Architecture of a Learning Surveillance System for Malaria

Elimination in India

S D Sreeganga

, Susanna G. Mitra

and Arkalgud Ramaprasad

1,2 c

Ramaiah Public Policy Center, Bengaluru, India

University of Illinois, Chicago, U.S.A.

Keywords: Cyberenvironment, Learning System, Surveillance, Feedback-loop, Malaria Elimination.

Abstract: Surveillance is critical for malaria elimination. Malaria transmission takes place in a dynamic and complex

environment. The key goal in developing a malaria surveillance system is to ensure that it is robust, systematic,

and effective for improving data availability for decision-making. We present a unified framework for

envisioning malaria surveillance informatics as an ontology-based feedback system. The framework presented

is a solution for the current fragmented and linear surveillance processes for malaria case management. It

encapsulates a comprehensive natural language enumeration of the requirements of the cyberenvironment,

structured into 5 dimensions - timing, surveillance process, information surveyed, malaria management, and

stakeholder, with each of them articulated as a taxonomy of its constituent elements. The elements are

combined to form natural language statements of the cyberenvironment requirement. The information

generation through the semiotic cycle provides real-time sense and response capability for timely and targeted

interventions. The response mechanism creates both positively and negatively reinforcing feedback-based

learning processes at multiple levels. Such a system enables data interoperability for capturing malaria

incidence, discover epidemiological clusters, and predict propagation dynamics. On a larger scale, the

integrative framework enables data harmonization, analytics, and visualization towards effective management

and knowledge generation on disease surveillance.

1 INTRODUCTION

Malaria is a major global health problem, and a

leading cause of disease and death across many

tropical and subtropical countries. The World Malaria

Report 2018 estimates that there were 219 million

malaria cases, and 435 thousand related deaths in

2017 (World Health Organization, 2018). Global

efforts to control malaria during 2000-2015 had

resulted in substantial reductions in cases of malaria

incidence and mortality rate (Cibulskis et al., 2016).

However, the public health burden of the disease has

continued through new manifestations of its source

from Plasmodium Falciparum to P. Vivax, emergence

of new transmission modes due to human mobility,

and epidemiological shifts in the populations most at

risk of malaria (Cotter et al., 2013). Adding to the

burden are issues of low malaria testing rates and high

https://orcid.org/0000-0001-7308-6851

https://orcid.org/0000-0001-5784-5950

https://orcid.org/0000-0003-1551-6854

numbers of unconfirmed malaria cases that need

constant monitoring to sustain the reductions

(McMorrow, Aidoo, & Kachur, 2011). These new

circumstances have prompted shifts in global

strategies from traditional control interventions to

novel measures for completeness, timeliness of

activities to seek out infections, and interrupt

transmissions (Cotter et al., 2013).

Constant malaria monitoring and surveillance

systems have been highlighted as critical and a core

intervention strategy to achieve malaria elimination

(The malERA Consultative Group on Monitoring,

Evaluation, and Surveillance, 2011). Malaria

surveillance in the current elimination phase is

directed at stopping local transmission of malaria. It

involves a dual strategy of a) identifying and

determining areas with local transmission and its

sources; and b) detecting the characteristics of

Sreeganga, S., Mitra, S. and Ramaprasad, A.

Architecture of a Learning Surveillance System for Malaria Elimination in India.

DOI: 10.5220/0008944103770382

In Proceedings of the 13th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2020) - Volume 5: HEALTHINF, pages 377-382

ISBN: 978-989-758-398-8; ISSN: 2184-4305

377

transmission with intensified surveillance and

appropriate control measures taken (Cibulskis, 2012).

WHO 2018 report emphasizes that a strong

surveillance system requires high levels of access to

care and case detection, and complete reporting of

health information by all sectors, whether public or

private (World Hea Organization, 2018). This has led

to a concerted global effort towards large-scale,

robust surveillance mechanisms that measure rather

than estimate the actual burden of malaria over time

from large areas of the continent (Nkumama,

O’Meara, & Osier, 2017). Aiding such efforts are

technological advances in surveillance systems,

including timeliness for rapid detection of local

outbreaks (Chehab M. et al., 2018), interoperability

for rapid data exchange between different platforms,

(Brenas, Al-Manir, Baker, & Shaban-Nejad, 2017)

and accessible data storage with management (UCSF

Global Health Sciences, 2014).

However, the need to communicate this change in

strategic thinking to large, cumbersome health

systems has proven a challenge (Cao et al., 2014).

Malaria represents complex and dynamic interactions

among ecosystems, livelihoods, and health systems

(Mboera, Mfinanga, Karimuribo, Rumisha, &

Sindato, 2014). In case of malaria surveillance, there

is a strong argument for designing data reservoir

platforms that facilitate monitoring, learning and

evaluation (MLE) among multiple actors to optimize

coordinated, integrated disease detection, and

intervention efforts (Barclay, Smith, & Findeis,

2012). Current surveillance systems remain

predominantly linear and ineffective in tackling the

complexities of malaria elimination. This is evident

from a recent empirical study evaluating malaria

surveillance in 16 countries during 2015-2017. It

highlighted the main systemic gaps as lack of

coverage in remote communities and inadequate

health information architecture to capture high

quality case-based data. Other shortcomings were

partial integration of intervention information, poor

visualization of generated information, and disjointed

data for making programmatic decisions (Lourenço et

al., 2019).

To bring in systematic and effective data

generation, integration, and dissemination for malaria

elimination, we argue for a Learning Surveillance

System. This is in line with the Learning Health

Systems described as ‘cyber-social ecosystem’, to

solve complex interdisciplinary problems of timely

evidence, and supporting best care practices (Lessard

et al., 2019). It requires explicit conceptualization

using tools that can be used to establish a

communication protocol, describe information flows

within a complex setting of malaria elimination,

facilitate analysis, and design of a learning

surveillance system. Our paper introduces a

promising first step to help address this challenge by

demonstrating how an ontological approach can

facilitate analysis and design of a learning

surveillance system for malaria.

2 ONTOLOGICAL FRAMEWORK

The ontology encapsulates a comprehensive natural

language enumeration of the requirements of the

cyberenvironment for malaria surveillance using a

structured terminology that can be used to

systematically analyze and prioritize the functions of

the cyberenvironment (Brooks & Ramaprasad, 2008).

It builds on an earlier work titled ‘Ontology of a

Cyberenvironment for Malaria Surveillance’(Brooks

& Ramaprasad, 2008), by adding more elements to

the framework to reflect the current complex and

dynamic malaria landscape. Making use of this

ontological framework one can move from the

traditional linear surveillance system to a nonlinear

responsive, and iterative surveillance system for

malaria elimination programmes across the world.

The malaria surveillance ontological framework

is shown in Figure 1. The object of the framework is

to create an architecture of socio-cyberenvironment

for a learning surveillance system for malaria

elimination. The ontology comprises of five

dimensions, with each being defined by a taxonomy

of elements that constitute a learning surveillance

system. The framework encapsulates pathways for

the management of a malaria surveillance system.

Each pathway is a concatenation of an element from

the five columns, left to right, with the adjacent

words/phrases.

Malaria surveillance is based on various types of

data used for managing malaria by different

stakeholders, as listed in third to fifth columns of the

framework. The third column represents various

types of surveillance data integral to malaria

elimination. It includes data on mosquito species

characteristics, their habitation, regional population

demographics, case incidence rates which form the

information base for health analytics (Merkord et al.,

2017).

The fourth column from the left denotes malaria

management that focuses on managing symptoms,

causes, treatment, and prevention of malaria. This

includes targeted interventions for malaria control

through measures such as rapid diagnostic tests,

insecticide treated mosquito nets, mosquito control,

HEALTHINF 2020 - 13th International Conference on Health Informatics

378

Figure 1: Ontology of a Cyberenvironment for Malaria Surveillance in India.

and strategic management (Dhamnetiya & Sahu,

2015; van Eijk et al., 2016). Effective surveillance of

malaria cases and deaths is essential for identifying

the areas or population groups that are most affected

by malaria, and for targeting resources for maximum

impact. The fifth column from the left provides the

multitude of stakeholders including the healthcare

sector, different external entities, and individuals

engaged in malarial control ecosystem. Considering

the columns of data, malaria management, and

stakeholder along with each of its elements the

framework forms a natural language sentence.

Combining the three columns will create pathways

from simple information service to complex

interaction service. For example: clinical data for

active malaria cases by a clinic; or, financial data for

stock of drugs by a pharmacy.

The surveillance tools and strategies are

themselves characterized by timing and stages, listed

in the first two columns of the framework (from the

left). The second column of the framework articulates

the full scope of a surveillance system that allows

sense and response, making it a learning surveillance

system. Case identification, detection, and data

collection are direct and cover both active and passive

cases at health facilities, communities during

investigation, and screening activities. A malaria

elimination information system should include

automated data analysis to ensure timely outputs,

expert analysis for policy, and programming

decisions. The data generated as output results will

enable identification of threats such as outbreaks and

inform responses. The impact of the response can be

captured by the surveillance system and can inform

further iterative changes to the interventions. Expert

analysis of the data and its interpretation will impact

different combinations of interventions. The whole

cycle will automatically generate outputs tailored to

the level of the health systems including

visualizations of analyzed data, work task lists,

reports for internal use, and by external organizations.

A feedback system occurs on a real-time basis.

The first column represents the temporal

dimension of the iterative process that increases the

quality and reliability of the data. It can range from

the ad-hoc through real-time to predictive. Thus, the

learning surveillance system encapsulates both

immediate, and predictive indicators for malaria

elimination.

Tracing the ontology, the pathways of a malaria

surveillance system read as:

 Real-time collection of clinical data for active

malaria cases by ASHA worker.

 Predictive analysis of socio-economic data for

mosquito vector control by private agency.

 On-demand feedback of epidemiological data for

Timing Surveillance Data MalariaManagemment Stakeholder

Adhoc Identifi cation Entomologi cal Medicaltreatment HealthcareProvider

Posthoc Detection Parasitological Activemalariacases People

On‐demand Collection Demographic Asymptomaticcases Phy sician

Periodic Analysis Socio‐economic Prophylaxis Nurse

Real‐time Interpretation Clinical Stock ofdrugs Pharmacist

Predictive Application Epidemiological Fakedrugs ASHAworke r

Reporting Ecological Drugresistance Volunteer

Feedback Climate Pe rsonal Protection Entity

Geographical Insecticidetreatedbednets Hospital

Financial Interiorresidential spraying Cl inic

Insecticidetreatedclothing Pharmacy

Housedesign Home

Physicalbarriers Citizen

Mosqui to(vector)control Indiv idual

Mosqui tosource control Family

Adultmosquitocontrol Community

Identificationofnewspeci es Agency

Strategicmanage me nt Publ ic

Resourceallocation Private

Training NGO

Outcomeassessment Academia

[of]

[datafor]

[+ ]

[by/for]

Architecture of a Learning Surveillance System for Malaria Elimination in India

379

strategic management by public agency.

3 DISCUSSION

The ontological framework described above provides

the architecture of an integrated and consistent

knowledge source for malaria elimination. Through

its frame, one can collect, formalize, integrate,

analyze, and manipulate all types of malaria-related

data. The pathways formed capture the relationships

between timing, surveillance, data, malaria

management, and stakeholders of the malarial

system.

Its usefulness as a comprehensive and readily

searchable knowledge repository is evident, when

applied to recent studies within the domain. For

instance, the ontology clearly encapsulates the key

focus areas for malaria surveillance, as emphasized

by Barclay et al. (2012). The first urgent need for

rapid detection of existing, new or re-introduced

infections is clearly reflected by the ontological

pathway of real-time/on-demand detection of

parasitological, entomological, epidemiological, and

demographic data. The authors also highlight the

need for identification of periods of low transmission

(e.g., from symptomatic and asymptomatic

infections) when the parasite population could be

most amenable to elimination as well as trends in

malaria incidence, and prevalence in different age

groups, increasing parasite heterogeneity, changes in

seasonality. This complex phenomenon is indicated

through the ontological pathways of identification,

detection, and collection of data on asymptomatic

cases and analysis of data collected on

parasitological, demographic, and climate data

respectively. Even their emphasis on the issue of

detection of resistance currently central to malaria

elimination is captured by ontological pathway of

analysis of clinical data on drug resistance. Hence, the

ontology, in conjunction with regular medical

standards, can construct a semantically intelligent

malaria decision-making system.

The ontology is also a useful domain link for the

feedback loop in surveillance systems, which in

recent years, has become essential to Learning Health

Care Systems (Kass & Faden, 2018). The usefulness

of the feedback model was evident in the enhanced

malaria surveillance programme undertaken by the

Zambian government that recorded success in Lusaka

District within two years. It replaced intermittent

population-based surveys with data generation from

continuously operating health information systems.

The learning from the feedback helped redesign the

strategies for malaria elimination as it significantly

reduced malaria reporting, and unnecessary anti-

malarial treatment administration, especially in areas

with variable malaria transmission patterns (Chisha et

al., 2015).

The key difference between existing surveillance

systems and the proposed one is the real-time learning

capability through the feedback-loop. The iterative

cycle inherent to the feedback-loop is transformed

into an advanced learning model that can guide the

system along the trajectory of malaria elimination.

The timely feedback system will help recognize,

amplify the effective actions for malaria elimination,

and similarly attenuate the ineffective ones. The

learning from the feedback will help redesign the

strategies for malaria elimination. This learning

capability can be deployed to develop: (a) positively

reinforcing feedback cycles that amplify and

accelerate the desirable outcomes, and (b) negatively

reinforcing cycles that attenuate and decelerate

undesirable outcomes. Further this combination of

positively and negatively reinforcing feedback cycles

will generate a desirable non-linear, positive impact

on malaria elimination, that will not only verify trends

in reported malaria, but also incorporate a data

feedback loop to improve data uptake, use, and

quality. The semiotic cycle will lead to predictive

capability, responsiveness to occurrence, and

propagation for pro-active management of malaria. It

facilitates the development of predictive systems for

malaria involving repeated updates on the initial

conditions based on the new epidemiological data,

and the inference method that naturally lends itself to

this purpose, given its time-sequential application

(Roy, Bouma, Dhiman, & Pascual, 2015). Such

precision will help improve both the efficiency and

effectiveness of the efforts to eliminate the disease. It

will also help foster the sharing of knowledge

generated and its application.

Malaria surveillance systems aim to assist public

health practitioners and decision makers to (a)

identify the regions or populations affected by

malaria; (b) identify trends in malaria morbidity and

mortality; and (c) evaluate preventive or therapeutic

malaria interventions, and programs (Brenas et al.,

2017). In combination with the latest technological

advancements, the feedback process based on this

ontological framework enables a multi-layered

approach to malaria surveillance system. It involves a

three-level feedback mechanism that creates a sense

and response capability at different levels, to enable a

quick feedback cycle facilitating a non-linear,

iterative process for malaria elimination. For a rapid

feedback on malaria occurrence, at the first level, the

HEALTHINF 2020 - 13th International Conference on Health Informatics

380

process involves a robust reporting system for

different stakeholders, including doctors, patients,

and care-providers. Epidemiological cluster data is a

second level data-based process that will enable

identifying malaria ‘hotspots’ including regional

variation of high and low endemic areas. Propagation

Dynamics is the third level of surveillance strategy

for the prevention of transmission of malaria; it will

focus on both temporal and spatial propagation of

malaria. The transmission parameters themselves are

also updated by refitting the model over a moving

window of time. Application of these approaches

enables the predictability of epidemic malaria at

different levels.

The ontology is amenable to a multi-

organizational setup inherent to malaria management.

It creates an appropriate interface with community-

based approaches, common in malaria management.

The global evidence on malaria management suggests

necessary preconditions to ensure the effectiveness of

community-based approaches. For instance, there is

an emphasis on community engagement at the

inception and planning stage rather than being mere

recipients (Whittaker & Smith, 2015). In the case of

India, where ASHA (Accredited Social Health

Activists) workers are engaged in management of the

disease at the local level, there is a strong pitch for

their empowerment. It has been pointed out that

communities should be empowered to regularly

monitor and evaluate the effectiveness of

interventions. Such practices through institutions, and

individuals further enhances the community's

participation and ownership. (Das et al., 2015). The

ontological framework for malaria surveillance

complements such community-based approaches: it

creates a learning driven process with a multi-layered

feedback mechanism that facilitates a ‘Sense and

Response’ system. In addition to detection, diagnosis,

and monitoring of the cases, it will increase the speed

by which regional and national surveillance teams are

alerted to local events and prepare intervention

services for local demands.

The near real-time technique provided by this

framework can be implemented within the scope of

existing infrastructure and human resources. It

leverages the current accelerated internet and

smartphone penetration across the world. Minimum

training only is required for a user as it’s easy to use.

For instance, through cloud computing platform

integrated with mobile apps, which facilitates access

to data in the cloud through smartphones, feature

phones, tablets and desktops is useful for various

stakeholders at various skill levels (El-Sappagh, Ali,

Hendawi, Jang, & Kwak, 2019; Quan, Hulth, Kok, &

Blumberg, 2014). Therefore, this approach is relevant

in the context of resource-constrained countries in

parts of Asia, Africa, and Latin America, with already

overburdened health systems.

4 CONCLUSIONS

This paper argues for a learning surveillance system

for malaria elimination and presents the ontological

framework to develop the system. It provides a

detailed, yet holistic understanding of how semiotic

interchanges will make the Learning Surveillance

System vision a reality. The ontology has policy

implications as governments around the world look to

improving the efficiency, and outcomes of their

surveillance organizations, and systems.

Understanding how learning system ontology can

support surveillance will contribute to funding

planning, and policies. It highlights the gaps related

to the type of digital technology currently leveraged

for surveillance systems. Healthcare providers will

find a supportive platform in this ontology as it is

likely to change their practice in future.

ACKNOWLEDGEMENTS

We thank Dr Chetan Singai for his valuable insights

on the paper.

REFERENCES

Barclay, V. C., Smith, R. A., & Findeis, J. L. (2012).

Surveillance considerations for malaria elimination.

Malaria Journal, 11, 304. https://doi.org/10.1186/

1475-2875-11-304

Brenas, J. H., Al-Manir, M. S., Baker, C. J. O., & Shaban-

Nejad, A. (2017). A Malaria Analytics Framework to

Support Evolution and Interoperability of Global

Health Surveillance Systems. IEEE Access, 5, 21605–

21619. https://doi.org/10.1109/ACCESS.2017.2761

232

Brooks, I., & Ramaprasad, A. (2008). Ontology of a

Cyberenvironment for Malaria Surveillance. In

Advances in Disease Surveillance (p. 5:8). Retrieved

from http://www.ssrn.com/abstract=1325788

Cao, J., Sturrock, H. J. W., Cotter, C., Zhou, S., Zhou, H.,

Liu, Y., … Gao, Q. (2014). Communicating and

Monitoring Surveillance and Response Activities for

Malaria Elimination: China’s “1-3-7” Strategy. PLoS

Medicine, 11(5), e1001642. https://doi.org/10.1371/

journal.pmed.1001642

Architecture of a Learning Surveillance System for Malaria Elimination in India

381

Chehab M., Bala, M. O., Al-Dahshan, A., Selim, N. A., Al-

Romaihi, H. E., Al-Thani, M., & Farag, E. A. (2018).

Evaluation of the Completeness and Timeliness of

National Malaria Surveillance System in Qatar, 2016.

Cureus, 10(6). Retrieved from https://www.cureus.

com/articles/10295-evaluation-of-the-completeness-

and-timeliness-of-national-malaria-surveillance-sys

tem-in-qatar-2016

Chisha, Z., Larsen, D. A., Burns, M., Miller, J. M., Chirwa,

J., Mbwili, C., … Winters, A. M. (2015). Enhanced

surveillance and data feedback loop associated with

improved malaria data in Lusaka, Zambia. Malaria

Journal, 14(1), 222. https://doi.org/10.1186/s12936-

015-0735-y

Cibulskis, R. E. (2012). Malaria surveillance systems: From

control to elimination. Malaria Journal, 11(S1), O1.

https://doi.org/10.1186/1475-2875-11-S1-O1

Cibulskis, R. E., Alonso, P., Aponte, J., Aregawi, M.,

Barrette, A., Bergeron, L., … Williams, R. (2016).

Malaria: Global progress 2000 – 2015 and future

challenges. Infectious Diseases of Poverty, 5(1), 61,

s40249-016-0151–0158. https://doi.org/10.1186/s402

49-016-0151-8

Cotter, C., Sturrock, H. J. W., Hsiang, M. S., Liu, J.,

Phillips, A. A., Hwang, J., … Feachem, R. G. A. (2013).

The changing epidemiology of malaria elimination:

New strategies for new challenges. Lancet (London,

England), 382(9895), 900–911. https://doi.org/10.

1016/S0140-6736(13)60310-4

Das, A., Friedman, J., Kandpal, E., Ramana, G. N. V.,

Gupta, R. K. D., Pradhan, M. M., & Govindaraj, R.

(2015). Strengthening Malaria Service Delivery

Through Supportive Supervision and Community

Mobilization in an Endemic Indian Setting: An

Evaluation of Nested Delivery Models. 12.

Dhamnetiya, D., & Sahu, M. (2015). Malaria Control in

India: Strategies, Progress and Challenges.

International Journal of Contemporary Medicine, 3(1),

14. https://doi.org/10.5958/2321-1032.2015.00005.4

El-Sappagh, S., Ali, F., Hendawi, A., Jang, J.-H., & Kwak,

K.-S. (2019). A mobile health monitoring-and-

treatment system based on integration of the SSN

sensor ontology and the HL7 FHIR standard. BMC

Medical Informatics and Decision Making, 19(1), 97.

https://doi.org/10.1186/s12911-019-0806-z

Kass, N. E., & Faden, R. R. (2018). Ethics and Learning

Health Care: The Essential roles of engagement,

transparency, and accountability. Learning Health

Systems, 2(4), e10066. https://doi.org/10.1002/

lrh2.10066

Lessard, L., Grudniewicz, A., Sauré, A., Szczotka, A.,

King, J., & Fung-Kee-Fung, M. (2019). Type and use

of digital technology in learning health systems: A

scoping review protocol. BMJ Open,

9(5), e026204.

https://doi.org/10.1136/bmjopen-2018-026204

Lourenço, C., Tatem, A. J., Atkinson, P. M., Cohen, J. M.,

Pindolia, D., Bhavnani, D., & Le Menach, A. (2019).

Strengthening surveillance systems for malaria

elimination: A global landscaping of system

performance, 2015–2017. Malaria Journal, 18(1), 315.

https://doi.org/10.1186/s12936-019-2960-2

Mboera, L. E. G., Mfinanga, S. G., Karimuribo, E. D.,

Rumisha, S. F., & Sindato, C. (2014). The changing

landscape of public health in sub-Saharan Africa:

Control and prevention of communicable diseases

needs rethinking. Onderstepoort Journal of Veterinary

Research, 81(2), 6. https://doi.org/10.4102/

ojvr.v81i2.734

McMorrow, M. L., Aidoo, M., & Kachur, S. P. (2011).

Malaria rapid diagnostic tests in elimination settings—

Can they find the last parasite? Clinical Microbiology

and Infection, 17(11), 1624–1631.

https://doi.org/10.1111/j.1469-0691.2011.03639.x

Merkord, C. L., Liu, Y., Mihretie, A., Gebrehiwot, T.,

Awoke, W., Bayabil, E., … Wimberly, M. C. (2017).

Integrating malaria surveillance with climate data for

outbreak detection and forecasting: The EPIDEMIA

system. Malaria Journal, 16(1), 89.

https://doi.org/10.1186/s12936-017-1735-x

Nkumama, I. N., O’Meara, W. P., & Osier, F. H. A. (2017).

Changes in Malaria Epidemiology in Africa and New

Challenges for Elimination. Trends in Parasitology,

33(2), 128–140. https://doi.org/10.1016/j.pt.2016.

11.006

Quan, V., Hulth, A., Kok, G., & Blumberg, L. (2014).

Timelier Notification and Action with Mobile Phones–

Towards Malaria Elimination in South Africa. Malaria

Journal, 13(1), 151. https://doi.org/10.1186/1475-

2875-13-151

Roy, M., Bouma, M., Dhiman, R. C., & Pascual, M. (2015).

Predictability of epidemic malaria under non-stationary

conditions with process-based models combining

epidemiological updates and climate variability.

Malaria Journal, 14(1), 419. https://doi.org/

10.1186/s12936-015-0937-3

The malERA Consultative Group on Monitoring,

Evaluation, and Surveillance. (2011). A Research

Agenda for Malaria Eradication: Monitoring,

Evaluation, and Surveillance. PLoS Medicine, 8(1),

e1000400. https://doi.org/10.1371/journal.pmed.

1000400

UCSF Global Health Sciences. (2014). Ideal surveillance

for malaria elimination. Retrieved October 4, 2019,

from https://globalhealthsciences.ucsf.edu/sites/global

healthsciences.ucsf.edu/files/pub/mei-pb-surveillance-

systems-to-facilitate.pdf

van Eijk, A. M., Ramanathapuram, L., Sutton, P. L.,

Kanagaraj, D., Sri Lakshmi Priya, G., Ravishankaran,

S., … Eapen, A. (2016). What Is the Value of Reactive

Case Detection in Malaria Control? A Case-Study in

India and a Systematic Review. Malaria Journal, 15(1),

67. https://doi.org/10.1186/s12936-016-1120-1

Whittaker, M., & Smith, C. (2015). Reimagining malaria:

Five reasons to strengthen community engagement in

the lead up to malaria elimination. Malaria Journal,

14(1), 410. https://doi.org/10.1186/s12936-015-0931-9

World HealthOrganization. (2018). World Malaria Report

2018. Retrieved from https://apps.who.int/iris/

bitstream/handle/10665/275867/9789241565653-

eng.pdf?ua=1.

HEALTHINF 2020 - 13th International Conference on Health Informatics

382