Data mining methods find demographic predictors of preterm birth

Recent Advances and Challenges in the Early Diagnosis and Treatment of Preterm Labor

Preterm birth (PTB) is the primary cause of neonatal mortality and long-term disabilities. The unknown mechanism behind PTB makes diagnosis difficult, yet early detection is necessary for controlling and averting related consequences. The primary focus of this work is to provide an overview of the known risk factors associated with preterm labor and the conventional and advanced procedures for early detection of PTB, including multi-omics and artificial intelligence/machine learning (AI/ML)- based approaches. It also discusses the principles of detecting various proteomic biomarkers based on lateral flow immunoassay and microfluidic chips, along with the commercially available point-of-care testing (POCT) devices and associated challenges. After briefing the therapeutic and preventive measures of PTB, this review summarizes with an outlook.

Machine Learning on Early Diagnosis of Depression

To review the recent progress of machine learning for the early diagnosis of depression (major depressive disorder). The source of data was 32 original studies in the Web of Science. The search terms were "depression" (title) and "random forest" (abstract). The eligibility criteria were the dependent variable of depression, the interventions of machine learning (the decision tree, the naïve Bayesian, the random forest, the support vector machine and/or the artificial neural network), the outcomes of accuracy and/or the area under the receiver operating characteristic curve (AUC) for the early diagnosis of depression, the publication year of 2000 or later, the publication language of English and the publication journal of SCIE/SSCI. Different machine learning methods would be appropriate for different types of data for the early diagnosis of depression, e.g., logistic regression, the random forest, the support vector machine and/or the artificial neural network in the case of numeric data, the random forest in the case of genomic data. Their performance measures reported varied within 60.1-100.0 for accuracy and 64.0-96.0 for the AUC. Machine learning provides an effective, non-invasive decision support system for early diagnosis of depression.

Identifying the Early Signs of Preterm Birth from U.S. Birth Records Using Machine Learning Techniques

Preterm birth (PTB) is the leading cause of infant mortality in the U.S. and globally. The goal of this study is to increase understanding of PTB risk factors that are present early in pregnancy by leveraging statistical and machine learning (ML) techniques on big data. The 2016 U.S. birth records were obtained and combined with two other area-level datasets, the Area Health Resources File and the County Health Ranking. Then, we applied logistic regression with elastic net regularization, random forest, and gradient boosting machines to study a cohort of 3.6 million singleton deliveries to identify generalizable PTB risk factors. The response variable is preterm birth, which includes spontaneous and indicated PTB, and we performed a binary classification. Our results show that the most important predictors of preterm birth are gestational and chronic hypertension, interval since last live birth, and history of a previous preterm birth, which explains 10.92, 5.98, and 5.63% of the predictive power, respectively. Parents' education is one of the influential variables in predicting PTB, explaining 7.89% of the predictive power. The relative importance of race declines when parents are more educated or have received adequate prenatal care. The gradient boosting machines outperformed with an AUC of 0.75 (sensitivity: 0.64, specificity: 0.73) for the validation dataset. In this study, we compare our results with seminal and most related studies to demonstrate the superiority of our results. The application of ML techniques improved the performance measures in the prediction of preterm birth. The results emphasize the importance of socioeconomic factors such as parental education as one of the most important indicators of preterm birth. More research is needed on these mechanisms through which socioeconomic factors affect biological responses.

PredictPTB: an interpretable preterm birth prediction model using attention-based recurrent neural networks

BACKGROUND

Early identification of pregnant women at risk for preterm birth (PTB), a major cause of infant mortality and morbidity, has a significant potential to improve prenatal care. However, we lack effective predictive models which can accurately forecast PTB and complement these predictions with appropriate interpretations for clinicians. In this work, we introduce a clinical prediction model (PredictPTB) which combines variables (medical codes) readily accessible through electronic health record (EHR) to accurately predict the risk of preterm birth at 1, 3, 6, and 9 months prior to delivery.

METHODS

The architecture of PredictPTB employs recurrent neural networks (RNNs) to model the longitudinal patient's EHR visits and exploits a single code-level attention mechanism to improve the predictive performance, while providing temporal code-level and visit-level explanations for the prediction results. We compare the performance of different combinations of prediction time-points, data modalities, and data windows. We also present a case-study of our model's interpretability illustrating how clinicians can gain some transparency into the predictions.

RESULTS

Leveraging a large cohort of 222,436 deliveries, comprising a total of 27,100 unique clinical concepts, our model was able to predict preterm birth with an ROC-AUC of 0.82, 0.79, 0.78, and PR-AUC of 0.40, 0.31, 0.24, at 1, 3, and 6 months prior to delivery, respectively. Results also confirm that observational data modalities (such as diagnoses) are more predictive for preterm birth than interventional data modalities (e.g., medications and procedures).

CONCLUSIONS

Our results demonstrate that PredictPTB can be utilized to achieve accurate and scalable predictions for preterm birth, complemented by explanations that directly highlight evidence in the patient's EHR timeline.

Artificial intelligence in obstetrics

This study reviews recent advances on the application of artificial intelligence for the early diagnosis of various maternal-fetal conditions such as preterm birth and abnormal fetal growth. It is found in this study that various machine learning methods have been successfully employed for different kinds of data capture with regard to early diagnosis of maternal-fetal conditions. With the more popular use of artificial intelligence, ethical issues should also be considered accordingly.

Clinical risk models for preterm birth less than 28 weeks and less than 32 weeks of gestation using a large retrospective cohort

OBJECTIVE

To develop risk prediction models for singleton preterm birth (PTB) < 28 weeks and <32 weeks.

METHODS

Using a retrospective cohort of 267,226 singleton births in Ontario hospitals, we included variables from the first and second trimester in multivariable logistic regression models to predict overall and spontaneous PTB < 28 weeks and <32 weeks.

RESULTS

During the first trimester, the area under the curve (AUC) for prediction of PTB < 28 weeks for nulliparous and multiparous women was 68.5% (95% CI: 63.5-73.6%) and 73.4% (68.6-78.2%), respectively, while for PTB < 32 weeks it was 68.9% (65.5-72.3%) and 75.5% (72.3-78.7%), respectively. AUCs for second-trimester models were 72.4% (95% CI: 69.7-75.1%) and 78.2% (95% CI: 75.8-80.5%), respectively, in nulliparous and multiparous women. Predicted probabilities were well-calibrated within a wide range around expected base prevalence for the study outcomes.

CONCLUSIONS

Our prediction models generated acceptable AUCs for PTB < 28 weeks and <32 weeks with good calibration during the first and second trimester.

Prediction of preterm birth in nulliparous women using logistic regression and machine learning

OBJECTIVE

To predict preterm birth in nulliparous women using logistic regression and machine learning.

DESIGN

Population-based retrospective cohort.

PARTICIPANTS

Nulliparous women (N = 112,963) with a singleton gestation who gave birth between 20-42 weeks gestation in Ontario hospitals from April 1, 2012 to March 31, 2014.

METHODS

We used data during the first and second trimesters to build logistic regression and machine learning models in a "training" sample to predict overall and spontaneous preterm birth. We assessed model performance using various measures of accuracy including sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (AUC) in an independent "validation" sample.

RESULTS

During the first trimester, logistic regression identified 13 variables associated with preterm birth, of which the strongest predictors were diabetes (Type I: adjusted odds ratio (AOR): 4.21; 95% confidence interval (CI): 3.23-5.42; Type II: AOR: 2.68; 95% CI: 2.05-3.46) and abnormal pregnancy-associated plasma protein A concentration (AOR: 2.04; 95% CI: 1.80-2.30). During the first trimester, the maximum AUC was 60% (95% CI: 58-62%) with artificial neural networks in the validation sample. During the second trimester, 17 variables were significantly associated with preterm birth, among which complications during pregnancy had the highest AOR (13.03; 95% CI: 12.21-13.90). During the second trimester, the AUC increased to 65% (95% CI: 63-66%) with artificial neural networks in the validation sample. Including complications during the pregnancy yielded an AUC of 80% (95% CI: 79-81%) with artificial neural networks. All models yielded 94-97% negative predictive values for spontaneous PTB during the first and second trimesters.

CONCLUSION

Although artificial neural networks provided slightly higher AUC than logistic regression, prediction of preterm birth in the first trimester remained elusive. However, including data from the second trimester improved prediction to a moderate level by both logistic regression and machine learning approaches.

A Machine Learning-Based Prediction Model for Preterm Birth in Rural India

Preterm birth (PTB) in a pregnant woman is the most serious issue in the field of Gynaecology and Obstetrics, especially in rural India. In recent years, various clinical prediction models for PTB have been developed to improve the accuracy of learning models. However, to the best of the authors' knowledge, most of them suffer from selecting the most accurate features from the medical dataset in linear time. The present paper attempts to design a machine learning model named as risk prediction conceptual model (RPCM) for the prediction of PTB. In this paper, a feature selection approach is proposed based on the notion of entropy. The novel approach is used to find the best maternal features (responsible for PTB) from the obstetrical dataset and aims to predict the classifier's accuracy at the highest level. The paper first deals with the review of PTB cases (which is neglected in many developing countries including India). Next, we collect obstetrical data from the Community Health Centre of rural areas (Kamdara, Jharkhand). The suggested approach is then applied on collected data to identify the excellent maternal features (text-based symptoms) present in pregnant women in order to classify all birth cases into term birth and PTB. The machine learning part of the model is implemented using three different classifiers, namely, decision tree (DT), logistic regression (LR), and support vector machine (SVM) for PTB prediction. The performance of the classifiers is measured in terms of accuracy, specificity, and sensitivity. Finally, the SVM classifier generates an accuracy of 90.9%, which is higher than other learning classifiers used in this study.

Risk assessment of preterm birth through identification and stratification of pregnancies using a real-time scoring algorithm

Introduction:

Preterm birth poses a significant challenge. This study evaluated a real-time scoring algorithm to identify and stratify pregnancies to indicate preterm birth.

Methods:

All claims data of pregnant women were reviewed between 1 January 2014 and 31 October 2018 in Kentucky.

Results:

A total of 29,166 unique women who were matched to a live newborn were documented, with the pregnancy identified during the first trimester in 54.1% of women. Negative predictive values, sensitivity, and positive likelihood ratios increased from the first to third trimesters as pregnant women who were matched to a live newborn had more visits with their physicians. The area under the receiving-operating characteristics curve on test data classifying preterm birth was 0.59 for pregnancies identified during the first trimester, 0.62 for pregnancies identified in the second trimester, and 0.73 for pregnancies identified in the third trimester.

Conclusions:

This study presents a real-time scoring algorithm of indicating preterm birth in the first trimester of gestation which permits stratification of pregnancies to provide more efficient early care management.

Application of Artificial Intelligence in Early Diagnosis of Spontaneous Preterm Labor and Birth

This study reviews the current status and future prospective of knowledge on the use of artificial intelligence for the prediction of spontaneous preterm labor and birth (“preterm birth” hereafter). The summary of review suggests that different machine learning approaches would be optimal for different types of data regarding the prediction of preterm birth: the artificial neural network, logistic regression and/or the random forest for numeric data; the support vector machine for electrohysterogram data; the recurrent neural network for text data; and the convolutional neural network for image data. The ranges of performance measures were 0.79–0.94 for accuracy, 0.22–0.97 for sensitivity, 0.86–1.00 for specificity, and 0.54–0.83 for the area under the receiver operating characteristic curve. The following maternal variables were reported to be major determinants of preterm birth: delivery and pregestational body mass index, age, parity, predelivery systolic and diastolic blood pressure, twins, below high school graduation, infant sex, prior preterm birth, progesterone medication history, upper gastrointestinal tract symptom, gastroesophageal reflux disease, Helicobacter pylori, urban region, calcium channel blocker medication history, gestational diabetes mellitus, prior cone biopsy, cervical length, myomas and adenomyosis, insurance, marriage, religion, systemic lupus erythematosus, hydroxychloroquine sulfate, and increased cerebrospinal fluid and reduced cortical folding due to impaired brain growth.

Determinants of Spontaneous Preterm Labor and Birth Including Gastroesophageal Reflux Disease and Periodontitis

BACKGROUND

Periodontitis is reported to be associated with preterm birth (spontaneous preterm labor and birth). Gastroesophageal reflux disease (GERD) is common during pregnancy and is expected to be related to periodontitis. However, little research has been done on the association among preterm birth, GERD and periodontitis. This study uses popular machine learning methods for analyzing preterm birth, GERD and periodontitis.

METHODS

Data came from Anam Hospital in Seoul, Korea, with 731 obstetric patients during January 5, 1995 - August 28, 2018. Six machine learning methods were applied and compared for the prediction of preterm birth. Variable importance, the effect of a variable on model performance, was used for identifying major determinants of preterm birth.

RESULTS

In terms of accuracy, the random forest (0.8681) was similar with logistic regression (0.8736). Based on variable importance from the random forest, major determinants of preterm birth are delivery and pregestational body mass indexes (BMI) (0.1426 and 0.1215), age (0.1211), parity (0.0868), predelivery systolic and diastolic blood pressure (0.0809 and 0.0763), twin (0.0476), education (0.0332) as well as infant sex (0.0331), prior preterm birth (0.0290), progesterone medication history (0.0279), upper gastrointestinal tract symptom (0.0274), GERD (0.0242), Helicobacter pylori (0.0151), region (0.0139), calcium-channel-blocker medication history (0.0135) and gestational diabetes mellitus (0.0130). Periodontitis ranked 22nd (0.0084).

CONCLUSION

GERD is more important than periodontitis for predicting and preventing preterm birth. For preventing preterm birth, preventive measures for hypertension, GERD and diabetes mellitus would be needed alongside the promotion of effective BMI management and appropriate progesterone and calcium-channel-blocker medications.

Prediction of Delayed Neurodevelopment in Infants Using Brainstem Auditory Evoked Potentials and the Bayley II Scales

Background: Brainstem auditory evoked potentials (BAEP) provide an objective analysis of central nervous system function and development in infants. This study proposed to examine the relationship between infant BAEP values at age 6 months, and their neurodevelopment at age 2 years assessed by the mental development indices (MDI), a form of Bayley Scales of Infant Development. We hypothesized that in infants with BAEP values outside normal range, there may be neurodevelopmental delays, as shown by their MDI scores. Methods: An exploratory investigation was conducted using preterm (28-36 weeks gestation; 95 cases) and term infants (≥37 weeks gestation; 100 cases) who were born with specific perinatal conditions. BAEP values were recorded in these infants from 1 to 8 months of age, and compared with MDI scores in these infants at age 2 years. A multivariate linear regressions model was performed to test the associations between all variables and MDI scores. Stratified linear regression was used to test the interactions between gestational age and BAEP values with MDI scores. Significance was determined at a p < 0.05. Results: We found that BAEP values were inversely associated with MDI scores in premature infants (β = -1.89; 95% confidence interval = -3.42 to -0.36), and that the effect of gestational age and BAEP values on the MDI scores is decreased by 1.89 points due to the interaction between these two variables. In premature babies, the lower the BAEP value below the mean, the greater the decrease in MDI score at age 2 years. Asphyxia and lower socioeconomic status in the family were also covariates associated with lower MDI scores at age 2 years. Conclusion: The data provided evidence that BAEP values outside the normal range in premature infants at age 6 months may predict developmental delays in cognitive and motor skills, as shown by MDI scores. We propose that BAEP assessment may be utilized as a potential indicator for neurodevelopment, and suggest that early intellectual and public health interventions should be encouraged to enrich neurodevelopment in premature babies with BAEP values outside the normal range.

Deep learning predicts extreme preterm birth from electronic health records

OBJECTIVE

Models for predicting preterm birth generally have focused on very preterm (28-32 weeks) and moderate to late preterm (32-37 weeks) settings. However, extreme preterm birth (EPB), before the 28th week of gestational age, accounts for the majority of newborn deaths. We investigated the extent to which deep learning models that consider temporal relations documented in electronic health records (EHRs) can predict EPB.

STUDY DESIGN

EHR data were subject to word embedding and a temporal deep learning model, in the form of recurrent neural networks (RNNs) to predict EPB. Due to the low prevalence of EPB, the models were trained on datasets where controls were undersampled to balance the case-control ratio. We then applied an ensemble approach to group the trained models to predict EPB in an evaluation setting with a nature EPB ratio. We evaluated the RNN ensemble models with 10 years of EHR data from 25,689 deliveries at Vanderbilt University Medical Center. We compared their performance with traditional machine learning models (logistical regression, support vector machine, gradient boosting) trained on the datasets with balanced and natural EPB ratio. Risk factors associated with EPB were identified using an adjusted odds ratio.

RESULTS

The RNN ensemble models trained on artificially balanced data achieved a higher AUC (0.827 vs. 0.744) and sensitivity (0.965 vs. 0.682) than those RNN models trained on the datasets with naturally imbalanced EPB ratio. In addition, the AUC (0.827) and sensitivity (0.965) of the RNN ensemble models were better than the AUC (0.777) and sensitivity (0.819) of the best baseline models trained on balanced data. Also, risk factors, including twin pregnancy, short cervical length, hypertensive disorder, systemic lupus erythematosus, and hydroxychloroquine sulfate, were found to be associated with EPB at a significant level.

CONCLUSION

Temporal deep learning can predict EPB up to 8 weeks earlier than its occurrence. Accurate prediction of EPB may allow healthcare organizations to allocate resources effectively and ensure patients receive appropriate care.

Artificial Neural Network Analysis of Spontaneous Preterm Labor and Birth and Its Major Determinants

BACKGROUND

Little research based on the artificial neural network (ANN) is done on preterm birth (spontaneous preterm labor and birth) and its major determinants. This study uses an ANN for analyzing preterm birth and its major determinants.

METHODS

Data came from Anam Hospital in Seoul, Korea, with 596 obstetric patients during March 27, 2014 - August 21, 2018. Six machine learning methods were applied and compared for the prediction of preterm birth. Variable importance, the effect of a variable on model performance, was used for identifying major determinants of preterm birth. Analysis was done in December, 2018.

RESULTS

The accuracy of the ANN (0.9115) was similar with those of logistic regression and the random forest (0.9180 and 0.8918, respectively). Based on variable importance from the ANN, major determinants of preterm birth are body mass index (0.0164), hypertension (0.0131) and diabetes mellitus (0.0099) as well as prior cone biopsy (0.0099), prior placenta previa (0.0099), parity (0.0033), cervical length (0.0001), age (0.0001), prior preterm birth (0.0001) and myomas & adenomyosis (0.0001).

CONCLUSION

For preventing preterm birth, preventive measures for hypertension and diabetes mellitus are required alongside the promotion of cervical-length screening with different guidelines across the scope/type of prior conization.

A data-driven and practice-based approach to identify risk factors associated with hospital-acquired falls: Applying manual and semi- and fully-automated methods

BACKGROUND AND PURPOSE

Electronic health record (EHR) data provides opportunities for new approaches to identify risk factors associated with iatrogenic conditions, such as hospital-acquired falls. There is a critical need to validate and translate prediction models that support fall prevention clinical decision-making in hospitals. The purpose of this study was to explore a combined data-driven and practice-based approach to identify risk factors associated with falls.

PROCEDURES

We conducted an observational case-control study of EHR data from January 1, 2013 to October 31, 2013 from 14 medical-surgical units of a tertiary referral teaching hospital. Patients aged 21 or older admitted to medical surgical units were included in the study. Manual and semi- and fully-automated methods were used to identify fall risk factors across four prediction models. Sensitivity, specificity, and the Area under the Receiver Operating Characteristic (AUROC) curve were calculated for all models using 10-fold cross validation.

FINDINGS

We confirmed the significance of a set of valid fall risk factors (i.e., age, gender, fall risk assessment, history of falling, mental status, mobility, and confusion) and identified set of new risk factors (i.e., # of fall risk increasing drugs, hemoglobin level, physical therapy initiation, Charlson Comorbity Index, nurse skill mix, and registered nurse staffing ratio) based on the most precise prediction approach, namely stepwise regression.

CONCLUSIONS

The use of semi- and fully-automated approaches with expert clinical knowledge over expert or data-driven only approaches can significantly improve identifying patient, clinical, and organizational risk factors of iatrogenic conditions, including hospital-acquired falls.

Maternal Race/Ethnicity and Predictors of Pregnancy and Infant Outcomes

Objective. To examine predictors of pregnancy and infant outcomes, including maternal race/ethnicity. Design. Prospective and observational follow-up of high-risk pregnancies and births. Participants. Three hundred fifty-four mothers and their preterm and/or high-risk live-born neonates were closely followed in three tertiary care centers from the prenatal to postnatal periods for potential high-risk and/or preterm births that required neonatal resuscitations. Major Outcome Measures. Pregnancy complications, birth complications, and infant outcomes were examined in conjunction with maternal factors, including preexisting health problems, health behaviors (smoking, alcohol consumption, prenatal visits), and the birth setting (tertiary care centers or community hospitals). Results. About 22% of these infants were transferred into the tertiary care centers from the community hospitals right after birth; the rest were born in the centers. According to regression analyses, predictors of the birth setting were race (White vs. non-White), maternal health behaviors, pregnancy complications, fetal distress, and the presence of congenital defects for infants (p < .001). Predictors for fetal distress included race (Whites) and pregnancy-induced hypertension (p < .003). Predictors for lower birth weight included race (non-Whites), maternal cigarette smoking, pregnancy complications, fetal distress, and congenital defects (p < .001). Infant mortality rate was 3.9% for these high-risk infants, with the highest rate in infants born to Black mothers (8%). Conclusions. There are obvious health disparities among White and non-White women experiencing high-risk pregnancies and births. Future studies are needed to develop interventions targeted to different racial/ethnic groups during pregnancy to reduce preterm and high-risk births.

Prognostic models in obstetrics: available, but far from applicable

Health care provision is increasingly focused on the prediction of patients' individual risk for developing a particular health outcome in planning further tests and treatments. There has been a steady increase in the development and publication of prognostic models for various maternal and fetal outcomes in obstetrics. We undertook a systematic review to give an overview of the current status of available prognostic models in obstetrics in the context of their potential advantages and the process of developing and validating models. Important aspects to consider when assessing a prognostic model are discussed and recommendations on how to proceed on this within the obstetric domain are given. We searched MEDLINE (up to July 2012) for articles developing prognostic models in obstetrics. We identified 177 papers that reported the development of 263 prognostic models for 40 different outcomes. The most frequently predicted outcomes were preeclampsia (n = 69), preterm delivery (n = 63), mode of delivery (n = 22), gestational hypertension (n = 11), and small-for-gestational-age infants (n = 10). The performance of newer models was generally not better than that of older models predicting the same outcome. The most important measures of predictive accuracy (ie, a model's discrimination and calibration) were often (82.9%, 218/263) not both assessed. Very few developed models were validated in data other than the development data (8.7%, 23/263). Only two-thirds of the papers (62.4%, 164/263) presented the model such that validation in other populations was possible, and the clinical applicability was discussed in only 11.0% (29/263). The impact of developed models on clinical practice was unknown. We identified a large number of prognostic models in obstetrics, but there is relatively little evidence about their performance, impact, and usefulness in clinical practice so that at this point, clinical implementation cannot be recommended. New efforts should be directed toward evaluating the performance and impact of the existing models.

Implications for Nursing Research and Generation of Evidence

A sound informatics infrastructure is essential to optimise the application of evidence in nursing practice. A comprehensive review of the infrastructure and associated research methods is supported by an extensive resource of references to point the interested reader to further resources for more in depth study. Information and communication technology (ICT) has been recognized as a fundamental component of applying evidence to practice for several decades. Although the role of ICT in generating knowledge from practice was formally identified as a nursing informatics research priority in the early 1990s (NINR Priority Expert Panel on Nursing Informatics, 1993), it has received heightened interest recently. In this chapter, the authors summarize some important trends in research that motivate increased attention to practice-based generation of evidence. These include an increased emphasis on interdisciplinary, translational, and comparative effectiveness research; novel research designs; frameworks and models that inform generation of evidence from practice; and creation of data sets that include not only variables related to biological and genetic measures, but also social and behavioral variables. The chapter also includes an overview of the ICT infrastructure and informatics processes required to facilitate generation of evidence from practice and across research studies: (1) information structures (e.g., re-usable concept representations, tailored templates for data acquisition), (2) processes (e.g., data mining algorithms, natural language processing), and (3) technologies (e.g., data repositories, visualization tools that optimize cognitive support). In addition, the authors identify key knowledge gaps related to informatics support for nursing research and generation of evidence from practice.

Interrelationship of cytokines, hypothalamic-pituitary-adrenal axis hormones, and psychosocial variables in the prediction of preterm birth

BACKGROUND/AIMS

To examine the relationship of biological mediators (cytokines, stress hormones), psychosocial, obstetric history, and demographic factors in the early prediction of preterm birth (PTB) using a comprehensive logistic regression model incorporating diverse risk factors.

METHODS

In this prospective case-control study, maternal serum biomarkers were quantified at 9-23 weeks' gestation in 60 women delivering at <37 weeks compared to 123 women delivering at term. Biomarker data were combined with maternal sociodemographic factors and stress data into regression models encompassing 22 preterm risk factors and 1st-order interactions.

RESULTS

Among individual biomarkers, we found that macrophage migration inhibitory factor (MIF), interleukin-10, C-reactive protein (CRP), and tumor necrosis factor-alpha were statistically significant predictors of PTB at all cutoff levels tested (75th, 85th, and 90th percentiles). We fit multifactor models for PTB prediction at each biomarker cutoff. Our best models revealed that MIF, CRP, risk-taking behavior, and low educational attainment were consistent predictors of PTB at all biomarker cutoffs. The 75th percentile cutoff yielded the best predicting model with an area under the ROC curve of 0.808 (95% CI 0.743-0.874).

CONCLUSION

Our comprehensive models highlight the prominence of behavioral risk factors for PTB and point to MIF as a possible psychobiological mediator.

Early prediction of preterm birth for singleton, twin, and triplet pregnancies

OBJECTIVES

To create prediction models of early preterm birth for singletons, twin, and triplet pregnancies.

STUDY DESIGN

We used a historical cohort study with the 1996 birth registration data for singletons and the 1995-1997 linked birth/infant death dataset for multiple births of the United States. Preterm birth was defined as gestational age <32 completed weeks. Eligible study subjects were randomly allocated to two groups: one group (80% subjects) for the creation of the prediction models, and the other group (20% subjects) for the validation of the established prediction models. Multivariate logistic regressions were used to establish the prediction models. We further assessed the sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of the established prediction models with different cut-off values in the validation group.

RESULTS

The sensitivity, specificity, PPV, and NPV of the established model were 24.58, 93.54, 5.91, and 98.69%, respectively for singletons, 64.66, 57.04, 16.29, and 92.59%, respectively for twins, and 63.57, 53.58, 42.96, and 72.78%, respectively for triplets.

CONCLUSION

The prediction models of early preterm birth for singleton, twin, and triplet pregnancies created by this study could be useful for obstetricians to identify women being at high risk of preterm birth at early gestation.

Maternal vaccination and preterm birth: using data mining as a screening tool

OBJECTIVE

The main purpose of this study was to identify possible associations between medicines used in pregnancy and preterm deliveries using data mining as a screening tool.

SETTINGS

Prospective cohort study.

METHODS

We used data mining to identify possible correlates between preterm delivery and medicines used by 92,235 pregnant Danish women who took part in the Danish National Birth Cohort (DNBC). We then evaluated the association between one of the identified exposures (vaccination) and the risk for preterm birth by using logistic regression. The women were classified into groups according to their exposure to vaccination. The regression analyses were adjusted for the following covariates: parity, infant's gender, maternal Body-Mass Index (BMI), age, smoking, drinking, job, number of inhabitants in the place of residence, infections, diabetes, high blood pressure and preeclampsia.

MAIN OUTCOME MEASURE

Preterm birth, a delivery occurring before the 259th day of gestation (i.e., less than 37 full weeks).

RESULTS

Data mining had indicated that maternal vaccination (among other factors) might be related to preterm birth. The following regression analysis showed that, the women who reported being vaccinated shortly before or during gestation had a slightly higher risk of giving preterm birth (O.R. = 1.14; 95% CI 1.04-1.25) as compared to the non-vaccinated group.

CONCLUSION

Whether the association between maternal vaccination and the risk for preterm birth found here is causal or not deserves further studies. Data mining, especially with additional refinements, may be a valuable and very efficient tool to screen large databases for relevant information which can be used in clinical and public health research.

Classification of smoking cessation status with a backpropagation neural network

This study examined the ability of a backpropagation neural network (BPNN) classifier to distinguish between current and former smokers in the 2000 National Health Interview Survey (NHIS) sample adult file. The BPNN classifier performance exceeded that of random chance, with asymmetric 95% confidence intervals for A(z) (area under receiver operating characteristic curve)=(0.7532, 0.7790). Separation of current and former smokers was imperfect, as illustrated by the receiver operating characteristic (ROC) curve. Additionally, performance did not exceed that of a comparison classifier created using logistic regression. Attribute subset selection identified three novel attributes related to smoking cessation status. This study establishes the ability of backpropagation neural networks to classify a complex health behavior, smoking cessation. It also illustrates the hypothesis-generating capacity of data mining methods when applied to large population-based health survey data. Ultimately, BPNN classifiers of smoking cessation status may be useful in decision support systems for smoking cessation interventions.

Nursing and the informatics revolution

The Institute of Medicine's quality initiatives have collectively emphasized the importance of information technology to the transformation of health care. Not coincidentally, federal initiatives in 2004 have signaled the start of "the decade of health information technology." Building on those reports, this article describes the informatics revolution in process, and nursing's readiness to move in that direction. The promise of informatics in reshaping practice is sketched out in terms of seven aims for improvement, followed by a listing of some of the issues that must be addressed for nursing to realize those possibilities. In similar fashion, changes in academia are discussed both in terms of the promise of informatics applications and the barriers to achieving that preferred future. The article ends with some policy recommendations and reflections on opportunities at hand, particularly the growing emphasis on patient self-management support.

Data mining issues and opportunities for building nursing knowledge

Health care information systems tend to capture data for nursing tasks, and have little basis in nursing knowledge. Opportunity lies in an important issue where the knowledge used by expert nurses (nursing knowledge workers) in caring for patients is undervalued in the health care system. The complexity of nursing's knowledge base remains poorly articulated and inadequately represented in contemporary information systems. There is opportunity for data mining methods to assist with discovering important linkages between clinical data, nursing interventions, and patient outcomes. Following a brief overview of relevant data mining techniques, a preterm risk prediction case study illustrates the opportunities and describes typical data mining issues in the nontrivial task of building knowledge. Building knowledge in nursing, using data mining or any other method, will make progress only if important data that capture expert nurses' contributions are available in clinical information systems configurations.

Have studies of urinary tract infection and preterm delivery used the most appropriate methods?

Published investigations of the association between urinary tract infection (UTI) and preterm delivery used logistic regression or chi-squared tests. Because both exposure and outcome are time dependent, these methods were not optimal and did not account for person-time under observation, potentially an important feature given the variability of women's entry to prenatal care as well as of gestational lengths. Previous researchers probably classified as exposed some women whose UTI occurred after their pregnancies exceeded 37 weeks. We applied the previous analytical methods to 1990-93 births from two Durham, NC, USA, hospitals (n = 4053) and demonstrate survival methods as an alternative. Two logistic regression models were fitted with differing exposure definitions: model 1 in which exposed = UTI diagnosed after 20 weeks' gestation; and model 2 in which exposed = UTI diagnosed between 20 weeks' and 37 weeks' gestation. Model 3 used proportional hazards regression with person-time after 20 weeks and before UTI diagnosis as unexposed, and person-time after diagnosis as exposed. Models were fit with and without five time-constant potential confounders. Model 1 yielded an adjusted odds ratio (OR) of 0.8 [95% confidence interval (CI) 0.5, 1.2], and model 2, which did not include UTI diagnoses after 37 weeks, an adjusted OR of 0.9 [95% CI 0.6, 1.4]. The Cox model hazard ratio (HR) for preterm delivery was 1.1 (adjusted) [95% CI 0.7, 1.7]. As these results indicated some bias, but not remarkable differences, we conducted a sensitivity analysis using 100 samples of 80% of the original data set, with replacement to determine how large the differences might be in other, similar data sets. The Cox method consistently produced higher effect estimates than either logistic model. The two samples with the greatest differences between the Cox and logistic model estimates yielded an OR of 1.47 [95% CI 0.95, 2.29] for model 1 vs. HR of 2.06 [95% CI 1.39, 3.06] for model 3, and an OR of 1.41 [95% CI 0.88, 2.25] for model 2 vs. HR of 1.79 [95% CI 1.17, 2.71] for model 3 respectively. Previous published results on UTI and preterm delivery require cautious interpretation. Data on UTI timing should be gathered to allow appropriate analyses; survival methods account for person-time under observation and ensure that studied exposures precede effects.