Kagiso Ndlovu

Kagiso Ndlovu

Auto-generated profile, based on publicly available information

Kagiso Ndlovu

Department of Computer Science, University of Botswana, Gaborone, Botswana

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
21 August 2021 in BMC Medical Informatics and Decision Making
Verified
Journal Article
Open access
PDF file
KNKagiso Ndlovu
Kagiso Ndlovu
RSRichard E Scott
Richard E Scott
MMMaurice Mars
Maurice Mars
Background: Significant investments have been made towards the implementation of mHealth applications and eRecord systems globally. However, fragmentation of these technologies remains a big challenge, often unresolved in developing countries. In particular, evidence shows little consideration for linking mHealth applications and eRecord systems. Botswana is a typical developing country in sub-Saharan Africa that has explored mHealth applications, but the solutions are not interoperable with existing eRecord systems. This paper describes Botswana’s eRecord systems interoperability landscape and provides guidance for linking mHealth applications to eRecord systems, both for Botswana and for developing countries using Botswana as an exemplar. Methods: A survey and interviews of health ICT workers and a review of the Botswana National eHealth Strategy were completed. Perceived interoperability benefits, opportunities and challenges were charted and analysed, and future guidance derived. Results: Survey and interview responses showed the need for interoperable mHealth applications and eRecord systems within the health sector of Botswana and within the context of the National eHealth Strategy. However, the current Strategy does not address linking mHealth applications to eRecord systems. Across Botswana’s health sectors, global interoperability standards and Application Programming Interfaces are widely used, with some level of interoperability within, but not between, public and private facilities. Further, a mix of open source and commercial eRecord systems utilising relational database systems and similar data formats are supported. Challenges for linking mHealth applications and eRecord systems in Botswana were identified and categorised into themes which led to development of guidance to enhance the National eHealth Strategy. Conclusion: Interoperability between mHealth applications and eRecord systems is needed and is feasible. Opportunities and challenges for linking mHealth applications to eRecord systems were identified, and future guidance stemming from this insight presented. Findings will aid Botswana, and other developing countries, in resolving the pervasive disconnect between mHealth applications and eRecord systems.

13 May 2021 in BMC Health Services Research
Verified
Journal Article
Open access
PDF file
KNKagiso Ndlovu
Kagiso Ndlovu
MMMaurice Mars
Maurice Mars
RSRichard E Scott
Richard E Scott
Background: mHealth presents innovative approaches to enhance primary healthcare delivery in developing countries like Botswana. The impact of mHealth solutions can be improved if they are interoperable with eRecord systems such as electronic health records, electronic medical records and patient health records. eHealth interoperability frameworks exist but their availability and utility for linking mHealth solutions to eRecords in developing world settings like Botswana is unknown. The recently adopted eHealth Strategy for Botswana recognises interoperability as an issue and mHealth as a potential solution for some healthcare needs, but does not address linking the two. Aim: This study reviewed published reviews of eHealth interoperability frameworks for linking mHealth solutions with eRecords, and assessed their relevance to informing interoperability efforts with respect to Botswana’s eHealth Strategy. Methods: A structured literature review and analysis of published reviews of eHealth interoperability frameworks was performed to determine if any are relevant to linking mHealth with eRecords. The Botswanan eHealth Strategy was reviewed. Results: Four articles presented and reviewed eHealth interoperability frameworks that support linking of mHealth interventions to eRecords and associated implementation strategies. While the frameworks were developed for specific circumstances and therefore were based upon varying assumptions and perspectives, they entailed aspects that are relevant and could be drawn upon when developing an mHealth interoperability framework for Botswana. Common emerging themes of infrastructure, interoperability standards, data security and usability were identified and discussed; all of which are important in the developing world context such as in Botswana. The Botswana eHealth Strategy recognises interoperability, mHealth, and eRecords as distinct issues, but not linking of mHealth solutions with eRecords. Conclusions: Delivery of healthcare is shifting from hospital-based to patient-centered primary healthcare and community-based settings, using mHealth interventions. The impact of mHealth solutions can be improved if data generated from them are converted into digital information ready for transmission and incorporation into eRecord systems. The Botswana eHealth Strategy stresses the need to have interoperable eRecords, but mHealth solutions must not be left out. Literature insight about mHealth interoperability with eRecords can inform implementation strategies for Botswana and elsewhere.

11 December 2014 in Frontiers in Public Health
Verified
Journal Article
Open access
PDF file
KNKagiso Ndlovu
Kagiso Ndlovu
RLRyan Littman-Quinn
Ryan Littman-Quinn
EPElizabeth Park
Elizabeth Park
ZDZambo Dikai
Zambo Dikai
CKCarrie Kovarik
Carrie Kovarik
Effective health care delivery is significantly compromised in an environment where resources, both human and technical, are limited. Botswana’s health care system is one of the many in the African continent with few specialised medical doctors, thereby posing a barrier to patients’ access to health care services. In addition, the traditional landline and non-robust Information Technology (IT) network infrastructure characterised by slow bandwidth still dominates the health care system in Botswana. Upgrading of the landline IT infrastructure to meet today’s health care demands is a tedious, long and expensive process. Despite these challenges, there still lies hope in health care delivery utilising wireless telecommunication services. Botswana has recently experienced a tremendous growth in the mobile telecommunication industry coupled with an increase in the number of individually owned mobile devices. This growth inspired the Botswana-UPenn Partnership (BUP) to collaborate with local partners to explore using mobile devices as tools to improve access to specialised health care delivery. Pilot studies were conducted across four medical specialties, including radiology, oral medicine, dermatology and cervical cancer screening. Findings from the studies became vital evidence in support of the first scale-up project of a mobile telemedicine solution in Botswana, also known as “Kgonafalo”. Some technical and social challenges were encountered during the initial studies, such as malfunctioning of mobile devices, accidental damage of devices and cultural misalignment between IT and healthcare providers. These challenges brought about lessons learnt, including a strong need for unwavering senior management support, establishment of solid local public-private partnerships, and efficient project sustainability plans. Sustainability milestones included the development and signing of a Memorandum of Understanding (MOU) between the Botswana government and private telecommuni

12 June 2023
Verified
Conference Paper
Open access
MMMelissa Mccradden
Melissa Mccradden
OOOluwadara Odusi
Oluwadara Odusi
SJShalmali Joshi
Shalmali Joshi
IAIsmail Akrout
Ismail Akrout
KNKagiso Ndlovu
Kagiso Ndlovu
AGAnna Goldenberg
Anna Goldenberg
The problem of algorithmic bias represents an ethical threat to the fair treatment of patients when their care involves machine learning (ML) models informing clinical decision-making. The design, development, testing, and integration of ML models therefore require a lifecycle approach to bias identification and mitigation efforts. Presently, most work focuses on the ML tool alone, neglecting the larger sociotechnical context in which these models operate. Moreover, the narrow focus on technical definitions of fairness must be integrated within the larger context of medical ethics in order to facilitate equitable care with ML. Drawing from principles of medical ethics, research ethics, feminist philosophy of science, and justice-based theories, we describe the Justice, Equity, Fairness, and Anti-Bias (JustEFAB) guideline intended to support the design, testing, validation, and clinical evaluation of ML models with respect to algorithmic fairness. This paper describes JustEFAB's development and vetting through multiple advisory groups and the lifecycle approach to addressing fairness in clinical ML tools. We present an ethical decision-making framework to support design and development, adjudication between ethical values as design choices, silent trial evaluation, and prospective clinical evaluation guided by medical ethics and social justice principles. We provide some preliminary considerations for oversight and safety to support ongoing attention to fairness issues. We envision this guideline as useful to many stakeholders, including ML developers, healthcare decision-makers, research ethics committees, regulators, and other parties who have interest in the fair and judicious use of clinical ML tools.

4 August 2021 in PLOS ONE
Verified
Journal Article
Open access
PDF file
MKMpho Keetile
Mpho Keetile
KNKagiso Ndlovu
Kagiso Ndlovu
GLGobopamang Letamo
Gobopamang Letamo
MDMpho Disang
Mpho Disang
SYSanni Yaya
Sanni Yaya
KNKannan Navaneetham
Kannan Navaneetham
Background: The most commonly diagnosed cancers among women are breast and cervical cancers, with cervical cancer being a relatively bigger problem in low and middle income countries (LMICs) than breast cancer. Methods: The main aim of this study was to asses factors associated with and socioeconomic inequalities in breast and cervical cancer screening among women aged 15–64 years in Botswana. This study is part of the broad study on Chronic Non-Communicable Diseases in Botswana conducted (NCD survey) in 2016. The NCD survey was conducted across 3 cities and towns, 15 urban villages and 15 rural areas of Botswana. The survey collected information on several NCDs and risk factors including cervical and breast cancer screening. The survey adopted a multistage sampling design and a sample of 1178 participants (males and females) aged 15 years and above was selected in both urban and rural areas of Botswana. For this study, a sub-sample of 813 women aged 15–64 years was selected and included in the analysis. The inequality analysis was conducted using decomposition analysis using ADePT software version 6. Logistic regression models were used to show the association between socioeconomic variables and cervical and breast cancer screening using SPSS version 25. All comparisons were considered statistically significant at 5%. Results: Overall, 6% and 62% of women reported that they were screened for breast and cervical cancer, respectively. Women in the poorest (AOR = 0.16, 95% CI = 0.06–0.45) and poorer (AOR = 0.37, 95% CI = 0.14–0.96) wealth quintiles were less likely to report cervical cancer screening compared to women in the richest wealth quintile. Similarly, for breast cancer, the odds of screening were found to be low among women in the poorest (AOR = 0.39, 95% CI = 0.06–0.68) and the poorer (AOR = 0.45, 95% CI = 0.13–0.81)) wealth quintiles. Concentration indices (CI) showed that cervical (CI = 0.2443) and breast cancer (CI = 0.3975) screening were more concentrated among women with high SES than women with low SES. Wealth status was observed to be the leading contributor to socioeconomic inequality observed for both cervical and breast cancer screening. Conclusions: Findings in this study indicate the need for concerted efforts to address the health care needs of the poor in order to reduce cervical and breast cancer screening inequalities.

2 May 2023 in JMIR Formative Research
Verified
Journal Article
Open access
KNKagiso Ndlovu
Kagiso Ndlovu
MMMaurice Mars
Maurice Mars
RSRichard E Scott
Richard E Scott
Background: Electronic record (eRecord) systems and mobile health (mHealth) apps have documented potential to improve health service delivery, resulting in increased global uptake. However, their interoperability remains a global challenge hindering diagnosis, monitoring of health conditions, and data access irrespective of geographic location. Given the widespread use of mobile devices by patients and health care providers, linking mHealth apps and eRecord systems could result in a comprehensive and seamless data exchange within a health care community. The Botswana National eHealth Strategy recognizes interoperability as an issue and mHealth as a potential solution for some health care needs but is silent on how to make mHealth apps interoperable with existing eRecord systems. A literature review and analysis of existing mHealth interoperability frameworks found none suitable for Botswana. As such, it was critical to conceptualize, design, and develop an mHealth-eRecord Interoperability Framework (mHeRIF) to enhance the interoperability pillar of the Botswana National eHealth Strategy and leverage the full benefits of linking mHealth apps with other health information systems. Objective: This study aimed to validate the developed mHeRIF and determine whether it requires further refinement before consideration towards enhancing the National eHealth Strategy. Methods: Published framework validation approaches guided the development of a survey administered to 12 purposively selected local and international eHealth experts. In total, 25% (3/12) of the experts were drawn from Botswana, 25% (3/12) were drawn from low- and middle-income countries in sub-Saharan Africa, 25% (3/12) were drawn from low- and middle-income countries outside Africa, and 25% (3/12) were drawn from high-income countries. Quantitative responses were collated in a Microsoft Excel (Microsoft Corp) spreadsheet for descriptive analysis, and the NVivo software (version 11; QSR International) was used to aid the thematic analysis of the qualitative open-ended questions. Results: The analysis of responses showed overall support for the content and format of the proposed mHeRIF. However, some experts’ suggestions led to 4 modest revisions of the mHeRIF. Conclusions: Overall, the experts’ reviews showed that the mHeRIF could contribute to the National eHealth Strategy by guiding the linking of mHealth apps to existing eRecord systems in Botswana. Similarly, the experts validated an architectural model derived from the mHeRIF in support of the first mobile telemedicine initiative considered for national rollout in Botswana. The mHeRIF helps identify key components to consider before and after linking mHealth apps to eRecord systems and is being considered for use as the foundation of such interoperability in Botswana.