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.

Sleep and sleep disorders during pregnancy and postpartum: The Life-ON study.

OBJECTIVE: to prospectively assess sleep and sleep disorders during pregnancy and postpartum in a large cohort of women. METHODS: multicenter prospective Life-ON study, recruiting consecutive pregnant women at a gestational age between 10 and 15 weeks, from the local gynecological departments. The study included home polysomnography performed between the 23rd and 25th week of pregnancy and sleep-related questionnaires at 9 points in time during pregnancy and 6 months postpartum. RESULTS: 439 pregnant women (mean age 33.7 ± 4.2 yrs) were enrolled. Poor quality of sleep was reported by 34% of women in the first trimester of pregnancy, by 46% of women in the third trimester, and by as many as 71% of women in the first month after delivery. A similar trend was seen for insomnia. Excessive daytime sleepiness peaked in the first trimester (30% of women), and decreased in the third trimester, to 22% of women. Prevalence of restless legs syndrome was 25%, with a peak in the third trimester of pregnancy. Polysomnographic data, available for 353 women, revealed that 24% of women slept less than 6 h, and 30.6% of women had a sleep efficiency below 80%. Sleep-disordered breathing (RDI≥5) had a prevalence of 4.2% and correlated positively with BMI. CONCLUSIONS: The Life-ON study provides the largest polysomnographic dataset coupled with longitudinal subjective assessments of sleep quality in pregnant women to date. Sleep disorders are highly frequent and distributed differently during pregnancy and postpartum. Routine assessment of sleep disturbances in the perinatal period is necessary to improve early detection and clinical management.

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.

The effects of microclimatic winter conditions in urban areas on the risk of establishment for Aedes albopictus.

The tiger mosquito, Aedes albopictus, has adjusted well to urban environments by adopting artificial water containers as oviposition sites. Its spread in temperate regions is favoured by the deposition of cold-tolerant diapausing eggs that survive winter temperatures to a certain degree. The probability of establishment in new geographical areas is estimated using predictive models usually based on meteorological data measured at coarse resolution. Here, we investigated if we could obtain more precise and realistic risk scenarios for the spread of Ae. albopictus when considering the winter microclimatic conditions of catch basins, one of the major sites of oviposition and egg overwintering in temperate urban areas. We monitored winter microclimatic conditions of catch basins in four Swiss cities and developed a regression model to predict the average microclimatic temperatures of catch basins, based on available meteorological parameters, accounting for the observed differences between cities. We then used the microclimatic model to correct the predictions of our previously developed risk model for the prediction of Ae. albopictus establishment. Comparison of the predictive model's results based on local climate data and microclimate data indicated that the risk of establishment for Ae. albopictus in temperate urban areas increases when microhabitat temperatures are considered.

Risk-Based Mapping Tools for Surveillance and Control of the Invasive Mosquito Aedes albopictus in Switzerland.

BACKGROUND: In Switzerland, Aedes albopictus is well established in Ticino, south of the Alps, where surveillance and control are implemented. The mosquito has also been observed in Swiss cities north of the Alps. Decision-making tools are urgently needed by the local authorities in order to optimize surveillance and control. METHODS: A regularized logistic regression was used to link the long-term dataset of Ae. albopictus occurrence in Ticino with socioenvironmental predictors. The probability of establishment of Ae. albopictus was extrapolated to Switzerland and more finely to the cities of Basel and Zurich. RESULTS: The model performed well, with an AUC of 0.86. Ten socio-environmental predictors were selected as informative, including the road-based distance in minutes of travel by car from the nearest cell established in the previous year. The risk maps showed high suitability for Ae. albopictus establishment in the Central Plateau, the area of Basel, and the lower Rhone Valley in the Canton of Valais. CONCLUSIONS: The areas identified as suitable for Ae. albopictus establishment are consistent with the actual current findings of tiger mosquito. Our approach provides a useful tool to prompt authorities' intervention in the areas where there is higher risk of introduction and establishment of Ae. albopictus.

The Influence of Baseline Clinical Status and Surgical Strategy on Early Good to Excellent Result in Spinal Lumbar Arthrodesis: A Machine Learning Approach.

The study aims to create a preoperative model from baseline demographic and health-related quality of life scores (HRQOL) to predict a good to excellent early clinical outcome using a machine learning (ML) approach. A single spine surgery center retrospective review of prospectively collected data from January 2016 to December 2020 from the institutional registry (SpineREG) was performed. The inclusion criteria were age ≥ 18 years, both sexes, lumbar arthrodesis procedure, a complete follow up assessment (Oswestry Disability Index-ODI, SF-36 and COMI back) and the capability to read and understand the Italian language. A delta of improvement of the ODI higher than 12.7/100 was considered a "good early outcome". A combined target model of ODI (Δ ≥ 12.7/100), SF-36 PCS (Δ ≥ 6/100) and COMI back (Δ ≥ 2.2/10) was considered an "excellent early outcome". The performance of the ML models was evaluated in terms of sensitivity, i.e., True Positive Rate (TPR), specificity, i.e., True Negative Rate (TNR), accuracy and area under the receiver operating characteristic curve (AUC ROC). A total of 1243 patients were included in this study. The model for predicting ODI at 6 months' follow up showed a good balance between sensitivity (74.3%) and specificity (79.4%), while providing a good accuracy (75.8%) with ROC AUC = 0.842. The combined target model showed a sensitivity of 74.2% and specificity of 71.8%, with an accuracy of 72.8%, and an ROC AUC = 0.808. The results of our study suggest that a machine learning approach showed high performance in predicting early good to excellent clinical results.

Profiling the Location and Extent of Musicians' Pain Using Digital Pain Drawings.

BACKGROUND AND AIMS: According to existing literature, musicians are at risk of experiencing a range of painful musculoskeletal conditions. Recently, a novel digital technology was developed to investigate pain location and pain extent. The aim of this study was to describe pain location and pain extent in musicians using a digital method for pain drawing (PD) analysis. Additionally, the association between PD variables and clinical features were explored in musicians with pain. METHODS: One hundred and fifty-eight musicians (90 women and 68 men; aged 22.4 ± 3.6 years) were recruited from Swiss and U.K. conservatories. Participants were asked to complete a survey including both background musical information and clinical features, the QuickDASH (QD) questionnaire, and the digital PDs. RESULTS: Of the 158 participants, 126 musicians (79.7%) reported having pain, with higher prevalence in the areas of the neck and shoulders, the lower back, and the right arm. The mean percentage of pain extent was 3.1% ± 6.5%. The mean QD score was higher for musicians with pain than for those without pain. Additionally, the results indicated a positive correlation between the QD score and pain extent, and there were significant correlations between age and pain intensity, as well as between pain extent and pain intensity. CONCLUSIONS: The high prevalence of pain among musicians has been confirmed using a digital technique for PD acquisition and analysis. In addition, positive correlations between pain extent and upper limb disability have been demonstrated. Our findings highlight the need for effective prevention and treatment strategies for musicians.

Reliable survival analysis based on the Dirichlet process.

We present a robust Dirichlet process for estimating survival functions from samples with right-censored data. It adopts a prior near-ignorance approach to avoid almost any assumption about the distribution of the population lifetimes, as well as the need of eliciting an infinite dimensional parameter (in case of lack of prior information), as it happens with the usual Dirichlet process prior. We show how such model can be used to derive robust inferences from right-censored lifetime data. Robustness is due to the identification of the decisions that are prior-dependent, and can be interpreted as an analysis of sensitivity with respect to the hypothetical inclusion of fictitious new samples in the data. In particular, we derive a nonparametric estimator of the survival probability and a hypothesis test about the probability that the lifetime of an individual from one population is shorter than the lifetime of an individual from another. We evaluate these ideas on simulated data and on the Australian AIDS survival dataset. The methods are publicly available through an easy-to-use R package.

Mycobacterium tuberculosis chaperonin 10 is secreted in the macrophage phagosome: is secretion due to dissociation and adoption of a partially helical structure at the membrane?

To confirm that Mycobacterium tuberculosis chaperonin 10 (Cpn10) is secreted outside the live bacillus, infected macrophages were examined by electron microscopy. This revealed that the mycobacterial protein accumulates both in the wall of the bacterium and in the matrix of the phagosomes in which ingested mycobacteria survive within infected macrophages. To understand the structural implications underlying this secretion, a structural study of M. tuberculosis Cpn10 was performed under conditions that are generally believed to mimic the membrane environment. It was found that in buffer-organic solvent mixtures, the mycobacterial protein forms two main species, namely, a partially helical monomer that prevails in dilute solutions at room temperature and a dimer that folds into a beta-sheet-dominated structure and prevails in either concentrated protein solutions at room temperature or in dilute solutions at low temperature. A partially helical monomer was also found and was completely associated with negatively charged detergents in a micelle-bound state. Remarkably, zwitterionic lipids had no effect on the protein structure. By using N- and C-truncated forms of the protein, the C- and N-terminal sequences were identified as possessing an amphiphilic helical character and as selectively associating with acidic detergent micelles. When the study was extended to other chaperonins, it was found that human Cpn10 is also monomeric and partially helical in dilute organic solvent-buffer mixtures. In contrast, Escherichia coli Cpn10 is mostly dimeric and predominately beta-sheet in both dilute and concentrated solutions. Interestingly, human Cpn10 also crosses biological membranes, whereas the E. coli homologue is strictly cytosolic. These results suggest that dissociation to partially helical monomers and interaction with acidic lipids may be two important steps in the mechanism of secretion of M. tuberculosis Cpn10 to the external environment.