Explore the vast range of titles available.

Background Heart failure is a clinical syndrome characterised by a reduced ability of the heart to pump blood. Patients with heart failure have a high mortality rate, and physicians need reliable prognostic predictions to make informed decisions about the appropriate application of devices, transplantation, medications, and palliative care. In this study, we demonstrate that combining symbolic regression with the Cox proportional hazards model improves the ability to predict death due to heart failure compared to using the Cox proportional hazards model alone. Methods We used a newly invented symbolic regression method called the QLattice to analyse a data set of medical records for 299 Pakistani patients diagnosed with heart failure. The QLattice identified non-linear mathematical transformations of the available covariates, which we then used in a Cox model to predict survival. Results An exponential function of age, the inverse of ejection fraction, and the inverse of serum creatinine were identified as the best risk factors for predicting heart failure deaths. A Cox model fitted on these transformed covariates had improved predictive performance compared with a Cox model on the same covariates without mathematical transformations. Conclusion Symbolic regression is a way to find transformations of covariates from patients’ medical records which can improve the performance of survival regression models. At the same time, these simple functions are intuitive and easy to apply in clinical settings. The direct interpretability of the simple forms may help researchers gain new insights into the actual causal pathways leading to deaths.

Pre-eclampsia (PE) is a leading cause of perinatal morbidity and mortality worldwide. Low-dose aspirin can prevent PE in high risk pregnancies if started early. However, despite intense research into the area, early pregnancy screening for PE risk is still not a routine part of pregnancy care. Several studies have described the application of artificial intelligence (AI) and machine learning (ML) in risk prediction of PE and its subtypes. A systematic review of available literature is necessary to catalogue the current applications of AI/ML methods in early pregnancy screening for PE, in order to better inform the development of clinically relevant risk prediction algorithms which will enable timely intervention and the development of new treatment strategies. The aim of this systematic review is to identify and assess studies regarding the application of AI/ML methods in early pregnancy screening for PE. A systematic review of peer-reviewed as well as the pre-published cohort, case-control, or cross-sectional studies will be conducted. Relevant information will be accessed from the following databases; PubMed, Google Scholar, Scopus, Embase, Web of Science, Cochrane Library, Arxiv, BioRxiv, and MedRxiv. The studies will be evaluated by two reviewers in a parallel, blind assessment of the literature, a third reviewer will assess any studies in which the first two reviewers did not agree. The free online tool Rayyan, will be used in this literature assessment stage. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 checklist will be used to guide the review process and the methods of the studies will be assessed using the Newcastle-Ottawa scale. Narrative synthesis will be conducted for all included studies. Meta-analysis will also be conducted where data quality and availability allow. The review will not require ethical approval and the findings will be published in a peer-reviewed journal using the PRISMA guidelines. Trial registration: The protocol for this systematic review has been registered in PROSPERO [CRD42022345786]. https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022345786.

In Denmark, a nationwide COVID-19 lockdown was implemented on March 12, 2020 and eased on April 14, 2020. The COVID-19 lockdown featured reduced prevalence of extremely preterm or extremely low birthweight births. This study aims to explore the impact of this COVID-19 lockdown on term birthweights in Denmark. We conducted a nationwide register-based cohort study on 27,870 live singleton infants, born at term (weeks 37–41), between March 12 and April 14, 2015–2020, using data from the Danish Neonatal Screening Biobank. Primary outcomes, corrected for confounders, were birthweight, small-for-gestational-age (SGA), and large-for-gestational-age (LGA), comparing the COVID-19 lockdown to the previous five years. Data were analysed using linear regression to assess associations with birthweight. Multinomial logistic regression was used to assess associations with relative-size-for-gestational-age (xGA) categories. Adjusted mean birthweight was significantly increased by 16.9 g (95% CI = 4.1–31.3) during the lockdown period. A dip in mean birthweight was found in gestational weeks 37 and 38 balanced by an increase in weeks 40 and 41. The 2020 lockdown period was associated with an increased LGA prevalence (aOR 1.13, 95% CI = 1.05–1.21). No significant changes in proportions of xGA groups were found between 2015 and 2019. The nationwide COVID-19 lockdown resulted in a small but significant increase in birthweight and proportion of LGA infants, driven by an increase in birthweight in gestational weeks 40 and 41.

IntroductionPre-eclampsia (PE) is a leading cause of perinatal morbidity and mortality worldwide. Low-dose aspirin can prevent PE in high risk pregnancies if started early. However, despite intense research into the area, early pregnancy screening for PE risk is still not a routine part of pregnancy care. Several studies have described the application of artificial intelligence (AI) and machine learning (ML) in risk prediction of PE and its subtypes. A systematic review of available literature is necessary to catalogue the current applications of AI/ML methods in early pregnancy screening for PE, in order to better inform the development of clinically relevant risk prediction algorithms which will enable timely intervention and the development of new treatment strategies. The aim of this systematic review is to identify and assess studies regarding the application of AI/ML methods in early pregnancy screening for PE.MethodsA systematic review of peer-reviewed as well as the pre-published cohort, case-control, or cross-sectional studies will be conducted. Relevant information will be accessed from the following databases; PubMed, Google Scholar, Scopus, Embase, Web of Science, Cochrane Library, Arxiv, BioRxiv, and MedRxiv. The studies will be evaluated by two reviewers in a parallel, blind assessment of the literature, a third reviewer will assess any studies in which the first two reviewers did not agree. The free online tool Rayyan, will be used in this literature assessment stage. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 checklist will be used to guide the review process and the methods of the studies will be assessed using the Newcastle-Ottawa scale. Narrative synthesis will be conducted for all included studies. Meta-analysis will also be conducted where data quality and availability allow.Ethics and disseminationThe review will not require ethical approval and the findings will be published in a peer-reviewed journal using the PRISMA guidelines.Trial registrationTrial registration: The protocol for this systematic review has been registered in PROSPERO [CRD42022345786]. https://www.crd.york.ac.uk/prospero/displayᵣecord.php?ID=CRD42022345786.

In Denmark, a nationwide COVID-19 lockdown was implemented on March 12, 2020 and eased on April 14, 2020. The COVID-19 lockdown featured reduced prevalence of extremely preterm or extremely low birthweight births. This study aims to explore the impact of this COVID-19 lockdown on term birthweights in Denmark. We conducted a nationwide register-based cohort study on 27,870 live singleton infants, born at term (weeks 37-41), between March 12 and April 14, 2015-2020, using data from the Danish Neonatal Screening Biobank. Primary outcomes, corrected for confounders, were birthweight, small-for-gestational-age (SGA), and large-for-gestational-age (LGA), comparing the COVID-19 lockdown to the previous five years. Data were analysed using linear regression to assess associations with birthweight. Multinomial logistic regression was used to assess associations with relative-size-for-gestational-age (xGA) categories. Adjusted mean birthweight was significantly increased by 16.9 g (95% CI = 4.1-31.3) during the lockdown period. A dip in mean birthweight was found in gestational weeks 37 and 38 balanced by an increase in weeks 40 and 41. The 2020 lockdown period was associated with an increased LGA prevalence (aOR 1.13, 95% CI = 1.05-1.21). No significant changes in proportions of xGA groups were found between 2015 and 2019. The nationwide COVID-19 lockdown resulted in a small but significant increase in birthweight and proportion of LGA infants, driven by an increase in birthweight in gestational weeks 40 and 41.

Machine learning is often applied in health science to obtain predictions and new understandings of complex phenomena and relationships, but an availability of sufficient data for model training is a widespread problem. Traditional machine learning techniques, such as random forests and gradient boosting, tend to overfit when working with data sets of only a few hundred observations. This study demonstrates that for small training sets of 250 observations, symbolic regression generalises better to out-of-sample data than traditional machine learning frameworks, as measured by the coefficient of determination R2 on the validation set. In 132 out of 240 cases, symbolic regression achieves a higher R2 than any of the other models on the out-of-sample data. Furthermore, symbolic regression also preserves the interpretability of linear models and decision trees, an added benefit to its superior generalisation. The second best algorithm was found to be a random forest, which performs best in 37 of the 240 cases. When restricting the comparison to interpretable models, symbolic regression performs best in 184 out of 240 cases.

In this article we introduce the supervised machine learning tool called Feyn. The simulation engine that powers this tool is called the QLattice. The QLattice is a supervised machine learning tool inspired by Richard Feynman's path integral formulation, that explores many potential models that solves a given problem. It formulates these models as graphs that can be interpreted as mathematical equations, allowing the user to completely decide on the trade-off between interpretability, complexity and model performance. We touch briefly upon the inner workings of the QLattice, and show how to apply the python package, Feyn, to scientific problems. We show how it differs from traditional machine learning approaches, what it has in common with them, as well as some of its commonalities with symbolic regression. We describe the benefits of this approach as opposed to black box models. To illustrate this, we go through an investigative workflow using a basic data set and show how the QLattice can help you reason about the relationships between your features and do data discovery.

Symbolic regression searches for analytic expressions that accurately describe studied phenomena. The main attraction of this approach is that it returns an interpretable model that can be insightful to users. Historically, the majority of algorithms for symbolic regression have been based on evolutionary algorithms. However, there has been a recent surge of new proposals that instead utilize approaches such as enumeration algorithms, mixed linear integer programming, neural networks, and Bayesian optimization. In order to assess how well these new approaches behave on a set of common challenges often faced in real-world data, we hosted a competition at the 2022 Genetic and Evolutionary Computation Conference consisting of different synthetic and real-world datasets which were blind to entrants. For the real-world track, we assessed interpretability in a realistic way by using a domain expert to judge the trustworthiness of candidate models.We present an in-depth analysis of the results obtained in this competition, discuss current challenges of symbolic regression algorithms and highlight possible improvements for future competitions.