Morteza Maleki

Mr. Morteza Maleki

Industrial Systems and Engineering, Georgia Institute of Technology, Atlanta, Georgia, USA
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
Morteza MalekiMorteza Maleki
Morteza Maleki
MBMohsen Bahrami
Mohsen Bahrami
Monica MenendezMonica Menendez
Monica Menendez
JBJose Balsa-Barreiro
Jose Balsa-Barreiro
Since its emergence, COVID-19 has caused a great impact in health and social terms. Governments and health authorities have attempted to minimize this impact by enforcing different mandates. Recent studies have addressed the relationship between various socioeconomic variables and compliance level to these interventions. However, little attention has been paid to what constitutes people’s response and whether people behave differently when faced with different interventions. Data collected from different sources show very significant regional differences across the United States. In this paper, we attempt to shed light on the fact that a response may be different depending on the health system capacity and each individuals’ social status. For that, we analyze the correlation between different societal (i.e., education, income levels, population density, etc.) and healthcare capacity-related variables (i.e., hospital occupancy rates, percentage of essential workers, etc.) in relation to people’s level of compliance with three main governmental mandates in the United States: mobility restrictions, mask adoption, and vaccine participation. Our aim was to isolate the most influential variables impacting behavior in response to these policies. We found that there was a significant relationship between individuals’ educational levels and political preferences with respect to compliance with each of these mandates.

23 July 2024 in Healthcare
Verified
Journal Article
Open access
PDF file
Morteza MalekiMorteza Maleki
Morteza Maleki
Seyed Ali GhahariSeyed Ali Ghahari
Seyed Ali Ghahari
This study employs comprehensive clustering analysis to examine COVID-19 vaccine hesitancy and related socio-demographic factors across U.S. counties, using the collected and curated data from Johns Hopkins University. Utilizing K-Means and hierarchical clustering, we identify five distinct clusters characterized by varying levels of vaccine hesitancy, MMR vaccination coverage, population demographics, and political affiliations. Principal Component Analysis (PCA) was conducted to reduce dimensionality, and key variables were selected based on their contribution to cumulative explained variance. Our analysis reveals significant geographic and demographic patterns in vaccine hesitancy, providing valuable insights for public health strategies and future pandemic responses. Geospatial analysis highlights the distribution of clusters across the United States, indicating areas with high and low vaccine hesitancy. In addition, multiple regression analyses within each cluster identify key predictors of vaccine hesitancy in corresponding U.S. county clusters, emphasizing the importance of socio-economic and demographic factors. The findings underscore the need for targeted public health interventions and tailored communication strategies to address vaccine hesitancy across the United States and, potentially, across the globe.

20 October 2022 in Preprints.org
Verified
Preprint
Open access
PDF file
Morteza MalekiMorteza Maleki
Morteza Maleki
MBMohsen Bahrami
Mohsen Bahrami
Monica MenendezMonica Menendez
Monica Menendez
JBJose Balsa-Barreiro
Jose Balsa-Barreiro
Since its emergence, COVID-19 has caused a great impact in health and social terms. Governments and health authorities have attempted to minimize this impact by enforcing different mandates. Recent studies have addressed the relationship between various socioeconomic variables and compliance level to these interventions. However, little attention has been paid to what constitutes people's response and whether people behave differently when faced with different interventions. Data collected from different sources show very significant regional differences across the United States. In this paper, we attempted to shed light on the fact that a response may be different depending on the health system capacity and each individuals’ social status. For that, we analyzed the correlation between different societal variables (i.e. education, income levels, population density, etc.) along with healthcare capacity related variables (i.e. hospital occupancy rates, percentage of essential workers, etc.) with regards to people's level of compliance with three main governmental mandates in the United States: mobility restrictions, mask adoption, and vaccine participation. Our aim was to isolate the most influential variables impacting behavior in response to these policies. We found that there was a strong relationship between individuals' educational levels and political preferences with respect to compliance with each of these mandates.

1 September 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Morteza MalekiMorteza Maleki
Morteza Maleki
SGSeyedAli Ghahari
SeyedAli Ghahari
Multimodal generative artificial intelligence (AI) has emerged as a transformative technology in clinical diagnostics, integrating diverse data sources—medical imaging, genomic profiles, clinical narratives, and electronic health records—to significantly enhance diagnostic accuracy, clinical decision-making, and personalized patient care. This review systematically explores the landscape of multimodal AI across key medical specialties, including radiology, pathology, dermatology, ophthalmology, neurology, and oncology, highlighting recent methodological advancements, performance evaluations, and practical clinical implementations. Technical strategies such as tool-use, grafting, and unified multimodal architectures are critically assessed, identifying their strengths and limitations concerning clinical applicability, interpretability, and computational efficiency. Synthetic multimodal data generation methodologies—Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), diffusion models, and large language models (LLMs)—are evaluated for addressing data scarcity in rare disease research, enhancing international collaboration, and mitigating privacy concerns. Additionally, this review addresses pivotal ethical, regulatory, and liability challenges, emphasizing fairness, transparency, and accountability in AI-driven clinical diagnostics. Strategic priorities for future research are identified, including rigorous prospective clinical validation, development of standardized multimodal datasets, enhanced model interpretability, and robust regulatory frameworks. Ultimately, realizing the transformative potential of multimodal generative AI in clinical practice will require interdisciplinary collaboration among clinicians, researchers, ethicists, regulators, and patient advocacy groups, ensuring these powerful tools effectively augment human expertise, improve healthcare delivery, and advance precision medicine.

1 January 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
PDF file
Morteza MalekiMorteza Maleki
Morteza Maleki
This paper introduces an innovative neighborhood search recommendation tool designed to aid individuals in making informed residential choices based on a variety of socio-economic and demographic indicators. While initially developed to assist homebuyers in selecting neighborhoods that align with their personal and familial needs, this tool's utility extends significantly into the healthcare sector. By incorporating healthcare-related attributes such as proximity to medical facilities, availability of health services, and environmental quality, the tool offers a unique approach to enhancing healthcare accessibility and improving public health outcomes. Utilizing dynamic visualization techniques and interactive web-based maps, the tool allows users to prioritize and visualize these attributes effectively. Our methodology integrates diverse datasets, applying sophisticated data processing techniques to ensure comprehensive and unbiased recommendations. The potential of this tool to influence healthcare decisions and policy-making by identifying optimal residential locations for health-centric living is profound. This paper discusses the application, methodology, results, and future implications of extending the use of our neighborhood search recommendation tool into the healthcare domain, aiming to support healthier community planning and resource allocation.

3 September 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Morteza MalekiMorteza Maleki
Morteza Maleki
SGSeyed Ali Ghahari
Seyed Ali Ghahari
We report the selective activation and transformation of unsaturated amides and esters at multinuclear osmium carbonyl clusters and clarify how these symmetry-enabled, cooperative reactions inform pharmaceutical synthesis. Treatment of the activated triosmium complex Os3(CO)10(NCCH3)2 with N,N-dimethylacrylamide (DMA) or methylacrylate (MA) furnishes eight structurally characterized products spanning Os2, Os3, Os4, Os5, and Os6 nuclearities. Single-crystal X-ray diffraction, IR, NMR, and MS data establish (i) β-C–H activation of the alkene unit to give bridg- ing μ-alkenyl/μ-hydride motifs, (ii) substrate–substrate coupling on the cluster to form a chelated DMA–DMA dimer, and (iii) carbonylation/decarbonylation events that reorganize Os–Os connectivity. The key intermediate HOs3(CO)10(μ-acryloyl) maps a stepwise sequence in which two or more metal centers share bond-making/bond-breaking—an intrinsic “symmetrical catalysis" element arising from the defined Os–Os edges. Solvent governs pathway selection: noncoordinating, higher-boiling media (e.g., heptane) favor direct C–H activation and dimerization, whereas CH2Cl2 enables gentler transformations that preserve cluster integrity and access higher nuclearities. Although the ransformations are stoichiometric, they recapitulate catalytic elementary steps central to late-stage functionalization and feedstock upgrading—concerted C–H cleavage, migratory insertion of CO, and controlled C–C coupling—and thus offer design rules for bimetallic/cluster catalysts targeting drug-like motifs (enamides, dienamides, and 1,4-dicarbonyl frameworks). By linking structure, mechanism, and chemoselectivity across a family of symmetric Os clusters, this work provides a mechanistic platform for translating cooperative multimetal activation into future catalytic processes relevant to API synthesis and process intensification.