Automated Cognitive Load Assessment Toward Medical Staff Training and Evaluation 

Lead Faculty: Dr. Scott Pappada and Dr. Thomas Papadimos

ACLAMATE is a tool for measuring knowledge, performance and skill acquired during medical simulation. More specifically, it is data collection, assessment, and alerting tool which provides unobtrusive and real-time assessments of learner states so that instructors can identify areas where improvement is needed and improve upon training scenarios and simulation based curricula. Leveraging data from portable neurophysiological monitors, ACLAMATE generates real-time assessments of cognitive workload and stress for individuals/teams during medical simulation-based training. University of Toledo is leading a study to evaluate and validate the utility of ACLAMATE through pilot study (i.e. simulation-based training of healthcare teams during surgical emergencies).


Application of Synthetic Assistant Technology for Improved First Responder Performance 

Lead Faculty: Dr. Thomas Papadimos and Dr. Ahmad Javaid

The project exploits hardware and software based synthetic assistant technology in the context of first responders. For example, the proposed voice-based synthetic assistant will continuously monitor emergency treatment processes in real time and warn medics and trainees against committing mistakes and violating protocols. Key features of the proposed system include continuous monitoring; prompting humans in executing a task based on audio, sensory, and visual data; logging progress of tasks and results; and generating statistics (e.g. success rate of a responder in performing a task such as hemorrhage). The project envisions developing a common language in which to code all processes.


Computer Aided Data-driven Retrospective Analysis for Improved Kidney Donor Match 

Lead Faculty: Dr. Michael Rees and Dr. Robert Green

More than 650,000 patients per year in the United States (and an estimated 2 million patients worldwide) are affected by end stage renal disease. Of the 650,000 patients, 415,000 patients require weekly dialysis. Kidney transplantation is the most definitive therapy for these patients, and its outcomes are highly correlated with effective kidney donor matching. This project aims to leverage machine learning and statistical methods, historical data, and medical know-how, to develop a software package that facilitates retrospective analysis and predictive transplant risk score for kidney donor matching. The overarching goal of this project is to extend longevity of organ recipients.


Development of a New ‘ICU of the Future’ Clinical Decision Support System Framework 

Lead Faculty: Dr. Scott Pappada and Dr. Thomas Papadimos

The framework will be designed to include a set of integrated and interoperable CDSS technologies to inform, monitor, and guide patient treatment on an organ system specific basis. The framework will include a set of integrated and interoperable intelligent data visualization features as well as CDSSs that offer real-time patient monitoring, assessment, and data-driven recommendations. Alerts and treatment recommendations generated by the ICUOTF’s CDSSs are derived by models (e.g. machine learning). The models are capable of predicting future EMR data changes and classifying patient status. Other features include patient-specific checklist and summary reporting tool for improved decision-making during ICU rounds.


Development of an Intelligent and Directed Antibiotic Decision Support System (IDADSS) 
Lead Faculty: Dr. Scott Pappada and Dr. Thomas Papadimos

The primary objective of this research project is the development of an Intelligent and Directed Antibiotic Decision Support System (IDADSS) to assist and guide in the optimization of preventive and directive antibiotic therapy for “healthcare providers” who do not have sufficient expertise in infectious disease management and pharmacy. IDADSS, currently being designed and developed, includes artificial neural network or ANN models trained to accurately predict patient outcomes (e.g. length of stay, mortality, and hospital readmission). At the higher level, rule-based logic is applied to ANN outputs for mapping and optimizing appropriate antibiotics and dosing regimens, toward significantly improving patient outcomes.


Internet Integrated Anesthesia Residency Achievement Tracking based on Virtual Badges 

Lead Faculty: Dr. Jason Stroud and Dr. Vijay Devabhaktuni

This project entails development of a web-based education management program for tracking the educational achievements and activities of anesthesia residents on UToledo health science campus. Starting by determining input data, the objective is to convert such data into standardized electronic format and then design basic software for aggregating data. The proposed output format includes badges and a dashboard. Features include a user-friendly interface (i.e. dashboard) for both the learner and the instructor to track progress of residents as well as to aggregate all educational activities (e.g. conference attendance, case logs, presentation evaluations, publications, and certifications) into a unified electronic hub.


Pain Mitigation Study by Localized Nerve Stimulation based on Various Physical Processes 

Lead Faculty: Dr. Joseph Atallah and Dr. Daniel Georgiev

Spinal cord stimulation for treatment of pain continues to attract significant interest. Pain relief implant devices based on sound and vibration stimulation have become available. There is, however, significant room for improvement and optimization of the stimulation processes, since the understanding of the role of different physical mechanisms in the stimulation process is limited. For example, recent studies have shown that 10 KHz stimulation is superior to traditional low-frequency approach. This project aims to study different stimulation mechanisms (e.g. heat, light, sound, and vibration) as a function of relevant parameters (e.g. sound stimulation vs. frequency) toward better understanding nerve stimulation.


Toledo Area Regional Transit Authority Bus Redesign for Mobile Clinical Simulation 

Lead Faculty: Dr. Thomas Papadimos and Dr. Vijay Devabhaktuni

The objective is to convert a TARTA bus (i.e. a public transport vehicle) into an advanced mobile clinical simulation station comprising of a human patient simulator; medical gear; and control & debrief rooms. The redesigned bus allows medical students and trainees to simulate treatment on a mannequin, while the control & debrief rooms are utilized for debriefing of possible problems and treatments from simulation. Tasks include 2D computer aided design of the bus interior, skeletal models, and redesigned models. Additional goals include identification of electrical systems for the bus (e.g. communications, displays, and generators) and electrical wiring and installation designs.


Last Updated: 2/27/20