Development of model for identifying homologous recombination deficiency (HRD) status of ovarian cancer with deep learning on whole slide images

Zhang, Ke; Qiu, Youhui; Feng, Songwei; Yin, Han; Liu, Qi; Zhu, Yuxin; Cui, Haoyu; Wei, Xiaoying; Wang, Guoqing; Wang, Xiangxue; Shen, Yang

doi:10.1186/s12967-025-06234-7

Table 3 The performance of the 12 combination of feature selection and classifier schemes for discriminating subtypes from ovarian cancer in training groups

From: Development of model for identifying homologous recombination deficiency (HRD) status of ovarian cancer with deep learning on whole slide images

Database	Classifier	Feature selection	AUC	Precision	Recall	F1-score
ND1	LR	LASSO	0.654 ± 0.141	0.575 ± 0.082	0.584 ± 0.160	0.559 ± 0.037
		RF	0.745 ± 0.053	0.704 ± 0.078	0.739 ± 0.049	0.718 ± 0.050
		mRMR	0.705 ± 0.087	0.715 ± 0.159	0.657 ± 0.230	0.646 ± 0.100
	RF	LASSO	0.680 ± 0.109	0.635 ± 0.097	0.577 ± 0.105	0.589 ± 0.028
		RF	*0.817 ± 0.052*	*0.751 ± 0.117*	*0.736 ± 0.070*	*0.734 ± 0.050*
		mRMR	0.661 ± 0.132	0.675 ± 0.224	0.637 ± 0.145	0.620 ± 0.118
	SVM	LASSO	0.601 ± 0.075	0.580 ± 0.103	0.531 ± 0.182	0.533 ± 0.084
		RF	0.807 ± 0.080	0.745 ± 0.150	0.741 ± 0.124	0.739 ± 0.126
		mRMR	0.642 ± 0.071	0.673 ± 0.198	0.671 ± 0.123	0.639 ± 0.066
	KNN	LASSO	0.656 ± 0.049	0.765 ± 0.134	0.456 ± 0.063	0.562 ± 0.062
		RF	0.674 ± 0.082	0.673 ± 0.127	0.679 ± 0.097	0.670 ± 0.094
		mRMR	0.574 ± 0.123	0.545 ± 0.187	0.452 ± 0.197	0.446 ± 0.158
ND2	LR	LASSO	0.608 ± 0.056	0.592 ± 0.185	0.549 ± 0.194	0.533 ± 0.167
		RF	0.752 ± 0.106	0.708 ± 0.169	0.706 ± 0.095	0.689 ± 0.061
		mRMR	0.645 ± 0.157	0.577 ± 0.195	0.601 ± 0.099	0.583 ± 0.141
	RF	LASSO	0.672 ± 0.124	0.602 ± 0.221	0.552 ± 0.111	0.558 ± 0.166
		RF	*0.815 ± 0.043*	*0.814 ± 0.167*	*0.736 ± 0.026*	*0.763 ± 0.069*
		mRMR	0.526 ± 0.076	0.516 ± 0.129	0.675 ± 0.042	0.577 ± 0.090
	SVM	LASSO	0.658 ± 0.113	0.685 ± 0.242	0.644 ± 0.127	0.649 ± 0.177
		RF	0.802 ± 0.037	0.693 ± 0.102	0.683 ± 0.126	0.675 ± 0.082
		mRMR	0.639 ± 0.121	0.626 ± 0.161	0.704 ± 0.162	0.639 ± 0.090
	KNN	LASSO	0.563 ± 0.109	0.573 ± 0.191	0.512 ± 0.119	0.521 ± 0.147
		RF	0.745 ± 0.087	0.736 ± 0.155	0.628 ± 0.184	0.656 ± 0.124
		mRMR	0.597 ± 0.075	0.621 ± 0.162	0.560 ± 0.067	0.571 ± 0.073
ND3	LR	LASSO	0.690 ± 0.131	0.683 ± 0.207	0.724 ± 0.095	0.693 ± 0.142
		RF	0.813 ± 0.118	0.756 ± 0.163	0.718 ± 0.155	0.715 ± 0.087
		mRMR	0.715 ± 0.056	0.683 ± 0.149	0.675 ± 0.101	0.662 ± 0.057
	RF	LASSO	0.608 ± 0.075	0.607 ± 0.135	0.688 ± 0.129	0.622 ± 0.086
		RF	*0.838 ± 0.051*	*0.780 ± 0.160*	*0.764 ± 0.065*	*0.757 ± 0.066*
		mRMR	0.611 ± 0.094	0.595 ± 0.158	0.596 ± 0.087	0.573 ± 0.092
	SVM	LASSO	0.569 ± 0.110	0.592 ± 0.141	0.576 ± 0.164	0.570 ± 0.140
		RF	0.782 ± 0.080	0.698 ± 0.148	0.724 ± 0.146	0.702 ± 0.127
		mRMR	0.672 ± 0.129	0.685 ± 0.176	0.578 ± 0.161	0.606 ± 0.140
	KNN	LASSO	0.533 ± 0.076	0.588 ± 0.169	0.428 ± 0.094	0.466 ± 0.057
		RF	0.763 ± 0.068	0.751 ± 0.168	0.676 ± 0.109	0.691 ± 0.068
		mRMR	0.551 ± 0.092	0.538 ± 0.182	0.554 ± 0.145	0.537 ± 0.144

Back to article page

ISSN: 1479-5876

Contact us

Submission enquiries: Access here and click Contact Us
General enquiries: journalsubmissions@springernature.com

Journal of Translational Medicine

Contact us