Author Interviews, Brigham & Women's - Harvard, Cancer Research, Genetic Research, Melanoma, Prostate Cancer / 23.11.2020
Deep Learning of Germline Mutations Enables Identification of More Patients at Risk of Cancer
MedicalResearch.com Interview with:
[caption id="attachment_56034" align="alignleft" width="97"]
Dr. AlDubayan[/caption]
Saud H AlDubayan, M.D.
Instructor in Medicine, Harvard Medical School
Attending Physician, Division of Genetics,
Brigham and Women's Hospital
Computational Biologist, Department of Medical Oncology,
Dana-Farber Cancer Institute
Associate Scientist, The Broad Institute of MIT and Harvard
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: The overall goal of this study was to assess the performance of the standard method currently used to detect germline (inhered) genetic variants in cancer patients and whether we could use recent advances in machine learning techniques to further improve the detection rate of clinically relevant genetic alterations.
To investigate this possibility, we performed a head to head comparison between the current gold-standard method for germline analysis that has been universally used in clinical and research laboratories and a new deep learning analysis approach using germline genetic data of thousands of patients with prostate cancer or melanoma. This analysis showed that across all different gene sets that were tested, the deep learning-based framework was able to identify additional cancer patients with clinically relevant germline variants that went undetected by the standard method. For example, several patients in our study also had germline variants that are associated with an increased risk of ovarian cancer, for which the surgical removal of the ovaries (at a certain age) is highly recommended. However, these genetic alterations were only identified by the proposed deep learning framework.
Dr. AlDubayan[/caption]
Saud H AlDubayan, M.D.
Instructor in Medicine, Harvard Medical School
Attending Physician, Division of Genetics,
Brigham and Women's Hospital
Computational Biologist, Department of Medical Oncology,
Dana-Farber Cancer Institute
Associate Scientist, The Broad Institute of MIT and Harvard
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: The overall goal of this study was to assess the performance of the standard method currently used to detect germline (inhered) genetic variants in cancer patients and whether we could use recent advances in machine learning techniques to further improve the detection rate of clinically relevant genetic alterations.
To investigate this possibility, we performed a head to head comparison between the current gold-standard method for germline analysis that has been universally used in clinical and research laboratories and a new deep learning analysis approach using germline genetic data of thousands of patients with prostate cancer or melanoma. This analysis showed that across all different gene sets that were tested, the deep learning-based framework was able to identify additional cancer patients with clinically relevant germline variants that went undetected by the standard method. For example, several patients in our study also had germline variants that are associated with an increased risk of ovarian cancer, for which the surgical removal of the ovaries (at a certain age) is highly recommended. However, these genetic alterations were only identified by the proposed deep learning framework.
Dr. Kubik[/caption]
Martha Kubik, Ph.D., R.N.
Professor and director of the School of Nursing
College of Health and Human Services at George Mason University
USPSTF Task Force Member
MedicalResearch.com: What is the background for this study? What are the main findings? Has the recommendation changed over the last decade?
Response: High blood pressure is becoming more common among children and teens in the United States and can have serious negative health effects in childhood and adulthood, such as kidney and heart disease. However, there is not enough research to know whether treating high blood pressure in young people improves cardiovascular health in adulthood.
The Task Force continued to find that there is not enough evidence to recommend for or against screening for high blood pressure in children and teens who do not have signs or symptoms.
Dr. Vazza
Dr. Barrett[/caption]
Emily Barrett, PhD
Associate Professor
Department of Biostatistics and Epidemiology
Rutgers School of Public Health
MedicalResearch.com: What is the background for this study?
Response: We started this study in the very early stages of the pandemic to look at SARS-CoV-2 viral transmission and disease severity in health care workers as compared to non-health care workers. There was a tremendous amount of fear and uncertainty about the virus and the early anecdotal reports coming out of China and Italy highlighted the plight of many frontline health care workers who had been infected on the job. We knew that our U.S. health care workers would soon be facing this tremendous challenge. We started this study to examine risks of infection in our vulnerable frontline health care workers and a comparison group of non-health care workers. Our results are from the early stages of the U.S. pandemic in March-April 2020.
Prof. Pottel[/caption]
Prof. Dr. Hans Pottel PhD
Professeur Invité (titre honorifique)
Faculté de Médecine
Université de Liège
KULeuven-KULAK, Kortrijk, Belgium
MedicalResearch.com: What is the background for this study? Why do we need a new GFR?
Response: The currently recommended equations have flaws, mainly because there is one equation (CKiD) recommended for children, and one recommended (CKD-EPI) for adults (by KDIGO). When transitioning from pediatric nephrology care to adult nephrology care, the switch from CKiD to CKD-EPI causes implausible jumps (of more than 50%), mainly because CKD-EPI largely overestimates GFR in young adults (18-30 years). The new equation overcomes this problem as it applies for all ages (for children and adults) and overcomes the known flaws of the currently most used equations. The new equation is less biased and more precise across the full age spectrum and for the full range of serum creatinine concentrations.
The equation was developed in 11 251 participants from 7 cohorts (development and internal validation datasets) and validated in 8 378 participants from 6 cohorts (external validation dataset). Data were coming from European and American nephrology centers. No patients of African-American ancestry were included. Actually, the previously published FAS-equation served as the basic mathematical form for the equation, but we adjusted the power coefficients for serum creatinine (very much like it was done in the CKD-EPI equation). You could say that we used properties of both the FAS and CKD-EPI equation to come to an improved equation to estimate GFR.
Dr. Ganson[/caption]
Kyle T. Ganson, PhD, MSW
Assistant Professor, Factor-Inwentash Faculty of Social Work
University of Toronto
Toronto, Canada
[caption id="attachment_55902" align="alignleft" width="132"]
Dr. Nagata[/caption]
Jason Nagata, MD, MSc
Assistant Professor of Pediatrics
University of California, San Francisco
San Francisco, California, USA
MedicalResearch.com: What is the background for this study?
Response: A quarter of young adults in the US have reported being unemployed during the COVID-19 pandemic. Young adults may be especially affected by employment loss as they often work in industries most adversely affected by social distancing.
MedicalResearch.com: What are the main findings?
Response: Among a sample of nearly 5,000 young adults age 18 to 26 in the US, we found that since March 2020, young adults who lost their job or were part of a household that experienced employment loss were more likely than those with secure employment to experience four common symptoms of anxiety and depression. This was also true of young adults who expected an employment loss in the next four weeks. The study also found that symptoms of anxiety and depression were common among the sample of young adults. In the seven days prior to the survey, 75% reported being nervous, anxious or on edge, 68% reported not being able to stop or control worrying, 67% reported having little interest or pleasure in doing things, and 64% reported feeling down, depressed, or hopeless.
Dr. Al Rifai[/caption]
Mahmoud Al Rifai, MD, MPH
Cardiovascular Disease Fellow
Baylor College of Medicine Houston, TX
[caption id="attachment_55680" align="alignleft" width="150"]
Dr. Virani[/caption]
Salim S. Virani, MD, PhD, FACC, FAHA, FASPC
Professor, Section of Cardiovascular Research
Director, Cardiology Fellowship Training Program
Baylor College of Medicine
Staff Cardiologist, Michael E. DeBakey Veterans Affairs Medical Center
Co-Director, VA Advanced Fellowship in Health Services Research & Development at the Michael E. DeBakey VA Medical Center
Investigator, Health Policy, Quality and Informatics Program
Michael E. DeBakey Veterans Affairs Medical Center HSR&D Center of Innovation Houston, TX
MedicalResearch.com: What is the background for this study? What are the main findings?
Response: E-cigarettes have gained popularity since their introduction in the U.S. market nearly 20 years ago and their use has increased especially among younger adults. On the other hand, public health efforts aimed at curbing tobacco use over the past few decades have resulted in a decrease in cigarette use. However, state-specific laws and regional cultural differences with regards to perception of these products may result in variability in tobacco use patterns. We therefore evaluate temporal changes in e-cigarette and cigarette use in each U.S. state between the years 2016 to 2018.
Prof Jeffrey S Tobias, Prof Jayant S Vaidya, Prof Max Bulsara. and Prof Michael Baum[/caption]
Response: The findings of the large international randomised trial (TARGIT-A trial), published in the British Medical Journal (