Mekia Shigute Gaso

Dr. Mekia Shigute Gaso


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
14 June 2024
Verified
Conference Paper
Open access
ZSZuhra Sadriddin
Zuhra Sadriddin
RMRemudin Reshid Mekuria
Remudin Reshid Mekuria
MGMekia Shigute Gaso
Mekia Shigute Gaso
Air quality stands as a pivotal factor influencing public health and well-being, shaping urban planning strategies, health management practices, and environmental policies. Having meticulously scrutinized PM2.5 concentration data from 42 monitoring stations across Bishkek, we have employed meteorological factors, including temperature and humidity from these stations to model air quality. We have thus implemented two distinct prediction methodologies namely, Random Forest Regression (RFR) and Long Short-Term Memory (LSTM). Our findings unequivocally favored RFR as the superior predictor for PM2.5 values, achieving accuracy levels of up to 90%.

14 June 2024
Verified
Conference Paper
Open access
MGMekia Shigute Gaso
Mekia Shigute Gaso
RMRemudin Reshid Mekuria
Remudin Reshid Mekuria
AKAl Khan
Al Khan
MGMohammad Imtiyaz Gulbarga
Mohammad Imtiyaz Gulbarga
ITIskender Tologonov
Iskender Tologonov
ZSZuhra Sadriddin
Zuhra Sadriddin
Analysing dataset representing ten years (1999-2008) of clinical care at 130 US hospitals and integrated delivery networks which includes over 50 features representing patient and hospital outcomes, we have implemented various machine learning and deep learning models to achieve higher accuracy in classifying diabetic patients in order to predict the early re-admission cases. To overcome the sever challenge we have faced with class imbalance in our datasets, we have introduced SMOTE sampling technique. Having resampled our data and implemented our deep learning architecture, we have obtained an accuracy of 98%. The relatively higher performances which were obtained upon using both support vector machine and deep learning models are suggestive of implementing these algorithms in order to overcome challenges related to hospital diabetic re-admission cases in both managing the patents and preventing this devastating disease.

23 January 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
ZEZhyldyz Ermatova
Zhyldyz Ermatova
MGMekia Shigute Gaso
Mekia Shigute Gaso
Air pollution is one of the leading environmental risk factors affecting human health worldwide. Fine particulate matter (PM2.5) is considered particularly harmful due to its ability to penetrate deep into the lungs and enter the bloodstream, increasing the risk of respiratory diseases. This study aims to analyze the relationship between PM2.5 concentration and respiratory disease incidence in Kyrgyzstan using data visualization techniques. The dataset was obtained from two main sources: annual PM2.5 concentration data were collected from the World Health Organization (WHO), while respiratory disease statistics were acquired from the National Statistical Committee of the Kyrgyz Republic. The data cover the period from 1990 to 2024. After preprocessing and merging the datasets, various visualization and statistical techniques were applied using Python libraries, including Pandas, Matplotlib, and Seaborn. Trend analysis revealed a significant increase in PM2.5 levels after 2010, which coincided with a rise in respiratory disease cases. Correlation analysis showed a moderate positive relationship between PM2.5 concentration and respiratory disease incidence (r = 0.56). Regression analysis further confirmed that higher pollution levels are associated with increased numbers of respiratory disease cases. Although the correlation is not strong, the results indicate that air pollution is an important contributing factor to respiratory health outcomes. The moderate strength of the relationship may be explained by delayed health effects and the influence of additional factors such as lifestyle, seasonal infections, and healthcare access.


26 January 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
DKDastan Karygulov
Dastan Karygulov
MGMekia Shigute Gaso
Mekia Shigute Gaso
The rapid expansion of artificial intelligence (AI) technologies has led to an increasing demand for skilled professionals across various industries. Understanding job market dynamics such as salary distribution, experience requirements, employment types, and remote work opportunities is crucial for students, job seekers, educators, and policymakers. This research presents a comprehensive visual analytics study of the global AI job market using a real-world dataset consisting of approximately 15,000 job postings. The dataset includes variables such as job titles, salaries in USD, experience levels, employment types, company locations, employee residence, remote work ratios, industry sectors, and benefits scores. Building on established visual analytics practices in employment and public-health data analysis, this study applies a range of exploratory tasks used in prior research, including trend identification, comparison across categories, correlation analysis, and outlier detection. Visualization techniques such as bar charts, box plots, scatter plots, line graphs, violin plots, and heatmaps are employed to explore patterns and relationships within the data. The analysis shows that salary is strongly correlated with experience level and geographic location. Senior-level professionals earn significantly more than entry-level employees, while countries such as the United States, Switzerland, and Canada offer the highest compensation. In addition, remote and hybrid work arrangements are increasingly prevalent and, in some cases, associated with higher average salaries. The study supports career decision-making by enabling stakeholders to identify high-paying regions, realistic experience pathways, and industries with strong AI demand.

27 June 2025
Verified
Conference Paper
Closed access
MGMekia Shigute Gaso
Mekia Shigute Gaso
RMRemudin Reshid Mekuria
Remudin Reshid Mekuria
HDHaji Aman Deybasso
Haji Aman Deybasso
SCSelcuk Cankurt
Selcuk Cankurt
BSBurul Shambetova
Burul Shambetova
Esophageal cancer (EC) is a growing public health concern in Ethiopia, particularly in the Arsi Zone, Oromia. While numerous studies have identified key dietary and environmental risk factors contributing to EC, the complexity of scientific data often limits its accessibility to healthcare professionals, policy-makers, and the general public. This study emphasizes the power of data visualization in transforming epidemiological findings into intuitive, user-friendly formats that enhance understanding, support decision-making, and promote targeted interventions. By employing various visualization techniques, including grouped bar charts, heatmaps, stacked bar charts, and forest plots, this study effectively illustrates the distribution of cases and controls, highlights major risk factors, and reveals key trends in esophageal cancer prevalence. Additionally, an interactive dashboard was developed to facilitate real-time data exploration, allowing healthcare professionals and researchers to uncover patterns that aid in risk assessment and disease prevention. The findings demonstrate that data visualization serves as a critical tool in bridging the gap between complex statistical analysis and practical health applications. By making esophageal cancer risk factors more comprehensible, visualization enhances public awareness, informs clinical decision-making, and supports policymakers in designing effective preventive strategies. This study underscores the need for integrating data visualization into public health research and calls for future advancements in interactive and predictive tools to further improve cancer prevention efforts in Ethiopia and beyond.