IC consists of a voltage doubler (VD) and a charge pump (CP) to obtain a sufficiently high voltage conversion ratio (VCR). Among various rectifier topologies, the VD is the optimal topology for the power receiver front-end because the parasitic ground coupling capacitances, which inevitably exist in the IBPT system, act as an inherent input-coupling capacitance for the VD. The implemented VD utilizes a dynamic VTH compensation (DVC) for its diode components. Compared to the conventional static VTH compensation (SVC), DVC in the VD reduces the reverse leakage current of the diode, thus maximizing the power conversion efficiency (PCE) and VCR. In addition, the PDL is enhanced by inserting an inductor on the TX board. It reduces the backward-path impedance without increasing the RX volume, boosting the PDL by up to 9.9 times compared to the PDL without the inductor insertion. The proposed IBPT system delivers up to 178.8 µW of power at 11.7% of maximum power efficiency with 3.3-V DC output voltage and even 1.385 mW of power with the inductor insertion, supporting various biomedical wearable sensors, such as ECG sensor modules.

Label-free multiplexed microtomography of endogenous subcellular dynamics using generalizable deep learning.

Simultaneous imaging of various facets of intact biological systems across multiple spatiotemporal scales is a long-standing goal in biology and medicine, for which progress is hindered by limits of conventional imaging modalities. Here we propose using the refractive index (RI), an intrinsic quantity governing light-matter interaction, as a means for such measurement. We show that major endogenous subcellular structures, which are conventionally accessed via exogenous fluorescence labelling, are encoded in three-dimensional (3D) RI tomograms. We decode this information in a data-driven manner, with a deep learning-based model that infers multiple 3D fluorescence tomograms from RI measurements of the corresponding subcellular targets, thereby achieving multiplexed microtomography. This approach, called RI2FL for refractive index to fluorescence, inherits the advantages of both high-specificity fluorescence imaging and label-free RI imaging. Importantly, full 3D modelling of absolute and unbiased RI improves generalization, such that the approach is applicable to a broad range of new samples without retraining to facilitate immediate applicability. The performance, reliability and scalability of this technology are extensively characterized, and its various applications within single-cell profiling at unprecedented scales (which can generate new experimentally testable hypotheses) are demonstrated.

Prediction of Coronary Stent Underexpansion by Pre-Procedural Intravascular Ultrasound-Based Deep Learning.

OBJECTIVES: The aim of this study was to develop pre-procedural intravascular ultrasound (IVUS)-based models for predicting the occurrence of stent underexpansion. BACKGROUND: Although post-stenting IVUS has been used to optimize percutaneous coronary intervention, there are no pre-procedural guidelines to estimate the degree of stent expansion and provide preemptive management before stent deployment. METHODS: A total of 618 coronary lesions in 618 patients undergoing percutaneous coronary intervention were randomized into training and test sets in a 5:1 ratio. Following the coregistration of pre- and post-stenting IVUS images, the pre-procedural images and clinical information (stent diameter, length, and inflation pressure; balloon diameter; and maximal balloon pressure) were used to develop a regression model using a convolutional neural network to predict post-stenting stent area. To separate the frames with from those without the occurrence of underexpansion (stent area <5.5 mm2), binary classification models (XGBoost) were developed. RESULTS: Overall, the frequency of stent underexpansion was 15% (5,209 of 34,736 frames). At the frame level, stent areas predicted by the pre-procedural IVUS-based regression model significantly correlated with those measured on post-stenting IVUS (r = 0.802). To predict stent underexpansion, maximal accuracy of 94% (area under the curve = 0.94) was achieved when the convolutional neural network- and mask image-derived features were used for the classification model. At the lesion level, there were significant correlations between predicted and measured minimal stent area (r = 0.832) and between predicted and measured total stent volume (r = 0.958). CONCLUSIONS: Deep-learning algorithms accurately predicted incomplete stent expansion. A data-driven approach may assist clinicians in making treatment decisions to avoid stent underexpansion as a preventable cause of stent failure.

Intravascular ultrasound-based deep learning for plaque characterization in coronary artery disease.

BACKGROUND AND AIMS: Although plaque characterization by intravascular ultrasound (IVUS) is important for risk stratification, frame-by-frame analysis of a whole vascular segment is time-consuming. The aim was to develop IVUS-based algorithms for classifying attenuation and calcified plaques. METHODS: IVUS image sets of 598 coronary arteries from 598 patients were randomized into training and test sets with 5:1 ratio. Each IVUS frame at a 0.4-mm interval was circumferentially labeled as one of three classes: attenuated plaque, calcified plaque, or plaque without attenuation or calcification. The model was trained on multi-class classification with 5-fold cross validation. By converting from Cartesian to polar coordinate images, the class corresponding to each array from 0 to 360° was plotted. RESULTS: At the angle-level, Dice similarity coefficients for identifying calcification vs. attenuation vs. none by using ensemble model were 0.79, 0.74 and 0.99, respectively. Also, the maximal accuracy was 98% to classify those groups in the test set. At the frame-level, the model identified the presence of attenuation with 80% sensitivity, 96% specificity, and 93% overall accuracy, and the presence of calcium with 86% sensitivity, 97% specificity, and 96% overall accuracy. In the per-vessel analysis, the attenuation and calcification burden index closely correlated with human measurements (r = 0.89 and r = 0.95, respectively), as did the maximal attenuation and calcification burden index over 4 mm (r = 0.82 and r = 0.91, respectively). The inference times were 0.05 s per frame and 7.8 s per vessel. CONCLUSIONS: Our deep learning algorithms for plaque characterization may assist clinicians in recognizing high-risk coronary lesions.

DeepRegularizer: Rapid Resolution Enhancement of Tomographic Imaging Using Deep Learning.

Optical diffraction tomography measures the three-dimensional refractive index map of a specimen and visualizes biochemical phenomena at the nanoscale in a non-destructive manner. One major drawback of optical diffraction tomography is poor axial resolution due to limited access to the three-dimensional optical transfer function. This missing cone problem has been addressed through regularization algorithms that use a priori information, such as non-negativity and sample smoothness. However, the iterative nature of these algorithms and their parameter dependency make real-time visualization impossible. In this article, we propose and experimentally demonstrate a deep neural network, which we term DeepRegularizer, that rapidly improves the resolution of a three-dimensional refractive index map. Trained with pairs of datasets (a raw refractive index tomogram and a resolution-enhanced refractive index tomogram via the iterative total variation algorithm), the three-dimensional U-net-based convolutional neural network learns a transformation between the two tomogram domains. The feasibility and generalizability of our network are demonstrated using bacterial cells and a human leukaemic cell line, and by validating the model across different samples. DeepRegularizer offers more than an order of magnitude faster regularization performance compared to the conventional iterative method. We envision that the proposed data-driven approach can bypass the high time complexity of various image reconstructions in other imaging modalities.

Expert-level segmentation using deep learning for volumetry of polycystic kidney and liver.

PURPOSE: Volumetry is used in polycystic kidney and liver diseases (PKLDs), including autosomal dominant polycystic kidney disease (ADPKD), to assess disease progression and drug efficiency. However, since no rapid and accurate method for volumetry has been developed, volumetry has not yet been established in clinical practice, hindering the development of therapies for PKLD. This study presents an artificial intelligence (AI)-based volumetry method for PKLD. MATERIALS AND METHODS: The performance of AI was first evaluated in comparison with ground-truth (GT). We trained a V-net-based convolutional neural network on 175 ADPKD computed tomography (CT) segmentations, which served as the GT and were agreed upon by 3 experts using images from 214 patients analyzed with volumetry. The dice similarity coefficient (DSC), interobserver correlation coefficient (ICC), and Bland-Altman plots of 39 GT and AI segmentations in the validation set were compared. Next, the performance of AI on the segmentation of 50 random CT images was compared with that of 11 PKLD specialists based on the resulting DSC and ICC. RESULTS: The DSC and ICC of the AI were 0.961 and 0.999729, respectively. The error rate was within 3% for approximately 95% of the CT scans (error<1%, 46.2%; 1%≤error<3%, 48.7%). Compared with the specialists, AI showed moderate performance. Furthermore, an outlier in our results confirmed that even PKLD specialists can make mistakes in volumetry. CONCLUSIONS: PKLD volumetry using AI was fast and accurate. AI performed comparably to human specialists, suggesting its use may be practical in clinical settings.

Detection of optical coherence tomography-defined thin-cap fibroatheroma in the coronary artery using deep learning.

AIMS: The aim of this study was to develop a deep learning model for classifying frames with versus without optical coherence tomography (OCT)-derived thin-cap fibroatheroma (TCFA). METHODS AND RESULTS: A total of 602 coronary lesions from 602 angina patients were randomised into training and test sets in a 4:1 ratio. A DenseNet model was developed to classify OCT frames with or without OCT-derived TCFA. Gradient-weighted class activation mapping was used to visualise the area of attention. In the training sample (35,678 frames of 480 lesions), the model with fivefold cross-validation had an overall accuracy of 91.6±1.7%, sensitivity of 88.7±3.4%, and specificity of 91.8±2.0% (averaged AUC=0.96±0.01) in predicting the presence of TCFA. In the test samples (9,722 frames of 122 lesions), the overall accuracy at the frame level was 92.8% within the lesion (AUC=0.96) and 91.3% in the entire OCT pullback. The correlation between the %TCFA burden per vessel predicted by the model compared with that identified by experts was significant (r=0.87, p<0.001). The region of attention was localised at the site of the thin cap in 93.4% of TCFA-containing frames. Total computational time per pullback was 2.1±0.3 seconds. CONCLUSIONS: A deep learning algorithm can accurately detect an OCT-TCFA with high reproducibility. The time-saving computerised process may assist clinicians to recognise high-risk lesions easily and to make decisions in the catheterisation laboratory.

Prediction of coronary thin-cap fibroatheroma by intravascular ultrasound-based machine learning.

BACKGROUND AND AIMS: Although grayscale intravascular ultrasound (IVUS) is commonly used for assessing coronary lesion morphology and optimizing stent implantation, detection of vulnerable plaques by IVUS remains challenging. We aimed to develop machine learning (ML) models for predicting optical coherence tomography-derived thin-cap fibroatheromas (OCT-TCFAs). METHODS: In 517 patients with angina, 414 and 103 coronary lesions were randomized into training vs. test sets. Each of the IVUS-OCT co-registered frames (including 32,807 for training and 8101 for test) was labeled according to the presence vs. absence of OCT-TCFA. Among 1449 computed IVUS features based on two-dimensional geometry and texture, 17 features were finally selected and used in supervised ML with artificial neural network (ANN), support vector machine (SVM), and naïve Bayes. RESULTS: IVUS sections with (vs. without) OCT-TCFA showed a larger plaque burden, and a smaller and eccentric lumen. TCFA-containing sections were characterized by increased ratios of variance, entropy, and kurtosis; reduced ratio of homogeneity within the superficial to the deeper plaque; and decreased smoothness within the fibrous cap. In addition, OCT-TCFA was associated with low ratios of gamma-beta, Nakagami-µ and Nakagami-ω, and a high ratio of Rayleigh-b within the superficial to the deeper region. With a 5-fold cross-validation, the averaged accuracies were 81 ±â€¯5% for ANN (area under the curve [AUC] = 0.80 ±â€¯0.08), 77 ±â€¯4% for SVM (AUC = 0.74 ±â€¯0.05), and 78 ±â€¯2% for naïve Bayes (AUC = 0.77 ±â€¯0.04) for predicting OCT-TCFA. In the test set, ANN and naïve Bayes showed the overall accuracies of >80%. CONCLUSIONS: Supervised ML algorithms with computed IVUS features predicted the presence of OCT-TCFA. This data-driven approach may help clinicians in recognizing high-risk coronary lesions.

Angiography-Based Machine Learning for Predicting Fractional Flow Reserve in Intermediate Coronary Artery Lesions.

Background An angiography-based supervised machine learning ( ML ) algorithm was developed to classify lesions as having fractional flow reserve ≤0.80 versus >0.80. Methods and Results With a 4:1 ratio, 1501 patients with 1501 intermediate lesions were randomized into training versus test sets. Between the ostium and 10 mm distal to the target lesion, a series of angiographic lumen diameter measurements along the centerline was plotted. The 24 computed angiographic features based on the diameter plot and 4 clinical features (age, sex, body surface area, and involve segment) were used for ML by XGBoost. The model was independently trained and tested by 2000 bootstrap iterations. External validation with 79 patients was conducted. Including all 28 features, the ML model with 5-fold cross-validation in the 1204 training samples predicted fractional flow reserve ≤0.80 with overall diagnostic accuracy of 78±4% (averaged area under the curve: 0.84±0.03). The 12 high-ranking features selected by scatter search were involved segment; body surface area; distal lumen diameter; minimal lumen diameter; length of a lumen diameter <2.0 mm, <1.5 mm, and <1.25 mm; mean lumen diameter within the worst segment; sex; diameter stenosis; distal 5-mm reference lumen diameter; and length of diameter stenosis >70%. Using those 12 features, the ML predicted fractional flow reserve ≤0.80 in the test set with sensitivity of 84%, specificity of 80%, and overall accuracy of 82% (area under the curve: 0.87). The averaged diagnostic accuracy in bootstrap replicates was 81±1% (averaged area under the curve: 0.87±0.01). External validation showed accuracy of 85% (area under the curve: 0.87). Conclusions Angiography-based ML showed good diagnostic performance in identifying ischemia-producing lesions and reduced the need for pressure wires.

Learning-based screening of hematologic disorders using quantitative phase imaging of individual red blood cells.

We present a rapid and label-free method for hematologic screening for diseases and syndromes, utilizing quantitative phase imaging (QPI) and machine learning. We aim to establish an efficient blood examination framework that does not suffer from the drawbacks of conventional blood assays, which are incapable of profiling single cells or require labeling procedures. Our method involves the synergistic employment of QPI and machine learning. The high-dimensional refractive index information arising from the QPI-based profiling of single red blood cells is processed to screen for diseases and syndromes using machine learning, which can utilize high-dimensional data beyond the human level. Accurate screening for iron-deficiency anemia, reticulocytosis, hereditary spherocytosis, and diabetes mellitus is demonstrated (>98% accuracy) using the proposed method. Furthermore, we highlight the synergy between QPI and machine learning in the proposed method by analyzing the performance of the method.

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.