Jennifer Emond, PhD, Assistant Professor of Biomedical Data Science and Pediatrics at Geisel School of Medicine at Dartmouth, led a study to show that fast food consumption uniquely contributes to weight gain in children ages 3 to 5 years old. While previous research has established a link between fast-food consumption and its prevalence among adolescents who become overweight or obese, this is the first study to determine that fast food independently contributes to excess weight gain in preschoolers.
A team of researchers led by Dr. Saeed Hassanpour at Geisel School of Medicine has developed a model that uses artificial intelligence for automated classification of colorectal polyps. The model was first developed using 326 slides from Dartmouth-Hitchcock for training, 157 slides for an internal data set, and 25 slides for a validation data set. For the external data set, 238 slides from 179 unique patients were sourced from 24 institutions across 13 states in the US.
In a report completed by investigators at Geisel School of Medicine and the University of Connecticut School of Medicine, researchers find that underage drinking is directly linked to exposure to alcohol marketing, marking the first time that public health experts have unequivocally determined that exposure to alcohol advertising is one cause of drinking onset in adolescents and is also one cause of binge drinking.
The National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) has awarded Catherine Stanger, PhD, CTBH Deputy Director, a 5-year grant for a study to test the effectiveness of innovative behavioral health intervention tools for high-risk patients who suffer from Type 1 diabetes. The aim of the study is to use novel recruitment methods, including social media, and a smartphone application to help this patient population improve self-management of Type 1 diabetes and achieve better health outcomes.
Research Summary: Nicholas Jacobson, PhD, leads a study on the impact of COVID-19 stay-at-home orders on Google search behavior in the US related to mental health symptoms to gain insight into acute mental health consequences associated with the pandemic.
Methods: The current manuscript evaluates the impact of stay-at-home orders on mental health search queries between March 16-23, 2020. This work utilizes Google Trends to quantify changes in search behavior in the 50 states within the United States as well as the District of Columbia (Washington D.C.) with the goal of better understanding the acute mental health impact of stay-at-home orders amidst COVID-19. Specifically, we sought to determine whether stay-at-home orders resulted in increased affective symptoms as might be suggested by theories related to potential impacts of prolonged social isolation, or, in contrast, whether there might be improved mental health from clear government action rather than continuing to live in a state of uncertainty caused by government inaction.
Findings: Prior to stay-at-home orders, searches on mental health symptoms were rising exponentially. Once stay-at home orders were announced, searches on mental health symptoms flattened immediately.
Public health relevance: COVID-19 stay-at-home orders immediately prevented further exacerbation in mental health symptoms, such as anxiety, depression, obsessive-compulsive, negative thoughts, irritability, fatigue, anhedonia, concentration, insomnia, and suicidal ideation. Future research could determine whether the observed plateau of mental-health related searches will be sustained through the duration of stay-at-home orders and the long-term meal health effects of COVID-119 and governmental responses to COVID-19.
Jacobson, N. C., Lekkas, D., Price, G., Heinz, M. V., Song, M., O’Malley, A. J., & Barr, P. J. (2020, April 8). Flattening the Mental Health Curve: COVID-19 Stay-at-Home Orders Result in Alterations in Mental Health Search Behavior in the United States. https://doi.org/10.31234/osf.io/24v5b
In 2019, the Center for Quantitative Biology was established at Geisel School of Medicine at Dartmouth under the leadership of Michael Whitfield, PhD, Chair and Professor of Biomedical Data Science. This new initiative is part of an exciting opportunity to make precision medicine technologies more broadly accessible to Dartmouth’s diverse scientific and clinical communities.
Read more here: https://dartmed.dartmouth.edu/spring20/html/features_cqb/
PROJECT TITLE: Clinicopathologic and Genetic Profiling through Machine Learning and Natural Language Processing for Precision Lung Cancer Management
National Institutes of Health (NIH)
National Cancer Institute (NCI)
Saeed Hassanpour, PhD
OTHER PROJECT STAFF
Laura Tafe, MD, Associate Professor of Pathology, Department of Pathology and Laboratory Medicine at Dartmouth-Hitchcock; Gregory Tsongalis, PhD, Professor of Pathology and Director of Molecular Pathology and Clinical Genomics and Advanced Technologies at Dartmouth-Hitchcock, and Co-Director of the Translational Research Program and Pathology Shared Resource at Dartmouth’s Norris Cotton Cancer Center; Konstantin Dragnev, MD, Professor of Medicine and Associate Director for Clinical Research at Dartmouth’s Norris Cotton Cancer Center; and external collaborators from the University of Vermont Medical Center and the Baylor College of Medicine
Lung cancer is the second-most common type of cancer and the leading cause of cancer death in men and women. Among the different types of lung cancer, non-small cell lung cancer (NSCLC) is the most common type and it constitutes 85% to 90% of all lung cancer cases. Current cancer research has shown that multiple somatic mutations affect the sensitivity of patients to various drugs used for NSCLC treatment. These mutations are essential factors for determining the most effective, “personalized” treatment for each NSCLC patient; however, most NSCLC patients develop resistance to these targeted therapies in their first year of treatment. Many mechanisms of this resistance are still unknown. Designing and prescribing better targeted therapies for NSCLC patients requires further understanding, particularly with respect to the relationship between NSCLC tumors’ pathological and clinical findings, genetic profiles, and targeted therapy responses/resistance. Currently, there is no computational method to connect observations and findings from pathology reports, medical records, somatic mutations, and the targeted therapy resistance. This project provides a plan to build a novel computational method to identify statistically significant associations between the pathological findings of NSCLC tumors and the presence of clinically-actionable somatic mutations. Furthermore, these associations, in combination with an innovative set of feature analysis from pathology reports and electronic medical records, will be leveraged to build and validate a machine-learning model to identify NSCLC patients with clinically-actionable somatic mutations. Finally, the associated clinical, pathological, and genetic findings for NSCLC patients will be used in a new machine-learning framework to predict patients’ time-to-resistance to targeted therapies. The required data to build and validate the proposed models in this project will be obtained through a collaboration with the Department of Pathology’s Laboratory for Clinical Genomics and Advanced Technologies at Dartmouth-Hitchcock Medical Center. In addition to internal validation, the investigators in this proposal established a collaboration with the Department of Pathology at the University of Vermont Medical Center to apply and validate the developed models on an external data source. Upon successful implementation of this bioinformatics approach, the developed models will be able to reveal statistically significant links between clinical and pathological findings, clinically-actionable somatic mutations, and targeted-therapy responses for a better understanding of NSCLC tumor development and treatment. The proposed approach will provide an accurate, fast, and inexpensive pre- selection method for screening NSCLC patients with clinically-actionable mutations for translational research and precision medicine. Furthermore, the proposed machine-learning method to identify NSCLC patients’ resistance to targeted therapies will help healthcare providers to select the best treatment strategies for these patients, improve their health outcomes, and establish this precision medicine paradigm for other types of cancer.
PUBLIC HEALTH RELEVANCE
Resistance to targeted therapies severely limits the ability to treat non-small cell lung cancer (NSCLC) patients. This project proposes a novel computational approach to find statistically-significant links between pathological and clinical findings, clinically-actionable mutations, and targeted-therapy responses for NSCLC patients. The outcomes of this proposal can assist healthcare providers to identify the most effective strategy for NSCLC treatment, improve public health, and promote precision medicine.
Geisel School of Medicine has been awarded a $12.5 Million COBRE Grant to establish a Center for Quantitative Biology, to be led by Michael Whitfield, PhD, chair and professor of Biomedical Data Science.
Read the full press release here:
Saeed Hassanpour, PhD, an assistant professor of biomedical data science at Dartmouth’s Geisel School of Medicine, and an adjunct assistant professor of epidemiology at Geisel and of computer science at Dartmouth College, is the winner of the 2019 Agilent Early Career Professor Award.
This year’s award focused on “contributions to the development of breakthrough artificial intelligence solutions advancing cancer diagnostics based on image analysis of pathology slides.”
Dr. Hassanpour’s current research focuses on the use of deep-learning technology for histopathological characterization of colorectal polyps to improve colon cancer screening, as well as on other cancer types
and imaging modalities.
Read more here:
Dartmouth researchers develop and validate a brief, parent-reported scale to measure external food cue responsiveness and conditioned eating behaviors for preschool-age children.
Preliminary evidence from a new Dartmouth study suggests that external food cue responsiveness is measurable by parental report in preschool-age children. Responsiveness was greater among children with, versus without, usual TV advertisement exposure. These results may provide a better understanding of how an obesogenic food environment shapes the development of children’s eating behaviors at a young age.
Official press release from Norris Cotton Cancer Center: