An optimization for postpartum depression risk assessment and preventive intervention strategy based machine learning approaches

Líu, Hao; Dai, Anran; Zhou, Zhou; Xu, Xia; Gao, Kai; Li, Qiuwen; Xu, Shouyu; Feng, Yunfei; Chen, Chen; Ge, Chun; Lu, Yuanjun; Zou, Jianjun; Wang, Saiying

doi:10.1016/j.jad.2023.02.028

Cited by 6 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This section evaluates the performance of OPOMLP in comparison to other existing models, namely MLP [16], XRT [25], DT [27], LR [29] and XGB [30].…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Postpartum Depression with Aid of Social Media Texts Using Optimized Machine Learning Model

2024

IJIES

View full text Add to dashboard Cite

Post-Partum Depression (PPD) is a significant medical condition that occurs in some women after childbirth as a consequence of physiological behavioral and mental alterations. The complicated symptoms of this condition make it difficult to diagnose and differentiate from other conditions. Timely detection and diagnosis of PPD are crucial for controlling morality rates and ensuring effective treatment. Various Machine Learning (ML) models was developed to predict PPD based on the patients demographic status, mental health history and vital signs. But, additional psychological attributes are needed for predicting mental status and identifying individuals with PPD risk. Also, costeffective and innovative methods are needed to identify individuals with PPD and detect potential development tendencies. Hence, in this paper, Osprey Parameter Optimized MLP (OPOMLP) is developed to address the above issues for efficient PPD. Initially, the Application Programming Interface (API) function of online social network like Twitter (tweets) and Instagram (comments) are used to collect the data posted by health care professionals. Then, Natural Language Processing (NLP) is utilized to pre-process the collected data \and extract relevant text of Twitter users to estimate PPD phases. The additional psychological attributes like mental health and behavioural changes attributes of women are extracted using Linguistic Inquiry Word Count (LIWC) and Latent Semantic Analysis (LSA) methods. Next, MLP network is trained using the extracted attributes along with the attributes of demographic status, mental health history and vital signs. Since, the parameters of MLP were not optimized properly which leads to computational complexities in the PPD prediction. So, the weights initialization and the hyper-parameters of MLP is optimized simultaneously by using an Osprey Optimization Algorithm (OOA). OOA is a metaheuristic optimization algorithm derived from osprey bird hunting behavior which aims to find the global optimum solutions and reduces the complex optimization issues. The relationship between hyperparameters and classification performance will identify an optimal hyperparameter space regions for optimal classification with less computational time and resources. Finally, the OPOMLP is employed for the final prediction of PPD. The test outcomes reveal that the OPOMLP model achieves an accuracy of 96.12% on the collected dataset compared to the classical PPD detection models.

show abstract

“…This section evaluates the performance of OPOMLP in comparison to other existing models, namely MLP [16], XRT [25], DT [27], LR [29] and XGB [30].…”

Section: Resultsmentioning

confidence: 99%

“…An optimization ML model was developed [30] for assessing PPD risk and implementing preventive interventions. It collected and pre-processed EHR data from caesarean delivery patients, used SHAP for data interpretation, developed Propensity Score Matching for PPD incidence comparison and employed XGB for early intervention.…”

Section: Literature Surveymentioning

confidence: 99%

Predicting Postpartum Depression with Aid of Social Media Texts Using Optimized Machine Learning Model

2024

IJIES

View full text Add to dashboard Cite

show abstract

“…We sought to establish the most effective predictive model by systematically comparing results obtained from various machine learning (ML) techniques and logistic regression (LR). While previous research in the domain of predicting parental mental health outcomes has delved into the application of ML models (8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18)(19), the specific context of parental depression in the NICU remains underexplored, with only logistic regression studies to date (20). In the absence of conclusive evidence supporting ML's superiority in predicting parental depression within the NICU, our study fills a critical gap by offering a rigorous comparison between ML techniques and logistic regression.…”

Section: Discussionmentioning

confidence: 99%

“…Having a predictive model to identify parents at risk of developing postpartum depression can assist in prioritizing those in need of screening. Prior research has focused on training machine learning (ML) models to predict postpartum depression (8)(9)(10)(11)(12)(13)(14)(15)(16)(17)(18)(19). A review of these studies revealed several significant predictors, including age, education, marital status, income, ethnicity, lifetime depression, depression during pregnancy, anxiety, smoking, mode of delivery, gestational age, APGAR score (appearance, pulse, grimace, activity, and respiration), BMI (body mass index), and history of antidepressant use (10).…”

Section: Introductionmentioning

confidence: 99%

Comparative analysis of machine learning versus traditional method for early detection of parental depression symptoms in the NICU

Sadjadpour,

Hosseinichimeh,

Abedi

et al. 2024

Front. Public Health

View full text Add to dashboard Cite

IntroductionNeonatal intensive care unit (NICU) admission is a stressful experience for parents. NICU parents are twice at risk of depression symptoms compared to the general birthing population. Parental mental health problems have harmful long-term effects on both parents and infants. Timely screening and treatment can reduce these negative consequences.ObjectiveOur objective is to compare the performance of the traditional logistic regression with other machine learning (ML) models in identifying parents who are more likely to have depression symptoms to prioritize screening of at-risk parents. We used data obtained from parents of infants discharged from the NICU at Children’s National Hospital (n = 300) from 2016 to 2017. This dataset includes a comprehensive list of demographic characteristics, depression and stress symptoms, social support, and parent/infant factors.Study designOur study design optimized eight ML algorithms – Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, XGBoost, Naïve Bayes, K-Nearest Neighbor, and Artificial Neural Network – to identify the main risk factors associated with parental depression. We compared models based on the area under the receiver operating characteristic curve (AUC), positive predicted value (PPV), sensitivity, and F-score.ResultsThe results showed that all eight models achieved an AUC above 0.8, suggesting that the logistic regression-based model’s performance is comparable to other common ML models.ConclusionLogistic regression is effective in identifying parents at risk of depression for targeted screening with a performance comparable to common ML-based models.

show abstract

“…The escalating prevalence of depression has prompted numerous proposed solutions; however, these interventions have not yet demonstrated a high level of accuracy, resulting in significant losses. Certain researchers utilize data from social media sites, the accuracy of which may vary 22 .…”

Section: Literature Reviewmentioning

confidence: 99%

Prevalence and risk factors analysis of postpartum depression at early stage using hybrid deep learning model

Lilhore,

Dalal,

Varshney

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Postpartum Depression Disorder (PPDD) is a prevalent mental health condition and results in severe depression and suicide attempts in the social community. Prompt actions are crucial in tackling PPDD, which requires a quick recognition and accurate analysis of the probability factors associated with this condition. This concern requires attention. The primary aim of our research is to investigate the feasibility of anticipating an individual's mental state by categorizing individuals with depression from those without depression using a dataset consisting of text along with audio recordings from patients diagnosed with PPDD. This research proposes a hybrid PPDD framework that combines Improved Bi-directional Long Short-Term Memory (IBi-LSTM) with Transfer Learning (TL) based on two Convolutional Neural Network (CNN) architectures, respectively CNN-text and CNN audio. In the proposed model, the CNN section efficiently utilizes TL to obtain crucial knowledge from text and audio characteristics, whereas the improved Bi-LSTM module combines written material and sound data to obtain intricate chronological interpersonal relationships. The proposed model incorporates an attention technique to augment the effectiveness of the Bi-LSTM scheme. An experimental analysis is conducted on the PPDD online textual and speech audio dataset collected from UCI. It includes textual features such as age, women's health tracks, medical histories, demographic information, daily life metrics, psychological evaluations, and ‘speech records’ of PPDD patients. Data pre-processing is applied to maintain the data integrity and achieve reliable model performance. The proposed model demonstrates a great performance in better precision, recall, accuracy, and F1-score over existing deep learning models, including VGG-16, Base-CNN, and CNN-LSTM. These metrics indicate the model's ability to differentiate among women at risk of PPDD vs. non-PPDD. In addition, the feature importance analysis demonstrates that specific risk factors substantially impact the prediction of PPDD. The findings of this research establish a basis for improved precision and promptness in assessing the risk of PPDD, which may ultimately result in earlier implementation of interventions and the establishment of support networks for women who are susceptible to PPDD.

show abstract

An optimization for postpartum depression risk assessment and preventive intervention strategy based machine learning approaches

Cited by 6 publications

References 47 publications

Predicting Postpartum Depression with Aid of Social Media Texts Using Optimized Machine Learning Model

Predicting Postpartum Depression with Aid of Social Media Texts Using Optimized Machine Learning Model

Comparative analysis of machine learning versus traditional method for early detection of parental depression symptoms in the NICU

Prevalence and risk factors analysis of postpartum depression at early stage using hybrid deep learning model

Contact Info

Product

Resources

About