Synapse - Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer

Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer Journal Article

Authors:	Boehm, K. M.; Aherne, E. A.; Ellenson, L.; Nikolovski, I.; Alghamdi, M.; Vázquez-García, I.; Zamarin, D.; Roche, K. L.; Liu, Y.; Patel, D.; Aukerman, A.; Pasha, A.; Rose, D.; Selenica, P.; Causa Andrieu, P. I.; Fong, C.; Capanu, M.; Reis-Filho, J. S.; Vanguri, R.; Veeraraghavan, H.; Gangai, N.; Sosa, R.; Leung, S.; McPherson, A.; Gao, J. J.; MSK MIND Consortium; Lakhman, Y.; Shah, S. P.
Contributors:	Sabbatini, P.; Stetson, P.; Swinburne, N.; Schultz, N.; Hellmann, M.; Gonen, M.; Razavi, P.; Sutton, E.; Khosravi, P.; Jee, J.; Pichotta, K.; Elsherif, E.; Begum, A.; Zakszewski, E.; Gross, B.; Geneslaw, L.
Editors:	Philip, J.; Pimienta, R.; Rangavajhala, S. N.
Article Title:	Multimodal data integration using machine learning improves risk stratification of high-grade serous ovarian cancer
Abstract:	Patients with high-grade serous ovarian cancer suffer poor prognosis and variable response to treatment. Known prognostic factors for this disease include homologous recombination deficiency status, age, pathological stage and residual disease status after debulking surgery. Recent work has highlighted important prognostic information captured in computed tomography and histopathological specimens, which can be exploited through machine learning. However, little is known about the capacity of combining features from these disparate sources to improve prediction of treatment response. Here, we assembled a multimodal dataset of 444 patients with primarily late-stage high-grade serous ovarian cancer and discovered quantitative features, such as tumor nuclear size on staining with hematoxylin and eosin and omental texture on contrast-enhanced computed tomography, associated with prognosis. We found that these features contributed complementary prognostic information relative to one another and clinicogenomic features. By fusing histopathological, radiologic and clinicogenomic machine-learning models, we demonstrate a promising path toward improved risk stratification of patients with cancer through multimodal data integration. © 2022, The Author(s).
Keywords:	human tissue; treatment response; unclassified drug; gene mutation; major clinical study; overall survival; histopathology; cancer staging; lymph node dissection; ovarian neoplasms; dna damage; progression free survival; computer assisted tomography; ovary cancer; gene amplification; image analysis; tumor volume; signal noise ratio; cohort analysis; diagnostic imaging; brca1 protein; brca2 protein; retrospective study; risk assessment; contrast enhancement; ovary tumor; cystadenocarcinoma, serous; cyclin dependent kinase; cystadenocarcinoma; machine learning; humans; human; female; article; cyclin dependent kinase 12
Journal Title:	Nature Cancer
Volume:	3
Issue:	6
ISSN:	2662-1347
Publisher:	Nature Research
Date Published:	2022-06-01
Start Page:	723
End Page:	733
Language:	English
DOI:	10.1038/s43018-022-00388-9
PUBMED:	35764743
PROVIDER:	scopus
PMCID:	PMC9239907
DOI/URL:	https://www.scopus.com/inward/record.uri?eid=2-s2.0-85132974208&doi=10.1038%2fs43018-022-00388-9&partnerID=40&md5=933f5317ed1a72f3f98938027d33dbaa
Notes:	Article -- Export Date: 1 August 2022 -- Source: Scopus