A machine learning model to predict the risk of perinatal depression: Psychosocial and sleep-related factors in the Life-ON study cohort.

Perinatal depression (PND) is a common complication of pregnancy associated with serious health consequences for both mothers and their babies. Identifying risk factors for PND is key to early detect women at increased risk of developing this condition. We applied a machine learning (ML) approach to data from a multicenter cohort study on sleep and mood changes during the perinatal period ("Life-ON") to derive models for PND risk prediction in a cross-validation setting. A wide range of sociodemographic variables, blood-based biomarkers, sleep, medical, and psychological data collected from 439 pregnant women, as well as polysomnographic parameters recorded from 353 women, were considered for model building. These covariates were correlated with the risk of future depression, as assessed by regularly administering the Edinburgh Postnatal Depression Scale across the perinatal period. The ML model indicated the mood status of pregnant women in the first trimester, previous depressive episodes and marital status, as the most important predictors of PND. Sleep quality, insomnia symptoms, age, previous miscarriages, and stressful life events also added to the model performance. Besides other predictors, sleep changes during early pregnancy should therefore assessed to identify women at higher risk of PND and support them with appropriate therapeutic strategies.

A transfer learning framework to elucidate the clinical relevance of altered proximal tubule cell states in kidney disease.

The application of single-cell technologies in clinical nephrology remains elusive. We generated an atlas of transcriptionally defined cell types and cell states of human kidney disease by integrating single-cell signatures reported in the literature with newly generated signatures obtained from 5 patients with acute kidney injury. We used this information to develop kidney-specific cell-level information ExtractoR (K-CLIER), a transfer learning approach specifically tailored to evaluate the role of cell types/states on bulk RNAseq data. We validated the K-CLIER as a reliable computational framework to obtain a dimensionality reduction and to link clinical data with single-cell signatures. By applying K-CLIER on cohorts of patients with different kidney diseases, we identified the most relevant cell types associated with fibrosis and disease progression. This analysis highlighted the central role of altered proximal tubule cells in chronic kidney disease. Our study introduces a new strategy to exploit the power of single-cell technologies toward clinical applications.

Optimal risk and diagnosis assessment strategies in perinatal depression: A machine learning approach from the life-ON study cohort.

This study aimed to assess the concordance of various psychometric scales in detecting Perinatal Depression (PND) risk and diagnosis. A cohort of 432 women was assessed at 10-15th and 23-25th gestational weeks, 33-40 days and 180-195 days after delivery using the Edinburgh Postnatal Depression Scale (EPDS), Visual Analogue Scale (VAS), Hamilton Depression Rating Scale (HDRS), Montgomery-Åsberg Depression Rating Scale (MADRS), and Mini International Neuropsychiatric Interview (MINI). Spearman's rank correlation coefficient was used to assess agreement across instruments, and multivariable classification models were developed to predict the values of a binary scale using the other scales. Moderate agreement was shown between the EPDS and VAS and between the HDRS and MADRS throughout the perinatal period. However, agreement between the EPDS and HDRS decreased postpartum. A well-performing model for the estimation of current depression risk (EPDS > 9) was obtained with the VAS and MADRS, and a less robust one for the estimation of current major depressive episode (MDE) diagnosis (MINI) with the VAS and HDRS. When the EPDS is not feasible, the VAS may be used for rapid and comprehensive postpartum screening with reliability. However, a thorough structured interview or clinical examination remains necessary to diagnose a MDE.

Impaired fatty acid metabolism perpetuates lipotoxicity along the transition to chronic kidney injury.

Energy metabolism failure in proximal tubule cells (PTCs) is a hallmark of chronic kidney injury. We combined transcriptomic, metabolomic, and lipidomic approaches in experimental models and patient cohorts to investigate the molecular basis of the progression to chronic kidney allograft injury initiated by ischemia/reperfusion injury (IRI). The urinary metabolome of kidney transplant recipients with chronic allograft injury and who experienced severe IRI was substantially enriched with long chain fatty acids (FAs). We identified a renal FA-related gene signature with low levels of carnitine palmitoyltransferase 2 (Cpt2) and acyl-CoA synthetase medium chain family member 5 (Acsm5) and high levels of acyl-CoA synthetase long chain family member 4 and 5 (Acsl4 and Acsl5) associated with IRI, transition to chronic injury, and established chronic kidney disease in mouse models and kidney transplant recipients. The findings were consistent with the presence of Cpt2-Acsl4+Acsl5+Acsm5- PTCs failing to recover from IRI as identified by single-nucleus RNA-Seq. In vitro experiments indicated that ER stress contributed to CPT2 repression, which, in turn, promoted lipids' accumulation, drove profibrogenic epithelial phenotypic changes, and activated the unfolded protein response. ER stress through CPT2 inhibition and lipid accumulation engaged an auto-amplification loop leading to lipotoxicity and self-sustained cellular stress. Thus, IRI imprints a persistent FA metabolism disturbance in the proximal tubule, sustaining the progression to chronic kidney allograft injury.

Auxiliary-Field Monte Carlo Method to Tackle Strong Interactions and Frustration in Lattice Bosons.

We introduce a new numerical technique, the bosonic auxiliary-field Monte Carlo method, which allows us to calculate the thermal properties of large lattice-boson systems within a systematically improvable semiclassical approach, and which is virtually applicable to any bosonic model. Our method amounts to a decomposition of the lattice into clusters, and to an ansatz for the density matrix of the system in the form of a cluster-separable state-with nonentangled, yet classically correlated clusters. This approximation eliminates any sign problem, and can be systematically improved upon by using clusters of growing size. Extrapolation in the cluster size allows us to reproduce numerically exact results for the superfluid transition of hard-core bosons on the square lattice, and to provide a solid quantitative prediction for the superfluid and chiral transition of hardcore bosons on the frustrated triangular lattice.

Quantum Correlations, Separability, and Quantum Coherence Length in Equilibrium Many-Body Systems.

Nonlocality is a fundamental trait of quantum many-body systems, both at the level of pure states, as well as at the level of mixed states. Because of nonlocality, mixed states of any two subsystems are correlated in a stronger way than what can be accounted for by considering the correlated probabilities of occupying some microstates. In the case of equilibrium mixed states, we explicitly build two-point quantum correlation functions, which capture the specific, superior correlations of quantum systems at finite temperature, and which are directly accessible to experiments when correlating measurable properties. When nonvanishing, these correlation functions rule out a precise form of separability of the equilibrium state. In particular, we show numerically that quantum correlation functions generically exhibit a finite quantum coherence length, dictating the characteristic distance over which degrees of freedom cannot be considered as separable. This coherence length is completely disconnected from the correlation length of the system-as it remains finite even when the correlation length of the system diverges at finite temperature-and it unveils the unique spatial structure of quantum correlations.