Digital Commons Network^™

Machine Learning To Optimize Use Of Natriuretic Peptides In The Diagnosis Of Acute Heart Failure, Dimitrios Doudesis, Kuan Ken Lee, Mohamed Anwar, Adam J. Singer, Judd E. Hollander, Camille Chenevier-Gobeaux, Yann-Erick Claessens, Desiree Wussler, Dominic Weil, Nikola Kozhuharov, Ivo Strebel, Zaid Sabti, Christopher Defilippi, Stephen Seliger, Evandro Tinoco Mesquita, Jan C. Wiemer, Martin Möckel, Joel Coste, Patrick Jourdain, Komukai Kimiaki, Michihiro Yoshimura, Irwani Ibrahim, Shirley Beng Suat Ooi, Win Sen Kuan, Alfons Gegenhuber, Thomas Mueller, Olivier Hanon, Jean-Sébastien Vidal, Peter Cameron, Louisa Lam, Ben Freedman, Tommy Chung, Sean P. Collins, Christopher J. Lindsell, David E. Newby, Alan G. Japp, Anoop S. V. Shah, Humberto Villacorta, A. Mark Richards, John J V Mcmurray, Christian Mueller, James L. Januzzi, Nicholas L. Mills, Gordon Moe, Carlos Fernando, Hanna K. Gaggin, Antoni Bayes-Genis, Roland Rj Van Kimmenade, Yigal Pinto, Joost H. W. Rutten, Anton H. Van Den Meiracker, Luna Gargani, Nicola R. Pugliese, Pemberton Christopher, Michael Neumaier, Michael Behnes, Ibrahim Akin, Michele Bombelli, Guido Grassi, Peiman Nazerian, Giovanni Albano, Philipp Bahrmann

Department of Emergency Medicine Faculty Papers

AIMS: B-type natriuretic peptide (BNP) and mid-regional pro-atrial natriuretic peptide (MR-proANP) testing are guideline-recommended to aid in the diagnosis of acute heart failure. Nevertheless, the diagnostic performance of these biomarkers is uncertain.

METHODS AND RESULTS: We performed a systematic review and individual patient-level data meta-analysis to evaluate the diagnostic performance of BNP and MR-proANP. We subsequently developed and externally validated a decision-support tool called CoDE-HF that combines natriuretic peptide concentrations with clinical variables using machine learning to report the probability of acute heart failure. Fourteen studies from 12 countries provided individual patient-level data in 8493 patients for BNP and 3899 …

Machine Learning To Optimize Use Of Natriuretic Peptides In The Diagnosis Of Acute Heart Failure, Dimitrios Doudesis, Kuan Ken Lee, Mohamed Anwar, Adam J. Singer, Judd Hollander, Md, Camille Chenevier-Gobeaux, Yann-Erick Claessens, Desiree Wussler, Dominic Weil, Nikola Kozhuharov, Ivo Strebel, Zaid Sabti, Christopher Defilippi, Stephen Seliger, Evandro Tinoco Mesquita, Jan C. Wiemer, Martin Möckel, Joel Coste, Patrick Jourdain, Komukai Kimiaki, Michihiro Yoshimura, Irwani Ibrahim, Shirley Beng Suat Ooi, Win Sen Kuan, Alfons Gegenhuber, Thomas Mueller, Olivier Hanon, Jean-Sébastien Vidal, Peter Cameron, Louisa Lam, Ben Freedman, Tommy Chung, Sean P. Collins, Christopher J Lindsell, David E. Newby, Alan G. Japp, Anoop S V Shah, Humberto Villacorta, A Mark Richards, John J V Mcmurray, Christian Mueller, James L. Januzzi, Nicholas L. Mills

Department of Emergency Medicine Faculty Papers

AIMS: B-type natriuretic peptide (BNP) and mid-regional pro-atrial natriuretic peptide (MR-proANP) testing are guideline-recommended to aid in the diagnosis of acute heart failure. Nevertheless, the diagnostic performance of these biomarkers is uncertain.

METHODS AND RESULTS: We performed a systematic review and individual patient-level data meta-analysis to evaluate the diagnostic performance of BNP and MR-proANP. We subsequently developed and externally validated a decision-support tool called CoDE-HF that combines natriuretic peptide concentrations with clinical variables using machine learning to report the probability of acute heart failure. Fourteen studies from 12 countries provided individual patient-level data in 8493 patients for BNP and 3899 …

Identifying The Human Olfactory And Chemosignaling Neural Networks Using Event Related Fmri And Graph Theory, Saideh Ferdowsi, Tom Foulsham, Alireza Rahmani, Dimitri Ognibene, Luca Citi, Wen Li

Faculty, Staff and Student Publications

This study aims to characterize and compare the functional neural networks associated with different olfactory stimuli, including air, non-social odours, and human body odours. We introduce a novel processing pipeline based on event-related functional magnetic resonance imaging (fMRI) and graph theory for network identification. To ensure the stability and small worldness of the characterized networks, we conduct statistical validations, network modularity assessments, and robustness measurement against local attacks. The key hypothesis is that human body odours (so-called social odours) and non-social odours engage distinct neural networks, particularly in regions responsible for social processing. We found that the posterior medial orbitofrontal …

Computational Sensitivity Evaluation Of Ultrasound Neuromodulation Resolution To Brain Tissue Sound Speed With Robust Beamforming, Boqiang Fan, Wayne Goodman, Sameer A Sheth, Richard R Bouchard, Behnaam Aazhang

Faculty, Staff and Student Publications

Low-intensity focused ultrasound (LIFU) neuromodulation requires precise targeting and high resolution enabled by phased array transducers and beamforming. However, focusing optimization usually relies on phantom measurements or simulations with inaccurate acoustic properties to degrade neuromodulation resolution. Therefore, this work analyzes the sensitivity of neuromodulation resolution, measured by off-target activation area (OTAA), to brain tissue sound speed. A Robust Optimal Resolution (ROR) beamforming method is proposed to minimize the worst-case OTAA with restricted sound speed inaccuracy and propagation information estimated with deviated sound speed. The propagation estimation model utilizes equivalent source method (ESM) to map sound field between different acoustic parameter …

Identifiability And Model Selection Frameworks For Models Of High-Grade Glioma Response To Chemoradiation, Khushi C Hiremath, Kenan Atakishi, Ernesto A B F Lima, Maguy Farhat, Bikash Panthi, Holly Langshaw, Mihir D Shanker, Wasif Talpur, Sara Thrower, Jodi Goldman, Caroline Chung, Thomas E Yankeelov, David A Hormuth Ii

Faculty, Staff and Student Publications

We have developed a family of biology-based mathematical models of high-grade glioma (HGG), capturing the key features of tumour growth and response to chemoradiation. We now seek to quantify the accuracy of parameter estimation and determine, when given a virtual patient cohort, which model was used to generate the tumours. In this way, we systematically test both the parameter and model identifiability. Virtual patients are generated from unique growth parameters whose growth dynamics are determined by the model family. We then assessed the ability to recover model parameters and select the model used to generate the tumour. We then evaluated …

Rhythm Is Essential: Unraveling The Relation Between The Circadian Clock And Cancer, Olajumoke Ogunlusi, Abantika Ghosh, Mrinmoy Sarkar, Kayla Carter, Harshini Davuluri, Mahul Chakraborty, Kristin Eckel-Mahan, Alex Keene, Jerome S Menet, Deborah Bell-Pedersen, Tapasree Roy Sarkar

The Brown Foundation: Institute of Molecular Medicine

Physiological processes such as the sleep-wake cycle, metabolism, hormone secretion, neurotransmitter release, sensory capabilities, and a variety of behaviors, including sleep, are controlled by a circadian rhythm adapted to 24-hour day-night periodicity. Disruption of circadian rhythm may lead to the risks of numerous diseases, including cancers. Several epidemiological and clinical data reveal a connection between the disruption of circadian rhythms and cancer. On the contrary, oncogenic processes may suppress the homeostatic balance imposed by the circadian clock. The integration of circadian biology into cancer research offers new options for making cancer treatment more effective, and the pharmacological modulation of core …

A Phase I Study Of The Pharmacokinetics, Pharmacodynamics, And Safety Of Liposomal Bupivacaine For Sciatic Nerve Block In The Popliteal Fossa For Bunionectomy, Daniel I Sessler, Xiaodong Bao, David Leiman, Jia Song, Jason Chittenden, Alexander Voelkner, Alparslan Turan, Jeffrey Gadsden

Faculty, Staff and Student Publications

This trial assessed the pharmacokinetics, pharmacodynamics, and safety of liposomal bupivacaine given via ultrasound-guided popliteal sciatic nerve block with or without immediate-release bupivacaine hydrochloride in adults having bunionectomies. Forty-five adults were enrolled into four sequential cohorts: (1) liposomal bupivacaine 266 mg with bupivacaine hydrochloride 50 mg; (2) liposomal bupivacaine 133 mg with bupivacaine hydrochloride 50 mg; (3) liposomal bupivacaine 266 mg; or (4) bupivacaine hydrochloride 100 mg. Outcomes included pharmacokinetics (e.g., bupivacaine maximum plasma concentration [C

G-Distance: On The Comparison Of Model And Human Heterogeneity, Lenard Dome, Andy J. Wills

School of Psychology

Models are often evaluated when their behavior is at its closest to a single, sometimes averaged, set of empirical results, but this evaluation neglects the fact that both model and human behavior can be heterogeneous. Here, we develop a measure, g-distance, which considers model adequacy as the extent to which models exhibit a similar range of behaviors to the humans they model. We define g as the combination of two easily interpretable dimensions of model adequacy: accommodation and excess flexibility. We apply this measure to five models of an irrational learning effect, the inverse base-rate effect. g-Distance identifies two models, …

A New Multiple Imputation Method For High-Dimensional Neuroimaging Data, Tong Lu, Peter Kochunov, Chixiang Chen, Hsin-Hsiung Huang, L Elliot Hong, Shuo Chen

Faculty, Staff and Student Publications

Missing data are a prevalent challenge in neuroimaging, with significant implications for downstream statistical analysis. Neglecting this issue can introduce bias and lead to erroneous inferential conclusions, making it crucial to employ appropriate statistical methods for handling missing data. Although the multiple imputation is a widely used technique, its application in neuroimaging is severely hindered by the high dimensionality of neuroimaging data, and the substantial computational demands. To tackle the critical computational challenges, we propose a novel approach, High dimensional Multiple Imputation (HIMA), based on Bayesian models specifically designed for large-scale neuroimaging datasets. HIMA introduces a new computational strategy to …

A Novel Method For Semi-Quantitative Detection Of Hpv16 And Hpv18 Mrna With A Low-Cost, Open-Source Fluorimeter, Kathryn A Kundrod, Mary E Natoli, Chelsey A Smith, Jackson B Coole, Megan M Chang, Emilie Newsham Novak, Elizabeth Chiao, Elizabeth A Stier, Jane R Montealegre, Michael E Scheurer, Philip E Castle, Kathleen M Schmeler, Rebecca R Richards-Kortum

Center for Medical Ethics and Health Policy Staff Publications

Despite global calls to eliminate cervical cancer, rates of cervical cancer incidence and mortality remain high in resource-limited settings, where it is challenging to implement and sustain screening, diagnosis, and treatment programs. The presence of high-risk HPV mRNA in cervical cells is a sensitive and specific biomarker of cervical precancer. Yet, current testing methods are too costly and complex for use in resource-limited settings. Here, we present a novel method for semi-quantitative detection of HPV16 and HPV18 mRNA with minimal infrastructure requirements. The assay relies on isothermal reverse transcription recombinase polymerase amplification (RT-RPA) with real-time fluorescence readout, demonstrated on rugged, …

Differential Treatment Effects On Β-Cell Function Using Model-Based Parameters In Type 2 Diabetes: Results From The Glycemia Reduction Approaches In Diabetes: A Comparative Effectiveness Study (Grade), Kristina M Utzschneider, Mark Tripputi, Nicole M Butera, Andrea Mari, Samuel P Rosin, Mary Ann Banerji, Richard M Bergenstal, Necole Brown, Anders L Carlson, Ralph A Defronzo, Michaela R Gramzinski, Tasma Harindhanavudhi, Alexandra Kozedub, William I Sivitz, Michael W Steffes, Ashok Balasubramanyam, Neda Rasouli

Faculty, Staff and Students Publications

Objective: To evaluate how model-based parameters of β-cell function change with glucose-lowering treatment and associate with glycemic deterioration in adults with type 2 diabetes (T2D).

Research design and methods: In the Glycemia Reduction Approaches in Diabetes: A Comparative Effectiveness Study (GRADE), β-cell function parameters derived from mathematical modeling of oral glucose tolerance tests were assessed at baseline (N = 4,712) and 1, 3, and 5 years following randomization to insulin glargine, glimepiride, liraglutide, or sitagliptin, added to baseline metformin. Parameters included insulin secretion rate (ISR), glucose sensitivity (insulin response to glucose), rate sensitivity (early insulin response), and potentiation. Linear mixed-effects …

Cell-Matrix Feedback Controls Stretch-Induced Cellular Memory And Fibroblast Activation, Yuan Hong, Xiangjun Peng, Haomin Yu, Delaram Shakiba, Yuxuan Huang, Chengqing Qu, Aliza Mujahid, Yin-Yuan Huang, Jacob A Sandler, Kenneth M Pryse, Justin M Sacks, Elliot L Elson, Guy M Genin, Et Al.

2020-Current year OA Pubs

Mechanical stretch can activate long-lived changes in fibroblasts, increasing their contractility and initiating phenotypic transformations. This activation, critical to wound healing and procedures such as skin grafting, increases with mechanical stimulus for cells cultured in two-dimensional but is highly variable in cells in three-dimensional (3D) tissue. Here, we show that static mechanical stretch of cells in 3D tissues can either increase or decrease fibroblast activation depending upon recursive cell-extracellular matrix (ECM) feedback and demonstrate control of this activation through integrated in vitro and mathematical models. ECM viscoelasticity, signaling dynamics, and cell mechanics combine to yield a predictable, but nonmonotonic, relationship …

Failure Mode And Effects Analysis Applied To Central Venous Catheter Placement, James R Duncan, Daniel Harwood, Bruno Maranhao, Ellen Wertenberger, Jacob Grant, Mona Ostman

2020-Current year OA Pubs

Despite diligent efforts, complications continue to occur during the placement of central venous catheters (CVCs). Healthcare Failure Mode and Effect Analysis has been promoted as a process improvement tool and this review describes the strategic application of Failure Mode and Effects Analysis (FMEA) to CVC placement. The objective is to demonstrate the utility of FMEA first as a tool for identifying quality or safety issues and second for guiding mitigation efforts.

Mathematical Modeling To Address Questions In Breast Cancer Screening: An Overview Of The Breast Cancer Models Of The Cancer Intervention And Surveillance Modeling Network, Oguzhan Alagoz, Jennifer L Caswell-Jin, Harry J De Koning, Hui Huang, Xuelin Huang, Sandra J Lee, Yisheng Li, Sylvia K Plevritis, Swarnavo Sarkar, Clyde B Schechter, Natasha K Stout, Amy Trentham-Dietz, Nicolien Van Ravesteyn, Kathryn P Lowry

Faculty, Staff and Student Publications

The National Cancer Institute-funded Cancer Intervention and Surveillance Modeling Network (CISNET) breast cancer mathematical models have been increasingly utilized by policymakers to address breast cancer screening policy decisions and influence clinical practice. These well-established and validated models have a successful track record of use in collaborations spanning over 2 decades. While mathematical modeling is a valuable approach to translate short-term screening performance data into long-term breast cancer outcomes, it is inherently complex and requires numerous inputs to approximate the impacts of breast cancer screening. This review article describes the 6 independently developed CISNET breast cancer models, with a particular focus …

Impact Of Vascular Geometry On Thrombosis In Pediatric Patients With Modified Blalock-Taussig-Thomas Shunt: A Pilot Study, Ethan Penn, Yi Qiao, Kimsey Platten, Scott M Bugenhagen, Ram Rohatgi, Jacob R Miller, Jiaxiao Fang, Kelsey Mercer, Blaire Kulp, Jinli Wang, Guy M Genin, David Bark, Edon J Rabinowitz

2020-Current year OA Pubs

BACKGROUND: Thrombosis in modified Blalock-Taussig-Thomas shunts (mBTTS) poses a life-threatening risk for infants with shunt-dependent congenital heart disease. Although hemodynamics influence thrombosis, the specific geometric contributors remain unclear. This study aimed to identify key variables to inform future hemodynamic analysis, hypothesizing that brachiocephalic, subclavian artery, mBTTS, and/or pulmonary artery (PA) geometry play a critical role in clot formation.

METHODS AND RESULTS: We retrospectively analyzed 11 infants with hypoplastic left heart syndrome who underwent mBTTS placement. Using computed tomography and magnetic resonance imaging, we generated 3-dimensional models of the shunt and surrounding vasculature. Geometric variables related to shunt positioning and vascular …

The Unified Phenotype Ontology : A Framework For Cross-Species Integrative Phenomics., Nicolas Matentzoglu, Susan M. Bello, Ray Stefancsik, Sarah M Alghamdi, Anna V Anagnostopoulos, James P Balhoff, Meghan A Balk, Yvonne M Bradford, Yasemin Bridges, Tiffany J Callahan, Harry Caufield, Alayne Cuzick, Leigh Carmody, Anita R Caron, Vinicius De Souza, Stacia R Engel, Petra Fey, Malcolm Fisher, Sarah Gehrke, Christian Grove, Peter Hansen, Nomi L Harris, Midori A Harris, Laura Harris, Arwa Ibrahim, Julius O B Jacobsen, Sebastian Köhler, Julie A Mcmurry, Violeta Munoz-Fuentes, Monica C Munoz-Torres, Helen Parkinson, Zoë M Pendlington, Clare Pilgrim, Sofia M C Robb, Peter N Robinson, James Seager, Erik Segerdell, Damian Smedley, Elliot Sollis, Sabrina Toro, Nicole Vasilevsky, Valerie Wood, Melissa A Haendel, Christopher J Mungall, James A Mclaughlin, David Osumi-Sutherland

Faculty Research 2025

Phenotypic data are critical for understanding biological mechanisms and consequences of genomic variation, and are pivotal for clinical use cases such as disease diagnostics and treatment development. For over a century, vast quantities of phenotype data have been collected in many different contexts covering a variety of organisms. The emerging field of phenomics focuses on integrating and interpreting these data to inform biological hypotheses. A major impediment in phenomics is the wide range of distinct and disconnected approaches to recording the observable characteristics of an organism. Phenotype data are collected and curated using free text, single terms or combinations of …

Investigation Of Dynamic Regulation Of Tfeb Nuclear Shuttling By Microfluidics And Quantitative Modelling, Iacopo Ruolo, Sara Napolitano, Lorena Postiglione, Gennaro Napolitano, Andrea Ballabio, Diego Di Bernardo

Duncan NRI Faculty and Staff Publications

Transcription Factor EB (TFEB) controls lysosomal biogenesis and autophagy in response to nutritional status and other stress factors. Although its regulation by nuclear translocation is known to involve a complex network of well-studied regulatory processes, the precise contribution of each of these mechanisms is unclear. Using microfluidics technology and real-time imaging coupled with mathematical modelling, we explored the dynamic regulation of TFEB under different conditions. We found that TFEB nuclear translocation upon nutrient deprivation happens in two phases: a fast one characterised by a transient boost in TFEB dephosphorylation dependent on transient calcium release mediated by mucolipin 1 (MCOLN1) followed …

Precision Phenotyping For Curating Research Cohorts Of Patients With Unexplained Post-Acute Sequelae Of Covid-19, Alaleh Azhir, Jonas Hügel, Jiazi Tian, Jingya Cheng, Ingrid V Bassett, Douglas S Bell, Elmer V Bernstam, Maha R Farhat, Darren W Henderson, Emily S Lau, Michele Morris, Yevgeniy R Semenov, Virginia A Triant, Shyam Visweswaran, Zachary H Strasser, Jeffrey G Klann, Shawn N Murphy, Hossein Estiri

Faculty, Staff and Student Publications

BACKGROUND: Scalable identification of patients with post-acute sequelae of COVID-19 (PASC) is challenging due to a lack of reproducible precision phenotyping algorithms, which has led to suboptimal accuracy, demographic biases, and underestimation of the PASC.

METHODS: In a retrospective case-control study, we developed a precision phenotyping algorithm for identifying cohorts of patients with PASC. We used longitudinal electronic health records data from over 295,000 patients from 14 hospitals and 20 community health centers in Massachusetts. The algorithm employs an attention mechanism to simultaneously exclude sequelae that prior conditions can explain and include infection-associated chronic conditions. We performed independent chart reviews …

Transcriptome Complexity Disentangled: A Regulatory Molecules Approach, Amir Asiaee, Zachary B Abrams, Heather H Pua, Kevin R Coombes

2020-Current year OA Pubs

Transcription factors (TFs) and microRNAs (miRNAs) are fundamental regulators of gene expression, cell state, and biological processes. This study investigated whether a small subset of TFs and miRNAs could accurately predict genome-wide gene expression. We analyzed 8895 samples across 31 cancer types from The Cancer Genome Atlas and identified 28 miRNA and 28 TF clusters using unsupervised learning. Medoids of these clusters could differentiate tissues of origin with 92.8% accuracy, demonstrating their biological relevance. We developed Tissue-Agnostic and Tissue-Aware models to predict 20,000 gene expressions using the 56 selected medoid miRNAs and TFs. The Tissue-Aware model attained an R2 of …

Leveraging Large Language Models For Knowledge-Free Weak Supervision In Clinical Natural Language Processing, Enshuo Hsu, Kirk Roberts

Faculty, Staff and Student Publications

The performance of deep learning-based natural language processing systems is based on large amounts of labeled training data which, in the clinical domain, are not easily available or affordable. Weak supervision and in-context learning offer partial solutions to this issue, particularly using large language models (LLMs), but their performance still trails traditional supervised methods with moderate amounts of gold-standard data. In particular, inferencing with LLMs is computationally heavy. We propose an approach leveraging fine-tuning LLMs and weak supervision with virtually no domain knowledge that still achieves consistently dominant performance. Using a prompt-based approach, the LLM is used to generate weakly-labeled …

Factors Driving Adolescent Tuberculosis Incidence By Age And Sex In 30 High-Tuberculosis Burden Countries: A Mathematical Modelling Study, Silvia S Chiang, Megan B Murray, Alexander W Kay, Peter J Dodd

Faculty, Staff and Students Publications

INTRODUCTION: During adolescence, tuberculosis incidence rises, with a greater increase in males compared with females. Tuberculosis notifications and estimates infrequently disaggregate adolescent age groups. Moreover, the factors that drive the increases in overall incidence and the male-to-female (MF) ratio remain unclear.

METHODS: We constructed a mechanistic model to estimate cumulative Mycobacterium tuberculosis infection and tuberculosis disease incidence in the WHO’s 30 high-tuberculosis burden countries (HBCs), which represent 86%–90% of global tuberculosis incidence. We derived infection risk from tuberculosis prevalence and assortative social mixing based on sex and age (10–14 years vs 15–19 years old). We adjusted age subgroup-specific risks of …

Learning Directed Acyclic Graphs For Ligands And Receptors Based On Spatially Resolved Transcriptomic Data Of Ovarian Cancer, Shrabanti Chowdhury, Sammy Ferri-Borgogno, Peng Yang, Wenyi Wang, Jie Peng, Samuel C Mok, Pei Wang

Faculty, Staff and Student Publications

To unravel the mechanism of immune activation and suppression within tumors, a critical step is to identify transcriptional signals governing cell-cell communication between tumor and immune/stromal cells in the tumor microenvironment. Central to this communication are interactions between secreted ligands and cell-surface receptors, creating a highly connected signaling network among cells. Recent advancements in in situ-omics profiling, particularly spatial transcriptomic (ST) technology, provide unique opportunities to directly characterize ligand-receptor signaling networks that power cell-cell communication. In this paper, we propose a novel statistical method, LRnetST, to characterize the ligand-receptor interaction networks between adjacent tumor and immune/stroma cells based on ST …

Addressing Health Disparities In Hematologic Malignancies: From Genes To Outreach, Christopher R Flowers, Rachel W Anantha, Veronica Leautaud, Pinkal Desai, Chancellor E Donald, Michelle A T Hildebrandt, Jean L Koff, Rulla M Tamimi, Wendy Cozen, Chijioke Nze, Ari M Melnick

Faculty, Staff and Student Publications

This review underscores our shared responsibility to champion multidimensional strategies rooted in basic and translational science, community involvement, and societal responsiveness for a meaningful impact. Unifying themes include the need to enhance collaborative infrastructure to engage laboratory researchers, epidemiologists, data scientists, clinicians, patients, community leaders, and policymakers; patient-level support services; outreach, education, and navigation for patients at the community level; recruitment and retention of underrepresented groups in the healthcare and research workforce; and funding for these efforts.

A Novel Sensitivity Maximization At A Given Specificity Method For Binary Classifications, Seyyed Mahmood Ghasemi, Chunhui Gu, Johannes F Fahrmann, Samir Hanash, Kim-Anh Do, James P Long, Ehsan Irajizad

Faculty, Staff and Student Publications

In the cancer early detection field, logistic regression (LR) is a frequently used approach to establish a combination rule that differentiates cancer from noncancer. However, the application of LR relies on a maximum likelihood approach, which may not yield optimal combination rules for maximizing sensitivity at a clinically desirable specificity and vice versa. In this article, we have developed an improved regression framework, sensitivity maximization at a given specificity (SMAGS), for binary classification that finds the linear decision rule, yielding the maximum sensitivity for a given specificity or the maximum specificity for a given sensitivity. We additionally expand the framework …

Leveraging Artificial Intelligence And Machine Learning To Accelerate Discovery Of Disease-Modifying Therapies In Type 1 Diabetes., Melanie R. Shapiro, Erin M. Tallon, Matthew E. Brown, Amanda L. Posgai, Mark A. Clements, Todd M. Brusko

Manuscripts, Articles, Book Chapters and Other Papers

Progress in developing therapies for the maintenance of endogenous insulin secretion in, or the prevention of, type 1 diabetes has been hindered by limited animal models, the length and cost of clinical trials, difficulties in identifying individuals who will progress faster to a clinical diagnosis of type 1 diabetes, and heterogeneous clinical responses in intervention trials. Classic placebo-controlled intervention trials often include monotherapies, broad participant populations and extended follow-up periods focused on clinical endpoints. While this approach remains the 'gold standard' of clinical research, efforts are underway to implement new approaches harnessing the power of artificial intelligence and machine learning …

Proceedings Of The National Cancer Institute Workshop On Combining Immunotherapy With Radiotherapy: Challenges And Opportunities For Clinical Translation, Zachary S Morris, Sandra Demaria, Arta M Monjazeb, Silvia C Formenti, Ralph R Weichselbaum, James Welsh, Heiko Enderling, Jonathan D Schoenfeld, Joshua D Brody, Heather M Mcgee, Michele Mondini, Michael S Kent, Kristina H Young, Lorenzo Galluzzi, Sana D Karam, Willemijn S M E Theelen, Joe Y Chang, Mai Anh Huynh, Adi Daib, Sean Pitroda, Caroline Chung, Raphael Serre, Clemens Grassberger, Jie Deng, Quaovi H Sodji, Anthony T Nguyen, Ravi B Patel, Simone Krebs, Anusha Kalbasi, Caroline Kerr, Claire Vanpouille-Box, Logan Vick, Todd A Aguilera, Irene M Ong, Fernanda Herrera, Hari Menon, Deedee Smart, Jalal Ahmed, Robyn D Gartrell, Christina L Roland, Fatemeh Fekrmandi, Binita Chakraborty, Eric H Bent, Tracy J Berg, Alan Hutson, Samir Khleif, Andrew G Sikora, Lawrence Fong

Faculty, Staff and Student Publications

Radiotherapy both promotes and antagonises tumour immune recognition. Some clinical studies show improved patient outcomes when immunotherapies are integrated with radiotherapy. Safe, greater than additive, clinical response to the combination is limited to a subset of patients, however, and how radiotherapy can best be combined with immunotherapies remains unclear. The National Cancer Institute-Immuno-Oncology Translational Network-Society for Immunotherapy of Cancer-American Association of Immunology Workshop on Combining Immunotherapy with Radiotherapy was convened to identify and prioritise opportunities and challenges for radiotherapy and immunotherapy combinations. Sessions examined the immune effects of radiation, barriers to anti-tumour immune response, previous clinical trial data, immunological and …

Difference-Makers For Collecting Sexual Orientation And Gender Identity Data In Oncology Settings, Mandi L Pratt-Chapman, Edward J Miech, Megan A Mullins, Shine Chang, Gwendolyn P Quinn, Shail Maingi, Matthew B Schabath, Charles Kamen

Faculty, Staff and Student Publications

Purpose: The purpose of this analysis was to identify key difference-making conditions that distinguish oncology institutions that collect sexual orientation and gender identity (SOGI) data across a sample of American Society of Clinical Oncology (ASCO) members.

Methods: From October to November 2020, an anonymous 54-item web-based survey was distributed to ASCO members. Coincidence analysis was used to identify difference-making conditions for the collection of SOGI data.

Results: ASCO members' responses to just three items consistently distinguished practices that reported collecting both SO and GI data (n = 25) from those who did not (n = 20): (1)."Do you ask your …

Qsp Modeling Shows Pathological Synergism Between Insulin Resistance And Amyloid-Beta Exposure In Upregulating Vcam1 Expression At The Bbb Endothelium, Zengtao Wang, Vaishnavi Veerareddy, Xiaojiao Tang, Kevin J Thompson, Sunil Krishnan, Krishna R Kalari, Karunya K Kandimalla

Faculty, Staff and Student Publications

Type 2 diabetes mellitus (T2DM), characterized by insulin resistance, is closely associated with Alzheimer's disease (AD). Cerebrovascular dysfunction is manifested in both T2DM and AD, and is often considered as a pathological link between the two diseases. Insulin signaling regulates critical functions of the blood-brain barrier (BBB), and endothelial insulin resistance could lead to BBB dysfunction, aggravating AD pathology. However, insulin signaling is intrinsically dynamic and involves interactions among numerous molecular mediators. Hence, a mechanistic systems biology model is needed to understand how insulin regulates BBB physiology and the consequences of its impairment in T2DM and AD. In this study, …

A Sample Size Analysis Of A Mathematical Model Of Longitudinal Tumor Volume And Progression-Free Survival For Bayesian Individual Dynamic Predictions In Recurrent High-Grade Glioma, Daniel J Glazar, Solmaz Sahebjam, Hsiang-Husan M Yu, Dung-Tsa Chen, Menal Bhandari, Heiko Enderling

Faculty, Staff and Student Publications

Patients with recurrent high-grade glioma (rHGG) have a poor prognosis with median progression-free survival (PFS) ofheterogenous, suggesting a clinical need for prognostic models. Bayesian data analysis can exploit individual patient follow-up imaging studies to adaptively predict the risk of progression. We propose a novel sample size analysis for Bayesian individual dynamic predictions and demonstrate proof of principle. We coupled a nonlinear mixed effects tumor growth inhibition model with a survival model. Longitudinal tumor volumes and time-to-progression were simulated for 2000 in silico rHGG patients. Bayesian individual dynamic predictions of PFS curves were evaluated using area under the receiver operating characteristic …

Robust Automated Method Of Spatial Resolution Measurement In Radiotherapy Ct Simulation Images, Pavel Govyadinov, Rick R Layman, Tucker Netherton, Raymond Mumme, Aaron K Jones, Laurence E Court, Moiz Ahmad

Faculty, Staff and Student Publications

Background: Variation in imaging protocol, patient positioning, and the presence of artifacts can vary image quality in CT images used for radiotherapy planning. Automated methods for spatial resolution (SR) estimation exist but require further investigation and validation for wider adoption.

Purpose: To validated previously existing algorithm for SR estimation and introduce improvements that make it robust to patient positioning, CT protocol, site, and artifacts.

Method: A reference algorithm based on the previous gold standard was recreated and modified to improve robustness. The algorithms were tested on three different datasets: (1) a cylindrical ACR CT QC phantom scanned using a Siemens …