Unveiling the prevalence and risk factors of early stage postpartum depression: a hybrid deep learning approach

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(26), P. 68281 - 68315

Published: Jan. 25, 2024

Language: Английский

---

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

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 24, 2024

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

Language: Английский

---

A random forest algorithm-based prediction model for moderate to severe acute postoperative pain after orthopedic surgery under general anesthesia

BMC Anesthesiology, Journal Year: 2023, Volume and Issue: 23(1)

Published: Nov. 6, 2023

Postoperative pain is one of the most common complications after surgery. In order to detect early and intervene in time for moderate severe postoperative pain, it necessary identify risk factors construct clinical prediction models. This study aimed significant establish a better-performing model predict acute orthopedic surgery under general anesthesia.Patients who underwent anesthesia were divided into patients with group (group P) without N) based on VAS scores. The features selected by Lasso regression processed random forest multivariate logistic models outcomes. classification performance two was evaluated through testing set. area curves (AUC), accuracy classifiers, error rate both classifiers calculated, used anesthesia.A total 327 enrolled this (228 training set 99 set). incidence 41.3%. revealed 25.2% an AUC 0.810 31.3% 0.764 chosen predicting outcomes study. greatest second contribution immobilization duration surgery, respectively.The can be anesthesia, which potential application value.

Language: Английский

---

Consumer opinion on the use of machine learning in healthcare settings: A qualitative systematic review

Digital Health, Journal Year: 2025, Volume and Issue: 11

Published: Jan. 1, 2025

Introduction Given the increasing number of artificial intelligence and machine learning (AI/ML) tools in healthcare, we aimed to gain an understanding consumer perspectives on use AI/ML for healthcare diagnostics. Methods We conducted a qualitative systematic review, following established standardized methods, existing literature indexed databases up 4 April 2022: OVID MEDLINE, EMBASE, Scopus Web Science. Results Fourteen studies were identified as appropriate inclusion meta-synthesis review. Most ( n = 12) high-income countries, with data extracted from both mixed methods (42.9%) (57.1%) studies. The four overarching themes across included studies: (1) Trust, fear, uncertainty; (2) Data privacy ML governance; (3) Impact delivery access; (4) Consumers want be engaged. Conclusion current evidence demonstrates consumers’ understandings medical diagnosis are complex. express complex combination hesitancy support towards diagnosis. Importantly, their views influenced by perceived trustworthiness providers who these tools. recognize potential improve diagnostic accuracy, efficiency access, strong interest engaged development implementation process into routine healthcare.

Language: Английский

---

Development of an explainable machine learning model for predicting depression in adolescent girls with non-suicidal self-injury: A cross-sectional multicenter study

Journal of Affective Disorders, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

---

DMN network and neurocognitive changes associated with dissociative symptoms in major depressive disorder: a research protocol

Frontiers in Psychiatry, Journal Year: 2025, Volume and Issue: 16

Published: April 1, 2025

Depression is a heterogeneous disorder with diverse clinical presentations and etiological underpinnings, necessitating the identification of distinct subtypes to enhance targeted interventions. Dissociative symptoms, commonly observed in major depressive (MDD) linked early life trauma, may represent unique dimension associated specific neurocognitive deficits. Although emerging research has begun explore role dissociation depression, most studies have provided only descriptive analyses, leaving mechanistic interplay between these phenomena underexplored. The primary objective this study determine whether MDD patients prominent dissociative symptoms differ from those without such presentation, performance, markers functional connectivity. This investigation will be first integrate comprehensive evaluations, advanced testing, high-resolution brain imaging delineate contribution MDD. We recruit fifty participants for each three groups: (1) (2) (3) healthy controls. Diagnostic assessments performed using Structured Clinical Interview DSM-5 (SCID) alongside standardized scales depression severity, dissociation, childhood trauma. Neurocognitive performance evaluated through battery tests assessing memory, attention, executive function, processing speed. Structural magnetic resonance (MRI) conducted on 3 Tesla scanner, focusing connectivity Default Mode Network key regions as orbitofrontal cortex, insula, posterior cingulate cortex. Data analyses employ SPM-12 Matlab-based CONN PRONTO tools, multiclass Gaussian process classification applied differentiate groups based clinical, cognitive, data. results introduce novel perspective understanding connection dissociation. It could also aid pinpointing form stressors. Future research, aiming forecast response biological psychological interventions anticipates subtype provides insights.

Language: Английский

---

Machine learning approaches forpredicting postpartum depression risk leveraging XGBoost and CatBoost algorithms

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3279, P. 020089 - 020089

Published: Jan. 1, 2025

Language: Английский

---

Text-Based Depression Prediction on Social Media Using Machine Learning: Systematic Review and Meta-Analysis

Journal of Medical Internet Research, Journal Year: 2025, Volume and Issue: 27, P. e59002 - e59002

Published: April 11, 2025

Background Depression affects more than 350 million people globally. Traditional diagnostic methods have limitations. Analyzing textual data from social media provides new insights into predicting depression using machine learning. However, there is a lack of comprehensive reviews in this area, which necessitates further research. Objective This review aims to assess the effectiveness user-generated texts and evaluate influence demographic, language, activity, temporal features on through Methods We searched studies 11 databases (CINHAL [through EBSCOhost], PubMed, Scopus, Ovid MEDLINE, Embase, PubPsych, Cochrane Library, Web Science, ProQuest, IEEE Explore, ACM digital library) January 2008 August 2023. included that used texts, learning, reported area under curve, Pearson r, specificity sensitivity (or for their calculation) predict depression. Protocol papers not written English were excluded. extracted study characteristics, population outcome measures, prediction factors each study. A random effects model was extract effect sizes with 95% CIs. Study heterogeneity evaluated forest plots P values Cochran Q test. Moderator analysis performed identify sources heterogeneity. Results total 36 included. observed significant overall correlation between depression, large size (r=0.630, CI 0.565-0.686). noted same demographic (largest size; r=0.642, 0.489-0.757), activity (r=0.552, 0.418-0.663), language (r=0.545, 0.441-0.649), (r=0.531, 0.320-0.693). The platform type (public or private; P<.001), learning approach (shallow deep; P=.048), use measures (yes no; P<.001) moderators. Sensitivity revealed no change results, indicating result stability. Begg-Mazumdar rank (Kendall τb=0.22063; P=.058) Egger test (2-tailed t34=1.28696; P=.207) confirmed absence publication bias. Conclusions Social content can be useful tool Demographics, should considered maximize accuracy models. Additionally, type, approach, models need attention. challenging, findings may apply broader population. Nevertheless, our offer valuable future Trial Registration PROSPERO CRD42023427707; https://www.crd.york.ac.uk/PROSPERO/view/CRD42023427707

Language: Английский

---

Machine learning models to predict posttraumatic stress injuries in a sample of firefighters: A proof of concept

International Journal of Mental Health, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 21

Published: April 12, 2025

Language: Английский

---

Targeted Research and Treatment Implications in Women With Depression

FOCUS The Journal of Lifelong Learning in Psychiatry, Journal Year: 2025, Volume and Issue: 23(2), P. 141 - 155

Published: April 1, 2025

Women with a history of traumatic experience, particularly adversity encountered during childhood, have an increased risk developing depression. The authors review the biological mechanisms associating trauma depression, including role hypothalamic-pituitary-adrenal axis. Additionally, psychosocial and cultural considerations experience depression are discussed, current gaps in knowledge about mechanisms, factors, aspects relating to that remain be addressed described. also at for engaging suicidal behaviors, ideation attempts. Increased suicidality women has been observed various populations, among victims intimate partner violence, female veterans, refugees, individuals who identify as lesbian, gay, bisexual, transgender, queer or questioning, other. Although associations between well documented, limited research examined impact age reproductive stage, important area future research. A wide range biological, psychosocial, factors can increase across lifespan described, how they may included when completing clinical assessments is highlighted. Machine learning, its use outcome prediction stages toward individualized psychiatric services, introduced, directions reviewed.

Language: Английский

---