ABSTRACT
BACKGROUND: Early identification of individuals at high risk for developing cardiovascular (CV) events is of paramount importance for efficient risk management. Here, the authors investigated whether using unsupervised machine learning methods on time-series data of left atrial (LA) strain could distinguish clinically meaningful phenogroups associated with the risk for developing adverse events. METHODS: In 929 community-dwelling individuals (mean age, 51.6 years; 52.9% women), clinical and echocardiographic data were acquired, including LA strain traces, at baseline, and cardiac events were collected on average 6.3 years later. Two unsupervised learning techniques were used: (1) an ensemble of a deep convolutional neural network autoencoder with k-medoids and (2) a self-organizing map to cluster spatiotemporal patterns within LA strain curves. Clinical characteristics and cardiac outcome were used to evaluate the validity of the k clusters using the original cohort, while an external population cohort (n = 378) was used to validate the trained models. RESULTS: In both approaches, the optimal number of clusters was five. The first three clusters had differences in sex distribution and heart rate but had a similar low CV risk profile. On the other hand, cluster 5 had the worst CV profile and a higher prevalence of left ventricular remodeling and diastolic dysfunction compared with the other clusters. The respective indexes of cluster 4 were between those of clusters 1 to 3 and 5. After adjustment for traditional risk factors, cluster 5 had the highest risk for cardiac events compared with clusters 1, 2, and 3 (hazard ratio, 1.36; 95% CI, 1.09-1.70; P = .0063). Similar LA strain patterns were obtained when the models were applied to the external validation cohort, and clinical characteristics revealed similar CV risk profiles across all clusters. CONCLUSION: Unsupervised machine learning algorithms used in time-series LA strain curves identified clinically meaningful clusters of LA deformation and provide incremental prognostic information over traditional risk factors.
Subject(s)
Atrial Fibrillation , Cardiovascular Diseases , Humans , Female , Middle Aged , Male , Cardiovascular Diseases/diagnostic imaging , Cardiovascular Diseases/epidemiology , Risk Factors , Risk Assessment , Heart Disease Risk Factors , Cluster Analysis , Ventricular Function, LeftABSTRACT
We explore the use of inverse design methods for the generation of periodic optical patterns in photonic integrated circuits. A carefully selected objective function based on the integer lattice method, which is an algebraic technique for optical lattice generation, is shown to be key for successful device design. Furthermore, we present a polychromatic pattern generating device that switches between optical lattices with different symmetry and periodicity depending on the operating wavelength. Important links are drawn between optical coherent lattices and optical potentials, pointing towards practical applications in the fields of quantum simulations and computing, optical trapping, and bio-sensing.
ABSTRACT
AIMS: Both left ventricular (LV) diastolic dysfunction (LVDD) and hypertrophy (LVH) as assessed by echocardiography are independent prognostic markers of future cardiovascular events in the community. However, selective screening strategies to identify individuals at risk who would benefit most from cardiac phenotyping are lacking. We, therefore, assessed the utility of several machine learning (ML) classifiers built on routinely measured clinical, biochemical, and electrocardiographic features for detecting subclinical LV abnormalities. METHODS AND RESULTS: We included 1407 participants (mean age, 51 years, 51% women) randomly recruited from the general population. We used echocardiographic parameters reflecting LV diastolic function and structure to define LV abnormalities (LVDD, n = 252; LVH, n = 272). Next, four supervised ML algorithms (XGBoost, AdaBoost, Random Forest (RF), Support Vector Machines, and Logistic regression) were used to build classifiers based on clinical data (67 features) to categorize LVDD and LVH. We applied a nested 10-fold cross-validation set-up. XGBoost and RF classifiers exhibited a high area under the receiver operating characteristic curve with values between 86.2% and 88.1% for predicting LVDD and between 77.7% and 78.5% for predicting LVH. Age, body mass index, different components of blood pressure, history of hypertension, antihypertensive treatment, and various electrocardiographic variables were the top selected features for predicting LVDD and LVH. CONCLUSION: XGBoost and RF classifiers combining routinely measured clinical, laboratory, and electrocardiographic data predicted LVDD and LVH with high accuracy. These ML classifiers might be useful to pre-select individuals in whom further echocardiographic examination, monitoring, and preventive measures are warranted.
Subject(s)
Hypertension , Ventricular Dysfunction, Left , Female , Humans , Hypertrophy, Left Ventricular , Machine Learning , Male , Middle Aged , Risk Factors , Ventricular Dysfunction, Left/diagnostic imaging , Ventricular RemodelingABSTRACT
An effective way to design structured coherent wave interference patterns that builds on the theory of coherent lattices, is presented. The technique combines prime number factorization in the complex plane with moiré theory to provide a robust way to design structured patterns with variable spacing of intensity maxima. In addition, the proposed theoretical framework facilitates an elegant computation of previously unexplored high-order superlattices both for the periodic and quasiperiodic case. A number of beam configurations highlighting prime examples of patterns for lattices with three-, four-, and fivefold symmetry are verified in a multibeam interference experiment.
ABSTRACT
Recent discovery of magnesium isotope effect in the rate of enzymatic synthesis of adenosine triphosphate (ATP) offers a new insight into the mechanochemistry of enzymes as the molecular machines. The activity of phosphorylating enzymes (ATP-synthase, phosphocreatine, and phosphoglycerate kinases) in which Mg(2+) ion has a magnetic isotopic nucleus 25Mg was found to be 2-3 times higher than that of enzymes in which Mg(2+) ion has spinless, nonmagnetic isotopic nuclei 24Mg or 26Mg. This isotope effect demonstrates unambiguously that the ATP synthesis is a spin-dependent ion-radical process. The reaction schemes, suggested to explain the effect, imply a reversible electron transfer from the terminal phosphate anion of ADP to Mg(2+) ion as a first step, generating ion-radical pair with singlet and triplet spin states. The yields of ATP along the singlet and triplet channels are controlled by hyperfine coupling of unpaired electron in 25Mg+ ion with magnetic nucleus 25Mg. There is no difference in the ATP yield for enzymes with 24Mg and 26Mg; it gives evidence that in this reaction magnetic isotope effect (MIE) operates rather than classical, mass-dependent one. Similar effects have been also found for the pyruvate kinase. Magnetic field dependence of enzymatic phosphorylation is in agreement with suggested ion-radical mechanism.