1. Title: Development and Evaluation of e-cancer registry and forecasting system for Amhara region, Northwest Ethiopia
Description:Cancer is an ever-evolving public health problem in both developed and developing countries due to increase in life expectancy, changes in diet, lifestyle and other factors. A rational cancer control program must be built on recent and accurate population-based data on incidence, survival, treatment, and outcome from within its nation. In this regard, cancer registries provide important information and should be prioritized for sustainable investment in sub-Saharan Africa including Ethiopia. However, low coverage of cancer registry with predominantly of manual/paper-based data capturing systems are persisting problem in subSaharan Africa in general and in Ethiopia in particular. Thus, this project aims to develop and evaluate electronic cancer (e-cancer) registry and forecasting system for Bahir Dar city.
As part of this research project we will gather requirements from Amhara region health centers and Amhara public health institute. Based on the gathered data we aim to design, develop, and evaluate a portable simple and full-fledged e-cancer registry and forecasting system following iterative software development methodology. After the development of the system, we plan to deploy and use the system for one year period. The data collected in its usage time will be used to design forecasting algorithm in order to predict the distribution rate, life expectancy and other
major parameters requested by stockholders.
This research benefits institutes and individuals in a significant ways the most common benefits are: It allows determining cancer patterns among various populations or sub-populations, monitor cancer trends over time, guide planning and evaluation of cancer control efforts, help prioritize health resource allocations, and advance clinical, epidemiological, and health services research. The research is expected to produce requirement specification and design document as the first phase output, e-cancer registry system tool, user and acceptance testing documents, as the second phase out put and forecasting system, 1 journal paper, 2 conference publications are expected to be produced as output from third phase implementation of this research. The study will be executed from September 01, 2022 to June 30, 2024 E.C. for two years
Researchers: Mr. Tegegn Kebebaw (PI), Dr. Muluken Azage, Dr. Eyaya Misgan, Mr. Dabere Nigatu, Dr. Esubalew, Mr. Biniam Behailu, Mr. Asamnew Gizaw
Fund: BDU
-------------------------------------------------------
2. Title: Developing a general purpose annotated monolingual text corpus and part of speech tagger tool for Ge'ez language
Description:
Information Technology have a great role for the development of languages through natural language processing thematic area by developing different language applications. But all natural language processing researches and applications need the well-organized and developed corpora for any language. In Ethiopia, we can say that almost all local languages are low-resource languages. Among those, Ge’ez language is classified as one of the languages that have a lack of corpora. Ge’ez language is a family of semitic language that contains many ancient historical, artistical, archaeological, astronomical, medical, theological, architectural, religious, educational, laws, cultural, administrative and political manuscripts. Therefore, it is a voluntary duty to maintain and develop the language by bringing it closer to the technological domain. The main purpose of this research work is to develop Geez text corpus and make avail free for any NLP researchers and educational use by annotating each and every word of collected Ge’ez text. The methodologies included are literature review, data collection, raw text pre-processing, tokenization of preprocessed data, generating sentences, annotation of the tokenized data, encoding the annotated corpus within appropriate file format, designing and implementation Ge’ez part of speech tagger by applying machine learning approach using TensorFlow development tool. The collected data will be pre-processed and annotated by the language experts. The outcome of the investigated project will be two types of corpora; written plain text (deposited by .txt extension), and annotated/tagged text (stored by .XML extension) with monolingual corpora (i.e., only for Geez language) that contain 1,000,000 words reflected from different Ge’ez text domain. Scheming and developing automatic part of speech tagger for Ge’ez language is additional research output. The duration of the research work is from 01/02/2015 E.C-30/10/2016 E.C
Researchers: Tsegaye Abebe,Dr. Abba Beaman Girum, Dr. Tesfa Tegegne, Abinew Ali, Kasanesh Meshesha, Debas Senshaw
Fund: BDU
-------------------------------------------------------
3. Title: AfriHate: Hate and Offensive Speech Dataset for African Languages
Description:Online hate is a growing problem across Africa. It inflicts harm on the people exposed to and targeted by it, pollutes and disrupts online communities and, in the worst cases, can be a precursor to physical violence. Machine learning tools for automatically finding and rating the hatefulness of online content can help to address this problem, supporting content moderation efforts, social media monitoring, and threat evaluation. However, at present, there are almost no hate detection tools available for any African languages, either in academia or industry. This means that African users of online services are more likely to not be protected against hate or to unfairly have their content moderated, which can severely restrict free expression and open use of the Internet.
This project addresses this problem by introducing AfriHate, the first labelled dataset for online hate in Africa, covering 14 languages from 6 countries. Four Ethiopian languages (Amharic, Afan Oromo, Tigrigna, & Somalia) will be part of this project. We are also creating baseline machine learning models for each language, which will be made available to other researchers, civil society organizations and social media platforms to use. This is a first-of-its-kind project which has the potential to transform how online hate is understood, tackled and researched across Africa.
Researchers: Abinew Ali, Dr. Seid Muhie, Dr. Esubalew Alemneh
Fund: Grant from Lacuna
4. Title: Enhancing interventions during pregnancy up-to child’s 1st birthday using information technology to improve maternal, neonatal and child health (MNCH) outcomes.
Description: Globally, a much progress in maternal and child survival has been made over the past two decades. However, still, one child is dying in every five seconds in 2018 and one women is dying in every two minutes in 2017 – with high variation amongst regions. The sub- Saharan Africa is the region with the highest maternal and under-five child mortality. Likewise, the high maternal and neonatal mortalities are persisting problems in Ethiopia. It is well understood that the health outcomes for mothers and their newborn and children are inextricably linked; maternal deaths and morbidities impact newborn and child survival, growth and development.
The maternal, perinatal, and neonatal mortality reduction efforts are connected with the availability of linked maternity care (antenatal care, skilled childbirth care, and postnatal care) and newborn care packages across life-cycle. Besides, quality care is critical across the continuum of care with functional linkages between levels of care in the health system and between service-delivery packages. However, in many low-income countries the maternal and child cares are neither continuous nor integrated because of shortage in human and financial resources and inadequate health-system infrastructure. The poor quality of care is also a major impediment to efforts aimed at improving the health of populations in developing countries, particularly with respect to maternal, neonatal and child health. The discontinuity of care is very high in Ethiopia. Up to 88% dropout was reported along the continuum of care (ANC 4+, skilled childbirth, and postnatal care) while up to 44% dropout was reported in between ANC4+ and childbirth.
Despite unacceptably high maternal and neonatal mortality, the global community is committed in the Sustainable Development Goals (SDGs) to end all preventable maternal and child deaths and ensure universal access to quality health care by 2030. Integration of Information and Communication Technology (ICT) in health, e-Health, is a key strategy to accelerate towards the global commitments and the national goals in the health sector. A systematic review suggested the importance of research in order to better document and measure the impact of interventions on the use of skilled maternity care.
Moreover, advances in ICT are changing the way health authorities and health care professionals can, through eHealth, help citizens everywhere to live longer and healthier lives (16). The ICT platforms (web, social media, SMS campaigns, direct access to personal data in electronic health records) can be leveraged to enhance accountability, transparency, and empowerment of citizens to be active contributors to governance in health and central to health care delivery. The e-Health is a cost-effective and secure use of ICT in support of health and health-related fields and should be viewed as a key enabler and driver for improved health outcomes for a population. Ethiopia is one of the WHO member states who have the eHealth strategy in place. Innovative approaches are mandatory to achieve the national and global maternal and child health targets via integrated eHealth. Therefore, the current project designed to evaluate the effectiveness of technology assisted interventions during pregnancy, childbirth, postpartum period and child immunization to reduce undesirable maternal, newborn and child health outcomes. The project applies a newly developed web and mobile based application called “ADHERE-IN” tool. The tools will operate starting from pregnant women enrollment for antenatal care through the continuum of maternal and child health care.
Researchers: Dabere Nigatu (PI), Dr. Muluken Azage, Dr. Eyaya Misgan, Dr. Eneyew Abate, Prof Tsunel Nigatu, Tegegn Kebebew, Dr. Esubalew Alemneh, and more
Fund: Finot Harvered Project, Ministry of Health.
-------------------------------------------------------