A5058195202- Trauma and Emergency Care Studies
- Facility Location and Emergency Management
- Advanced Radiotherapy Techniques
- Cardiac Arrest and Resuscitation
- Intergenerational Family Dynamics and Caregiving
- Dementia and Cognitive Impairment Research
- Prostate Cancer Treatment and Research
- Prostate Cancer Diagnosis and Treatment
- Mobile Health and mHealth Applications
- Emergency and Acute Care Studies
- Bipolar Disorder and Treatment
- Geriatric Care and Nursing Homes
- Technology Use by Older Adults
- Health Systems, Economic Evaluations, Quality of Life
- Mental Health Research Topics
- Digital Mental Health Interventions
- Transportation and Mobility Innovations
- Tryptophan and brain disorders
- Evacuation and Crowd Dynamics
- Urban Transport and Accessibility
- Chronic Disease Management Strategies
- Cardiovascular Health and Risk Factors
- Neonatal and fetal brain pathology
- Healthcare Quality and Satisfaction
- Health Literacy and Information Accessibility
University of Ottawa
2024-2025
University of Wisconsin–Madison
2020-2025
Indiana University Bloomington
2022
University of Toronto
2014-2020
Queen's University
2017
Sunnybrook Hospital
2017
St. Michael's Hospital
2017
Public access defibrillation programs can improve survival after out-of-hospital cardiac arrest, but automated external defibrillators (AEDs) are rarely available for bystander use at the scene. Drones an emerging technology that deliver AED to scene of arrest use. We hypothesize a drone network designed with aid mathematical model combining both optimization and queuing reduce time arrival.
The purpose of this study was to automatically generate radiation therapy plans for oropharynx patients by combining knowledge-based planning (KBP) predictions with an inverse optimization (IO) pipeline.We developed two KBP approaches, the bagging query (BQ) method and generalized principal component analysis-based (gPCA) method, predict achievable dose-volume histograms (DVHs). These approaches generalize existing methods predicting physically feasible organ-at-risk (OAR) target DVHs in...
Improving Ambulance Response Times in Developing Urban Centers
Purpose: To develop and evaluate the clinical applicability of advanced machine learning models that simultaneously predict multiple optimization objective function weights from patient geometry for intensity‐modulated radiation therapy prostate cancer. Methods: A previously developed inverse method was applied retrospectively to determine optimal 315 treated patients. The authors used an overlap volume ratio (OV) bladder rectum different PTV expansions histogram slopes (OVSR OVSB bladder,...
Purpose: To determine how training set size affects the accuracy of knowledge‐based treatment planning (KBP) models. Methods: The authors selected four models from three classes KBP approaches, corresponding to distinct quantities that may predict: dose–volume histogram (DVH) points, DVH curves, and objective function weights. point prediction is done using best plan a database similar clinical plans; curve employs principal component analysis multiple linear regression; weights uses either...
We developed and evaluated a novel inverse optimization (IO) model to estimate objective function weights from clinical dose-volume histograms (DVHs). These were used solve treatment planning problem generate 'inverse plans' that had similar DVHs the original DVHs. Our methodology was applied 217 head neck cancer plans previously delivered at Princess Margaret Cancer Centre in Canada. Inverse plan compared using values, differences, frequency of criteria satisfaction. Median differences...
Problem definition: Our objective is to design a defibrillator-enabled drone network that augments the existing emergency medical services (EMS) system rapidly respond out-of-hospital cardiac arrest (OHCA). Academic/practical relevance: OHCA claims more than 400,000 lives each year in North America and one of most time-sensitive emergencies. Drone-delivered automated external defibrillators (AEDs) have potential be transformative innovation provision care for OHCA. Methodology: We develop an...
Background The impending scale up of noncommunicable disease screening programs in low- and middle-income countries coupled with limited health resources require that such be as accurate possible at identifying patients high risk. Objective aim this study was to develop machine learning–based risk stratification algorithms for diabetes hypertension are tailored the at-risk population served by community-based low-resource settings. Methods We trained tested our models using data from 2278...
Pre-hospital and emergency services in Indonesia are still developing. Despite recent improvements the Indonesian healthcare system, issues with provision of pre-hospital persist. The demand for has not been subject previous research and, therefore, fully understood. Our explored utilization medical by patients attending hospital departments Jakarta, Indonesia.The study used a cross-sectional survey design involving five general hospitals (four government-funded one private). Each patient's...
Problem definition: Behavioral health interventions, delivered through digital platforms, have the potential to significantly improve outcomes education, motivation, reminders, and outreach. We study problem of optimizing personalized interventions for patients maximize a long-term outcome, in which are costly capacity constrained. assume we access historical data set collected from an initial pilot study. Methodology/results: present new approach this that dub [Formula: see text],...
Emergency department (ED) admissions are one of the most critical decisions made in health care, with 40% ED visits resulting inpatient hospitalization for Medicare patients. A main challenge process is inability to move patients from an unit quickly. Identifying hospital discharge volume advance may be valuable helping hospitals determine capacity management mechanisms reduce boarding, such as transferring low-complexity neighboring hospitals. Although previous research has studied...
Introduction Tuberculosis (TB) is a global health emergency and low treatment adherence among patients major barrier to ending the TB epidemic. The WHO promotes digital technologies (DATs) as facilitators for improving in resource-limited settings. However, limited research has investigated whether DATs improve outcomes high-risk (ie, those with high probability of an unsuccessful outcome), leading concerns that may cause intervention-generated inequality. Methods We conducted secondary...
Artificial intelligence (AI) and operations research (OR) have long been intertwined because of their synergistic relationship. Given the increasing popularity AI machine learning in particular, we face growing demand for educational offerings this area from our students. This paper describes two courses that introduce concepts to undergraduate, predominantly industrial engineering Instead taking a methods-first approach, these use real-world applications motivate, introduce, explore...
Objective Specialty care may improve diabetic foot ulcer outcomes. Medically underserved populations receive less specialty care. We aimed to determine the association between and progression, major amputation, or death. If a beneficial is found, increasing access might help advance health equity. Research design methods retrospectively analyzed cohort of Wisconsin Illinois Medicare patients with ulcers (n = 55,409), stratified by severity (i.e., early stage, osteomyelitis, gangrene). Within...
People living with Alzheimer disease and related dementias (ADRD) require prolonged complex care that is primarily managed by informal caregivers who face significant unmet needs regarding support for communicating coordinating across their network. To address this need, we developed CareVirtue, which provides (1) the ability to invite network members; (2) a guide detailing plan; (3) journal where members can document, communicate, coordinate; (4) shared calendar; (5) vetted geolocated...
Abstract Objectives The objectives of this study are to construct the high definition phenotype (HDP), a novel time-series data structure composed both primary and derived parameters, using heterogeneous clinical sources determine whether different predictive models can utilize HDP in neonatal intensive care unit (NICU) improve mortality prediction settings. Materials Methods A total 49 parameters were collected from July 2018 May 2020 eight level-III NICUs. From 1546 patients, 757 patients...
Problem definition: Lack of patient adherence to treatment protocols is a main barrier reducing the global disease burden tuberculosis (TB). We study operational design support (TAS) platform that requires patients verify their on daily basis. Academic/practical relevance: Experimental results effectiveness TAS programs have been mixed; and rigorous research needed how structure these motivational programs, particularly in resource-limited settings. Our analysis establishes engagement can be...
Fuel is an essential commodity in society with amplified role during disasters. Disasters often cause a spike demand for fuel and impose physical operational constraints on distribution. Accordingly, public private sector stakeholders seek disaster preparedness response interventions to ensure adequate supply of emergency activities. We develop models quantify downstream flow capacity, i.e., the volume that can be distributed from bulk storage terminals retail gas stations via tanker trucks....
Childhood acute myeloid leukemia (AML) requires intensive chemotherapy, which may result in life-threatening bloodstream infections (BSIs). This study evaluated whether machine learning (ML) could predict BSI using electronic medical records. All children treated for AML at Children's Minnesota between 2005 and 2019 were included. Patients with Down syndrome or promyelocytic excluded. Standard statistics analyzed predictors of BSI, ML models trained to BSI. Of 95 patients, 54.7% had 480...
Current practice for treatment planning optimization can be both inefficient and time consuming. In this paper, we propose an automated methodology that aims to combine explorative prescriptive approaches improving the efficiency quality of process. Given a plan, our approach explores trade-offs between different objectives finds acceptable region objective function weights via inverse optimization. Intuitively, shape size these regions describe how 'sensitive' patient is perturbations in...
The initial months of the COVID-19 pandemic were marked by widespread shortages personal protective equipment (PPE) because surging demand and a fragile global supply chain. In response, many domestic suppliers pivoted to producing PPE, such as masks face shields, made possible low material costs simple designs. A key challenge that remained was lack an established marketplace for nontraditional PPE connect with healthcare facilities in need. To address this inefficiency, we launched online...