Browsing by Author "Martin, Thomas"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- FPGA-Based Accelerator Development for Non-EngineersUliana, David Christopher (Virginia Tech, 2014-04-15)In today's world of big-data computing, access to massive, complex data sets has reached an unprecedented level, and the task of intelligently processing such data into useful information has become a growing concern to the high-performance computing community. However, domain experts, who are the brains behind this processing, typically lack the skills required to build FPGA-based hardware accelerators ideal for their applications, as traditional development flows targeting such hardware require digital design expertise. This work proposes a usable, end-to-end accelerator development methodology that attempts to bridge this gap between domain-experts and the vast computational capacity of FPGA-based heterogeneous platforms. To accomplish this, two development flows were assembled, both targeting the Convey Hybrid-Core HC-1 heterogeneous platform and utilizing existing graphical design environments for design entry. Furthermore, incremental implementation techniques were applied to one of the flows to accelerate bitstream compilation, improving design productivity. The efficacy of these flows in extending FPGA-based acceleration to non-engineers in the life sciences was informally tested at two separate instances of an NSF-funded summer workshop, organized and hosted by the Virginia Bioinformatics Institute at Virginia Tech. In both workshops, groups of four or five non-engineer participants made significant modifications to a bare-bones Smith-Waterman accelerator, extending functionality and improving performance.
- Inclusion of Clinicians in the Development and Evaluation of Clinical Artificial Intelligence Tools: A Systematic Literature ReviewJesso, Stephanie Tulk; Kelliher, Aisling; Sanghavi, Harsh; Martin, Thomas; Parker, Sarah H. (Frontiers, 2022-04-07)The application of machine learning (ML) and artificial intelligence (AI) in healthcare domains has received much attention in recent years, yet significant questions remain about how these new tools integrate into frontline user workflow, and how their design will impact implementation. Lack of acceptance among clinicians is a major barrier to the translation of healthcare innovations into clinical practice. In this systematic review, we examine when and how clinicians are consulted about their needs and desires for clinical AI tools. Forty-five articles met criteria for inclusion, of which 24 were considered design studies. The design studies used a variety of methods to solicit and gather user feedback, with interviews, surveys, and user evaluations. Our findings show that tool designers consult clinicians at various but inconsistent points during the design process, and most typically at later stages in the design cycle (82%, 19/24 design studies). We also observed a smaller amount of studies adopting a human-centered approach and where clinician input was solicited throughout the design process (22%, 5/24). A third (15/45) of all studies reported on clinician trust in clinical AI algorithms and tools. The surveyed articles did not universally report validation against the “gold standard” of clinical expertise or provide detailed descriptions of the algorithms or computational methods used in their work. To realize the full potential of AI tools within healthcare settings, our review suggests there are opportunities to more thoroughly integrate frontline users’ needs and feedback in the design process.
- The peripheral neutrophils in subjects with COPD-OSA overlap syndrome and severe comorbidities: A feasible inflammatory biomarker?Macrea, Madallna; Campbell, Sabrina; Martin, Thomas; Oursler, Kris Ann (2018-12)Background. Overlap syndrome (OS) describes the association of obstructive sleep apnea (OSA) and chronic obstructive pulmonary disease (COPD) in a single individual. Subjects with OS have increased cardiovascular mortality which is presumed to be inflammation-mediated. As a clinical biomarker, an increased neutrophil count correlates with the severity of coronary artery stenosis. Objectives. As little is known about the role of neutrophils in the underlying inflammatory mechanisms in OS, we aimed to assess the percentage of peripheral neutrophils (PPN) in OS vs in COPD alone. Material and methods. A cross-sectional study of patients with COPD and severe comorbidities, as defined by a Care Assessment Need score over 95, were seen in the Pulmonary Tele-Health Clinic at the Salem Veteran Affairs Medical Center, USA, over a 1-year period. Demographic and polysomnographic data, FEV1 and the Charlson Comorbidity Index (CCI) were extracted from the Electronic Medical Records. Obstructive sleep apnea was defined according to the American Academy of Sleep Medicine (AASM) guidelines. Serum inflammatory markers (PPN, CRP, fibrinogen and procalcitonin) were obtained after the Tele-Health appointment. Results. Out of the 38 subjects with COPD, 17 (44%) had OS. Compliance with continuous positive airway pressure therapy (CPAP) was excellent in 7 OS subjects (41%). There was a significant difference in the PPN of subjects with OS vs COPD alone, regardless of whether they were compliant (p = 0.03) with the CPAP therapy or not (p = 0.005). No differences in the severity of COPD, baseline comorbidity, smoking, or inflammatory markers were found between the OS and COPD-only subjects. Body mass index (BMI), COPD severity, smoking, and home oxygen therapy (HOT) use were not associated with PPN (p > 0.2). Conclusions. Overlap syndrome subjects have higher PPN than those with COPD alone, regardless of their CPAP compliance. Our results could be used to motivate OS subjects to improve their lifestyles and to comply with drug therapies aimed at reducing cardiovascular disease (CVD).
- Reimagining medical workspaces through on-site observations and bodystormingIshida, Aki; Martin, Thomas; Gracanin, Denis; Franusich, David; Buck, Carl; Parker, Sarah H.; Knapp, R. Benjamin; Haley, Vince; Zagarese, Vivian; Tasooji, Reza (2023-01)Clinicians in acute care hospitals experience highly stressful situations daily. They work long, variable hours, complete complex technical tasks, and must also be emotionally engaged with patients and families to meet the caring demands of this profession, which can lead to burnout. In response to these challenges, a multi-disciplinary team from Virginia Tech collaborated with Steelcase to study the impact of medical workspaces on the clinician experience and how those workspaces could be improved to reduce some of the sources of burnout. The team sought to identify conditions that could either aid or hinder clinician workflow and affect burnout rate, then based on interviews and in-situ ethnographic studies, generated design concepts for nurse stations, both centralized and mobile. Using digital and physical full-scale prototypes, we enacted clinical care scenarios to seek feedback and reflect on the design.