Please login first
Predicting pregnancy complications in low resource contexts (A case study of maternal healthcare in Uganda)
1  University of Gothernburg

Published: 09 June 2017 by MDPI in DIGITALISATION FOR A SUSTAINABLE SOCIETY session Doctoral Symposium



 Every day in 2015, about 830 women died from pregnancy or childbirth-related complications around the world, with 99% of the deaths reported from developing countries (WHO, 2015). Maternal deaths result from complications of pregnancy, complications of childbirth and postpartum complications (Kassebaum et al., 2014). Despite improvement activities, the United Nations’ fifth Millennium Development Goal (MDG 5) of a 75% reduction in the maternal mortality ratio (MMR; number of maternal deaths per 100 000 livebirths) between 1990 and 2015 has not been met. Worldwide, the number of maternal deaths dropped only by 43% (WHO, 2015).

 Uganda has a maternal mortality ratio of 343 per 100,000 live births with a 53% reduction between 1990 and 2013 (WHO, 2014). Uganda shows a slow progress in the reduction of maternal mortality, with only a 2.8% annual decline (WHO, 2015). The slow progress is explained by limited access to healthcare and shortage of medically trained health professionals that can provide maternal and child healthcare services (Nabudere et al., 2011). The public healthcare system includes national and regional hospitals and a tiered system of health centers (HCs), consisting of HC II at the parish level, HC III at the sub-county level and HC IV at the county level (MoH, 2012). The HCs use a referral system where patients are transferred to the next level from a health center that cannot provide adequate healthcare services.

 While only 13% of Uganda’s population is urban (World Bank, 2010) the distribution of resources for healthcare, particularly specialized health professionals, is skewed toward urban areas. In fact, this leads to a very limited access to high quality healthcare in rural, remote, and hard-to-reach areas (MoH, 2012). In order to strengthen and extend the maternal healthcare workforce to rural areas, Uganda has employed a task shifting strategy (WHO, 2007). The strategy enables healthcare professionals such as doctors and specialized clinicians to move tasks to less trained and qualified health practitioners, such as nurses and community health workers organized in village health teams in rural areas (VHTs) (WHO/PEPFAR/ UNAIDS, 2008).

 In the task shifting strategy, the VHTs are the first point of contact for pregnant women and face the task to predict pregnancy complications but, they cannot accurately predict pregnancy complications (Okuga et al., 2014) making it difficult to achieve the MDG5 goals. In order to achieve the goals, with the task shifting strategy, it requires an effective and efficient maternal healthcare system with adequate resources and capabilities. Information Systems research has led to the development of computer-based health information systems that support healthcare professionals, nurses and hospital administrative staff in daily activities, hence leading to increased quality and efficiency of patient care (Haux, 2006). Developing a health information system in developing countries is difficult due to the “organizational complexity, fragmentation, lack of coordinated organizational structures and unrealistic ambitions” (Asangansi and Braa, 2010). It has been noted that the adoption and use of eHealth interventions in developing countries is challenged with poor physical infrastructure such as poor transport network, unreliable power supply, low ICT illiteracy and poor data management structures (Wilson, 2000; Asangansi and Braa, 2010). For instance, electronic health (eHealth) interventions such as predictive models aimed at predicting pregnancy risks (Kleinrouweler et al. 2016) cannot be used by the VHTs and mid-level healthcare workers. Explanations for not using the models are that they are too complex for daily use in clinical settings because they require computer support (James, 2001; Payne et al., 2014).

 Mobile Health (mHealth) extends the health information infrastructure to the villages and provides an opportunity to strengthen the healthcare systems in developing countries (Braa and Purkayastha, 2010). mHealth does not only support people in rural areas with limited access to healthcare but also supports people in urban areas and in developed countries to access care while on the move (Varshney, 2014). Given the potential benefits of mHealth, strengthening the work of VHTs and mid-level community health workers may require a mobile solution that is coordinated with the backbone systems to support maternal healthcare processes at different levels of the healthcare system.

 Full utilization of mHealth in developing countries is challenged by technical issues such as costs of the mobile phones, installation, and mobile network infrastructure, mobile application usability issues and sociopolitical issues such as communication patterns and lack of power (Braa and Purkayastha , 2010; Braa and Sanner, 2011).  There is still limited research on how sustainable mobile health information can be effectively deployed and scaled (Braa and Purkayastha, 2010). There is need to research on the challenges and needs for a sustainable and scalable mHealth solution in application domains such as clinical decision support, monitoring, evaluation and patient tracking, and electronic health records (Sanner et al., 2012) and on how such solutions can reduce financial costs to patients (Silva et al., 2015).

 This research proposes a study on how to design a system that supports efficient predictions of pregnancy complications in low resource settings. 


The main objective of the research is to investigate the role of IT in value co-creation for predictions of pregnancy complications in low resource settings. Specific research objectives include:

  1. To explain factors that enable co-creation of value to predict pregnancy complications in low resource settings
  2. To describe the relationships between IT and value co-creation in predicting pregnancy complications
  3. To recommend guidelines on how to design IT that enables value co-creation in predicting pregnancy complications in low resource settings

 Research question(s)

 In order to design systems that support health practitioners in the rural areas to identify, prevent and manage pregnancy complications, we need to understand the human, technology and contextual factors in terms of structures and processes that may affect the use of the designed system. Therefore, the overall research question would be:

  “How can IT support value co-creation in predicting of pregnancy complications in low resource settings?”

 To answer this overall research question, we need to answer the following specific research questions:

  1. Which factors enable value co-creation in predicting pregnancy complications in low resource settings?
  2. In what ways can IT facilitate value co-creation in predicting pregnancy complications in low resource contexts?
  3. In what ways can IT be designed to enable value co-creation in predicting pregnancy complications in low resource contexts?

 Contribution and significance

 The practical contribution is to improve maternal healthcare in Uganda specifically through improved predictions of pregnancy complications in order for Uganda to meet the MDG5. Furthermore, the research supports the task shifting strategy by increasing access to quality care in low resource settings. The theoretical contribution is to identify how social capital theory and the service innovation framework enhance the use of IT to co-create value in the low-resource setting.

2. Literature

 Value co-creation in the service-dominant (S-D) lens is defined as “the processes and activities that underlie resource integration and incorporate different actor roles in the service ecosystem” (Lusch and Nambisan, 2015).

 The task shifting strategy presents challenges of inadequate access to quality maternal healthcare services in the rural communities. The quality of healthcare is not only achieved through service delivery but also through improved healthcare outcomes or the value obtained from the healthcare service delivery process (McColl-Kennedy et al., 2012).  Improved healthcare outcomes require innovative ways of healthcare service provision. Michie et al. (2003) indicates that treatment plans and related health care activities do not only include interactions with health professionals but rather extends to the individual lifestyle and beliefs. Evidence has shown that involvement of the patients in their treatment creates value as they actively seek and share information with health professionals, friends, family, support groups and colleagues to redesign their treatment programs (McColl-Kennedy et al., 2012) and prevent diseases through proper diet and exercises (Groves et al., 2013).

 Models and frameworks have been developed to improve healthcare outcomes in low-resource settings. Mburu (2014) developed a conceptual model for designing and deploying mHealth solutions for low-resource settings and tested it in maternal healthcare. The model was aimed at narrowing the gap between design of mHealth solutions and the use context. However, the model is inclined to processes between the healthcare provider and the patient and limits patients-patients or patients-family relationships. This limits research that focuses on other processes that support prevention and management of complications in rural settings with limited healthcare professionals. In this situation, the model is suitable for use in the traditional healthcare system that makes the healthcare provider at the center of healthcare and hence leads to limited quality of healthcare outcomes or reduced value.  

 Higa and Davidson (2017) developed a model that uses the S-D logic perspective for value co-creation in rural under-resourced settings. The model focuses of three actors including the patients, family or friends and healthcare providers who integrate resources to co-create value which is in this case, improving chronic disease health outcomes.  The resources considered in the model include social capital in form of social support from family and friends, eHealth resources to facilitate service delivery and eHealth resources that enhance patient engagement in health behavioral changes. The model assumes that the resources are readily available and that the actors are willing and available to exchange services despite acknowledging that the different actors are situated in both formal and informal institutions that may limit their interactions. Higa and Davidson suggest further research on the contributions on different actors and how limitations faced by actors to access and integrate services.

 The models and frameworks indicate the need to consider a social-technical approach when designing IT solutions that lead to improved health outcomes. The models also emphasize the need to consider the fit between the technical factors such as infrastructure, systems and the social factors such as the environment, individual characteristics and culture. Therefore, I will use a socio-technical approach to design a system that integrates social and technical factors. 

 3. Method 

To design IT innovations in healthcare, there is need to adopt the transdisciplinary approach in the research process. Pohl and Hadorn (2007) indicates that through transdisciplinary research, researchers understand the complexity of the problems as they analyze the life-world and scientific perceptions of the problem. This analysis can be achieved if different stakeholders in life-world participate in identifying and structuring the problem (Hadorn et al., 2008). This collaborative effort enables to bridge the gap between knowledge production in academia and knowledge required to solve a societal problem (ibid).

Community input into the research process requires an understanding of who to involve in the research process (Davis and Wagner, 2003). Community input can be used to either guide the research process or as a means of gathering empirical evidence for the research process (Gaber, 2016). Pike (1967) presents two perspectives of gathering community data which include emic and etic perspectives. He states that the emic perspective requires understanding the “lived experiences of the community members” while the etic perspective focuses on the “observations made by people outside the community”. In addition to the two perspectives, Gaber (2016) identified two other perspectives that include the emic-etic and etic-emic perspectives which are expressed as “insider-outsider vista” and “outsider-insider vista” respectively. He explains the emic-etic community perspective as being provided by advocacy groups who are members of the community and have worked with a community issue for some time hence, have an insider view. At the same time, such members work with other members in the advocacy groups who provide them with etic awareness view.  The etic-emic community perspective is provided by community organization representatives with etic and emic contacts for different community issues (Gaber, 2016)

Qualitative research that uses an interpretive approach aims at understanding the emic perspective of the people through the meanings they attach to their experiences rather than focusing on facts (Hennink et al., 2011). Therefore, in the interpretive approach, particularly during data collection and interpretation, “the study participants reflect their subjective views of their social world while the researcher brings subjective influences to the research process” (ibid).

 I will adopt the qualitative research approaches such as case study and ethnographic action research in my research process. This is because the approaches help to understand the interactions between people, technology and the organization. Such interactions inform theory development or solutions to the problem (Klein and Meyers, 1999). I used a case study research approach to conduct an exploratory and qualitative study in the Ugandan context to get an initial understanding of the maternal healthcare system. This helped me to identify some of the current problems facing the maternal healthcare system in Uganda for instance, the organizational, technical and human resource challenges. Data was collected through conducting interviews with the village health teams, midwives and healthcare professionals. The results from the study were analyzed using “the service innovation framework with the Service-Dominant (S-D) lens” (Lusch and Nambisan, 2015).

 Given the fact that Sweden is among the countries with the lowest mortality rates, I plan to conduct a comparative study in Sweden to understand the best practices in maternal health care system and opportunities that can be transferred to the Ugandan context. A case study research design will be used to conduct this study. The data will be collected from midwives, midwife healthcare managers and IT managers in Gothenburg, Sweden. Midwife healthcare managers and IT managers will be interviewed and in addition, a survey will be sent out to the midwives.   Further still, observations will be made at one of the healthcare clinics in Gothenburg to confirm the results from the interviews. The collected data will be analyzed using the S-D lens.

 The Ethnographic action research enables the researcher to focus beyond individual ICT to include the entire structure of communication and information in people’s way of life (Tacchi et al., 2003). The approach provides IS researchers with insights into the human, social and cultural aspects of IS information development and application (Harvey and Myers, 1995). Ethnographic research will enable me to see “what people are doing as well as what they say they are doing” (Myers, 1999) through participant observation (Baskerville and Myers (2015). Through ethnography I will observe how VHTs interact with the pregnant women and the midwives during the pregnancy process.

 Analyzing results from the research studies will be done with reference to the social capital theory (Lewis et al., 2013) and service innovation framework (Lusch and Nambisan, 2015). Analysis from the studies will enable me to design requirements for the use of IT to support value-co-creation in predicting pregnancy complications.  I will evaluate the design guidelines using quality attributes of usability, reliability and organizational fit.

4. References

 Asangansi, I., & Braa, K. (2010). The emergence of mobile-supported national health information systems in developing countries. Stud Health Technol Inform, 160(Pt 1), 540-544.

Balci, B. (2014). The State of the Art on Process Virtualization: A Literature Review.

Baskerville, R. L., & Myers, M. D. (2015). Design ethnography in information systems. Information Systems Journal, 25(1), 23-46.

Braa, K., & Purkayastha, S. (2010). Sustainable mobile information infrastructures in low resource settings. Studies in health technology and informatics, 157, 127-132.

Braa, K., & Sanner, T. (2011). Making mHealth happen for health information systems in low resource contexts. In Proceedings of the 11 th International Conference on Social Implications of Computers in Developing Countries (pp. 530-541).

Davis, A., & Wagner, J. R. (2003). Who knows? On the importance of identifying “experts” when researching local ecological knowledge. Human ecology, 31(3), 463-489.

Gaber, J. (2016). Seeing the community’s perspective through multiple emic and etic vistas. Health Promotion International, daw043.

Groves, P., Kayyali, B., Knott, D., & Van Kuiken, S. (2013). The ‘big data’revolution in healthcare. McKinsey Quarterly, 2.

Hadorn, G. H., Biber-Klemm, S., Grossenbacher-Mansuy, W., Hoffmann-Riem, H., Joye, D., Pohl, C., ... & Zemp, E. (Eds.). (2008). Handbook of transdisciplinary research (pp. 19-39). Zurich^ eSwitzerland Switzerland: Springer.

Harvey, L. J., & Myers, M. D. (1995). Scholarship and practice: the contribution of ethnographic research methods to bridging the gap. Information Technology & People, 8(3), 13-27.

Haux, R. (2006). Health information systems–past, present, future. International journal of medical informatics, 75(3), 268-281.

Hennink, M., Hutter, I., & Bailey, A. (2011). Qualitative research methods. Sage Publications.

Higa, C., & Davidson, E. (2017). Building Healthier Communities: Value Co-Creation within the Chronic Care Model for Rural Under-Resourced Areas. In Proceedings of the 50th Hawaii International Conference on System Sciences.

James, B. C. (2001). Making it easy to do it right. New England Journal of Medicine, 345(13), 991-993.

Kassebaum, N. J., Bertozzi-Villa, A., Coggeshall, M. S., Shackelford, K. A., Steiner, C., Heuton, K. R., ... & Templin, T. (2014). Global, regional, and national levels and causes of maternal mortality during 1990–2013: a systematic analysis for the Global Burden of Disease Study 2013. The Lancet, 384(9947), 980-1004.

Klein, H. K., & Myers, M. D. (1999). A set of principles for conducting and evaluating interpretive field studies in information systems. MIS quarterly, 67-93.

Kleinrouweler, C. E., Cheong-See, F. M., Collins, G. S., Kwee, A., Thangaratinam, S., Khan, K. S., ... & Schuit, E. (2016). Prognostic models in obstetrics: available, but far from applicable. American journal of obstetrics and gynecology, 214(1), 79-90.

Lewis, J. M., DiGiacomo, M., Luckett, T., Davidson, P. M., & Currow, D. C. (2013). A social capital framework for palliative care: supporting health and well-being for people with life-limiting illness and their carers through social relations and networks. Journal of pain and symptom management, 45(1), 92-103.

Lusch, R. F., & Nambisan, S. (2015). Service Innovation: A Service-Dominant Logic Perspective. Mis Quarterly, 39(1), 155-175.

Mburu, S. N. (2014). A model for design and deployment of mhealth solutions fit for low-resource settings: case of maternal care (Doctoral dissertation, University of Nairobi).

McColl-Kennedy, J. R., Vargo, S. L., Dagger, T. S., Sweeney, J. C., & van Kasteren, Y. (2012). Health care customer value cocreation practice styles. Journal of Service Research, 1094670512442806.

Michie, S., Miles, J., & Weinman, J. (2003). Patient-centredness in chronic illness: what is it and does it matter?. Patient education and counseling, 51(3), 197-206.

MoH(Ministry of Health), Health Systems 20/20, Makerere University School of Public Health (2012) .  Uganda Health System Assessment 2011. Kampala, Uganda and Bethesda, MD: Health Systems 20/20 project, Abt Associates Inc

Myers, M. (1999). Investigating information systems with ethnographic research. Communications of the AIS, 2(4es), 1.

Okuga, M., Kemigisa, M., Namutamba, S., Namazzi, G., & Waiswa, P. (2014). Engaging community health workers in maternal and newborn care in eastern Uganda. Glob Health Action, 7, 23968.

Payne, B. A., Hutcheon, J. A., Ansermino, J. M., Hall, D. R., Bhutta, Z. A., Bhutta, S. Z., ... & Li, J. (2014). A risk prediction model for the assessment and triage of women with hypertensive disorders of pregnancy in low-resourced settings: the miniPIERS (Pre-eclampsia Integrated Estimate of RiSk) multi-country prospective cohort study. PLoS Med, 11(1), e1001589.

Pike, K. L. (1967). Language in relation to a unified theory of the structure of human behavior, 2nd rev.

Pohl, C., & Hirsch Hadorn, G. (2007). Principles for designing transciplinary research, proposed by the Swiss academies of arts and sciences. München: Oekom.

Sanner, T. A., Roland, L. K., & Braa, K. (2012). From pilot to scale: Towards an mHealth typology for low-resource contexts. Health Policy and Technology, 1(3), 155-164.

Silva, B. M., Rodrigues, J. J., de la Torre Díez, I., López-Coronado, M., & Saleem, K. (2015). Mobile-health: a review of current state in 2015. Journal of biomedical informatics, 56, 265-272.

Tacchi, J. A., Slater, D., & Hearn, G. N. (2003). Ethnographic action research: A user’s handbook.

UCC (Uganda Communications Commission) 2015. Postal, boradcastig and telecommunications annual market and industry report 2014/2015.  (Retrieved on 10/01/2017)

Varshney, U. (2014). Mobile health: Four emerging themes of research. Decision Support Systems, 66, 20-35.

WHO (World Health Organization) (2007). Task Shifting to Tackle Human Resource Shortages. Geneva: URL: (Retrieved on 10/01/2017).

WHO (World Health Organization) (2014). Global maternal newborn, child and adolescent health policy indicator database based on key informant surveys in 2009-10, 2011 & 2013-14

WHO (World Health Organization) (2015), "Media center, Maternal mortality, Fact sheet Nº348," URL: (Retrieved on 16/10/2016).

WHO, U.S. President’s Emergency Plan for AIDS Relief (PEPFAR), and UNAIDS (2008). Treat, Train, and Retain: Task Shifting—Global Recommendations and Guidelines. Geneva: WHO. URL: (visited on 16/10/2016).

Wilson, R. (2000). Using computers in health information systems. Design and Implementation of Health Information System. Geneva: World Health Organization, 198-212.

World Bank (2010) World Development Indicators [dataset]. Washington, DC: World Bank.


Keywords: Predictions, pregnancy, value co-creation, low resource context