Predictive Algorithms for Early Postpartum Depression Detection: CatBoost vs. LightGBM DOI
Vinayak Gupta,

Shailja Tripathi,

Dhruv K. Singh

et al.

2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 4

Published: March 14, 2024

Postpartum depression (PPD) is a growing concern for mothers on global stage and usually linked to the varied emotional changes which happen woman postdelivery. This issue pressing one as such early detection acts essential bridge between growth development of mother-child bond while promoting nurturing environment. The paper makes use two classification algorithms namely, CatBoost LightGBM, dataset 1503 records, with primary aim list out various indicators contribute PPD. It has been seen that guilt, anger, sleep depravity irritability act prime this disease. While comparing outshines LightGBM owing its prowess in handling categorical data ordered boosting approaches. In all study outlines potential these predictive modelling well timely disease, establishing foundation better efforts mitigate manage

Language: Английский

Emotion regulation in bipolar disorder type-I: multivariate analysis of fMRI data DOI Creative Commons

Fumika Kondo,

Jocelyne C. Whitehead,

Fernando Corbalán

et al.

International Journal of Bipolar Disorders, Journal Year: 2023, Volume and Issue: 11(1)

Published: March 25, 2023

Bipolar disorder type-I (BD-I) patients are known to show emotion regulation abnormalities. In a previous fMRI study using an explicit paradigm, we compared responses from 19 BD-I and 17 matched healthy controls (HC). A standard general linear model-based univariate analysis revealed that BD showed increased activations in inferior frontal gyrus when instructed decrease their emotional response as elicited by neutral images. We implemented multivariate pattern recognition analyses on the same data examine if could classify conditions within-group well HC versus BD. reanalyzed approach, PRONTO software. The original experimental paradigm consisted of full 2 × factorial design, with valence (Negative/Neutral) instruction (Look/Decrease) within subject factors. models were able accurately different task analyzed separately (63.24%-75.00%, p = 0.001-0.012). addition, correctly significant accuracy where subjects downregulate felt (59.60%-60.84%, 0.014-0.018). results for classification demonstrated contributions salience network, several occipital regions, parietal lobes, other cortical achieve above-chance classifications. Our successfully reproduced some main obtained analysis, confirming these findings not dependent approach. particular, both types suggest there is difference neural patterns between each group. approach also reappraisal provide most informative activity differentiating BD, irrespective (negative or neutral). current illustrate importance investigating cognitive control propose set candidate regions further

Language: Английский

Citations

1

Optimal risk and diagnosis assessment strategies in perinatal depression: A machine learning approach from the life-ON study cohort DOI Creative Commons
Armando D’Agostino, Corrado Garbazza, Daniele Malpetti

et al.

Psychiatry Research, Journal Year: 2023, Volume and Issue: 332, P. 115687 - 115687

Published: Dec. 24, 2023

This study aimed to assess the concordance of various psychometric scales in detecting Perinatal Depression (PND) risk and diagnosis. A cohort 432 women was assessed at 10-15th 23-25th gestational weeks, 33-40 days 180-195 after delivery using Edinburgh Postnatal Scale (EPDS), Visual Analogue (VAS), Hamilton Rating (HDRS), Montgomery-Åsberg (MADRS), Mini International Neuropsychiatric Interview (MINI). Spearman's rank correlation coefficient used agreement across instruments, multivariable classification models were developed predict values a binary scale other scales. Moderate shown between EPDS VAS HDRS MADRS throughout perinatal period. However, decreased postpartum. well-performing model for estimation current depression (EPDS > 9) obtained with MADRS, less robust one major depressive episode (MDE) diagnosis (MINI) HDRS. When is not feasible, may be rapid comprehensive postpartum screening reliability. thorough structured interview or clinical examination remains necessary diagnose MDE.

Language: Английский

Citations

1

The Future of Prediction Modeling in Clinical Practice for Obstetrics and Gynecology DOI
Digna R. Velez Edwards, Todd L. Edwards

Obstetrics and Gynecology, Journal Year: 2024, Volume and Issue: 143(3), P. 355 - 357

Published: Feb. 15, 2024

Language: Английский

Citations

0

Machine learning approach for early prediction of postpartum depression DOI

S M Morris,

Dipika Rawat

Elsevier eBooks, Journal Year: 2024, Volume and Issue: unknown, P. 163 - 172

Published: Jan. 1, 2024

Language: Английский

Citations

0

Predictive Algorithms for Early Postpartum Depression Detection: CatBoost vs. LightGBM DOI
Vinayak Gupta,

Shailja Tripathi,

Dhruv K. Singh

et al.

2022 10th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions) (ICRITO), Journal Year: 2024, Volume and Issue: unknown, P. 1 - 4

Published: March 14, 2024

Postpartum depression (PPD) is a growing concern for mothers on global stage and usually linked to the varied emotional changes which happen woman postdelivery. This issue pressing one as such early detection acts essential bridge between growth development of mother-child bond while promoting nurturing environment. The paper makes use two classification algorithms namely, CatBoost LightGBM, dataset 1503 records, with primary aim list out various indicators contribute PPD. It has been seen that guilt, anger, sleep depravity irritability act prime this disease. While comparing outshines LightGBM owing its prowess in handling categorical data ordered boosting approaches. In all study outlines potential these predictive modelling well timely disease, establishing foundation better efforts mitigate manage

Language: Английский

Citations

0