Data-driven insights towards risk assessment of postpartum depression. Valavani, E., Doudesis, D., Kourtesis, I., Chin, R., F., MacIntyre, D., J., Fletcher-Watson, S., Boardman, J., P., & Tsanas, A. In BIOSIGNALS 2020 - 13th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020, pages 382-389, 2020.
![Data-driven insights towards risk assessment of postpartum depression [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex
Paper doi abstract bibtex Postpartum depression is defined as depressive episodes that occur during pregnancy or within 12 months of parturition. The goal of this study is the exploration of the birth features and maternal traits which affect the risk of postpartum depression for mothers with preterm neonates. We analysed data from 144 women (63 mothers of term and 81 mothers of preterm infants) who completed the Edinburgh Postnatal Depression Scale (EPDS) in the postpartum period. We used three feature selection algorithms: ReliefF, Random Forests (RF) variable importance, and Boruta, in order to select the most predictive feature subsets, which were subsequently mapped onto the binarized EPDS total score (a threshold of 10 was used to binarize the EPDS total scores) using RF. We found that positive affectivity (rs=-0.467, p<0.001), and the Apgar score at 5 minutes (rs=-0.430, p<0.001) are the most statistically strongly associated features with the risk of postpartum depression. We used 10-fold cross-validation with 100 iterations and report out-of-sample balanced accuracy (median±IQR): 75.0±16.7, sensitivity: 66.7±16.7, specificity: 100±16.7, and F1 score: 0.8±0.2. Collectively, these findings highlight the potential of using a data-driven process to automate risk prediction using standard clinical characteristics and motivate the deployment of the developed tool using larger-scale datasets.
@inproceedings{
title = {Data-driven insights towards risk assessment of postpartum depression},
type = {inproceedings},
year = {2020},
keywords = {Feature Selection,Postpartum Depression,Random Forests},
pages = {382-389},
id = {52d35341-0ff8-3d10-8b52-afeadda9118e},
created = {2021-05-14T07:53:57.207Z},
file_attached = {true},
profile_id = {63c14ecf-8d9b-3014-983a-e77627cb99e3},
group_id = {6263fdf5-2843-3956-90fd-c0f66d8de277},
last_modified = {2021-05-14T07:54:03.472Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
private_publication = {false},
abstract = {Postpartum depression is defined as depressive episodes that occur during pregnancy or within 12 months of parturition. The goal of this study is the exploration of the birth features and maternal traits which affect the risk of postpartum depression for mothers with preterm neonates. We analysed data from 144 women (63 mothers of term and 81 mothers of preterm infants) who completed the Edinburgh Postnatal Depression Scale (EPDS) in the postpartum period. We used three feature selection algorithms: ReliefF, Random Forests (RF) variable importance, and Boruta, in order to select the most predictive feature subsets, which were subsequently mapped onto the binarized EPDS total score (a threshold of 10 was used to binarize the EPDS total scores) using RF. We found that positive affectivity (rs=-0.467, p<0.001), and the Apgar score at 5 minutes (rs=-0.430, p<0.001) are the most statistically strongly associated features with the risk of postpartum depression. We used 10-fold cross-validation with 100 iterations and report out-of-sample balanced accuracy (median±IQR): 75.0±16.7, sensitivity: 66.7±16.7, specificity: 100±16.7, and F1 score: 0.8±0.2. Collectively, these findings highlight the potential of using a data-driven process to automate risk prediction using standard clinical characteristics and motivate the deployment of the developed tool using larger-scale datasets.},
bibtype = {inproceedings},
author = {Valavani, Evdoxia and Doudesis, Dimitrios and Kourtesis, Ioannis and Chin, Richard F.M. and MacIntyre, Donald J. and Fletcher-Watson, Sue and Boardman, James P. and Tsanas, Athanasios},
doi = {10.5220/0009369303820389},
booktitle = {BIOSIGNALS 2020 - 13th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020}
}Downloads: 0
{"_id":"NaSLayrPGYvqk35X3","bibbaseid":"valavani-doudesis-kourtesis-chin-macintyre-fletcherwatson-boardman-tsanas-datadriveninsightstowardsriskassessmentofpostpartumdepression-2020","authorIDs":["5QZWBssgDGi584Z7c","5e4b151fc59ab1f30100000a","5e52e132a3b344de010000fe","5e596efb56d60ade01000189","5e5f73695766d9df01000090","5e608a4f1fc211de01000063","5e60d734839e59df01000015","5e60de5c839e59df01000069","5e60e86a839e59df010000f2","5e6b746ac024f9de01000107","7eXDwgP4Xr3S2tPx4","7v45sehfdNnKbNsNd","9Y4EEsoFDeXA5y9AT","Bfo68DN4MMYKFCJ5Z","F3Zzn7nfR3vkqup66","FjaboZvo764d7iJSe","GM3H3t7vSnnaQs7Fy","JKQyHYjzjyWBMdqDs","JxJtQhiZ2A5TyZGfw","KjuxZbcEAZ6pZ5fwW","LYPJAug66aqHMrTHK","NQemzTgSGLZNNCYAe","R9bx9dKg9MDSEgFzw","RgmQEkoEDHDN3Ldyx","SDtBagJY4bbwQb3Wm","WNQYd6gHhurxd4qKv","WdaBuApLheFTtLs3h","Y9H68NM7Afsi9mvne","YtRNnnvZ78tB6u7t6","YwSyjTF2FhKzvqNmh","dhKK6RKMzaPpnSAXJ","eq42u48snGhcXX6Hj","fSEqQkDggpwyHty9H","j32Yt4nwptQ7888KW","j7ht4beC5JYDfWZpu","jQiLtnHkg24nY8A5d","nj2GrMzkCjyqi2ZTe","pycY6z4hcyqpaxqqQ","sYf7528yAHsdZGr2a","uRTA9yYriKS5w27tg","yZiXJscmMWnXK9aJC"],"author_short":["Valavani, E.","Doudesis, D.","Kourtesis, I.","Chin, R., F.","MacIntyre, D., J.","Fletcher-Watson, S.","Boardman, J., P.","Tsanas, A."],"bibdata":{"title":"Data-driven insights towards risk assessment of postpartum depression","type":"inproceedings","year":"2020","keywords":"Feature Selection,Postpartum Depression,Random Forests","pages":"382-389","id":"52d35341-0ff8-3d10-8b52-afeadda9118e","created":"2021-05-14T07:53:57.207Z","file_attached":"true","profile_id":"63c14ecf-8d9b-3014-983a-e77627cb99e3","group_id":"6263fdf5-2843-3956-90fd-c0f66d8de277","last_modified":"2021-05-14T07:54:03.472Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"private_publication":false,"abstract":"Postpartum depression is defined as depressive episodes that occur during pregnancy or within 12 months of parturition. The goal of this study is the exploration of the birth features and maternal traits which affect the risk of postpartum depression for mothers with preterm neonates. We analysed data from 144 women (63 mothers of term and 81 mothers of preterm infants) who completed the Edinburgh Postnatal Depression Scale (EPDS) in the postpartum period. We used three feature selection algorithms: ReliefF, Random Forests (RF) variable importance, and Boruta, in order to select the most predictive feature subsets, which were subsequently mapped onto the binarized EPDS total score (a threshold of 10 was used to binarize the EPDS total scores) using RF. We found that positive affectivity (rs=-0.467, p<0.001), and the Apgar score at 5 minutes (rs=-0.430, p<0.001) are the most statistically strongly associated features with the risk of postpartum depression. We used 10-fold cross-validation with 100 iterations and report out-of-sample balanced accuracy (median±IQR): 75.0±16.7, sensitivity: 66.7±16.7, specificity: 100±16.7, and F1 score: 0.8±0.2. Collectively, these findings highlight the potential of using a data-driven process to automate risk prediction using standard clinical characteristics and motivate the deployment of the developed tool using larger-scale datasets.","bibtype":"inproceedings","author":"Valavani, Evdoxia and Doudesis, Dimitrios and Kourtesis, Ioannis and Chin, Richard F.M. and MacIntyre, Donald J. and Fletcher-Watson, Sue and Boardman, James P. and Tsanas, Athanasios","doi":"10.5220/0009369303820389","booktitle":"BIOSIGNALS 2020 - 13th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020","bibtex":"@inproceedings{\n title = {Data-driven insights towards risk assessment of postpartum depression},\n type = {inproceedings},\n year = {2020},\n keywords = {Feature Selection,Postpartum Depression,Random Forests},\n pages = {382-389},\n id = {52d35341-0ff8-3d10-8b52-afeadda9118e},\n created = {2021-05-14T07:53:57.207Z},\n file_attached = {true},\n profile_id = {63c14ecf-8d9b-3014-983a-e77627cb99e3},\n group_id = {6263fdf5-2843-3956-90fd-c0f66d8de277},\n last_modified = {2021-05-14T07:54:03.472Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n private_publication = {false},\n abstract = {Postpartum depression is defined as depressive episodes that occur during pregnancy or within 12 months of parturition. The goal of this study is the exploration of the birth features and maternal traits which affect the risk of postpartum depression for mothers with preterm neonates. We analysed data from 144 women (63 mothers of term and 81 mothers of preterm infants) who completed the Edinburgh Postnatal Depression Scale (EPDS) in the postpartum period. We used three feature selection algorithms: ReliefF, Random Forests (RF) variable importance, and Boruta, in order to select the most predictive feature subsets, which were subsequently mapped onto the binarized EPDS total score (a threshold of 10 was used to binarize the EPDS total scores) using RF. We found that positive affectivity (rs=-0.467, p<0.001), and the Apgar score at 5 minutes (rs=-0.430, p<0.001) are the most statistically strongly associated features with the risk of postpartum depression. We used 10-fold cross-validation with 100 iterations and report out-of-sample balanced accuracy (median±IQR): 75.0±16.7, sensitivity: 66.7±16.7, specificity: 100±16.7, and F1 score: 0.8±0.2. Collectively, these findings highlight the potential of using a data-driven process to automate risk prediction using standard clinical characteristics and motivate the deployment of the developed tool using larger-scale datasets.},\n bibtype = {inproceedings},\n author = {Valavani, Evdoxia and Doudesis, Dimitrios and Kourtesis, Ioannis and Chin, Richard F.M. and MacIntyre, Donald J. and Fletcher-Watson, Sue and Boardman, James P. and Tsanas, Athanasios},\n doi = {10.5220/0009369303820389},\n booktitle = {BIOSIGNALS 2020 - 13th International Conference on Bio-Inspired Systems and Signal Processing, Proceedings; Part of 13th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2020}\n}","author_short":["Valavani, E.","Doudesis, D.","Kourtesis, I.","Chin, R., F.","MacIntyre, D., J.","Fletcher-Watson, S.","Boardman, J., P.","Tsanas, A."],"urls":{"Paper":"https://bibbase.org/service/mendeley/63c14ecf-8d9b-3014-983a-e77627cb99e3/file/79495a10-a86d-f747-40a7-439095497405/93693.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/63c14ecf-8d9b-3014-983a-e77627cb99e3","bibbaseid":"valavani-doudesis-kourtesis-chin-macintyre-fletcherwatson-boardman-tsanas-datadriveninsightstowardsriskassessmentofpostpartumdepression-2020","role":"author","keyword":["Feature Selection","Postpartum Depression","Random Forests"],"metadata":{"authorlinks":{"tsanas, a":"https://www-darth-group-com.filesusr.com/html/bebb15_3ebaa10c912c1baa868d24d66a9fab67.html"}},"downloads":0},"bibtype":"inproceedings","creationDate":"2020-02-17T22:35:26.601Z","downloads":0,"keywords":["feature selection","postpartum depression","random forests"],"search_terms":["data","driven","insights","towards","risk","assessment","postpartum","depression","valavani","doudesis","kourtesis","chin","macintyre","fletcher-watson","boardman","tsanas"],"title":"Data-driven insights towards risk assessment of postpartum depression","year":2020,"biburl":"https://bibbase.org/service/mendeley/63c14ecf-8d9b-3014-983a-e77627cb99e3","dataSources":["BWwsvRmrYfLjX4QW2","ya2CyA73rpZseyrZ8"]}