Multivariate adaptive regression splines analysis to predict biomarkers of spontaneous preterm birth

Incorporating machine learning and statistical methods to address maternal healthcare disparities in US: A systematic review

BACKGROUND

Maternal health disparities are recognized as a significant public health challenge, with pronounced disparities evident across racial, socioeconomic, and geographic dimensions. Although healthcare technologies have advanced, these disparities remain primarily unaddressed, indicating that enhanced analytical approaches are needed.

OBJECTIVES

This review aims to evaluate the impact of machine learning (ML) and statistical methods on identifying and addressing maternal health disparities and to outline future research directions for enhancing these methodologies.

METHODS

Following the PRISMA guidelines, the review of studies employing ML and statistical methods to analyze maternal health disparities within the United States was conducted. Publications between January 1, 2012, and February 2024 were systematically searched through PubMed, Web of Science, and ScienceDirect. Inclusion criteria targeted studies conducted within the U.S., peer-reviewed articles published during the period, research covering the postpartum period up to one year post-delivery, and studies incorporating both maternal and infant health data with a focus primarily on maternal outcomes.

RESULTS

A total of 147 studies met the inclusion criteria for this analysis. Among these, 129 (88 %) utilized statistical methods in health sciences to analyze correlations, treatment effects, and public health initiatives, thus providing vital, actionable insights for policy and clinical decisions. Meanwhile, 18 articles (12 %) applied ML techniques to explore complex, nonlinear relationships in data. The findings indicate that while ML and statistical methods offer valuable insights into the factors contributing to health disparities, there are limitations regarding dataset diversity and methodological precision. Most studies concentrate on racial and socioeconomic inequalities, with fewer addressing the geographical aspects of maternal health. This review emphasizes the necessity for broader dataset utilization and methodology improvements to enhance the findings' predictive accuracy and applicability.

CONCLUSIONS

ML and statistical methods show great potential to transform maternal healthcare by identifying and addressing disparities. Future research should focus on broadening dataset diversity, improving methodological precision, and enhancing interdisciplinary efforts.

Prediction of insulin resistance using multiple adaptive regression spline in Chinese women

Insulin resistance (IR) is the core for type 2 diabetes and metabolic syndrome. The homeostasis assessment model is a straightforward and practical tool for quantifying insulin resistance (HOMA-IR). Multiple adaptive regression spline (MARS) is a machine learning method used in many research fields but has yet to be applied to estimating HOMA-IR. This study uses MARS to build an equation to estimate HOMA-IR in pre-menopausal Chinese women based on a sample of 4,071 healthy women aged 20-50 with no major diseases and no medication use for blood pressure, blood glucose or blood lipids. Thirty variables were applied to build the HOMA-IR model, including demographic, laboratory, and lifestyle factors. MARS results in smaller prediction errors than traditional multiple linear regression (MLR) methods, and is thus more accurate. The model was established based on key impact factors including waist-hip ratio (WHR), C reactive protein (CRP), uric acid (UA), total bilirubin (TBIL), leukocyte (WBC), serum glutamic oxaloacetic transaminase (GOT), high-density lipoprotein cholesterol (HDL-C), systolic blood pressure (SBP), serum glutamic pyruvic transaminase (GPT), and triglycerides (TG). The equation is as following:HOMA-IR = 6.634 - 1.448MAX(0, 0.833 - WHR) + 10.152MAX(0, WHR - 0.833) - 1.351MAX(0, 0.7 - CRP) - 0.449MAX(0, CRP - 0.7) + 1.062MAX(0, UA - 8.5) + +1.047(MAX(0, 0.83 - TBIL) + 0.681MAX(0, WBC - 11.53) - 0.071MAX(0, 11.53 - WBC) + 0.043MAX(0, 24 - GOT) - 0.017MAX(0, GOT - 24) + 0.021MAX(0, 59 - HDL) - 0.005MAX(0, HDL - 59) - 0.013MAX(0, 141 - SBP) - 0.033MAX(0, 100 - GPT) + 0.013MAX(0, GPT - 100) - 0.004MAX(303 - TG)Results indicate that MARS is a more precise tool than fasting plasma insulin (FPI) levels, and could be used in the daily practice, and further longitudinal studies are warranted.

Development and validation of a spontaneous preterm birth risk prediction algorithm based on maternal bioinformatics: A single-center retrospective study

BACKGROUND

Spontaneous preterm birth (sPTB) is a primary cause of adverse neonatal outcomes. The objective of this study is to analyze the factors influencing the occurrence of sPTB in pregnant women and to construct and validate a predictive model for sPTB risk based on big data from clinical and laboratory assessments during pregnancy.

METHODS

A retrospective analysis was conducted on the clinical data of 3,082 pregnant women, categorizing those who delivered before 37 weeks of gestation as the sPTB group and those who delivered at or after 37 weeks as the full-term group. The performance of five machine learning models was compared using metrics such as the AUC, accuracy, sensitivity, specificity, and precision to identify the optimal predictive model. The top 10 predictive variables were selected based on their significance in disease prediction. The data were then divided into a training set (70%) and a validation set (30%) for validation. External data were also utilized to validate the model's predictive performance.

RESULTS

A total of 24 indicators with significant differences were identified. In terms of predicting the risk of preterm birth, the XGBoost algorithm demonstrated the most outstanding performance, with an AUCROC of 0.89 (95% CI: 0.88-0.90). The top 10 critical indicators included ALP, AFP, ALB, HCT, TC, DBP, ALT, PLT, height, and SBP, which are essential for constructing an accurate predictive model. The model exhibited stable performance on both the training and validation sets, with AUC values of 0.93 and 0.87, respectively. Furthermore, the external testing set also showed superior performance, with an AUC of 0.79.

CONCLUSIONS

At the time of delivery, ALP, AFP, ALB, HCT, TC, DBP, ALT, PLT, height, and SBP are influential factors for sPTB in pregnant women. The XGBoost algorithm, constructed based on these factors, demonstrated the most outstanding performance.

Black-white differences in chronic stress exposures to predict preterm birth: interpretable, race/ethnicity-specific machine learning model

BACKGROUND

Differential exposure to chronic stressors by race/ethnicity may help explain Black-White inequalities in rates of preterm birth. However, researchers have not investigated the cumulative, interactive, and population-specific nature of chronic stressor exposures and their possible nonlinear associations with preterm birth. Models capable of computing such high-dimensional associations that could differ by race/ethnicity are needed. We developed machine learning models of chronic stressors to both predict preterm birth more accurately and identify chronic stressors and other risk factors driving preterm birth risk among non-Hispanic Black and non-Hispanic White pregnant women.

METHODS

Multivariate Adaptive Regression Splines (MARS) models were developed for preterm birth prediction for non-Hispanic Black, non-Hispanic White, and combined study samples derived from the CDC's Pregnancy Risk Assessment Monitoring System data (2012-2017). For each sample population, MARS models were trained and tested using 5-fold cross-validation. For each population, the Area Under the ROC Curve (AUC) was used to evaluate model performance, and variable importance for preterm birth prediction was computed.

RESULTS

Among 81,892 non-Hispanic Black and 277,963 non-Hispanic White live births (weighted sample), the best-performing MARS models showed high accuracy (AUC: 0.754-0.765) and similar-or-better performance for race/ethnicity-specific models compared to the combined model. The number of prenatal care visits, premature rupture of membrane, and medical conditions were more important than other variables in predicting preterm birth across the populations. Chronic stressors (e.g., low maternal education and intimate partner violence) and their correlates predicted preterm birth only for non-Hispanic Black women.

CONCLUSIONS

Our study findings reinforce that such mid or upstream determinants of health as chronic stressors should be targeted to reduce excess preterm birth risk among non-Hispanic Black women and ultimately narrow the persistent Black-White gap in preterm birth in the U.S.

Estimation of racial and language disparities in pediatric emergency department triage using statistical modeling and natural language processing

OBJECTIVES

The study aims to assess racial and language disparities in pediatric emergency department (ED) triage using analytical techniques and provide insights into the extent and nature of the disparities in the ED setting.

MATERIALS AND METHODS

The study analyzed a cross-sectional dataset encompassing ED visits from January 2019 to April 2021. The study utilized analytical techniques, including K-mean clustering (KNN), multivariate adaptive regression splines (MARS), and natural language processing (NLP) embedding. NLP embedding and KNN were employed to handle the chief complaints and categorize them into clusters, while the MARS was used to identify significant interactions among the clinical features. The study also explored important variables, including age-adjusted vital signs. Multiple logistic regression models with varying specifications were developed to assess the robustness of analysis results.

RESULTS

The study consistently found that non-White children, especially African American (AA) and Hispanic, were often under-triaged, with AA children having >2 times higher odds of receiving lower acuity scores compared to White children. While the results are generally consistent, incorporating relevant variables modified the results for specific patient groups (eg, Asians).

DISCUSSION

By employing a comprehensive analysis methodology, the study checked the robustness of the analysis results on racial and language disparities in pediatric ED triage. The study also recognized the significance of analytical techniques in assessing pediatric health conditions and analyzing disparities.

CONCLUSION

The study's findings highlight the significant need for equal and fair assessment and treatment in the pediatric ED, regardless of their patients' race and language.

Assessing the length of hospital stay for patients with myasthenia gravis based on the data mining MARS approach

Predicting the length of hospital stay for myasthenia gravis (MG) patients is challenging due to the complex pathogenesis, high clinical variability, and non-linear relationships between variables. Considering the management of MG during hospitalization, it is important to conduct a risk assessment to predict the length of hospital stay. The present study aimed to successfully predict the length of hospital stay for MG based on an expandable data mining technique, multivariate adaptive regression splines (MARS). Data from 196 MG patients' hospitalization were analyzed, and the MARS model was compared with classical multiple linear regression (MLR) and three other machine learning (ML) algorithms. The average hospital stay duration was 12.3 days. The MARS model, leveraging its ability to capture non-linearity, identified four significant factors: disease duration, age at admission, MGFA clinical classification, and daily prednisolone dose. Cut-off points and correlation curves were determined for these risk factors. The MARS model outperformed the MLR and the other ML methods (including least absolute shrinkage and selection operator MLR, classification and regression tree, and random forest) in assessing hospital stay length. This is the first study to utilize data mining methods to explore factors influencing hospital stay in patients with MG. The results highlight the effectiveness of the MARS model in identifying the cut-off points and correlation for risk factors associated with MG hospitalization. Furthermore, a MARS-based formula was developed as a practical tool to assist in the measurement of hospital stay, which can be feasibly supported as an extension of clinical risk assessment.

Artificial Intelligence Modeling to Predict Periprosthetic Infection and Explantation following Implant-Based Reconstruction

BACKGROUND

Despite improvements in prosthesis design and surgical techniques, periprosthetic infection and explantation rates following implant-based reconstruction (IBR) remain relatively high. Artificial intelligence is an extremely powerful predictive tool that involves machine learning (ML) algorithms. We sought to develop, validate, and evaluate the use of ML algorithms to predict complications of IBR.

METHODS

A comprehensive review of patients who underwent IBR from January of 2018 to December of 2019 was conducted. Nine supervised ML algorithms were developed to predict periprosthetic infection and explantation. Patient data were randomly divided into training (80%) and testing (20%) sets.

RESULTS

The authors identified 481 patients (694 reconstructions) with a mean ± SD age of 50.0 ± 11.5 years, mean ± SD body mass index of 26.7 ± 4.8 kg/m 2 , and median follow-up time of 16.1 months (range, 11.9 to 3.2 months). Periprosthetic infection developed in 113 of the reconstructions (16.3%), and explantation was required with 82 (11.8%) of them. ML demonstrated good discriminatory performance in predicting periprosthetic infection and explantation (area under the receiver operating characteristic curve, 0.73 and 0.78, respectively), and identified nine and 12 significant predictors of periprosthetic infection and explantation, respectively.

CONCLUSIONS

ML algorithms trained using readily available perioperative clinical data accurately predict periprosthetic infection and explantation following IBR. The authors' findings support incorporating ML models into perioperative assessment of patients undergoing IBR to provide data-driven, patient-specific risk assessment to aid individualized patient counseling, shared decision-making, and presurgical optimization.

Low-dose aspirin and racial disparities in spontaneous preterm delivery in low-risk individuals

BACKGROUND

Preterm birth is a leading cause of perinatal morbidity and mortality. There are significant racial disparities in the rates of preterm delivery in the United States, with Black individuals at disproportionately higher risk than their White counterparts. Although low-dose aspirin is currently under investigation for reducing the rates of preterm delivery, limited data are available on how the use of low-dose aspirin might affect racial and ethnic disparities in the rates of preterm delivery.

OBJECTIVE

Our group and others have shown that low-dose aspirin decreases spontaneous preterm delivery in low-risk parturients. This study aimed to examine whether the relationship between low-dose aspirin and the risk of spontaneous preterm delivery is modified by race and ethnicity.

STUDY DESIGN

This was a secondary analysis of a randomized clinical trial examining low-dose aspirin for preeclampsia prevention in low-risk nulliparous individuals. The parent trial defined low risk as the absence of preexisting hypertension or other medical comorbidities. Participants received 60-mg aspirin or placebo between 13 and 25 weeks of gestation. Here, multiple pregnancies, fetal anomalies, terminations or abortions at <20 weeks of gestation, and participants with previous miscarriages were excluded. Our exposure, race and ethnicity, was self-reported in the parent trial and categorized as non-Hispanic White, Hispanic, non-Hispanic Black, and other. The primary outcome was spontaneous preterm delivery at <34 weeks of gestation; the secondary outcomes included spontaneous preterm delivery at <37 weeks of gestation and all preterm deliveries at <34 and <37 weeks of gestation. Fit logistic regression models were used to examine how the use of low-dose aspirin modified the relationship between race and ethnicity and preterm delivery, adjusting for confounders. Furthermore, sensitivity analyses were performed to compare the rates of preterm delivery by race and ethnicity.

RESULTS

Of note, 2528 of 3171 parent study participants were included in this analysis. Of the participants, 425 (16.8%) were White, 819 (32.4%) were Hispanic, 1265 (50%) were Black, and 19 (0.8%) were other. The baseline characteristics differed among racial and ethnic groups, including maternal age, body mass index, education level, marital status, tobacco and alcohol use, and pregnancy loss. The rate of spontaneous preterm delivery at <34 weeks of gestation was significantly higher in Black participants (2.8%) than in White (1.2%) and Hispanic (1.2%) participants (P=.04). Logistical regression analysis showed that Black race was no longer an independent risk factor for spontaneous preterm delivery at <34 weeks of gestation when controlling for low-dose aspirin (adjusted odds ratio, 1.71; 95% confidence interval, 0.67-4.40). A similar pattern was found for spontaneous preterm delivery at <37 weeks of gestation and preterm delivery at <34 and <37 weeks of gestation. In our sensitivity analyses, spontaneous preterm delivery at <34 weeks of gestation differed by race and ethnicity in the placebo group (P=.01) but did not differ in the low-dose aspirin group (P=.90).

CONCLUSION

The use of low-dose aspirin mitigated racial disparities in spontaneous preterm delivery at <34 weeks of gestation. Additional investigation is warranted to assess the reproducibility of our findings.

Development and Assessment of Machine Learning Models for Individualized Risk Assessment of Mastectomy Skin Flap Necrosis

OBJECTIVE

To develop, validate, and evaluate ML algorithms for predicting MSFN.

BACKGROUND

MSFN is a devastating complication that causes significant distress to patients and physicians by prolonging recovery time, compromising surgical outcomes, and delaying adjuvant therapy.

METHODS

We conducted comprehensive review of all consecutive patients who underwent mastectomy and immediate implant-based reconstruction from January 2018 to December 2019. Nine supervised ML algorithms were developed to predict MSFN. Patient data were partitioned into training (80%) and testing (20%) sets.

RESULTS

We identified 694 mastectomies with immediate implant-based reconstruction in 481 patients. The patients had a mean age of 50 ± 11.5 years, years, a mean body mass index of 26.7 ± 4.8 kg/m 2 , and a median follow-up time of 16.1 (range, 11.9-23.2) months. MSFN developed in 6% (n = 40) of patients. The random forest model demonstrated the best discriminatory performance (area under curve, 0.70), achieved a mean accuracy of 89% (95% confidence interval, 83-94), and identified 10 predictors of MSFN. Decision curve analysis demonstrated that ML models have a superior net benefit regardless of the probability threshold. Higher body mass index, older age, hypertension, subpectoral device placement, nipple-sparing mastectomy, axillary nodal dissection, and no acellular dermal matrix use were all independently associated with a higher risk of MSFN.

CONCLUSIONS

ML algorithms trained on readily available perioperative clinical data can accurately predict the occurrence of MSFN and aid in individualized patient counseling, preoperative optimization, and surgical planning to reduce the risk of this devastating complication.

The Use of Machine Learning for Predicting Complications of Free-Flap Head and Neck Reconstruction

BACKGROUND

Machine learning has been increasingly used for surgical outcome prediction, yet applications in head and neck reconstruction are not well-described. In this study, we developed and evaluated the performance of ML algorithms in predicting postoperative complications in head and neck free-flap reconstruction.

METHODS

We conducted a comprehensive review of patients who underwent microvascular head and neck reconstruction between January 2005 and December 2018. Data were used to develop and evaluate nine supervised ML algorithms in predicting overall complications, major recipient-site complication, and total flap loss.

RESULTS

We identified 4000 patients who met inclusion criteria. Overall, 33.7% of patients experienced a complication, 26.5% experienced a major recipient-site complication, and 1.7% suffered total flap loss. The k-nearest neighbors algorithm demonstrated the best overall performance for predicting any complication (AUROC = 0.61, sensitivity = 0.60). Regularized regression had the best performance for predicting major recipient-site complications (AUROC = 0.68, sensitivity = 0.66), and decision trees were the best predictors of total flap loss (AUROC = 0.66, sensitivity = 0.50).

CONCLUSIONS

ML accurately identified patients at risk of experiencing postsurgical complications, including total flap loss. Predictions from ML models may provide insight in the perioperative setting and facilitate shared decision making.

Global Distribution of Culex tritaeniorhynchus and Impact Factors

Culex tritaeniorhynchus is the primary vector of Japanese encephalitis (JE) and has a wide global distribution. However, the current and future geographic distribution maps of Cx. tritaeniorhynchus in global are still incomplete. Our study aims to predict the potential distribution of Cx. tritaeniorhynchus in current and future conditions to provide a guideline for the formation and implementation of vector control strategies all over the world. We collected and screened the information on the occurrence of Cx. tritaeniorhynchus by searching the literature and online databases and used ten algorithms to investigate its global distribution and impact factors. Cx. tritaeniorhynchus had been detected in 41 countries from 5 continents. The final ensemble model (TSS = 0.864 and AUC = 0.982) indicated that human footprint was the most important factor for the occurrence of Cx. tritaeniorhynchus. The tropics and subtropics, including southeastern Asia, Central Africa, southeastern North America and eastern South America, showed high habitat suitability for Cx. tritaeniorhynchus. Cx. tritaeniorhynchus is predicted to have a wider distribution in all the continents, especially in Western Europe and South America in the future under two extreme emission scenarios (SSP5-8.5 and SSP1-2.6). Targeted strategies for the control and prevention of Cx. tritaeniorhynchus should be further strengthened.

Study on the prediction effect of a combined model of SARIMA and LSTM based on SSA for influenza in Shanxi Province, China

BACKGROUND

Influenza is an acute respiratory infectious disease that is highly infectious and seriously damages human health. Reasonable prediction is of great significance to control the epidemic of influenza.

METHODS

Our Influenza data were extracted from Shanxi Provincial Center for Disease Control and Prevention. Seasonal-trend decomposition using Loess (STL) was adopted to analyze the season characteristics of the influenza in Shanxi Province, China, from the 1st week in 2010 to the 52nd week in 2019. To handle the insufficient prediction performance of the seasonal autoregressive integrated moving average (SARIMA) model in predicting the nonlinear parts and the poor accuracy of directly predicting the original sequence, this study established the SARIMA model, the combination model of SARIMA and Long-Short Term Memory neural network (SARIMA-LSTM) and the combination model of SARIMA-LSTM based on Singular spectrum analysis (SSA-SARIMA-LSTM) to make predictions and identify the best model. Additionally, the Mean Squared Error (MSE), Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) were used to evaluate the performance of the models.

RESULTS

The influenza time series in Shanxi Province from the 1st week in 2010 to the 52nd week in 2019 showed a year-by-year decrease with obvious seasonal characteristics. The peak period of the disease mainly concentrated from the end of the year to the beginning of the next year. The best fitting and prediction performance was the SSA-SARIMA-LSTM model. Compared with the SARIMA model, the MSE, MAE and RMSE of the SSA-SARIMA-LSTM model decreased by 38.12, 17.39 and 21.34%, respectively, in fitting performance; the MSE, MAE and RMSE decreased by 42.41, 18.69 and 24.11%, respectively, in prediction performances. Furthermore, compared with the SARIMA-LSTM model, the MSE, MAE and RMSE of the SSA-SARIMA-LSTM model decreased by 28.26, 14.61 and 15.30%, respectively, in fitting performance; the MSE, MAE and RMSE decreased by 36.99, 7.22 and 20.62%, respectively, in prediction performances.

CONCLUSIONS

The fitting and prediction performances of the SSA-SARIMA-LSTM model were better than those of the SARIMA and the SARIMA-LSTM models. Generally speaking, we can apply the SSA-SARIMA-LSTM model to the prediction of influenza, and offer a leg-up for public policy.

Prediction of preterm birth using artificial intelligence: a systematic review

Preterm birth is the leading cause of neonatal death. It is challenging to predict preterm birth. We elucidated the state of artificial intelligence research on the prediction of preterm birth, clarifying the predictive values and accuracy. We performed a systematic review using three databases (PubMed, Web of Science, and Scopus) in August 2020, with keywords as 'artificial intelligence,' 'deep learning,' 'machine learning,' and 'neural network' combined with 'preterm birth'. We included 22 publications between 2010 and 2020. Regarding the predictive values, electrohysterogram images were mostly used, followed by the biological profiles, the metabolic panel in amniotic fluid or maternal blood, and the cervical images on the ultrasound examination. The size of dataset in most studies was hundred cases and too small for learning, although only three studies used the medical database over a hundred thousand cases. The accuracy was better in the studies using the metabolic panel and electrohysterogram images. Impact statementWhat is already known on this subject? Preterm birth is the leading cause of newborn morbidity and mortality. Presently, the prediction of preterm birth in individual cases is still challenging.What the results of this study add? Using artificial intelligence such as deep learning and machine learning models, clinical data could lead to accurate prediction of preterm birth.What the implications are of these findings for clinical practice and/or further research? The size of the datasets was too small for the models using artificial intelligence in the previous studies. Big data should be prepared for the future studies.

Machine Learning-Based Prediction Model of Preterm Birth Using Electronic Health Record

Objective

Preterm birth (PTB) was one of the leading causes of neonatal death. Predicting PTB in the first trimester and second trimester will help improve pregnancy outcomes. The aim of this study is to propose a prediction model based on machine learning algorithms for PTB.

Method

Data for this study were reviewed from 2008 to 2018, and all the participants included were selected from a hospital in China. Six algorisms, including Naive Bayesian (NBM), support vector machine (SVM), random forest tree (RF), artificial neural networks (ANN), K-means, and logistic regression, were used to predict PTB. The receiver operating characteristic curve (ROC), accuracy, sensitivity, and specificity were used to assess the performance of the model.

Results

A total of 9550 pregnant women were included in the study, of which 4775 women had PTB. A total of 4775 people were randomly selected as controls. Based on 27 weeks of gestation, the area under the curve (AUC) and the accuracy of the RF model were the highest compared with other algorithms (accuracy: 0.816; AUC = 0.885, 95% confidence interval (CI): 0.873–0.897). Meanwhile, there was positive association between the accuracy and AUC of the RF model and gestational age. Age, magnesium, fundal height, serum inorganic phosphorus, mean platelet volume, waist size, total cholesterol, triglycerides, globulins, and total bilirubin were the main influence factors of PTB.

Conclusion

The results indicated that the prediction model based on the RF algorithm had a potential value to predict preterm birth in the early stage of pregnancy. The important analysis of the RF model suggested that intervention for main factors of PTB in the early stages of pregnancy would reduce the risk of PTB.

Preterm birth buccal cell epigenetic biomarkers to facilitate preventative medicine

Preterm birth is the major cause of newborn and infant mortality affecting nearly one in every ten live births. The current study was designed to develop an epigenetic biomarker for susceptibility of preterm birth using buccal cells from the mother, father, and child (triads). An epigenome-wide association study (EWAS) was used to identify differential DNA methylation regions (DMRs) using a comparison of control term birth versus preterm birth triads. Epigenetic DMR associations with preterm birth were identified for both the mother and father that were distinct and suggest potential epigenetic contributions from both parents. The mother (165 DMRs) and female child (136 DMRs) at p < 1e-04 had the highest number of DMRs and were highly similar suggesting potential epigenetic inheritance of the epimutations. The male child had negligible DMR associations. The DMR associated genes for each group involve previously identified preterm birth associated genes. Observations identify a potential paternal germline contribution for preterm birth and identify the potential epigenetic inheritance of preterm birth susceptibility for the female child later in life. Although expanded clinical trials and preconception trials are required to optimize the potential epigenetic biomarkers, such epigenetic biomarkers may allow preventative medicine strategies to reduce the incidence of preterm birth.

A Strategic Program for Risk Assessment and Intervention to Mitigate Environmental Stressor-Related Adverse Pregnancy Outcomes in the Indian Population

The Problem: Global environmental stressors of human health include, but are not limited to, conflict, migration, war, natural disasters, climate change, pollution, trauma, and pandemics. In combination with other factors, these stressors influence physical and mental as well as reproductive health. Maternal stress is a known factor for adverse pregnancy outcomes such as preterm birth (PTB); however, environmental stressors are less well-understood in this context and the problem is relatively under-researched. According to the WHO, major Indian cities including New Delhi are among the world's 20 most polluted cities. It is known that maternal exposure to environmental pollution increases the risk of premature births and other adverse pregnancy outcomes which is evident in this population.

Response to the Problem: Considering the seriousness of this problem, an international and interdisciplinary group of researchers, physicians, and organizations dedicated to the welfare of women at risk of adverse pregnancy outcomes launched an international program named Optimal Pregnancy Environment Risk Assessment (OPERA). The program aims to discover and disseminate inexpensive, accessible tools to diagnose women at risk for PTB and other adverse pregnancy outcomes due to risky environmental factors as early as possible and to promote effective interventions to mitigate these risks. OPERA has been supported by the Worldwide Universities Network, World Health Organization (WHO) and March of Dimes USA.

Addressing the Problem: This review article addresses the influence of environmental stressors on maternal-fetal health focusing on India as a model population and describes the role of OPERA in helping local practitioners by sharing with them the latest risk prediction and mitigation tools. The consequences of these environmental stressors can be partially mitigated by experience-based interventions that build resilience and break the cycle of inter- and-transgenerational transmission. The shared knowledge and experience from this collaboration are intended to guide and facilitate efforts at the local level in India and other LMIC to develop strategies appropriate for the jurisdiction for improving pregnancy outcomes in vulnerable populations.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

BACKGROUND

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

OBJECTIVE

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians' decision making.

METHODS

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians' decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ2 and I2.

RESULTS

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I2=86%; τ2=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I2=75%; τ2=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I2=75%; τ2=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I2=83%; τ2=0.07).

CONCLUSIONS

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

TRIAL REGISTRATION

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106.

Specific inflammatory profile in each pregnancy complication: A comparative study

PROBLEM

Pre-eclampsia (PE), preterm birth (PTB) and intra-uterine growth restriction (IUGR) affect 5%-12% of pregnancies. They have been associated with placental inflammation, although the detection of inflammatory mediators in the maternal circulation is still controversial. Our goal was to determine the inflammatory changes occurring in the second part of pregnancy to identify profiles distinguishing pathological pregnancies from each other.

METHOD OF STUDY

We performed a nested case-control study of 200 women randomly selected from a cohort recruited at the CHU de Quebec-Universite Laval, Quebec, Canada. Women with uncomplicated term pregnancy (CTRL); PE (severe or not); PTB or IUGR (N = 50/each) were included. Plasma samples, obtained from the late second trimester and at delivery, were analysed for over 30 selected mediators (including cytokines/alarmins), by multiplex, ELISA or specific assays. Demographic and obstetrical information were obtained for classification.

RESULTS

In CTRL, we observed significant differences between 2nd trimester and delivery, with increased levels of inflammatory mediators (ex. MCP-1, IL-6), supporting an inflammatory profile towards term. Increased levels of IL-6, CXCL10 and CRP were observed in PE as compared to CTRL. In PTB, we observed increased CXCL9 in 2nd trimester and decreased progesterone at delivery. In IUGR, increased HMGB1 and IL-1α were observed only in the 2nd trimester.

CONCLUSIONS

Our work showed significant inflammatory changes in uncomplicated pregnancies towards delivery, supporting that normal delivery is pro-inflammatory, although not to the same extent as in pathological pregnancies. Inflammatory profiles are specific to each pregnancy complication which may help to understand the contribution of inflammation to the clinical presentation of these conditions.

Fetal membrane extracellular vesicle profiling reveals distinct pathways induced by infection and inflammation in vitro

PROBLEM

Fetal inflammatory signals can be propagated to maternal tissues to initiate labor via exosomes (extracellular vesicles; 30-150 nm). We tested the hypothesis that fetal membrane cells exposed to infectious and inflammatory mediators associated with preterm birth (PTB) produce exosomes with distinct protein cargo contents indicative of underlying pathobiology.

METHODS OF STUDY

Fetal membrane explants (FM) as well as primary amnion epithelial (AEC) and mesenchymal cells (AMC), and chorion cells (CC) from term deliveries were maintained in normal conditions (control) or exposed to LPS 100 ng/mL or TNF-α 50 ng/mL for 48 hours. Exosomes were isolated from media by differential centrifugation and size exclusion chromatography and characterized using cryo-electron microscopy (morphology), nanoparticle tracking analysis (size and quantity), Western blot (markers), and mass spectroscopy (cargo proteins). Ingenuity pathway analysis (IPA) determined pathways indicated by differentially expressed proteins.

RESULTS

Irrespective of source or treatment, exosomes were spherical, had similar size, quantities, and markers (ALIX, CD63, and CD81). However, exosome cargo proteins were different between FM and individual fetal membrane cell-derived exosomes in response to treatments. Several common proteins were seen; however, there are several unique proteins expressed by exosomes from different cell types in response to distinct stimuli indicative of unique pathways and physiological functions in cells.

CONCLUSIONS

We demonstrate collective tissue and independent cell response reflected in exosomes in response to infectious and inflammatory stimuli. These cargoes determined underlying physiology and their potential in enhancing inflammation in a paracrine fashion.

Prediction of Sewage Treatment Cost in Rural Regions with Multivariate Adaptive Regression Splines

In this paper, to interpret the cost structure of decentralized wastewater treatment plants (DWWTPs) in rural regions, a simple nonparametric regression algorithm known as multivariate adaptive regression spline (MARS) was proposed and applied to simulate the construction cost (CC), operation and maintenance cost (OMC), and total cost (TC). The effects of design treatment capacity (DTC), removal efficiency of chemical oxygen demand (RCOD), and removal efficiency of ammonia nitrogen (RNH3-N) on the cost functions of CC, OMC, and TC were analyzed in detail. The results indicated that: (1) DTC is the most important parameter to determine cost structure with relative importance of 100%, followed by RCOD and RNH3-N with relative importance of 16.55%, and 9.75%, respectively; (2) when DTC is less than 5 m3/d, the slopes of CC and TC on DTC are constants of 1.923 and 1.809, respectively, with no relationship with RCOD and RNH3-N; (3) when DTC is less than 20 m3/d, the OMC is a constant of 435 RMB/year; and (4) in other cases, CC, OMC, and TC are related to RCOD and RNH3-N besides DTC. Compared with widely used support vector machine (SVM) models and multiple linear regression (MLR) models, the MARS model has better statistical significance with greater R values and smaller RMSE and MAPE values, which indicated that the MARS model is a better way to approximate the cost for DWWTPs.

Prediction of preterm birth with and without preeclampsia using mid-pregnancy immune and growth-related molecular factors and maternal characteristics

OBJECTIVE

To evaluate if mid-pregnancy immune and growth-related molecular factors predict preterm birth (PTB) with and without (±) preeclampsia.

STUDY DESIGN

Included were 400 women with singleton deliveries in California in 2009-2010 (200 PTB and 200 term) divided into training and testing samples at a 2:1 ratio. Sixty-three markers were tested in 15-20 serum samples using multiplex technology. Linear discriminate analysis was used to create a discriminate function. Model performance was assessed using area under the receiver operating characteristic curve (AUC).

RESULTS

Twenty-five serum biomarkers along with maternal age <34 years and poverty status identified >80% of women with PTB ± preeclampsia with best performance in women with preterm preeclampsia (AUC = 0.889, 95% confidence interval (0.822-0.959) training; 0.883 (0.804-0.963) testing).

CONCLUSION

Together with maternal age and poverty status, mid-pregnancy immune and growth factors reliably identified most women who went on to have a PTB ± preeclampsia.

Racial and ethnic differences in preterm birth: A complex, multifactorial problem

Preterm birth remains the leading cause of morbidity and mortality among nonanomalous neonates, and is a major public health problem. Non-Hispanic black women have a 2-fold greater risk for preterm birth compared with non-Hispanic white race. The reasons for this disparity are poorly understood and cannot be explained solely by sociodemographic factors. Underlying factors including a complex interaction between maternal, paternal, and fetal genetics, epigenetics, the microbiome, and these sociodemographic risk factors likely underlies the differences between racial groups, but these relationships are currently poorly understood. This article reviews the epidemiology of disparities in preterm birth rates and adverse pregnancy outcomes and discuss possible explanations for the racial and ethnic differences, while examining potential solutions to this major public health problem.

Influence of vaginal lactoferrin administration on amniotic fluid cytokines and its role against inflammatory complications of pregnancy

Background

An altered amniotic cytokine profile has been reported in inflammatory pregnancy complications with a leading role for IL-6, a marker of the foetal systemic inflammatory response. Up to this date there is no exhaustive information neither on the foetal cytokine balance nor on the best method for its modulation. We aimed to evaluate the influence of vaginal lactoferrin administration on amniotic fluid concentration of 47 cytokines, chemokines and growth factors.

Methods

Sixty women undergoing genetic amniocentesis were enrolled in an open-label clinical trial. 300 mg of vaginal lactoferrin (Florence, Italy) were randomly administered to obtain 3 groups: A, 20 untreated patients; B and C (20 patients in each) respectively treated 4 and 12 h before amniocentesis. Cytokines, chemokines and growth factors concentrations were quantified by a magnetic bead Luminex multiplex immunoassays panel technology. Data analysis was performed with the software Stata (v. 13.1) and GraphPad Prism (v. 5). Group comparisons were performed using Kruskal–Wallis followed by Mann–Whitney U tests, with Bonferroni correction for multiple comparisons. A p < 0.05 was considered significant.

Results

Among the 47 tested mediators, 24 (51.06%) were influenced by lactoferrin. 11 (23.4%), showed a highly significant difference (p <0.001); among these IL-9, IL-15, IFN-γ, IP-10, TNF-α, IL-1α and MCP-3 underwent a down-regulation, while IL-17 and FGF-basic, G-CSF, GM-CSF an up-regulation. Difference between group C and both B and A was small for IL-15, IP-10, IL-1α, MCP-3, while it was negligible for IL-9, IFN-γ and TNF-α. IL-17 and the 3 growth factors were strongly enhanced in B and C groups. IL-17, FGF-basic and GM-CSF showed increasing concentrations in both B and C groups, while G-CSF resulted up-regulated only in group C. Significance was intermediate (p < 0.01) for the down regulated IL-2RA, IL-12p40 and IFNα2 (6.38%) while it was small for 10 mediators (21.27%) 7 of which (IL-2, IL-4, eotaxin, PDGF-BB, RANTES, IL-18 and MIF) down-regulated and 3 (MCP-1, IL-3, and SDF-1α) up-regulated.

Conclusion

Lactoferrin down-regulates 17 pro-inflammatory amniotic mediators while up-regulating 7 anti-inflammatory amniotic mediators, 5 of which definitively belonging to an anti-inflammatory profile. These findings open to clinical investigation on its use against inflammatory complications of pregnancy.

Early- or mid-trimester amniocentesis biomarkers for predicting preterm delivery: a meta-analysis

OBJECTIVE

To determine the value of early- or mid-trimester amniotic fluid levels of interleukin-6 (IL-6), matrix metalloproteinase-8 (MMP-8), and glucose for predicting preterm delivery.

METHODS

Randomized controlled trials and two-arm prospective, retrospective, cohorts, and case-controlled studies in which patients received early- or mid-trimester amniocentesis for karyotyping, and biomarker testing of the amniotic fluid was performed and delivery data were available were included in the analysis.

RESULTS

Outcome measures were the associations of amniotic fluid IL-6, MMP-8, and glucose levels with preterm delivery. Differences in means with 95% confidence intervals (CIs) were calculated. Of 288 articles identified, 14 were included in the meta-analysis with a total of 675 patients who had preterm birth and 2518 patients who had term births. The preterm-delivery group had significantly higher amniotic fluid IL-6 and MMP-8 levels, and a significantly lower glucose level than the term delivery group (IL-6: difference in means = 0.32, 95% CI: 0.22-0.43, p < 0.001; MMP-8: difference in means = 4.47, 95% CI: 0.83-8.11), p = 0.016; glucose: difference in means = -5.22, 95% CI: -8.19 to -2.26, p = 0.001) Conclusion: Early- or mid-trimester amniotic fluid IL-6, MMP-8, and glucose levels are useful for predicting the risk of preterm delivery. KEY MESSAGES Median amniotic fluid ferritin and IL-6 levels, and mean amniotic fluid ALP levels were higher in the preterm group. The preterm-delivery group had significantly higher amniotic fluid IL-6 and MMP-8 levels, and a significantly lower glucose level than the term-delivery group.

Biomarkers of spontaneous preterm birth: a systematic review of studies using multiplex analysis

OBJECTIVE

Despite decades of research on risk indicators of spontaneous preterm birth (PTB), reliable biomarkers are still not available to screen or diagnose high-risk pregnancies. Several biomarkers in maternal and fetal compartments have been mechanistically linked to PTB, but none of them are reliable predictors of pregnancy outcome. This systematic review was conducted to synthesize the knowledge on PTB biomarkers identified using multiplex analysis.

MATERIALS AND METHODS

Three electronic databases (PubMed, EMBASE and Web of Science) were searched for studies in any language reporting the use of multiplex assays for maternal biomarkers associated with PTB published from January 2005 to March 2014.

RESULTS

Retrieved citations (3631) were screened, and relevant studies (33) were selected for full-text reading. Ten studies were included in the review. Forty-two PTB-related proteins were reported, and RANTES and IL-10 (three studies) followed by MIP-1β, GM-CSF, Eotaxin, and TNF-RI (two studies) were reported more than once in maternal serum. However, results could not be combined due to heterogeneity in type of sample, study population, assay, and analysis methods.

CONCLUSION

By this systematic review, we conclude that multiplex assays are a potential technological advancement for identifying biomarkers of PTB, although no single or combination of biomarkers could be identified to predict PTB risk.

Epigenetic Biomarkers of Preterm Birth and Its Risk Factors

A biomarker is a biological measure predictive of a normal or pathogenic process or response. Biomarkers are often useful for making clinical decisions and determining treatment course. One area where such biomarkers would be particularly useful is in identifying women at risk for preterm delivery and related pregnancy complications. Neonates born preterm have significant morbidity and mortality, both in the perinatal period and throughout the life course, and identifying women at risk of delivering preterm may allow for targeted interventions to prevent or delay preterm birth (PTB). In addition to identifying those at increased risk for preterm birth, biomarkers may be able to distinguish neonates at particular risk for future complications due to modifiable environmental factors, such as maternal smoking or alcohol use during pregnancy. Currently, there are no such biomarkers available, though candidate gene and epigenome-wide association studies have identified DNA methylation differences associated with PTB, its risk factors and its long-term outcomes. Further biomarker development is crucial to reducing the health burden associated with adverse intrauterine conditions and preterm birth, and the results of recent DNA methylation studies may advance that goal.

Evidence of perturbations of the cytokine network in preterm labor

OBJECTIVE

Intraamniotic inflammation/infection is the only mechanism of disease with persuasive evidence of causality for spontaneous preterm labor/delivery. Previous studies about the behavior of cytokines in preterm labor have been largely based on the analysis of the behavior of each protein independently. Emerging evidence indicates that the study of biologic networks can provide insight into the pathobiology of disease and improve biomarker discovery. The goal of this study was to characterize the inflammatory-related protein network in the amniotic fluid of patients with preterm labor.

STUDY DESIGN

A retrospective cohort study was conducted that included women with singleton pregnancies who had spontaneous preterm labor and intact membranes (n = 135). These patients were classified according to the results of amniotic fluid culture, broad-range polymerase chain reaction coupled with electrospray ionization mass spectrometry, and amniotic fluid concentration of interleukin (IL)-6 into the following groups: (1) those without intraamniotic inflammation (n = 85), (2) those with microbial-associated intraamniotic inflammation (n = 15), and (3) those with intraamniotic inflammation without detectable bacteria (n = 35). Amniotic fluid concentrations of 33 inflammatory-related proteins were determined with the use of a multiplex bead array assay.

RESULTS

Patients with preterm labor and intact membranes who had microbial-associated intraamniotic inflammation had a higher amniotic fluid inflammatory-related protein concentration correlation than those without intraamniotic inflammation (113 perturbed correlations). IL-1β, IL-6, macrophage inflammatory protein (MIP)-1α, and IL-1α were the most connected nodes (highest degree) in this differential correlation network (degrees of 20, 16, 12, and 12, respectively). Patients with sterile intraamniotic inflammation had correlation patterns of inflammatory-related proteins, both increased and decreased, when compared to those without intraamniotic inflammation (50 perturbed correlations). IL-1α, MIP-1α, and IL-1β were the most connected nodes in this differential correlation network (degrees of 12, 10, and 7, respectively). There were more coordinated inflammatory-related protein concentrations in the amniotic fluid of women with microbial-associated intraamniotic inflammation than in those with sterile intraamniotic inflammation (60 perturbed correlations), with IL-4 and IL-33 having the largest number of perturbed correlations (degrees of 15 and 13, respectively).

CONCLUSIONS

We report for the first time an analysis of the inflammatory-related protein network in spontaneous preterm labor. Patients with preterm labor and microbial-associated intraamniotic inflammation had more coordinated amniotic fluid inflammatory-related proteins than either those with sterile intraamniotic inflammation or those without intraamniotic inflammation. The correlations were also stronger in patients with sterile intraamniotic inflammation than in those without intraamniotic inflammation. The findings herein could be of value in the development of biomarkers of preterm labor.

A proposed bio-panel to predict risk for spontaneous preterm birth among African American women

Preterm birth (PTB), or birth prior to 37 weeks gestation, impacts 11.5% of U.S. deliveries. PTB results in significant morbidity and mortality among affected children and imposes a large societal financial burden. Racial disparities in PTB are alarming. African American women are at more than 1.5 times the risk for PTB than white women. Unfortunately, the medical community's ability to predict who is at risk for PTB is extremely limited. History of a prior PTB remains the strongest predictor during a singleton gestation. Cervical length and fetal fibronectin measurement are helpful tools. However, usefulness is limited, particularly among the 95% of U.S. women currently pregnant and lacking a history of PTB. Therefore, preventive therapies do not reach a great number of women who may benefit from them. This manuscript, in response to the pressing need for predictors of PTB risk and elimination of racial disparities in PTB, presents a proposed bio-panel for use in predicting risk for spontaneous PTB among African American women. This bio-panel, measured each trimester, includes stimulated production of interleukin (IL)-1β, tumor necrosis factor (TNF)-α, IL-1 receptor antagonist (Ra), soluble(s) TNF receptor(R) 1, and sTNFR2, and cortisol responsiveness. We hypothesize that greater IL-1β and TNF-α production, decreased IL-1Ra, sTNFR1, and sTNFR2 production, and decreased cortisol responsiveness at each time point as well as a more expedient alignment with this unfavorable profile over time will be associated with PTB. The choice to focus on inflammatory parameters is supported by data highlighting a crucial role for inflammation in labor. Specific inflammatory mediators have been chosen due to their potential importance in preterm labor among African American women. The bio-panel also focuses on inflammatory regulation (i.e., cytokine production upon ex vivo stimulation), which is hypothesized to provide insight into potential in vivo leukocyte responses and potential for initiation of a preterm inflammatory cascade. Production of receptor antagonists is also considered, as pro-inflammatory mediator effects can be greatly influenced by their balance with respective antagonists. Finally, leukocyte responsiveness to cortisol is included as a measure of cortisol's ability to convey anti-inflammatory signals. The development of a bio-panel predictive of risk for spontaneous PTB among African American women would represent a significant advancement. Available preventive therapies, namely progesterone supplementation, could be delivered to women deemed at risk. Further, the identification of biological predictors of PTB may uncover novel targets for preventive therapies.

Predicting Preterm Labour: Current Status and Future Prospects

Preterm labour and birth are a major cause of perinatal morbidity and mortality. Despite modern advances in obstetric and neonatal management, the rate of preterm birth in the developed world is increasing. Yet even though numerous risk factors associated with preterm birth have been identified, the ability to accurately predict when labour will occur remains elusive, whether it is at a term or preterm gestation. In the latter case, this is likely due to the multifactorial aetiology of preterm labour wherein women may display different clinical presentations that lead to preterm birth. The discovery of novel biomarkers that could reliably identify women who will subsequently deliver preterm may allow for timely medical intervention and targeted therapeutic treatments aimed at improving maternal and fetal outcomes. Various body fluids including amniotic fluid, urine, saliva, blood (serum/plasma), and cervicovaginal fluid all provide a rich protein source of putative biochemical markers that may be causative or reflective of the various pathophysiological disorders of pregnancy, including preterm labour. This short review will highlight recent advances in the field of biomarker discovery and the utility of single and multiple biomarkers for the prediction of preterm birth in the absence of intra-amniotic infection.

Targeted proteomics for biomarker discovery and validation of hepatocellular carcinoma in hepatitis C infected patients

Hepatocellular carcinoma (HCC)-related mortality is high because early detection modalities are hampered by inaccuracy, expense and inherent procedural risks. Thus there is an urgent need for minimally invasive, highly specific and sensitive biomarkers that enable early disease detection when therapeutic intervention remains practical. Successful therapeutic intervention is predicated on the ability to detect the cancer early. Similar unmet medical needs abound in most fields of medicine and require novel methodological approaches. Proteomic profiling of body fluids presents a sensitive diagnostic tool for early cancer detection. Here we describe such a strategy of comparative proteomics to identify potential serum-based biomarkers to distinguish high-risk chronic hepatitis C virus infected patients from HCC patients. In order to compensate for the extraordinary dynamic range in serum proteins, enrichment methods that compress the dynamic range without surrendering proteome complexity can help minimize the problems associated with many depletion methods. The enriched serum can be resolved using 2D-difference in-gel electrophoresis and the spots showing statistically significant changes selected for identification by liquid chromatography-tandem mass spectrometry. Subsequent quantitative verification and validation of these candidate biomarkers represent an obligatory and rate-limiting process that is greatly enabled by selected reaction monitoring (SRM). SRM is a tandem mass spectrometry method suitable for identification and quantitation of target peptides within complex mixtures independent on peptide-specific antibodies. Ultimately, multiplexed SRM and dynamic multiple reaction monitoring can be utilized for the simultaneous analysis of a biomarker panel derived from support vector machine learning approaches, which allows monitoring a specific disease state such as early HCC. Overall, this approach yields high probability biomarkers for clinical validation in large patient cohorts and represents a strategy extensible to many diseases.

Quantitative structure-activity relationship study on BTK inhibitors by modified multivariate adaptive regression spline and CoMSIA methods

Bruton's tyrosine kinase (BTK) plays a crucial role in B-cell activation and development, and has emerged as a new molecular target for the treatment of autoimmune diseases and B-cell malignancies. In this study, two- and three-dimensional quantitative structure-activity relationship (2D and 3D-QSAR) analyses were performed on a series of pyridine and pyrimidine-based BTK inhibitors by means of genetic algorithm optimized multivariate adaptive regression spline (GA-MARS) and comparative molecular similarity index analysis (CoMSIA) methods. Here, we propose a modified MARS algorithm to develop 2D-QSAR models. The top ranked models showed satisfactory statistical results (2D-QSAR: Q(2) = 0.884, r(2) = 0.929, r(2)pred = 0.878; 3D-QSAR: q(2) = 0.616, r(2) = 0.987, r(2)pred = 0.905). Key descriptors selected by 2D-QSAR were in good agreement with the conclusions of 3D-QSAR, and the 3D-CoMSIA contour maps facilitated interpretation of the structure-activity relationship. A new molecular database was generated by molecular fragment replacement (MFR) and further evaluated with GA-MARS and CoMSIA prediction. Twenty-five pyridine and pyrimidine derivatives as novel potential BTK inhibitors were finally selected for further study. These results also demonstrated that our method can be a very efficient tool for the discovery of novel potent BTK inhibitors.