Bushra Rashrash

Ms. Bushra Rashrash


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 May 2025 in JMIR Medical Informatics
Verified
Journal Article
Open access
Suhila SawesiSuhila Sawesi
Suhila Sawesi
AJArya Jadhav
Arya Jadhav
BRBushra Rashrash
Bushra Rashrash
Background: Leptospirosis, a zoonotic disease caused by Leptospira bacteria, continues to pose significant public health risks, particularly in tropical and subtropical regions. Objective: This systematic review aimed to evaluate the application of machine learning (ML) and deep learning (DL) techniques in predicting and diagnosing leptospirosis, focusing on the most used algorithms, validation methods, data types, and performance metrics. Methods: Using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS), and Prediction model Risk of Bias Assessment Tool (PROBAST) tools, we conducted a comprehensive review of studies applying ML and DL models for leptospirosis detection and prediction, examining algorithm performance, data sources, and validation approaches. Results: Out of a total of 374 articles screened, 17 studies were included in the qualitative synthesis, representing approximately 4.5% of the initial pool. The review identified frequent use of algorithms such as support vector machines, artificial neural networks, decision trees, and convolutional neural networks (CNNs). Among the included studies, 88% (15/17) used traditional ML methods, and 24% (4/17) used DL techniques. Several models demonstrated high predictive performance, with reported accuracy rates ranging from 80% to 98%, notably with the U-Net CNN achieving 98.02% accuracy. However, public datasets were underused, with only 35% (6/17) of studies incorporating publicly available data sources; the majority (65%, 11/17) relied primarily on private datasets from hospitals, clinical records, or regional surveillance systems. Conclusions: ML and DL techniques demonstrate potential for improving leptospirosis prediction and diagnosis, but future research should focus on using larger, more diverse datasets, adopting transfer learning strategies, and integrating advanced ensemble and validation techniques to strengthen model accuracy and generalization.

5 September 2024 in Sustainability
Verified
Journal Article
Open access
PDF file
Elena LioubimtsevaElena Lioubimtseva
Elena Lioubimtseva
HZHannah Zylman
Hannah Zylman
KCKatherine Carron
Katherine Carron
KPKaytlin Marie Poynter
Kaytlin Marie Poynter
BRBushra Rashrash
Bushra Rashrash
Community engagement in climate action and adaptation planning is an essential prerequisite for overcoming existing and projected environmental injustices associated with the negative impacts of climate change. The diversity and inclusion of stakeholders are crucial for addressing equity in both the development and implementation of local climate plans. Our study attempts to evaluate and compare consideration of equity in climate action and climate adaptation plans of Michigan cities and its association with the diversity of stakeholders involved in the planning process. Data analysis is based on the content of eight municipal climate action and/or climate adaptation plans, related documents, and interviews with city planners along with community activists. Data derived from the climate action and adaptation plans were also compared to the strategies outlined in the Tribal Climate Adaptation Menu, which integrates climate science and indigenous knowledge. The study concludes that municipalities that engage more diverse groups of stakeholders appear to be more attentive to social equity and more likely to offer specific climate action and adaptation measures focusing on vulnerable groups. The integration of indigenous knowledge could provide valuable insights for municipalities through collaboration with tribal communities and climate adaptation experts.

15 July 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Elena LioubimtsevaElena Lioubimtseva
Elena Lioubimtseva
HZHannah Zylman
Hannah Zylman
KCKatherine Carron
Katherine Carron
KPKaytlin Marie Poynter
Kaytlin Marie Poynter
BRBushra Rashrash
Bushra Rashrash
Community engagement in climate action and adaptation planning is an essential prerequisite for overcoming existing and projected environmental injustices associated with the negative impacts of climate change. Diversity and inclusion of stakeholders are crucial for addressing equity both in the development and implementation of local climate plans. Our study attempts to evaluate and compare consideration of equity in climate action and climate adaptation plans of Michigan cities and its association with a diversity of stakeholders involved in the planning process. Data analysis is based on the content of eight municipal climate action and/or climate adaptation plans, related documents, and interviews with city planners along with community activists. Data derived from climate action and adaptation plans were also compared to the strategies outlined in the Tribal Climate Adaptation Menu, which integrates climate science and indigenous knowledge. The study concludes that municipalities that engage more diverse groups of stakeholders appear to be more attentive to social equity and more likely to offer specific climate action and adaptation measures focusing on vulnerable groups. Integration of indigenous knowledge could provide valuable insights for municipalities through collaboration with tribal communities and climate adaptation experts.

27 October 2026 in International Medical Education
Verified
Journal Article
Open access
PDF file
Suhila SawesiSuhila Sawesi
Suhila Sawesi
DDDiane M Dolezel
Diane M Dolezel
MSMohamed Ihab Soltana
Mohamed Ihab Soltana
PPPranitha Presingu
Pranitha Presingu
BRBushra Rashrash
Bushra Rashrash
AAAlyssa Adamczak
Alyssa Adamczak
This systematic review examined virtual reality (VR) interventions in higher and health professions education and their alignment with the AMIA foundational domains underpinning CAHIIM accreditation to inform competency-based health informatics (HI) virtual placements. Following PRISMA 2020 (PROSPERO CRD420251009479), four databases were searched for English-language empirical studies published from 1 January 2011 to 1 October 2026; studies were appraised with JBI checklists and synthesized narratively following SWiM. A total of 323 studies were included, most quasi-experimental (48.0%), fully immersive (39.9%), guided (70.9%), and assessed only immediately after the intervention (75.9%). In the primary analysis (directly assessed and transferable mappings), coverage concentrated in decision-making (33.4%) and workflow analysis (24.1%), with computational reasoning (21.4%), communication/teamwork (20.1%), data interpretation (13.9%), systems thinking (1.9%), and privacy/security (0.6%) less common, and excluding spatial, motor, and procedural analogs left little of the computational-reasoning coverage. Only one study enrolled HI learners, none simulated an operational informatics setting, and five reports could not be retrieved, so the coverage estimates are conditional on the retrieved corpus. Transferable VR evidence therefore concentrates in cognitive competencies and is near-absent for governance competencies; the findings identify candidate instructional relevance rather than demonstrated effectiveness, and the proposed design requirements for HI virtual placements are a hypothesis-generating model derived from, not demonstrated by, the review.