Development and validation of a machine learning algorithm for predicting the risk of postpartum depression among pregnant women.
Ontology highlight
ABSTRACT: Objective
There 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).Methods
Two 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.Results
The 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.Limitations
The prevalence of PPD in the study data represented a treatment prevalence and is likely lower than the illness prevalence.Conclusions
EHRs 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.
SUBMITTER: Zhang Y
PROVIDER: S-EPMC7738412 | 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:BACKGROUND:Risk-based breast cancer screening is a cost-effective intervention for controlling breast cancer in China, but the successful implementation of such intervention requires an accurate breast cancer prediction model for Chinese women. OBJECTIVE:This study aimed to evaluate and compare the performance of four machine learning algorithms on predicting breast cancer among Chinese women using 10 breast cancer risk factors. METHODS:A dataset consisting of 7127 breast cancer cases and 7127 matched healthy controls was used for model training and testing. We used repeated 5-fold cross-validation and calculated AUC, sensitivity, specificity, and accuracy as the measures of the model performance. RESULTS:The three novel machine-learning algorithms (XGBoost, Random Forest and Deep Neural Network) all achieved significantly higher area under the receiver operating characteristic curves (AUCs), sensitivity, and accuracy than logistic regression. Among the three novel machine learning algorithms, XGBoost (AUC 0.742) outperformed deep neural network (AUC 0.728) and random forest (AUC 0.728). Main residence, number of live births, menopause status, age, and age at first birth were considered as top-ranked variables in the three novel machine learning algorithms. CONCLUSIONS:The novel machine learning algorithms, especially XGBoost, can be used to develop breast cancer prediction models to help identify women at high risk for breast cancer in developing countries.
| S-EPMC7308891 | biostudies-literature
Project description:Postpartum depression (PPD) is a detrimental health condition that affects 12% of new mothers. Despite negative effects on mothers' and children's health, many women do not receive adequate care. Preventive interventions are cost-efficient among high-risk women, but our ability to identify these is poor. We leveraged the power of clinical, demographic, and psychometric data to assess if machine learning methods can make accurate predictions of postpartum depression. Data were obtained from a population-based prospective cohort study in Uppsala, Sweden, collected between 2009 and 2018 (BASIC study, n = 4313). Sub-analyses among women without previous depression were performed. The extremely randomized trees method provided robust performance with highest accuracy and well-balanced sensitivity and specificity (accuracy 73%, sensitivity 72%, specificity 75%, positive predictive value 33%, negative predictive value 94%, area under the curve 81%). Among women without earlier mental health issues, the accuracy was 64%. The variables setting women at most risk for PPD were depression and anxiety during pregnancy, as well as variables related to resilience and personality. Future clinical models that could be implemented directly after delivery might consider including these variables in order to identify women at high risk for postpartum depression to facilitate individualized follow-up and cost-effectiveness.
| S-EPMC8041863 | biostudies-literature
Project description:Postpartum depression is a serious health issue beyond the mental health problems that affect mothers after childbirth. There are no predictive tools available to screen postpartum depression that also allow early interventions. We aimed to develop predictive models for postpartum depression using machine learning (ML) approaches. We performed a retrospective cohort study using data from the Pregnancy Risk Assessment Monitoring System 2012-2013 with 28,755 records (3339 postpartum depression and 25,416 normal cases). The imbalance between the two groups was addressed by a balanced resampling using both random down-sampling and the synthetic minority over-sampling technique. Nine different ML algorithms, including random forest (RF), stochastic gradient boosting, support vector machines (SVM), recursive partitioning and regression trees, naïve Bayes, k-nearest neighbor (kNN), logistic regression, and neural network, were employed with 10-fold cross-validation to evaluate the models. The overall classification accuracies of the nine models ranged from 0.650 (kNN) to 0.791 (RF). The RF method achieved the highest area under the receiver-operating-characteristic curve (AUC) value of 0.884, followed by SVM, which achieved the second-best performance with an AUC value of 0.864. Predictive modeling developed using ML-approaches may thus be used as a prediction (screening) tool for postpartum depression in future studies.
| S-EPMC7564708 | biostudies-literature
Project description:BackgroundLinguistic accessibility has an important impact on the reception and utilization of translated health resources among multicultural and multilingual populations. Linguistic understandability of health translation has been understudied.ObjectiveOur study aimed to develop novel machine learning models for the study of the linguistic accessibility of health translations comparing Chinese translations of the World Health Organization health materials with original Chinese health resources developed by the Chinese health authorities.MethodsUsing natural language processing tools for the assessment of the readability of Chinese materials, we explored and compared the readability of Chinese health translations from the World Health Organization with original Chinese materials from the China Center for Disease Control and Prevention.ResultsA pairwise adjusted t test showed that the following 3 new machine learning models achieved statistically significant improvement over the baseline logistic regression in terms of area under the curve: C5.0 decision tree (95% CI -0.249 to -0.152; P<0.001), random forest (95% CI 0.139-0.239; P<0.001) and extreme gradient boosting tree (95% CI 0.099-0.193; P<0.001). There was, however, no significant difference between C5.0 decision tree and random forest (P=0.513). The extreme gradient boosting tree was the best model, achieving statistically significant improvement over the C5.0 model (P=0.003) and the random forest model (P=0.006) at an adjusted Bonferroni P value at 0.008.ConclusionsThe development of machine learning algorithms significantly improved the accuracy and reliability of current approaches to the evaluation of the linguistic accessibility of Chinese health information, especially Chinese health translations in relation to original health resources. Although the new algorithms developed were based on Chinese health resources, they can be adapted for other languages to advance current research in accessible health translation, communication, and promotion.
| S-EPMC8532010 | biostudies-literature
Project description:BackgroundFoodborne diseases, as a type of disease with a high global incidence, place a heavy burden on public health and social economy. Foodborne pathogens, as the main factor of foodborne diseases, play an important role in the treatment and prevention of foodborne diseases; however, foodborne diseases caused by different pathogens lack specificity in clinical features, and there is a low proportion of clinically actual pathogen detection in real life.ObjectiveWe aimed to analyze foodborne disease case data, select appropriate features based on analysis results, and use machine learning methods to classify foodborne disease pathogens to predict foodborne disease pathogens that have not been tested.MethodsWe extracted features such as space, time, and exposed food from foodborne disease case data and analyzed the relationship between these features and the foodborne disease pathogens using a variety of machine learning methods to classify foodborne disease pathogens. We compared the results of 4 models to obtain the pathogen prediction model with the highest accuracy.ResultsThe gradient boost decision tree model obtained the highest accuracy, with accuracy approaching 69% in identifying 4 pathogens including Salmonella, Norovirus, Escherichia coli, and Vibrio parahaemolyticus. By evaluating the importance of features such as time of illness, geographical longitude and latitude, and diarrhea frequency, we found that they play important roles in classifying the foodborne disease pathogens.ConclusionsData analysis can reflect the distribution of some features of foodborne diseases and the relationship among the features. The classification of pathogens based on the analysis results and machine learning methods can provide beneficial support for clinical auxiliary diagnosis and treatment of foodborne diseases.
| S-EPMC7872834 | biostudies-literature
Project description:Advances in neuroimaging, genomic, motion tracking, eye-tracking and many other technology-based data collection methods have led to a torrent of high dimensional datasets, which commonly have a small number of samples because of the intrinsic high cost of data collection involving human participants. High dimensional data with a small number of samples is of critical importance for identifying biomarkers and conducting feasibility and pilot work, however it can lead to biased machine learning (ML) performance estimates. Our review of studies which have applied ML to predict autistic from non-autistic individuals showed that small sample size is associated with higher reported classification accuracy. Thus, we have investigated whether this bias could be caused by the use of validation methods which do not sufficiently control overfitting. Our simulations show that K-fold Cross-Validation (CV) produces strongly biased performance estimates with small sample sizes, and the bias is still evident with sample size of 1000. Nested CV and train/test split approaches produce robust and unbiased performance estimates regardless of sample size. We also show that feature selection if performed on pooled training and testing data is contributing to bias considerably more than parameter tuning. In addition, the contribution to bias by data dimensionality, hyper-parameter space and number of CV folds was explored, and validation methods were compared with discriminable data. The results suggest how to design robust testing methodologies when working with small datasets and how to interpret the results of other studies based on what validation method was used.
| S-EPMC6837442 | biostudies-literature
Project description:Accurate stratification of sepsis can effectively guide the triage of patient care and shared decision making in the emergency department (ED). However, previous research on sepsis identification models focused mainly on ICU patients, and discrepancies in model performance between the development and external validation datasets are rarely evaluated. The aim of our study was to develop and externally validate a machine learning model to stratify sepsis patients in the ED. We retrospectively collected clinical data from two geographically separate institutes that provided a different level of care at different time periods. The Sepsis-3 criteria were used as the reference standard in both datasets for identifying true sepsis cases. An eXtreme Gradient Boosting (XGBoost) algorithm was developed to stratify sepsis patients and the performance of the model was compared with traditional clinical sepsis tools; quick Sequential Organ Failure Assessment (qSOFA) and Systemic Inflammatory Response Syndrome (SIRS). There were 8296 patients (1752 (21%) being septic) in the development and 1744 patients (506 (29%) being septic) in the external validation datasets. The mortality of septic patients in the development and validation datasets was 13.5% and 17%, respectively. In the internal validation, XGBoost achieved an area under the receiver operating characteristic curve (AUROC) of 0.86, exceeding SIRS (0.68) and qSOFA (0.56). The performance of XGBoost deteriorated in the external validation (the AUROC of XGBoost, SIRS and qSOFA was 0.75, 0.57 and 0.66, respectively). Heterogeneity in patient characteristics, such as sepsis prevalence, severity, age, comorbidity and infection focus, could reduce model performance. Our model showed good discriminative capabilities for the identification of sepsis patients and outperformed the existing sepsis identification tools. Implementation of the ML model in the ED can facilitate timely sepsis identification and treatment. However, dataset discrepancies should be carefully evaluated before implementing the ML approach in clinical practice. This finding reinforces the necessity for future studies to perform external validation to ensure the generalisability of any developed ML approaches.
| S-EPMC8623760 | biostudies-literature
Project description:BackgroundSeizures are the main cause of maternal death in women with epilepsy, but there are no tools for predicting seizures in pregnancy. We set out to develop and validate a prognostic model, using information collected during the antenatal booking visit, to predict seizure risk at any time in pregnancy and until 6 weeks postpartum in women with epilepsy on antiepileptic drugs.Methods and findingsWe used datasets of a prospective cohort study (EMPiRE) of 527 pregnant women with epilepsy on medication recruited from 50 hospitals in the UK (4 November 2011-17 August 2014). The model development cohort comprised 399 women whose antiepileptic drug doses were adjusted based on clinical features only; the validation cohort comprised 128 women whose drug dose adjustments were informed by serum drug levels. The outcome was epileptic (non-eclamptic) seizure captured using diary records. We fitted the model using LASSO (least absolute shrinkage and selection operator) regression, and reported the performance using C-statistic (scale 0-1, values > 0.5 show discrimination) and calibration slope (scale 0-1, values near 1 show accuracy) with 95% confidence intervals (CIs). We determined the net benefit (a weighted sum of true positive and false positive classifications) of using the model, with various probability thresholds, to aid clinicians in making individualised decisions regarding, for example, referral to tertiary care, frequency and intensity of monitoring, and changes in antiepileptic medication. Seizures occurred in 183 women (46%, 183/399) in the model development cohort and in 57 women (45%, 57/128) in the validation cohort. The model included age at first seizure, baseline seizure classification, history of mental health disorder or learning difficulty, occurrence of tonic-clonic and non-tonic-clonic seizures in the 3 months before pregnancy, previous admission to hospital for seizures during pregnancy, and baseline dose of lamotrigine and levetiracetam. The C-statistic was 0.79 (95% CI 0.75, 0.84). On external validation, the model showed good performance (C-statistic 0.76, 95% CI 0.66, 0.85; calibration slope 0.93, 95% CI 0.44, 1.41) but with imprecise estimates. The EMPiRE model showed the highest net proportional benefit for predicted probability thresholds between 12% and 99%. Limitations of this study include the varied gestational ages of women at recruitment, retrospective patient recall of seizure history, potential variations in seizure classification, the small number of events in the validation cohort, and the clinical utility restricted to decision-making thresholds above 12%. The model findings may not be generalisable to low- and middle-income countries, or when information on all predictors is not available.ConclusionsThe EMPiRE model showed good performance in predicting the risk of seizures in pregnant women with epilepsy who are prescribed antiepileptic drugs. Integration of the tool within the antenatal booking visit, deployed as a simple nomogram, can help to optimise care in women with epilepsy.
| S-EPMC6513048 | biostudies-literature
Project description:BackgroundObjective and early identification of hospitalized patients, and particularly those with novel coronavirus disease 2019 (COVID-19), who may require mechanical ventilation (MV) may aid in delivering timely treatment.Research questionCan a transparent deep learning (DL) model predict the need for MV in hospitalized patients and those with COVID-19 up to 24 h in advance?Study design and methodsWe trained and externally validated a transparent DL algorithm to predict the future need for MV in hospitalized patients, including those with COVID-19, using commonly available data in electronic health records. Additionally, commonly used clinical criteria (heart rate, oxygen saturation, respiratory rate, Fio2, and pH) were used to assess future need for MV. Performance of the algorithm was evaluated using the area under receiver operating characteristic curve (AUC), sensitivity, specificity, and positive predictive value.ResultsWe obtained data from more than 30,000 ICU patients (including more than 700 patients with COVID-19) from two academic medical centers. The performance of the model with a 24-h prediction horizon at the development and validation sites was comparable (AUC, 0.895 vs 0.882, respectively), providing significant improvement over traditional clinical criteria (P < .001). Prospective validation of the algorithm among patients with COVID-19 yielded AUCs in the range of 0.918 to 0.943.InterpretationA transparent deep learning algorithm improves on traditional clinical criteria to predict the need for MV in hospitalized patients, including in those with COVID-19. Such an algorithm may help clinicians to optimize timing of tracheal intubation, to allocate resources and staff better, and to improve patient care.
| S-EPMC8027289 | biostudies-literature