Authors:
Evdoxia Valavani
1
;
Dimitrios Doudesis
2
;
1
;
Ioannis Kourtesis
3
;
Richard F. M. Chin
4
;
5
;
Donald J. MacIntyre
6
;
Sue Fletcher-Watson
7
;
James P. Boardman
8
;
9
and
Athanasios Tsanas
10
;
1
Affiliations:
1
Usher Institute, Medical School, University of Edinburgh, Teviot Place, Edinburgh EH8 9AG, U.K.
;
2
BHF Centre for Cardiovascular Sciences, University of Edinburgh, 47 Little France Crescent Edinburgh EH16 4TJ, U.K.
;
3
Psychiatric Hospital of Attica Dafni, Athinon Avenue, Athens 12462, Greece
;
4
Muir Maxwell Epilepsy Centre, Centre for Clinical Brain Sciences, The University of Edinburgh, 9 Sciennes Road, Edinburgh EH9 1LF, U.K.
;
5
Royal Hospital for Sick Children, 9 Sciennes Road, Edinburgh EH9 1LF, U.K.
;
6
Division of Psychiatry, Deanery of Clinical Sciences, Royal Edinburgh Hospital, University of Edinburgh, Morningside Park, Edinburgh EH10 5HF, U.K.
;
7
Salvesen Mindroom Research Centre, Kennedy Tower, Royal Edinburgh Hospital, University of Edinburgh, Morningside Park, Edinburgh EH10 5HF, U.K.
;
8
Centre for Clinical Brain Sciences, University of Edinburgh, Chancellor’s Building, 49 Little France Crescent, Edinburgh EH16 4SB, U.K.
;
9
MRC, Centre for Reproductive Health, University of Edinburgh, 47 Little France Crescent, Edinburgh EH16 4TJ, U.K.
;
10
Mathematical Institute, University of Oxford, Woodstock Road, Oxford OX2 6GG, U.K.
Keyword(s):
Postpartum Depression, Feature Selection, Random Forests.
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 cro
ss-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.
(More)