1
|
Guan BZ, Parmigiani G, Braun D, Trippa L. PREDICTION OF HEREDITARY CANCERS USING NEURAL NETWORKS. Ann Appl Stat 2022; 16:495-520. [PMID: 37873507 PMCID: PMC10593124 DOI: 10.1214/21-aoas1510] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/25/2023]
Abstract
Family history is a major risk factor for many types of cancer. Mendelian risk prediction models translate family histories into cancer risk predictions, based on knowledge of cancer susceptibility genes. These models are widely used in clinical practice to help identify high-risk individuals. Mendelian models leverage the entire family history, but they rely on many assumptions about cancer susceptibility genes that are either unrealistic or challenging to validate, due to low mutation prevalence. Training more flexible models, such as neural networks, on large databases of pedigrees can potentially lead to accuracy gains. In this paper we develop a framework to apply neural networks to family history data and investigate their ability to learn inherited susceptibility to cancer. While there is an extensive literature on neural networks and their state-of-the-art performance in many tasks, there is little work applying them to family history data. We propose adaptations of fully-connected neural networks and convolutional neural networks to pedigrees. In data simulated under Mendelian inheritance, we demonstrate that our proposed neural network models are able to achieve nearly optimal prediction performance. Moreover, when the observed family history includes misreported cancer diagnoses, neural networks are able to outperform the Mendelian BRCAPRO model embedding the correct inheritance laws. Using a large dataset of over 200,000 family histories, the Risk Service cohort, we train prediction models for future risk of breast cancer. We validate the models using data from the Cancer Genetics Network.
Collapse
Affiliation(s)
- By Zoe Guan
- Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center
| | | | - Danielle Braun
- Department of Biostatistics, Harvard T.H. Chan School of Public Health
| | - Lorenzo Trippa
- Department of Data Sciences, Dana-Farber Cancer Institute
| |
Collapse
|
2
|
Stefansdottir V, Thorolfsdottir E, Hognason HB, Patch C, van El C, Hentze S, Cordier C, Mendes Á, Jonsson JJ. Web-based return of BRCA2 research results: one-year genetic counselling experience in Iceland. Eur J Hum Genet 2020; 28:1656-1661. [PMID: 32523053 PMCID: PMC7784695 DOI: 10.1038/s41431-020-0665-1] [Citation(s) in RCA: 6] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/12/2019] [Revised: 05/18/2020] [Accepted: 05/26/2020] [Indexed: 11/09/2022] Open
Abstract
There is an increased pressure to return results from research studies. In Iceland, deCODE Genetics has emphasised the importance of returning results to research participants, particularly the founder pathogenic BRCA2 variant; NM_000059.3:c.771_775del. To do so, they opened the website www.arfgerd.is . Individuals who received positive results via the website were offered genetic counselling (GC) at Landspitali in Reykjavik. At the end of May 2019, over 46.000 (19% of adults of Icelandic origin) had registered at the website and 352 (0.77%) received text message informing them about their positive results. Of those, 195 (55%) contacted the GC unit. Additionally, 129 relatives asked for GC and confirmatory testing, a total of 324 individuals. Various information such as gender and age, prior knowledge of the variant and perceived emotional impact, was collected. Of the BRCA2 positive individuals from the website, 74 (38%) had prior knowledge of the pathogenic variant (PV) in the family. The majority initially stated worries, anxiety or other negative emotion but later in the process many communicated gratitude for the knowledge gained. Males represented 41% of counsellees as opposed to less than 30% in the regular hereditary breast and ovarian (HBOC) clinic. It appears that counselling in clinical settings was more reassuring for worried counsellees. In this article, we describe one-year experience of the GC service to those who received positive results via the website. This experience offers a unique opportunity to study the public response of a successful method of the return of genetic results from research.
Collapse
Affiliation(s)
- Vigdis Stefansdottir
- Department of Genetics and Molecular Medicine, Iceland, Landspitali - the National University Hospital of Iceland, Reykjavik, Iceland.
| | - Eirny Thorolfsdottir
- Department of Genetics and Molecular Medicine, Iceland, Landspitali - the National University Hospital of Iceland, Reykjavik, Iceland
| | - Hakon B Hognason
- Department of Genetics and Molecular Medicine, Iceland, Landspitali - the National University Hospital of Iceland, Reykjavik, Iceland
| | - Christine Patch
- Florence Nightingale Faculty, Nursing and Midwifery & Palliative Care, King's College London, London, UK
| | - Carla van El
- Amsterdam UMC, Vrije Universiteit Amsterdam, Department of Clinical Genetics and Amsterdam Public Health Research Institute, Amsterdam, the Netherlands
| | | | - Christophe Cordier
- Association suisse des conseillers en génétique, c/o Anne Murphy, 26 rue de la Colline, 1205, Genève, Switzerland
- Département de génétique, SYNLAB, Chemin d'Entre-Bois 21, 1018, Lausanne, Switzerland
| | - Álvaro Mendes
- UnIGENe and CGPP - Centre for Predictive and Preventive Genetics, IBMC - Institute for Molecular and Cell Biology, i3S - Instituto de Investigação e Inovação em Saúde, Universidade do Porto, Porto, Portugal
| | - Jon J Jonsson
- Department of Genetics and Molecular Medicine, Iceland, Landspitali - the National University Hospital of Iceland, Reykjavik, Iceland
- Department of Biochemistry and Molecular Biology, Faculty of Medicine, University of Iceland, Reykjavik 101, Reykjavik, Iceland
| |
Collapse
|