Machine learning applications on neonatal sepsis treatment: a scoping review.

INTRODUCTION: Neonatal sepsis is a major cause of health loss and mortality worldwide. Without proper treatment, neonatal sepsis can quickly develop into multisystem organ failure. However, the signs of neonatal sepsis are non-specific, and treatment is labour-intensive and expensive. Moreover, antimicrobial resistance is a significant threat globally, and it has been reported that over 70% of neonatal bloodstream infections are resistant to first-line antibiotic treatment. Machine learning is a potential tool to aid clinicians in diagnosing infections and in determining the most appropriate empiric antibiotic treatment, as has been demonstrated for adult populations. This review aimed to present the application of machine learning on neonatal sepsis treatment. METHODS: PubMed, Embase, and Scopus were searched for studies published in English focusing on neonatal sepsis, antibiotics, and machine learning. RESULTS: There were 18 studies included in this scoping review. Three studies focused on using machine learning in antibiotic treatment for bloodstream infections, one focused on predicting in-hospital mortality associated with neonatal sepsis, and the remaining studies focused on developing machine learning prediction models to diagnose possible sepsis cases. Gestational age, C-reactive protein levels, and white blood cell count were important predictors to diagnose neonatal sepsis. Age, weight, and days from hospital admission to blood sample taken were important to predict antibiotic-resistant infections. The best-performing machine learning models were random forest and neural networks. CONCLUSION: Despite the threat antimicrobial resistance poses, there was a lack of studies focusing on the use of machine learning for aiding empirical antibiotic treatment for neonatal sepsis.

Incidence of Group B Streptococcus Disease in Infants in China: An Updated Systematic Review and Meta-analysis.

New studies of Group B Streptococcus (GBS) in infants <3 months of age in China have been published since our previous systematic review and meta-analysis. Using the same methodology, we updated these estimates and determined a total incidence of 0.41 (95% CI, 0.32-0.51) cases/1000 live births, lower than previously (0.55/1000). New intrapartum antibiotic prophylaxis policies may have played an important role in this reduction.

Family-Centered Care During Constraint-Induced Therapy After Chronic Stroke: A Feasibility Study.

PURPOSE: This feasibility study evaluated a theory-based intervention (CARE-CITE) designed to engage carepartners (CPs) in supporting stroke survivor upper extremity rehabilitation. DESIGN: The study was a one-group design with pre- and posttest and 1 month follow-up (N = 7 dyads). METHODS: Feasibility was determined by participant retention, CP and stroke survivor intervention adherence, and CP acceptability of the intervention (exit interview). Measures of CP depressive symptoms, fatigue, and family conflict around stroke recovery and stroke survivor upper extremity function are reported. Data were analyzed using descriptive statistics. FINDINGS: All participants completed the study and adhered to the intervention, and CPs found CARE-CITE helpful. Descriptively, better scores were observed for CP's mental health, family conflict, stroke survivor confidence, and upper extremity tasks performed. CONCLUSION: These results provide initial evidence that CARE-CITE is feasible after chronic stroke and that CPs and stroke survivors may benefit from family-centered care. CLINICAL RELEVANCE: Improving CP skills in supporting rehabilitation activities may improve stroke survivor upper extremity function.

Detecting autism spectrum disorder from early intervention charts: methodology and preliminary findings.

Federal laws mandating a "single point of entry" for early intervention (EI) create a potential database for surveillance of early childhood disabilities. This study evaluated EI records for estimating rates of autism spectrum disorder (ASD) using a chart abstraction protocol, with good interrater agreement (k = .86). Sampling 304 EI records yielded a point prevalence of (per 1,000) 8.5 (95% CI: 4.8-10.9) and a cumulative incidence of 7.4 (95% CI: 5.5-12.4). These rates are similar to recent published estimates. Additionally, the male-to-female ratio for autism, and rates of other developmental disorders were found to be consistent with current literature. These results suggest that local systems EI records may provide an excellent resource for ASD surveillance and research.

Uterine secretion of ISP1 & 2 tryptases is regulated by progesterone and estrogen during pregnancy and the endometrial cycle.

We have described two novel implantation serine proteinase (ISP) genes that are expressed during the implantation period. The ISP1 gene may encode the embryo-derived enzyme strypsin, which is necessary for blastocyst hatching in vitro and the initiation of invasion. The ISP2 gene, which encodes a related tryptase, is expressed in endometrial glands and is regulated by progesterone during the peri-implantation period. Based on similarities between ISP2 gene expression and that of a progesterone-regulated lumenal serine proteinase activity associated with lysis of the zona pellucida, we have suggested that the strypsin related protein, ISP2, may encode a zona lysin proteinase. Recently strypsin has also been found within uterine fluid, suggesting a second potential role in hatching. Consistently, we have discovered that ISP1 is also expressed in the uterine secretory gland at the time of hatching. In this study we demonstrate that both ISP1 and ISP2 are secreted together into the uterine lumen at peri-implantation, and that the appearance of ISP protein is regulated positively at the transcriptional level by progesterone and negatively at the posttranscriptional level by estrogen. This negative regulation by estrogen may be overridden in pregnancy as ISP protein expression is restored during oil-induced decidualization. ISP1 and ISP2 proteins are also expressed in proestrous suggesting additional roles in the endometrial cycle.

Origin of the murine implantation serine proteinase subfamily.

The S1 serine protease family is one of the largest gene families known. Within this family there are several subfamilies that have been grouped together as a result of sequence comparisons and substrate identification. The grouping of related genes allows for the speculation of function for newly found members by comparison and for novel subfamilies by contrast. Analysis of the evolutionary patterns of genes indicates whether or not orthologs are likely to be identified in other species as well as potentially indicating that hypothesized orthologs are in fact not. Looking at subtle differences between subfamily members can reveal intricacies about function and expression. Previously, we have described genes encoding two novel serine proteinases, ISP1 and ISP2, which are most closely related to tryptases. The ISP1 gene encodes the embryo-derived enzyme strypsin, which is necessary for blastocyst hatching and invasion in vitro. Additionally both ISP1 and ISP2 are co-expressed in the endometrial gland during the time of hatching, suggesting that they may also both participate in zona lysis from within the uterine lumen. Here, we demonstrate that the ISPs are tandemly linked within the tryptase cluster on 17A3.3. We suggest that remarkable similarities within the 5'-untranslated and first intron regions of ISP1 and ISP2 may explain their intimate co-regulation in uterus. We also suggest that ISP genes have evolved through gene duplication and that the ISP1 gene has also begun to adopt an additional new function in the murine preimplantation embryo.

Embryonic hatching enzyme strypsin/ISP1 is expressed with ISP2 in endometrial glands during implantation.

Embryo hatching and outgrowth are the first critical steps on the way to a successful pregnancy. It is generally held that serine proteases are responsible for this process, although the exact mechanisms of action are not clearly understood. Recently, we described two novel implantation serine proteinase (ISP) genes that are expressed during the implantation period. The ISP1 gene encodes the embryo-derived enzyme strypsin, which is necessary for blastocyst hatching in vitro and the initiation of invasion. The ISP2 gene, which encodes a related tryptase, is expressed in endometrial glands and is regulated by progesterone during the peri-implantation period. Based on similarities between ISP2 gene expression and that of a progesterone-regulated lumenal serine proteinase activity associated with lysis of the zona pellucida, we have suggested that the strypsin related protein, ISP2, may encode a zona lysin proteinase. As tryptases naturally assemble to form tetrameric structures, we have hypothesized that ISP1 and ISP2 tetramerize to form strypsin and lysin, respectively. In this study, we demonstrate that like ISP2, the ISP1 gene is also expressed in endometrial glands and is positively regulated by progesterone during implantation. Using in situ hybridization of adjacent tissue sections, we show that the ISP1 and ISP2 genes are co-expressed within the endometrial gland. Following evidence that ISP1 and 2 can efficiently form homotetramers and heterotetramers in silico, we suggest that ISP heterotetramers may be also be secreted into the uterine lumen during the implantation period. That the embryonic hatching enzyme, may also be secreted into the uterine lumen from uterus, may provide insight into the mechanisms of hatching and implantation initiation.