Notes

Alkali-Activated Stainless Steel Slag being a Cementitious Materials from the Output of Self-Compacting Concrete.
BACKGROUND Postpartum depression (PPD) is a serious public health problem. Building a predictive model for PPD using data during pregnancy can facilitate earlier identification and intervention. OBJECTIVE The aims of this study are to compare the effects of four different machine learning models using data during pregnancy to predict PPD and explore which factors in the model are the most important for PPD prediction. METHODS Information on the pregnancy period from a cohort of 508 women, including demographics, social environmental factors, and mental health, was used as predictors in the models. The Edinburgh Postnatal Depression Scale score within 42 days after delivery was used as the outcome indicator. Using two feature selection methods (expert consultation and random forest-based filter feature selection [FFS-RF]) and two algorithms (support vector machine [SVM] and random forest [RF]), we developed four different machine learning PPD prediction models and compared their prediction effects. RESULTS There was no significant difference in the effectiveness of the two feature selection methods in terms of model prediction performance, but 10 fewer factors were selected with the FFS-RF than with the expert consultation method. The model based on SVM and FFS-RF had the best prediction effects (sensitivity=0.69, area under the curve=0.78). In the feature importance ranking output by the RF algorithm, psychological elasticity, depression during the third trimester, and income level were the most important predictors. CONCLUSIONS In contrast to the expert consultation method, FFS-RF was important in dimension reduction. When the sample size is small, the SVM algorithm is suitable for predicting PPD. In the prevention of PPD, more attention should be paid to the psychological resilience of mothers. ©Weina Zhang, Han Liu, Vincent Michael Bernard Silenzio, Peiyuan Qiu, Wenjie Gong. Originally published in JMIR Medical Informatics (http//medinform.jmir.org), 30.04.2020.BACKGROUND Elderly trauma patients constitute a vulnerable group, with a substantial risk of morbidity and mortality even after low-energy falls. As the world's elderly population continues to increase, the number of elderly trauma patients is expected to increase. Limited data are available about the possible patient safety challenges that elderly trauma patients face. The outcomes and characteristics of the Norwegian geriatric trauma population are not described on a national level. OBJECTIVE The aim of this project is to investigate whether patient safety challenges exist for geriatric trauma patients in Norway. An important objective of the study is to identify risk areas that will facilitate further work to safeguard and promote quality and safety in the Norwegian trauma system. METHODS This is a population-based mixed methods project divided into 4 parts 3 quantitative retrospective cohort studies and 1 qualitative interview study. The quantitative studies will compare adult (aged 16-64 years) and elder on a national level that will form the basis for further research aiming at developing interventions that hopefully will make the trauma system better equipped to manage the rising tide of geriatric trauma. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) PRR1-10.2196/15722. ©Mathias Cuevas-Østrem, Olav Røise, Torben Wisborg, Elisabeth Jeppesen. Originally published in JMIR Research Protocols (http//www.researchprotocols.org), 30.04.2020.BACKGROUND A fixed-dose combination of ledipasvir/sofosbuvir (LDV/SOF) is efficacious in treating chronic hepatitis C virus (HCV) infection; however, objective adherence to prescribed regimens in real-world clinical settings has not been well studied. OBJECTIVE This study aimed to evaluate adherence and virologic outcomes in patients with chronic HCV infection treated with LDV/SOF using a novel digital medicine program that directly measures drug ingestion adherence. METHODS This prospective, observational, open-label, single-arm pilot study was conducted at 2 clinical research sites and followed patients with HCV infection who were prescribed LDV/SOF along with an ingestible sensor. Patients were treated for 8 or 12 weeks. The main outcomes were ingestion adherence, medical interventions, virologic response, safety, and patient satisfaction. RESULTS Of the 28 patients (mean 59 years, SD 7), 61% (17/28) were male, 61% (17/28) were non-Caucasian, and 93% (26/28) were treatment naïve. All 28 had genotype 1 HCV,n populations at high risk for nonadherence. ©Maurizio Bonacini, Yoona Kim, Caroline Pitney, Lee McKoin, Melody Tran, Charles Landis. SF2312 cost Originally published in the Journal of Medical Internet Research (http//www.jmir.org), 24.02.2020.BACKGROUND Deidentification of clinical records is a critical step before their publication. This is usually treated as a type of sequence labeling task, and ensemble learning is one of the best performing solutions. Under the framework of multi-learner ensemble, the significance of a candidate rule-based learner remains an open issue. OBJECTIVE The aim of this study is to investigate whether a rule-based learner is useful in a hybrid deidentification system and offer suggestions on how to build and integrate a rule-based learner. METHODS We chose a data-driven rule-learner named transformation-based error-driven learning (TBED) and integrated it into the best performing hybrid system in this task. RESULTS On the popular Informatics for Integrating Biology and the Bedside (i2b2) deidentification data set, experiments showed that TBED can offer high performance with its generated rules, and integrating the rule-based model into an ensemble framework, which reached an F1 score of 96.76%, achieved the best performance reported in the community. CONCLUSIONS We proved the rule-based method offers an effective contribution to the current ensemble learning approach for the deidentification of clinical records. Such a rule system could be automatically learned by TBED, avoiding the high cost and low reliability of manual rule composition. In particular, we boosted the ensemble model with rules to create the best performance of the deidentification of clinical records. ©Zhenyu Zhao, Muyun Yang, Buzhou Tang, Tiejun Zhao. Originally published in JMIR Medical Informatics (http//medinform.jmir.org), 30.04.2020.
Here's my website: https://www.selleckchem.com/products/sf2312.html