In many Low- and Middle Income-Countries (LMIC), access to health care is a challenge. Some of the bottlenecks are associated with long distances and poor communications between health care providers in (rural) health clinics and health centers at a higher level where better facilities and more experienced staff are often present. These limitations may lead to inequities in access to and quality of care [1]–[3].

Laboratory services are vital to public health, disease control and surveillance and individual patient diagnosis [4]. However, diagnosis is frequently based on clinical symptoms rather than on laboratory results [5]. Despite efforts to improve laboratory services, these continue to be one of the most neglected areas of health care provision all through LMIC. Poor and vulnerable populations are most affected by weak laboratory services because they carry the largest burden of ill health. Effective diagnosis of infectious diseases at both laboratory and community level will help reduce this burden [2], [6]. In many low resource settings, microscopy is one of the most important procedures for the diagnosis and control of various bacterial and parasitic infections, including tuberculosis, malaria and diarrhoeal, urinary and reproductive tract diseases [7]. Microscopy services are often suboptimal due to, for example, insufficient training and maintenance, poor slide preparation techniques, poor condition of the microscope, and low quality of essential laboratory supplies [8]. As a result, many common diseases are misdiagnosed and improperly treated, with far reaching consequences for individual patients and high costs for the health system [5], [8].

Modern means of communication, including mobile phones and the Internet, may be used to improve communication between the players in the health system. Increased availability of modern telecommunications has the potential to improve co-ordination within health systems. However reliable internet access remains poor in remote areas. Mobile phones are a notable exception since the coverage of mobile networks is already impressive and rapidly increasing even in remote areas. The number of mobile subscribers exceeds the number of fixed line connections in many LMIC [9]–[11].

Mobile phones offer an attractive possibility to address problems in accessibility, quality, effectiveness, efficiency and costs of health care. Several initiatives have shown previously that mobile phones can be used to take pictures through a microscope [8], [12]–[14] or be modified to serve as a microscope [15], [16]. The next logical step is to send the captured images via mobile networks, for example to a reference laboratory for confirmation of diagnosis by an expert.

For this study, we developed a system of mobile phone-based imaging in combination with a data transfer and response platform. We piloted the performance of this system in Uganda and discussed its acceptability and potential applications with local stakeholders.

Long distances and poor communication result in inadequate access to health care in many LMICs [1]–[3]. Here we combine microscopy with mobile phones and mobile Internet to show that image capture combined with data transfer could be realized in Uganda. The sites visited in Uganda are largely representative of others in East Africa. The aim was to determine the feasibility of using mobile phones for capturing microscopy images and transferring these to a central database for evaluation, feedback and educational purposes. The future objective is to improve diagnosis in peripheral health settings by empowering undereducated and insufficiently experienced health care and laboratory workers to meet quality standards. The long term goal is to improve diagnosis in order to reduce mortality and morbidity.

Image capture was simple once the connector and mobile phone were in place and the staff was enthusiastic to see the microscopy image on their phones. The main bottleneck was to mount the connector to the microscope; the connector will need adjustment to become more user-friendly. In our experiments numerous people showed that it was not easy to capture a clear image by hand. They found that the camera was difficult to stabilize, centre and focus. End users were very responsive to using a connector as using hands only would require numerous trainings. However it is possible to capture an image without the use of a connector.

Generally, microscopy fields seen using naked eye examination are of higher quality than images captured by mobile phone, though for analysis of malaria parasites and with a phone camera resolution of 2MP or more, images were often so clear that specific stages of the malaria parasite could be identified. This is useful for treatment strategies. Microorganisms in urine and stool, which are sometimes morphologically difficult to determine were captured using short video, of which the file size was slightly larger than that of an image. Additional to the microbes mentioned in table 2, we assume that short video can also be used for verification of other common pathogenic stool (i.e. Ascaris lumbricoides) and urine parasite stages, (i.e. Trichomonas vaginalis, Schistosoma haematobium) as well as for identification of trypanosomes in chancre or cerebrospinal fluid.

A remaining challenge is TB diagnosis, which often requires the examination of many microscopic fields. Here, mobile phone imaging could be used for confirmation of positive cases. Alternatively we showed that it is possible to use a mobile phone in combination with fluorescence microscopy as a lower magnification (40×) is required and thus fewer microscopic fields need to be scanned. The smaller the magnification of the microscope the more camera pixels necessary for a good image and the best results with fluorescent microscopy were obtained with a camera resolution of 5MP. The use of these images for quality control purposes, which was one of the recommended activities of this system, is still limited due to the lower resolution compared to naked eye examination.

In a future study it is important to consider the preparation (staining) of samples, microscope settings and other factors that may influence the quality of the images. Additionally, a formal blinded assessment of diagnostic performance should be included for instance with slides containing different malaria species.

Image capture of microscopy images has been tried before with and without use of connecting devices or modifications to the mobile phone [12]–[16], [20]. The novel aspect of the current study is the combination of mobile phone imaging with data transfer via mobile Internet and feedback. Transferring data from the mobile phone to a website/platform can be done by Bluetooth, MMS or mobile Internet:

For providing feedback, the steps to log on to the server, access the sent image, zoom in when necessary, and send back a reply from the central platform to the mobile phone were straightforward. If zooming is required then something to consider is that the larger the image on a computer screen, the greater the amount of pixels that are needed. In addition, using the mobile phone's digital zoomed images for data transfer is not recommended as this would strongly limit the resolution of the image.

This pilot study used a bottom-up approach. End users and stakeholders were included in the design process and the initial testing of the system, increasing the chance of our concept to meaningfully improve laboratory services and support health workers and practitioners in their diagnosis and training. The possibility of constructing a connector locally, thereby reducing costs and enhancing local sustainability was introduced and discussed, yet further investigation and development is required and will be carried out in the next phase.

This study also included discussions on applicability and feasibility with laboratory/health care workers and other stakeholders in the health care chain. Laboratory staff emphasized the importance of sharing knowledge, receiving feedback and being able to learn to identify diseases that are rare or not (yet) present in their region. Together, we identified possibilities for improvement of quality control, better monitoring of disease, improved microscopy performance and improving confidence by being able to get in touch with other staff and experts. Most people thought that this system could facilitate the improvement of diagnosis by reducing misdiagnosis and incorrect treatment. Also it would benefit students who could gain access to a database of real life samples, rather than studying perfect text-book illustrations.

We observed that in Kampala most people in the laboratory have phones with cameras but not always with pre-installed Java software and a mobile Internet subscription, which are both essential for our system. This is also the case for health care workers in rural/remote areas. During discussions it was suggested that this could be overcome by supplying a camera phone to laboratories through programme funds or through the government system (with phone restrictions to avoid excessive and inappropriate use). Furthermore it was mentioned that the costs for mobile Internet, currently around 30 euro per month [21], could be incorporated in a service package.

Connecting mobile technology to diagnosis has a considerable potential to improve diagnostic services in resource poor settings with widely distributed and remote clinical centres. This field study proves that the concept works and that there is a demand from the end user and great interest from other stakeholders. It sets the stage for the next phase, during which several connector prototypes and various formats of the mobile forms need to be designed and the whole system tested in a controlled setting with one reference hospital supervising a limited number of peripheral clinics.