Statistical biopsy: An emerging screening approach for early detection of cancers
Despite large investment cancer continues to be a major source of mortality and morbidity throughout the world. Traditional methods of detection and diagnosis such as biopsy and imaging, tend to be expensive and have risks of complications. As data becomes more abundant and machine learning continue...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Artificial Intelligence |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/frai.2022.1059093/full |
| _version_ | 1828057890642984960 |
|---|---|
| author | Gregory R. Hart Vanessa Yan Bradley J. Nartowt David A. Roffman Gigi Stark Wazir Muhammad Jun Deng |
| author_facet | Gregory R. Hart Vanessa Yan Bradley J. Nartowt David A. Roffman Gigi Stark Wazir Muhammad Jun Deng |
| author_sort | Gregory R. Hart |
| collection | DOAJ |
| description | Despite large investment cancer continues to be a major source of mortality and morbidity throughout the world. Traditional methods of detection and diagnosis such as biopsy and imaging, tend to be expensive and have risks of complications. As data becomes more abundant and machine learning continues advancing, it is natural to ask how they can help solve some of these problems. In this paper we show that using a person's personal health data it is possible to predict their risk for a wide variety of cancers. We dub this process a “statistical biopsy.” Specifically, we train two neural networks, one predicting risk for 16 different cancer types in females and the other predicting risk for 15 different cancer types in males. The networks were trained as binary classifiers identifying individuals that were diagnosed with the different cancer types within 5 years of joining the PLOC trial. However, rather than use the binary output of the classifiers we show that the continuous output can instead be used as a cancer risk allowing a holistic look at an individual's cancer risks. We tested our multi-cancer model on the UK Biobank dataset showing that for most cancers the predictions generalized well and that looking at multiple cancer risks at once from personal health data is a possibility. While the statistical biopsy will not be able to replace traditional biopsies for diagnosing cancers, we hope there can be a shift of paradigm in how statistical models are used in cancer detection moving to something more powerful and more personalized than general population screening guidelines. |
| first_indexed | 2024-04-10T21:19:23Z |
| format | Article |
| id | doaj.art-2cb1cc909ab14854b8a7f4dbfae3f717 |
| institution | Directory Open Access Journal |
| issn | 2624-8212 |
| language | English |
| last_indexed | 2024-04-10T21:19:23Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Artificial Intelligence |
| spelling | doaj.art-2cb1cc909ab14854b8a7f4dbfae3f7172023-01-20T07:37:34ZengFrontiers Media S.A.Frontiers in Artificial Intelligence2624-82122023-01-01510.3389/frai.2022.10590931059093Statistical biopsy: An emerging screening approach for early detection of cancersGregory R. Hart0Vanessa Yan1Bradley J. Nartowt2David A. Roffman3Gigi Stark4Wazir Muhammad5Jun Deng6Institute for Disease Modeling, Global Health Division, Bill and Melinda Gates Foundation, Seattle, WA, United StatesDepartment of Therapeutic Radiology, Yale University, New Haven, CT, United StatesSMFE, Wright-Patterson Air Force Base, Dayton, OH, United StatesResearch Partners, Sun Nuclear Corporation (Mirion Technologies Inc.), Melbourne, FL, United StatesDepartment of Therapeutic Radiology, Yale University, New Haven, CT, United StatesDepartment of Physics, Florida Atlantic University, Boca Raton, FL, United StatesDepartment of Therapeutic Radiology, Yale University, New Haven, CT, United StatesDespite large investment cancer continues to be a major source of mortality and morbidity throughout the world. Traditional methods of detection and diagnosis such as biopsy and imaging, tend to be expensive and have risks of complications. As data becomes more abundant and machine learning continues advancing, it is natural to ask how they can help solve some of these problems. In this paper we show that using a person's personal health data it is possible to predict their risk for a wide variety of cancers. We dub this process a “statistical biopsy.” Specifically, we train two neural networks, one predicting risk for 16 different cancer types in females and the other predicting risk for 15 different cancer types in males. The networks were trained as binary classifiers identifying individuals that were diagnosed with the different cancer types within 5 years of joining the PLOC trial. However, rather than use the binary output of the classifiers we show that the continuous output can instead be used as a cancer risk allowing a holistic look at an individual's cancer risks. We tested our multi-cancer model on the UK Biobank dataset showing that for most cancers the predictions generalized well and that looking at multiple cancer risks at once from personal health data is a possibility. While the statistical biopsy will not be able to replace traditional biopsies for diagnosing cancers, we hope there can be a shift of paradigm in how statistical models are used in cancer detection moving to something more powerful and more personalized than general population screening guidelines.https://www.frontiersin.org/articles/10.3389/frai.2022.1059093/fullcancer screeningmachine learning and AIneural networkbiopsydata miningcancer detection |
| spellingShingle | Gregory R. Hart Vanessa Yan Bradley J. Nartowt David A. Roffman Gigi Stark Wazir Muhammad Jun Deng Statistical biopsy: An emerging screening approach for early detection of cancers Frontiers in Artificial Intelligence cancer screening machine learning and AI neural network biopsy data mining cancer detection |
| title | Statistical biopsy: An emerging screening approach for early detection of cancers |
| title_full | Statistical biopsy: An emerging screening approach for early detection of cancers |
| title_fullStr | Statistical biopsy: An emerging screening approach for early detection of cancers |
| title_full_unstemmed | Statistical biopsy: An emerging screening approach for early detection of cancers |
| title_short | Statistical biopsy: An emerging screening approach for early detection of cancers |
| title_sort | statistical biopsy an emerging screening approach for early detection of cancers |
| topic | cancer screening machine learning and AI neural network biopsy data mining cancer detection |
| url | https://www.frontiersin.org/articles/10.3389/frai.2022.1059093/full |
| work_keys_str_mv | AT gregoryrhart statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers AT vanessayan statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers AT bradleyjnartowt statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers AT davidaroffman statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers AT gigistark statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers AT wazirmuhammad statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers AT jundeng statisticalbiopsyanemergingscreeningapproachforearlydetectionofcancers |