Predicting women with depressive symptoms postpartum with machine learning methods.
Ontology highlight
ABSTRACT:
SUBMITTER: Andersson S
PROVIDER: S-EPMC8041863 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundMachine learning (ML) offers vigorous statistical and probabilistic techniques that can successfully predict certain clinical conditions using large volumes of data. A review of ML and big data research analytics in maternal depression is pertinent and timely, given the rapid technological developments in recent years.ObjectiveThis study aims to synthesize the literature on ML and big data analytics for maternal mental health, particularly the prediction of postpartum depression (PPD).MethodsWe used a scoping review methodology using the Arksey and O'Malley framework to rapidly map research activity in ML for predicting PPD. Two independent researchers searched PsycINFO, PubMed, IEEE Xplore, and the ACM Digital Library in September 2020 to identify relevant publications in the past 12 years. Data were extracted from the articles' ML model, data type, and study results.ResultsA total of 14 studies were identified. All studies reported the use of supervised learning techniques to predict PPD. Support vector machine and random forest were the most commonly used algorithms in addition to Naive Bayes, regression, artificial neural network, decision trees, and XGBoost (Extreme Gradient Boosting). There was considerable heterogeneity in the best-performing ML algorithm across the selected studies. The area under the receiver operating characteristic curve values reported for different algorithms were support vector machine (range 0.78-0.86), random forest method (0.88), XGBoost (0.80), and logistic regression (0.93).ConclusionsML algorithms can analyze larger data sets and perform more advanced computations, which can significantly improve the detection of PPD at an early stage. Further clinical research collaborations are required to fine-tune ML algorithms for prediction and treatment. ML might become part of evidence-based practice in addition to clinical knowledge and existing research evidence.
| S-EPMC8663566 | biostudies-literature
Project description:ObjectiveThere is a scarcity in tools to predict postpartum depression (PPD). We propose a machine learning framework for PPD risk prediction using data extracted from electronic health records (EHRs).MethodsTwo EHR datasets containing data on 15,197 women from 2015 to 2018 at a single site, and 53,972 women from 2004 to 2017 at multiple sites were used as development and validation sets, respectively, to construct the PPD risk prediction model. The primary outcome was a diagnosis of PPD within 1 year following childbirth. A framework of data extraction, processing, and machine learning was implemented to select a minimal list of features from the EHR datasets to ensure model performance and to enable future point-of-care risk prediction.ResultsThe best-performing model uses from clinical features related to mental health history, medical comorbidity, obstetric complications, medication prescription orders, and patient demographic characteristics. The model performances as measured by area under the receiver operating characteristic curve (AUC) are 0.937 (95% CI 0.912 - 0.962) and 0.886 (95% CI 0.879-0.893) in the development and validation datasets, respectively. The model performances were consistent when tested using data ending at multiple time periods during pregnancy and at childbirth.LimitationsThe prevalence of PPD in the study data represented a treatment prevalence and is likely lower than the illness prevalence.ConclusionsEHRs and machine learning offer the ability to identify women at risk for PPD early in their pregnancy. This may facilitate scalable and timely prevention and intervention, reducing negative outcomes and the associated burden.
| S-EPMC7738412 | biostudies-literature
Project description:To determine whether prenatal depressive symptoms are associated with postpartum sexual risk among young, urban women of color.Participants completed surveys during their second trimester of pregnancy and at 1 year postpartum. Depressive symptoms were measured using the Center for Epidemiologic Studies-Depression Scale, excluding somatic items because women were pregnant. Logistic and linear regression models adjusted for known predictors of sexual risk and baseline outcome variables were used to assess whether prenatal depressive symptoms make an independent contribution to sexual risk over time.Fourteen community health centers and hospitals in New York City.The participants included 757 predominantly black and Latina (91%, n = 692) pregnant teens and young women aged 14-21 years.The main outcome measures were number of sex partners, condom use, exposure to high-risk sex partners, diagnosis of a sexually transmitted disease, and repeat pregnancy.High levels of prenatal depressive symptoms were significantly associated with increased number of sex partners (? = 0.17; standard error, 0.08), decreased condom use (? = -7.16; standard error, 3.08), and greater likelihood of having had sex with a high-risk partner (odds ratio = 1.84; 95% confidence interval, 1.26-2.70), and repeat pregnancy (odds ratio = 1.72; 95% confidence interval, 1.09-2.72), among participants who were sexually active (all P < .05). Prenatal depressive symptoms were not associated with whether participants engaged in postpartum sexual activity or sexually transmitted disease incidence.Screening and treatment for depression should be available routinely to women at risk for antenatal depression.
| S-EPMC5536107 | biostudies-literature
Project description:ObjectivesTo test effects of a social media-based parenting program for mothers with postpartum depressive symptoms.MethodsWe conducted a randomized controlled trial from December 2019 to August 2021 of a parenting program using Facebook. Women with mild-to-moderate depressive symptoms (Edinburgh Postnatal Depression Scale [EPDS] 10-19) were randomized to the program, plus online depression treatment or depression treatment alone for 3 months. Women completed the EPDS monthly and the Parent-Child Early Relational Assessment, Parenting Stress Index-Short Form, and Parenting Sense of Competence pre- and postintervention. Differences among groups were assessed using intention-to-treat analysis.ResultsSeventy-five women enrolled and 66 (88%) completed the study. Participants were predominantly Black (69%), single (57%), with incomes <$55 000 (68%). The parenting group reported a more rapid decline in depressive symptoms than the comparison group (adjusted EPDS difference, -2.9; 95% confidence interval, -4.8 to -1.0 at 1 month). There were no significant group X time interactions for the Parent-Child Early Relational Assessment, Parenting Stress Index-Short Form, or Parenting Sense of Competence scores. Forty-one percent of women sought mental health treatment for worsening symptoms or suicidality. Women in the parenting group who exhibited greater engagement or reported mental health treatment had greater parenting responsiveness.ConclusionsA social media-based parenting program led to more rapid declines in depressive symptoms but no differences in responsive parenting, parenting stress, or parenting competence relative to a comparison group. Social media can provide parenting support for women with postpartum depressive symptoms, but greater attention to engagement and treatment access are needed to improve parenting outcomes.
| S-EPMC9979254 | biostudies-literature
Project description:Land development intensity is a comprehensive indicator to measure the degree of saving and intensive land construction and economic production activities. It is also the result of the joint action of natural, social, economic, and ecological elements in land development and utilization. Scientific prediction of land development intensity has particular reference significance for future regional development planning and the formulation of reasonable land use policies. Based on the inter-provincial land development intensity and its influencing factors in China, this study applied four algorithms, XGBoost, random forest model, support vector machine, and decision tree, to simulate and predict the land development intensity, and then compared the prediction accuracy of the four algorithms, and also carried out hyperparameter adjustment and prediction accuracy verification. The results show that the model with the best prediction performance among the four algorithms is XGBoost, and its R2 and MSE between predicted and valid values are 95.66% and 0.16, respectively, which are higher than the other three models. During the training process, the learning curve of the XGBoost model exhibited low fluctuation and fast fitting. Hyperparameter tuning is crucial to exploit the model's potential. The XGBoost model has the best prediction performance with the best hyperparameter combination of max_depth:19, learning_rate: 0.47, and n_estimatiors:84. This study provides some reference significance for the simulation of land development and utilization dynamics.
| S-EPMC10075418 | biostudies-literature
Project description:Background Depression is common in the human immunodeficiency virus (HIV)-hepatitis C virus (HCV) co-infected population. Demographic, behavioural, and clinical data collected in research settings may be of help in identifying those at risk for clinical depression. We aimed to predict the presence of depressive symptoms indicative of a risk of depression and identify important classification predictors using supervised machine learning. Methods We used data from the Canadian Co-infection Cohort, a multicentre prospective cohort, and its associated sub-study on Food Security (FS). The Center for Epidemiologic Studies Depression Scale-10 (CES-D-10) was administered in the FS sub-study; participants were classified as being at risk for clinical depression if scores ≥ 10. We developed two random forest algorithms using the training data (80%) and tenfold cross validation to predict the CES-D-10 classes—1. Full algorithm with all candidate predictors (137 predictors) and 2. Reduced algorithm using a subset of predictors based on expert opinion (46 predictors). We evaluated the algorithm performances in the testing data using area under the receiver operating characteristic curves (AUC) and generated predictor importance plots. Results We included 1,934 FS sub-study visits from 717 participants who were predominantly male (73%), white (76%), unemployed (73%), and high school educated (52%). At the first visit, median age was 49 years (IQR:43–54) and 53% reported presence of depressive symptoms with CES-D-10 scores ≥ 10. The full algorithm had an AUC of 0.82 (95% CI:0.78–0.86) and the reduced algorithm of 0.76 (95% CI:0.71–0.81). Employment, HIV clinical stage, revenue source, body mass index, and education were the five most important predictors. Conclusion We developed a prediction algorithm that could be instrumental in identifying individuals at risk for depression in the HIV-HCV co-infected population in research settings. Development of such machine learning algorithms using research data with rich predictor information can be useful for retrospective analyses of unanswered questions regarding impact of depressive symptoms on clinical and patient-centred outcomes among vulnerable populations. Supplementary Information The online version contains supplementary material available at 10.1186/s12874-022-01700-y.
| S-EPMC9375382 | biostudies-literature
Project description:BackgroundWhile the majority of research on postpartum depressive and anxious symptoms has focused on mothers, a growing body of research suggests a need to understand the role of the partner's health and relationship quality as predictors of postpartum maternal depression, while also better understanding correlates of partner or paternal depression in the postpartum period. The purpose of the current study is to evaluate mother and partner stress, anxiety, mood, infant care support, and relationship quality as predictors of perinatal depressive and anxious symptoms in first time mothers and partners during the postpartum hospital stay.MethodsFirst time parent couples (n = 116) completed a survey during the two-day postpartum stay in a Midwest hospital. Depressive (EPDS) and anxiety symptoms (DASS-21-Anxiety) were assessed in both mothers and partners. Hierarchical linear regression was used to evaluate relationship satisfaction, partner infant care support, stress, and co-parent mood as predictors of mood in mothers and partners separately.ResultsStress was a predictor of anxiety and depression symptoms in both mothers and partners. Additionally, co-parent anxiety significantly predicted anxiety in both mothers and partners. Maternal relationship satisfaction was a predictor of the partner's depressive symptoms, and maternal perceptions of partner infant support predicted maternal depressive symptoms.ConclusionsTogether, these results suggest that stress, relationship satisfaction, and co-parent mood are related to depressive and anxious symptoms in mothers and partner, underscoring the need to continue exploring mother and partner mental health in a dyadic framework.
| S-EPMC10041514 | biostudies-literature
Project description:During the COVID-19 pandemic, an increase in the incidence of psychiatric disorders in the general population and an increase in the severity of symptoms in psychiatric patients have been reported. Anxiety and depression symptoms are the most commonly observed during large-scale dramatic events such as pandemics and wars, especially when these implicate an extended lockdown. The early detection of higher risk clinical and non-clinical individuals would help prevent the new onset and/or deterioration of these symptoms. This in turn would lead to the implementation of public policies aimed at protecting vulnerable populations during these dramatic contingencies, therefore optimising the effectiveness of interventions and saving the resources of national healthcare systems. We used a supervised machine learning method to identify the predictors of the severity of psychiatric symptoms during the Italian lockdown due to the COVID-19 pandemic. Via a case study, we applied this methodology to a small sample of healthy individuals, obsessive-compulsive disorder patients, and adjustment disorder patients. Our preliminary results show that our models were able to predict depression, anxiety, and obsessive-compulsive symptoms during the lockdown with up to 92% accuracy based on demographic and clinical characteristics collected before the pandemic. The presented methodology may be used to predict the psychiatric prognosis of individuals under a large-scale lockdown and thus supporting the related clinical decisions.
| S-EPMC9025309 | biostudies-literature
Project description:BackgroundMajor depressive disorder (MDD) is a global health challenge that impacts the quality of patients' lives severely. The disorder can manifest in many forms with different combinations of symptoms, which makes its clinical diagnosis difficult. Robust biomarkers are greatly needed to improve diagnosis and to understand the etiology of the disease. The main purpose of this study was to create a predictive model for MDD diagnosis based on peripheral blood transcriptomes.Materials and methodsWe collected nine RNA expression datasets for MDD patients and healthy samples from the Gene Expression Omnibus database. After a series of quality control and heterogeneity tests, 302 samples from six studies were deemed suitable for the study. R package "MetaOmics" was applied for systematic meta-analysis of genome-wide expression data. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic effectiveness of individual genes. To obtain a better diagnostic model, we also adopted the support vector machine (SVM), random forest (RF), k-nearest neighbors (kNN), and naive Bayesian (NB) tools for modeling, with the RF method being used for feature selection.ResultsOur analysis revealed six differentially expressed genes (AKR1C3, ARG1, KLRB1, MAFG, TPST1, and WWC3) with a false discovery rate (FDR) < 0.05 between MDD patients and control subjects. We then evaluated the diagnostic ability of these genes individually. With single gene prediction, we achieved a corresponding area under the curve (AUC) value of 0.63 ± 0.04, 0.67 ± 0.07, 0.70 ± 0.11, 0.64 ± 0.08, 0.68 ± 0.07, and 0.62 ± 0.09, respectively, for these genes. Next, we constructed the classifiers of SVM, RF, kNN, and NB with an AUC of 0.84 ± 0.09, 0.81 ± 0.10, 0.73 ± 0.11, and 0.83 ± 0.09, respectively, in validation datasets, suggesting that the SVM classifier might be superior for constructing an MDD diagnostic model. The final SVM classifier including 70 feature genes was capable of distinguishing MDD samples from healthy controls and yielded an AUC of 0.78 in an independent dataset.ConclusionThis study provides new insights into potential biomarkers through meta-analysis of GEO data. Constructing different machine learning models based on these biomarkers could be a valuable approach for diagnosing MDD in clinical practice.
| S-EPMC8249859 | biostudies-literature
Project description:ObjectivePressure injuries are common and serious complications for hospitalized patients. The pressure injury rate is an important patient safety metric and an indicator of the quality of nursing care. Timely and accurate prediction of pressure injury risk can significantly facilitate early prevention and treatment and avoid adverse outcomes. While many pressure injury risk assessment tools exist, most were developed before there was access to large clinical datasets and advanced statistical methods, limiting their accuracy. In this paper, we describe the development of machine learning-based predictive models, using phenotypes derived from nurse-entered direct patient assessment data.MethodsWe utilized rich electronic health record data, including full assessment records entered by nurses, from 5 different hospitals affiliated with a large integrated healthcare organization to develop machine learning-based prediction models for pressure injury. Five-fold cross-validation was conducted to evaluate model performance.ResultsTwo pressure injury phenotypes were defined for model development: nonhospital acquired pressure injury (N = 4398) and hospital acquired pressure injury (N = 1767), representing 2 distinct clinical scenarios. A total of 28 clinical features were extracted and multiple machine learning predictive models were developed for both pressure injury phenotypes. The random forest model performed best and achieved an AUC of 0.92 and 0.94 in 2 test sets, respectively. The Glasgow coma scale, a nurse-entered level of consciousness measurement, was the most important feature for both groups.ConclusionsThis model accurately predicts pressure injury development and, if validated externally, may be helpful in widespread pressure injury prevention.
| S-EPMC7973453 | biostudies-literature