In Nan fang yi ke da xue xue bao = Journal of Southern Medical University

OBJECTIVE : To propose a semi-supervised epileptic seizure prediction model (ST-WGAN-GP-Bi-LSTM) to enhance the prediction performance by improving time-frequency analysis of electroencephalogram (EEG) signals, enhancing the stability of the unsupervised feature learning model and improving the design of back-end classifier.

METHODS : Stockwell transform (ST) of the epileptic EEG signals was performed to locate the time-frequency information by adaptive adjustment of the resolution and retaining the absolute phase to obtain the time-frequency inputs. When there was no overlap between the generated data distribution and the real EEG data distribution, to avoid failure of feature learning due to a constant JS divergence, Wasserstein GAN was used as a feature learning model, and the cost function based on EM distance and gradient penalty strategy was adopted to constrain the unsupervised training process to allow the generation of a high-order feature extractor. A temporal prediction model was finally constructed based on a bi-directional long short term memory network (Bi-LSTM), and the classification performance was improved by obtaining the temporal correlation between high-order time-frequency features. The CHB-MIT scalp EEG dataset was used to validate the proposed patient-specific seizure prediction method.

RESULTS : The AUC, sensitivity, and specificity of the proposed method reached 90.40%, 83.62%, and 86.69%, respectively. Compared with the existing semi-supervised methods, the propose method improved the original performance by 17.77%, 15.41%, and 53.66%. The performance of this method was comparable to that of a supervised prediction model based on CNN.

CONCLUSION : The utilization of ST, WGAN-GP, and Bi-LSTM effectively improves the prediction performance of the semi-supervised deep learning model, which can be used for optimization of unsupervised feature extraction in epileptic seizure prediction.

Liao J, Li H, Zhan C, Yang F

2023-Jan-20

Stockwell transform, bi-directional long short term memory network, epileptic seizure prediction, generative adversarial network, scalp EEG

In The British journal of radiology

OBJECTIVES : A dose deposition matrix (DDM) prediction method using several voxel features and a machine learning (ML) approach is proposed for plan optimization in radiation therapy.

METHODS : Head and lung cases with the inhomogeneous medium are used as training and testing data. The prediction model is a cascade forward backprop neural network where the input is the features of the voxel, including 1) voxel to body surface distance along the beamlet axis, 2) voxel to beamlet axis distance, 3) voxel density, 4) heterogeneity corrected voxel to body surface distance, 5) heterogeneity corrected voxel to beamlet axis, and (6) the dose of voxel obtained from the pencil beam (PB) algorithm. The output is the predicted voxel dose corresponding to a beamlet. The predicted DDM was used for plan optimization (ML method) and compared with the dose of MC-based plan optimization (MC method) and the dose of pencil beam-based plan optimization (PB method). The mean absolute error (MAE) value was calculated for full volume relative to the dose of the MC method to evaluate the overall dose performance of the final plan.

RESULTS : For patient with head tumor, the ML method achieves MAE value 0.49 × 10^-4 and PB has MAE 1.86 × 10^-4. For patient with lung tumor, the ML method has MAE 1.42 × 10^-4 and PB has MAE 3.72 × 10^-4. The maximum percentage difference in PTV dose coverage (D₉₈) between ML and MC methods is no more than 1.2% for patient with head tumor, while the difference is larger than 10% using the PB method. For patient with lung tumor, the maximum percentage difference in PTV dose coverage (D₉₈) between ML and MC methods is no more than 2.1%, while the difference is larger than 16% using the PB method.

CONCLUSIONS : In this work, a reliable DDM prediction method is established for plan optimization by applying several voxel features and the ML approach. The results show that the ML method based on voxel features can obtain plans comparable to the MC method and is better than the PB method in achieving accurate dose to the patient, which is helpful for rapid plan optimization and accurate dose calculation.

ADVANCES IN KNOWLEDGE : Establishment of a new machine learning method based on the relationship between the voxel and beamlet features for dose deposition matrix prediction in radiation therapy.

Jiao Shengxiu, Zhao Xiaoqian, Yao Shuzhan

2023-Mar-01

In Clinical transplantation ; h5-index 26.0

BACKGROUND : Increasing access and better allocation of organs in the field of transplantation is a critical problem in clinical care. Limitations exist in accurately predicting allograft discard. Potential exists for machine learning to provide a balanced assessment of the potential for an organ to be used in a transplantation procedure.

METHODS : We accessed and utilized all available deceased donor United Network for Organ Sharing data from 1987 to 2020. With these data, we evaluated the performance of multiple machine learning methods for predicting organ use. The machine learning methods trialed included XGBoost, random forest, Naïve Bayes, logistic regression, and fully connected feedforward neural network classifier methods. The top two methods, XGBoost and random forest, were fully developed using 10-fold cross validation and Bayesian optimization of hyperparameters.

RESULTS : The top performing model at predicting liver organ use was an XGBoost model which achieved an AUC-ROC of 0.925, an AUC-PR of 0.868, and an F1 statistic of 0.756. The top performing model for predicting kidney organ use classification was an XGBoost model which achieved an AUC-ROC of 0.952, and AUC-PR of 0.883, and an F1 statistic of 0.786.

CONCLUSIONS : The XGBoost method demonstrated a significant improvement in predicting donor allograft discard for both kidney and livers in solid organ transplantation procedures. Machine learning methods are well suited to be incorporated into the clinical workflow; they can provide robust quantitative predictions and meaningful data insights for clinician consideration and transplantation decision-making. This article is protected by copyright. All rights reserved.

Pettit Rowland W, Marlatt Britton B, Miles Travis J, Uzgoren Selim, Corr Stuart J, Shetty Anil, Havelka Jim, Rana Abbas

2023-Mar-01

XGBoost, discard, machine learning, outcomes, prediction, random forest, transplantation

In Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine

STUDY OBJECTIVES : Machine learning (ML) models have been employed in the setting of sleep disorders. This review aims to summarize the existing data about the role of ML techniques in the diagnosis, classification, and treatment of sleep related breathing disorders.

METHODS : A systematic search in MedLine, EMBASE, and Cochrane databases through January 2022 was performed.

RESULTS : Our search strategy revealed 132 studies that were included in the systematic review. Existing data show that ML models have been successfully used for diagnostic purposes. Specifically, ML models showed good performance in diagnosing sleep apnea using easily obtained features from the electrocardiogram, pulse oximetry and sound signals. Similarly, ML showed good performance for the classification of sleep apnea into obstructive and central categories, as well as predicting apnea severity. Existing data show promising results for the ML-based guided treatment of sleep apnea. Specifically, the prediction of outcomes following surgical treatment and optimization of continuous positive airway pressure therapy, can be guided by ML models.

CONCLUSIONS : The adoption and implementation of ML in the field of sleep related breathing disorders is promising. Advancements in wearable sensor technology and ML models can help clinicians predict, diagnose and classify sleep apnea more accurately and efficiently.

Bazoukis George, Bollepalli Sandeep Chandra, Chung Cheuk To, Li Xinmu, Tse Gary, Bartley Bethany L, Batool-Anwar Salma, Quan Stuart F, Armoundas Antonis A

2023-Mar-01

artificial intelligence, machine learning, sleep apnea

In Circulation ; h5-index 165.0

BACKGROUND : The human heart primarily metabolizes fatty acids, and this decreases as alternative fuel use rises in heart failure with reduced ejection fraction (HFrEF). Patients with severe obesity and diabetes are thought to have increased myocardial fatty acid metabolism, but whether this is found in those who also have heart failure with preserved ejection fraction (HFpEF) is unknown.

METHODS : Plasma and endomyocardial biopsies were randomly selected from a 2-center derived biobank of HFpEF (n=38), HFrEF (n=30), and nonfailing donor control (n=20) tissue. Quantitative targeted metabolomics measured organic acids, amino acids, and acylcarnitines in myocardium (72 metabolites) and plasma (69 metabolites). The results were integrated with reported RNA sequencing data. Metabolomics were analyzed using agnostic clustering tools, Kruskal-Wallis test with Dunn test, and machine learning.

RESULTS : Agnostic clustering of myocardial but not plasma metabolites separated disease groups. Despite more obesity and diabetes in HFpEF versus HFrEF (body mass index, 39.8 kg/m² versus 26.1 kg/m²; diabetes, 70% versus 30%; both P<0.0001), medium- and long-chain acylcarnitines (mostly metabolites of fatty acid oxidation) were markedly lower in myocardium from both heart failure groups versus control. In contrast, plasma levels were no different or higher than control. Gene expression linked to fatty acid metabolism was generally lower in HFpEF versus control. Myocardial pyruvate was higher in HFpEF whereas the tricarboxylic acid cycle intermediates succinate and fumarate were lower, as were several genes controlling glucose metabolism. Non-branched-chain and branched-chain amino acids (BCAA) were highest in HFpEF myocardium, yet downstream BCAA metabolites and genes controlling BCAA metabolism were lower. Ketone levels were higher in myocardium and plasma of patients with HFrEF but not HFpEF. HFpEF metabolomic-derived subgroups showed few differences in BCAA metabolites but little else.

CONCLUSIONS : Despite marked obesity and diabetes, HFpEF myocardium exhibited lower fatty acid metabolites compared with HFrEF. Ketones and metabolites of the tricarboxylic acid cycle and BCAA were also lower in HFpEF, suggesting insufficient use of alternative fuels. These differences were not detectable in plasma and challenge conventional views of myocardial fuel use in HFpEF with marked diabetes and obesity and suggest substantial fuel inflexibility in this syndrome.

Hahn Virginia S, Petucci Christopher, Kim Min-Soo, Bedi Kenneth C, Wang Hanghang, Mishra Sumita, Koleini Navid, Yoo Edwin J, Margulies Kenneth B, Arany Zoltan, Kelly Daniel P, Kass David A, Sharma Kavita

2023-Mar-01

HFpEF, branched chain amino acid, fatty acid oxidation, human, metabolism, metabolomics

In Journal of cellular biochemistry

Chen Zhe, Luo Xuling, Liu Meiqing, Jiang Jinyong, Li Yao, Huang Zhen, Wang Lingzhi, Cao Jiangang, He Lu, Huang Shifang, Hu Haoliang, Li Lanfang, Chen Linxi

2023-Mar-01

Schisandrin A, cobicistat, elabela-apelin/APJ system, pannexin1, thrombosis