Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

Cardiology Cardiology

Association of pregnancy outcomes in women with type 2 diabetes treated with metformin versus insulin when becoming pregnant.

In BMC pregnancy and childbirth ; h5-index 58.0

BACKGROUND : Metformin use in pregnancy is controversial because metformin crosses the placenta and the safety on the fetus has not been well-established. This retrospective study aimed to compare pregnancy outcomes in women with preexisting type 2 diabetes receiving metformin or standard insulin treatment.

METHODS : The cohort of this population-based study includes women of age 20-44 years with preexisting type 2 diabetes and singleton pregnancies in Taiwan between 2003 and 2014. Subjects were classified into three mutually exclusive groups according to glucose-lowering treatments received before and after becoming pregnant: insulin group, switching group (metformin to insulin), and metformin group. A generalized estimating equation model adjusted for patient age, duration of type 2 diabetes, hypertension, hyperlipidemia, retinopathy, and aspirin use was used to estimate the adjusted odds ratio (aOR) and 95% confidence interval (CI) of adverse pregnancy outcomes.

RESULTS : A total of 1166 pregnancies were identified in the insulin group (n = 222), the switching group (n = 318) and the metformin group (n = 626). The insulin group and the switching group had similar pregnancy outcomes for both the mother and fetus, including risk of primary cesarean section, pregnancy-related hypertension, preeclampsia, preterm birth (< 37 weeks), very preterm birth (< 32 weeks), low birth weight (< 2500 g), high birth weight (> 4000 g), large for gestational age, and congenital malformations. The metformin group had a lower risk of primary cesarean section (aOR = 0.57; 95% CI, 0.40-0.82) and congenital malformations (aOR, 0.51; 95% CI; 0.27-0.94) and similar risk for the other outcomes as compared with the insulin group.

CONCLUSIONS : Metformin therapy was not associated with increased adverse pregnancy outcomes in women with type 2 diabetes as compared with standard insulin therapy.

Lin Shu-Fu, Chang Shang-Hung, Kuo Chang-Fu, Lin Wan-Ting, Chiou Meng-Jiun, Huang Yu-Tung


Insulin, Metformin, Pregnancy outcome

General General

Developing Electron Microscopy Tools for Profiling Plasma Lipoproteins Using Methyl Cellulose Embedment, Machine Learning and Immunodetection of Apolipoprotein B and Apolipoprotein(a).

In International journal of molecular sciences ; h5-index 102.0

Plasma lipoproteins are important carriers of cholesterol and have been linked strongly to cardiovascular disease (CVD). Our study aimed to achieve fine-grained measurements of lipoprotein subpopulations such as low-density lipoprotein (LDL), lipoprotein(a) (Lp(a), or remnant lipoproteins (RLP) using electron microscopy combined with machine learning tools from microliter samples of human plasma. In the reported method, lipoproteins were absorbed onto electron microscopy (EM) support films from diluted plasma and embedded in thin films of methyl cellulose (MC) containing mixed metal stains, providing intense edge contrast. The results show that LPs have a continuous frequency distribution of sizes, extending from LDL (> 15 nm) to intermediate density lipoprotein (IDL) and very low-density lipoproteins (VLDL). Furthermore, mixed metal staining produces striking "positive" contrast of specific antibodies attached to lipoproteins providing quantitative data on apolipoprotein(a)-positive Lp(a) or apolipoprotein B (ApoB)-positive particles. To enable automatic particle characterization, we also demonstrated efficient segmentation of lipoprotein particles using deep learning software characterized by a Mask Region-based Convolutional Neural Networks (R-CNN) architecture with transfer learning. In future, EM and machine learning could be combined with microarray deposition and automated imaging for higher throughput quantitation of lipoproteins associated with CVD risk.

Giesecke Yvonne, Soete Samuel, MacKinnon Katarzyna, Tsiaras Thanasis, Ward Madeline, Althobaiti Mohammed, Suveges Tamas, Lucocq James E, McKenna Stephen J, Lucocq John M


apolipoprotein B, apolipoprotein(a), cardiovascular disease, electron microscopy, lipoproteins, low-density lipoproteins, machine learning, nanoparticles

General General

Differentiating Females with Rett Syndrome and Those with Multi-Comorbid Autism Spectrum Disorder Using Physiological Biomarkers: A Novel Approach.

In Journal of clinical medicine

This study explored the use of wearable sensor technology to investigate autonomic function in children with autism spectrum disorder (ASD) and Rett syndrome (RTT). We aimed to identify autonomic biomarkers that can correctly differentiate females with ASD and Rett Syndrome using an innovative methodology that applies machine learning approaches. Our findings suggest that we can predict (95%) the status of ASD/Rett. We conclude that physiological biomarkers may be able to assist in the differentiation between patients with RTT and ASD and could allow the development of timely therapeutic strategies.

Iakovidou Nantia, Lanzarini Evamaria, Singh Jatinder, Fiori Federico, Santosh Paramala


Rett syndrome, autism spectrum disorder, children, machine learning, physiological biomarkers

General General

Managing gestational diabetes mellitus using a smartphone application with artificial intelligence (SineDie) during the COVID-19 pandemic: Much more than just telemedicine.

In Diabetes research and clinical practice ; h5-index 50.0

We describe our experience in the remote management of women with gestational diabetes mellitus during the COVID-19 pandemic. We used a mobile phone application with artificial intelligence that automatically classifies and analyses the data (ketonuria, diet transgressions, and blood glucose values), making adjustment recommendations regarding the diet or insulin treatment.

Albert Lara, Capel Ismael, García-Sáez Gema, Martín-Redondo Pablo, Hernando M Elena, Rigla Mercedes


Artificial intelligence, Gestational diabetes mellitus, Mobile phone application, Telemedicine, eHealth

General General

Non-REM sleep instability in children with restless sleep disorder.

In Sleep medicine

STUDY OBJECTIVES : Restless sleep disorder (RSD) is a newly recognized condition characterized by motor movements involving large muscle groups with frequent repositioning or bed sheets disruption. We analyzed cyclic alternating pattern (CAP) in these children, a marker of sleep instability that might be associated with the motor episodes of RSD and may play a role in their daytime symptoms.

METHODS : Polysomnographic recordings from thirty-eight children who fulfilled RSD diagnostic criteria (23 boys and 15 girls), 23 children with restless legs syndrome (RLS, 18 boys and 5 girls) and 19 controls (10 boys and 9 girls) were included. For CAP analysis, a previously developed, highly precise automated system, based on a deep learning recurrent neural network, was used.

RESULTS : Age and gender were not statistically different between groups. RSD patients showed a lower percentage of A3 CAP subtypes than controls (median 9.8 vs. 18.2, p = 0.0089), accompanied by shorter duration of the B phase of the CAP cycle (median 28.2 vs. 29.8 in controls, 30.2 in RLS, p = 0.005) and shorter CAP cycle duration than both controls and RLS subjects (median 33.8 vs. 35.0 in controls, 35.8 in RLS, p = 0.002). Finally, RSD children also showed a longer duration of CAP cycle sequences, when compared to controls (median 172.7 vs. 141.9, p = 0.0063).

CONCLUSIONS : In conclusion, our study indicates that NREM sleep EEG shows an increased instability in RSD; these findings add to the current knowledge on the mechanisms of this newly recognized sleep disorder and suggest that sleep instability might be a favoring mechanism for the emergence of the motor episodes characterizing RSD.

DelRosso Lourdes M, Hartmann Simon, Baumert Mathias, Bruni Oliviero, Ruth Chris, Ferri Raffaele


Cyclic alternating pattern, NREM sleep instability, Restless legs syndrome, Restless sleep disorder

General General

Leveraging maximum entropy and correlation on latent factors for learning representations.

In Neural networks : the official journal of the International Neural Network Society

Many tasks involve learning representations from matrices, and Non-negative Matrix Factorization (NMF) has been widely used due to its excellent interpretability. Through factorization, sample vectors are reconstructed as additive combinations of latent factors, which are represented as non-negative distributions over the raw input features. NMF models are significantly affected by latent factors' distribution characteristics and the correlations among them. And NMF models are faced with the challenge of learning robust latent factor. To this end, we propose to learn representations with an awareness of the semantic quality evaluated from the aspects of intra- and inter-factors. On the one hand, a Maximum Entropy-based function is devised for the intra-factor semantic quality. On the other hand, the semantic uniqueness is evaluated via inter-factor correlation, which reinforces the aim of semantic compactness. Moreover, we present a novel non-linear NMF framework. The learning algorithm is presented and the convergence is theoretically analyzed and proved. Extensive experimental results on multiple datasets demonstrate that our method can be successfully applied to representative NMF models and boost performances over state-of-the-art models.

He Zhicheng, Liu Jie, Dang Kai, Zhuang Fuzhen, Huang Yalou


Correlated latent factor learning, Maximum entropy, Non-negative Matrix Factorization