Search

Your search keyword '"Mensah, Daniel Opoku"' showing total 12 results
Start Over Author "Mensah, Daniel Opoku"
12 results on '"Mensah, Daniel Opoku"'

1. Robustness Analysis of Deep Learning Models for Population Synthesis

Author

Mensah, Daniel Opoku, Badu-Marfo, Godwin, and Farooq, Bilal

Subjects
Computer Science - Machine Learning
Abstract

Deep generative models have become useful for synthetic data generation, particularly population synthesis. The models implicitly learn the probability distribution of a dataset and can draw samples from a distribution. Several models have been proposed, but their performance is only tested on a single cross-sectional sample. The implementation of population synthesis on single datasets is seen as a drawback that needs further studies to explore the robustness of the models on multiple datasets. While comparing with the real data can increase trust and interpretability of the models, techniques to evaluate deep generative models' robustness for population synthesis remain underexplored. In this study, we present bootstrap confidence interval for the deep generative models, an approach that computes efficient confidence intervals for mean errors predictions to evaluate the robustness of the models to multiple datasets. Specifically, we adopt the tabular-based Composite Travel Generative Adversarial Network (CTGAN) and Variational Autoencoder (VAE), to estimate the distribution of the population, by generating agents that have tabular data using several samples over time from the same study area. The models are implemented on multiple travel diaries of Montreal Origin- Destination Survey of 2008, 2013, and 2018 and compare the predictive performance under varying sample sizes from multiple surveys. Results show that the predictive errors of CTGAN have narrower confidence intervals indicating its robustness to multiple datasets of the varying sample sizes when compared to VAE. Again, the evaluation of model robustness against varying sample size shows a minimal decrease in model performance with decrease in sample size. This study directly supports agent-based modelling by enabling finer synthetic generation of populations in a reliable environment., Comment: arXiv admin note: text overlap with arXiv:2203.03489, arXiv:1909.07689 by other authors

Published
2022

2. eFedDNN: Ensemble based Federated Deep Neural Networks for Trajectory Mode Inference

Author

Mensah, Daniel Opoku, Badu-Marfo, Godwin, Mallah, Ranwa Al, and Farooq, Bilal

Subjects
Computer Science - Machine Learning
Abstract

As the most significant data source in smart mobility systems, GPS trajectories can help identify user travel mode. However, these GPS datasets may contain users' private information (e.g., home location), preventing many users from sharing their private information with a third party. Hence, identifying travel modes while protecting users' privacy is a significant issue. To address this challenge, we use federated learning (FL), a privacy-preserving machine learning technique that aims at collaboratively training a robust global model by accessing users' locally trained models but not their raw data. Specifically, we designed a novel ensemble-based Federated Deep Neural Network (eFedDNN). The ensemble method combines the outputs of the different models learned via FL by the users and shows an accuracy that surpasses comparable models reported in the literature. Extensive experimental studies on a real-world open-access dataset from Montreal demonstrate that the proposed inference model can achieve accurate identification of users' mode of travel without compromising privacy.

Published
2022

3. The epidemiology and drivers of healthy, sustainable diets in Sub-Saharan Africa

Author

Mensah, Daniel Opoku

Subjects
GT Manners and customs, RA Public aspects of medicine
Abstract

Background: The food environment in sub-Saharan Africa (SSA) has transformed rapidly in recent decades to increase the availability of unhealthy food options. Dietary changes are significantly contributing to adverse environmental impacts and a rapidly increasing burden of obesity and diet-related noncommunicable diseases (NCDs) co-existing with unresolved undernutrition and communicable disease prevalence. Trends in the consumption of foods, the characteristics of the prevailing food environment, and how individuals interact with their food environment to contribute to the double malnutrition burden in SSA are less understood. The aims of this PhD were to examine secular trends in consumption of food groups important for health in SSA; examine the food environment characteristics in a case study elite urban community in Ghana; investigate how residents of the urban community interact with their food environment to shape dietary behaviours; and explore their willingness and attitudes towards the adoption of healthy and sustainable diets. Methods: A mixed methods approach was adopted as follows: (1) evidence synthesis of literature reporting meat, fruit, and vegetable (MFV) consumption in SSA and (2) of literature reporting ultra-processed foods consumption in SSA; (3) Geographic Information Systems (GIS) tools were used to collect data on the characteristics of the food environment within University of Ghana campus including the location, count, and distribution of food outlets. An adapted food classification tool was utilized to categorise outlets as NCD-health, NCD-intermediate or NCD-unhealthy; and (4) qualitative focus group discussions (FGDs) and dyadic interviews with best friend pairs (or best friend pair interviews-BFPIs) were used to collect students' perspectives of their interaction with their food environment and how it impacts their dietary practices. The FGDs and BFPIs also gathered students' attitudes to dietary change in relation to health and environmental sustainability. Results: Study components 1 and 2 highlighted that MFV consumption has seen upward trends in SSA populations over the last 38-year period between 1977 and 2015, although fruit and vegetable consumption remain significantly below WHO recommendations. Richer SSA countries are consuming more meat (ß =36.76, p=0.04) and vegetable (ß =43.49, p=0.00) than poorer countries. Further, it suggested that ultra-processed foods (UPFs) consumption in SSA populations has gone up and highlighted key gaps in the UPFs consumption literature in SSA. Urban residents and females appeared to be consuming more UPFs than rural dwellers and males. Study 3 showed that the characteristics of the food environment is suggestive of an obesogenic one, dominated by more NCD-unhealthy than NCD-healthy food-outlets (50.72% vs 39.86%). Food outlets were unevenly distributed over the university foodscape, with more NCD-unhealthy outlets clustering closer to residential than departmental buildings. This difference was statistically significant for food outlets within 100-meter buffer (p=0.00) of residential structures and those within 100 and 500 meters from departmental buildings/lecture halls (p=0.05 and p=0.00, respectively). Study component 4 (n=46) identified a complex interplay of individual and social level factors interacting with food environment characteristics to shape dietary behaviours. Conclusion: The findings of this thesis provide detailed understanding of trends in consumption of food groups important for health and the environmental sustainability in Sub-Saharan Africa. It also provides in-depth understanding of how young adults interact with their food environment and how the food environment influences dietary behaviours, which could be used to inform context and culturally specific interventions.

Published
2021

11. The epidemiology and drivers of healthy, sustainable diets in Sub-Saharan Africa

Author

Mensah, Daniel Opoku

Subjects
GT, RA
Abstract

Background: The food environment in sub-Saharan Africa (SSA) has transformed rapidly in recent decades to increase the availability of unhealthy food options. Dietary changes are significantly contributing to adverse environmental impacts and a rapidly increasing burden of obesity and diet-related noncommunicable diseases (NCDs) co-existing with unresolved undernutrition and communicable disease prevalence. Trends in the consumption of foods, the characteristics of the prevailing food environment, and how individuals interact with their food environment to contribute to the double malnutrition burden in SSA are less understood. The aims of this PhD were to examine secular trends in consumption of food groups important for health in SSA; examine the food environment characteristics in a case study elite urban community in Ghana; investigate how residents of the urban community interact with their food environment to shape dietary behaviours; and explore their willingness and attitudes towards the adoption of healthy and sustainable diets. \ud \ud Methods: A mixed methods approach was adopted as follows: (1) evidence synthesis of literature reporting meat, fruit, and vegetable (MFV) consumption in SSA and (2) of literature reporting ultra-processed foods consumption in SSA; (3) Geographic Information Systems (GIS) tools were used to collect data on the characteristics of the food environment within University of Ghana campus including the location, count, and distribution of food outlets. An adapted food classification tool was utilized to categorise outlets as NCD-health, NCD-intermediate or NCD-unhealthy; and (4) qualitative focus group discussions (FGDs) and dyadic interviews with best friend pairs (or best friend pair interviews-BFPIs) were used to collect students’ perspectives of their interaction with their food environment and how it impacts their dietary practices. The FGDs and BFPIs also gathered students’ attitudes to dietary change in relation to health and environmental sustainability. \ud \ud Results: Study components 1 and 2 highlighted that MFV consumption has seen upward trends in SSA populations over the last 38-year period between 1977 and 2015, although fruit and vegetable consumption remain significantly below WHO recommendations. Richer SSA countries are consuming more meat (ß =36.76, p=0.04) and vegetable (ß =43.49, p=0.00) than poorer countries. Further, it suggested that ultra-processed foods (UPFs) consumption in SSA populations has gone up and highlighted key gaps in the UPFs consumption literature in SSA. Urban residents and females appeared to be consuming more UPFs than rural dwellers and males. Study 3 showed that the characteristics of the food environment is suggestive of an obesogenic one, dominated by more NCD-unhealthy than NCD-healthy food-outlets (50.72% vs 39.86%). Food outlets were unevenly distributed over the university foodscape, with more NCD-unhealthy outlets clustering closer to residential than departmental buildings. This difference was statistically significant for food outlets within 100-meter buffer (p=0.00) of residential structures and those within 100 and 500 meters from departmental buildings/lecture halls (p=0.05 and p=0.00, respectively). Study component 4 (n=46) identified a complex interplay of individual and social level factors interacting with food environment characteristics to shape dietary behaviours. \ud \ud Conclusion: The findings of this thesis provide detailed understanding of trends in consumption of food groups important for health and the environmental sustainability in Sub-Saharan Africa. It also provides in-depth understanding of how young adults interact with their food environment and how the food environment influences dietary behaviours, which could be used to inform context and culturally specific interventions.\ud

12. Health Care Professionals' Experience of Using AI: Systematic Review With Narrative Synthesis.

Author

Ayorinde A, Mensah DO, Walsh J, Ghosh I, Ibrahim SA, Hogg J, Peek N, and Griffiths F

Subjects
Humans, Decision Support Systems, Clinical, Clinical Decision-Making methods, Artificial Intelligence, Health Personnel psychology
Abstract

Background: There has been a substantial increase in the development of artificial intelligence (AI) tools for clinical decision support. Historically, these were mostly knowledge-based systems, but recent advances include non-knowledge-based systems using some form of machine learning. The ability of health care professionals to trust technology and understand how it benefits patients or improves care delivery is known to be important for their adoption of that technology. For non-knowledge-based AI tools for clinical decision support, these issues are poorly understood., Objective: The aim of this study is to qualitatively synthesize evidence on the experiences of health care professionals in routinely using non-knowledge-based AI tools to support their clinical decision-making., Methods: In June 2023, we searched 4 electronic databases, MEDLINE, Embase, CINAHL, and Web of Science, with no language or date limit. We also contacted relevant experts and searched reference lists of the included studies. We included studies of any design that reported the experiences of health care professionals using non-knowledge-based systems for clinical decision support in their work settings. We completed double independent quality assessment for all included studies using the Mixed Methods Appraisal Tool. We used a theoretically informed thematic approach to synthesize the findings., Results: After screening 7552 titles and 182 full-text articles, we included 25 studies conducted in 9 different countries. Most of the included studies were qualitative (n=13), and the remaining were quantitative (n=9) and mixed methods (n=3). Overall, we identified 7 themes: health care professionals' understanding of AI applications, level of trust and confidence in AI tools, judging the value added by AI, data availability and limitations of AI, time and competing priorities, concern about governance, and collaboration to facilitate the implementation and use of AI. The most frequently occurring are the first 3 themes. For example, many studies reported that health care professionals were concerned about not understanding the AI outputs or the rationale behind them. There were issues with confidence in the accuracy of the AI applications and their recommendations. Some health care professionals believed that AI provided added value and improved decision-making, and some reported that it only served as a confirmation of their clinical judgment, while others did not find it useful at all., Conclusions: Our review identified several important issues documented in various studies on health care professionals' use of AI tools in real-world health care settings. Opinions of health care professionals regarding the added value of AI tools for supporting clinical decision-making varied widely, and many professionals had concerns about their understanding of and trust in this technology. The findings of this review emphasize the need for concerted efforts to optimize the integration of AI tools in real-world health care settings., Trial Registration: PROSPERO CRD42022336359; https://tinyurl.com/2yunvkmb., (©Abimbola Ayorinde, Daniel Opoku Mensah, Julia Walsh, Iman Ghosh, Siti Aishah Ibrahim, Jeffry Hogg, Niels Peek, Frances Griffiths. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 30.10.2024.)

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results