Not there yet: Biometrics to link developing world community, hospital patient data

Studies bode well with impressive stats, but the devil is always in the details
Not there yet: Biometrics to link developing world community, hospital patient data

Researchers who conducted a new study on an effort to assign biometric IDs to HIV patients in Kenya discovered that the “implementation of [the] iris recognition system [used] in routine health information systems is feasible and highly acceptable as part of routine care in Kenya,” and that the ability to “scale-up could improve unique patient identification and tracking, enhancing disease surveillance activities.”

However, the authors also signaled that there were at least some manifest problems with bureaucracy, equipment, processes, logistics, training … even privacy concerns and skepticism on the part of patients – as well as health care providers — about the technology.

Still, the researchers said they established that “iris biometric scanning was highly acceptable in both rural and urban settings in Kenya, with 8,794 unique patients accepting iris scanning at least once, and 6,663 repeat scans obtained over the study period.”

“Our findings of high acceptability and system performance integrated within routine healthcare services demonstrate that [the] use of iris biometrics for unique patient identification in routine HIV programs is feasible,” the authors assured.

However, the scientists disclosed in their report, Feasibility and Acceptability of an Iris Biometric System for Unique Patient Identification in Routine HIV Services in Kenya (to be published in the January 2020 International Journal of Medical Informatics), that the “use of routine HIV program data for surveillance is often limited due to inaccuracies associated with patient misclassification, which can be addressed by unique patient identification.”

The study was funded by a grant from the National Institute of Allergy and Infectious Diseases, National Institutes of Health.

The authors said they “assessed the feasibility and acceptability of integrating an iris recognition biometric identification system into routine HIV care services at [only] four sites in Kenya.” While they acknowledged “the small scale of the project,” they affirmed they had nonetheless “demonstrate[d] the utility of a unique [biometric] identifier in improving program data inaccuracies.”

The study’s key take away conclusions are:

• Biometric patient identification addresses patient misidentification inaccuracies;
• Iris biometric systems can be implemented within routine clinical care settings; and
• Biometrics can be linked to electronic medical records for patient longitudinal follow-up.

The study employed CMITech‘s model BMT-20 binocular iris recognition cameras connected via USB to laptops to capture patients’ iris images. A proprietary digital identity solution provided by iRespond was networked across the study sites to analyze the iris patterns.

iRespond VP of Engineering Ed Eykholt spoke to Biometric Update about the potential of self-sovereign identity systems for empowering biometrics users at the Internet Identity Workshop earlier this year.

Over the course of the 55 week study, the authors reported that 8,614, or 98 percent, of 8,794 new patients were assigned a unique biometric ID on their first visit, and that among the 6,078 patients who returned for follow-up visits, “the system correctly re-identified patients’ IDs 5,234 times, or 86 percent.”

The authors attributed the false match rate to some new patients having been given the ID of another patient. But even with this snafu, the failure rate was only a 0.5 percent false match. Meanwhile, the authors noted that “while the generalized false reject rate (re-scans assigned a new ID) was 4.7 percent,” overall, “9 (0.1 percent) agreed to enroll but declined to have an iris scan.”

Perhaps not surprisingly, the authors reported that “the most common reasons cited for declining an iris scan were concerns about privacy and confidentiality.”

But this is, Kenya, after all. Denis Nzioka, a prominent activist and journalist with a particular focus on sex worker communities in Kenya and in Africa who has consulted regional and international organizations on health and human rights, wrote a cogent evaluation a year ago on why some Kenyans’ are distrustful of biometrics and other personal digital tracking capabilities in his column in The Star, Why Key Populations in Kenya are Opposed to Biometrics?

Fears and suspicions about biometric technologies in these sorts of out-of-the-way health settings is legitimate – and a hindrance in adequately identifying as many HIV patients as possible, and how this gap undoubtedly is vexing scientists’ efforts to track the spread of the virus, as well as where it seems to be predominate or “clustered,” according to a significant number of researchers in this space.

“Fears exist … regarding the potential for invasion of privacy. It will therefore be necessary to convince not only trial participants, but also investigators that templates of fingerprints stored in databases are less likely to be subject to abuse than currently used information databases,” said the authors of the April 23, 2005, Lancet paper, Fingerprint Identification of AIDS Patients on ART.

Then there are the technical and engineering glitches, resources limitations, shortage of trained manpower, and a myriad of other challenging issues restraining expanded use of biometrics, which has been tied to U.S. aide.

The authors of the International Journal of Medical Informatics study confirmed that, overall, the main reason for the failure to issue a unique ID was Internet failure, followed by the “issuance of an already existent ID to a new patient.” They explained though that the “identification errors improved with time as the software algorithm was improved to match the populations’ irises.”

Of note, they observed that “by the end of the study, in sites with a strong Internet signal, the average time required for enrolment for a newly tested HIV-infected individual was 4·6 minutes, with the actual image capture and template generation taking about 20 seconds,” which “was even shorter during re-visits where only the biodata was collected.” And this, they held, “is comparable to” the study, The Application of a Biometric Identification Technique for Linking Community and Hospital Data in Rural Ghana, published in the January 2016 Global Health Action. That study – which used fingerprint biometrics in Ghana — had an average of 7 minutes for a new enrolment.

That report also construed that “fingerprint identification should be combined with other methods [in order] to be feasible in identifying community members in African rural settings,” and suggests they “can be enhanced in communities with some basic Demographic Surveillance System or census information.” The study called attention still to the fact that “the reliability of counts for estimating population dynamics and disease burdens in communities depends on the availability of a common unique identifier for matching general population data with health facility data,” which studies like the one in International Journal of Medical Informatics have shown to be challenging.

The study relied on 27,662 hospital visits which “were linked to resident individuals,” over 85 percent of whose “visits were successfully identified using at least one identification method. Over 65 percent were successfully identified and linked using their fingerprints.”

Despite this seeming success rate and that “no concerns were expressed by community members about the fingerprint registration and identification processes,” the authors of the study did underscore the concern that “supervisory support from the hospital administration was critical in integrating this identification system into its routine activities.”

During the Feasibility and Acceptability of an Iris Biometric System for Unique Patient Identification in Routine HIV Services in Kenya study, only patients who had “recently tested HIV-positive or were engaged in care were enrolled,” as was the researchers’ methodology. “Images of the iris were captured using a dual-iris camera connected to a laptop. A prototype iris biometric identification system networked across the sites” and analyzed the iris patterns; created a template from those patterns; and then generated a 12-digit ID number based on the template.”

During succeeding appointments, the patients’ irises were re-scanned and the pattern matched to stored templates to retrieve the biometric ID number.

The study emphasized the importance of unique patient identification to “clinical procedures, reporting of test and procedure results,” as well as managing administrative functions like scheduling and billing.

Unique identification of individuals is also “essential in case-based disease surveillance,” the authors stated, noting that with regards to HIV surveillance, “it is impossible to know if the Joint United Nations Program on HIV/AIDS’s (UNAIDS) 90-90-90 targets have been achieved if individuals are not uniquely identified and tracked through the care continuum.”

In the first edition of The Lancet HIV in 2014, the authors of the paper, 90-90-90: How Do We Get There? declared that “the 2012 world AIDS conference in Washington, DC, heralded the ‘beginning of the end of AIDS’ and ‘an AIDS free generation’ as the benefits of antiretroviral therapy (ART) and combination prevention became evident. Two years later, at AIDS 2014 in Melbourne, the focus of stepping up the pace was reinvigorated by new 2020 targets released by UNAIDS, which described the effort rather overconfidently as “an ambitious treatment target to help end the AIDS epidemic.”

UNAIDS’ targets called for 90 percent of people living with HIV to know their status, 90 percent of diagnosed people to receive ART, and 90 percent of people receiving ART to be virologically suppressed.”

The authors of the 90-90-90: How Do We Get There? study in the Lancet perceived that “the cascade of care from HIV diagnosis through to successful treatment is … central to the monitoring of the HIV epidemic, and [the] identification of steps where intervention would have the greatest effect. The UNAIDS’ targets translate into 81 percent of people with HIV receiving ART, and 73 percent achieving virological suppression.”

But they also discerned, “(g)iven that the highest current reported national ART coverage is 67 percent in the UK and 62 percent in Botswana, achieving these goals will be challenging in all settings.” Even UNAIDS admits that, “despite the availability of a widening array of effective HIV prevention tools and methods—and a massive scale-up of antiretroviral therapy in recent years—there has been insufficient progress in reducing global new HIV infections, which have fallen by only 16 percent since 2010.” Still, the organization declares countries should be able to “ensure that 90 percent of those at risk of HIV infection are reached by comprehensive prevention services by 2020.”

And therein is the rub – one of them, anyway. The authors of the upcoming International Journal of Medical Informatics paper took note that there is “poor retention in HIV care” for a multitude of reasons that are plaguing healthcare services, including a lack of “accurate and timely surveillance.” Consequently, “linkage of … patient care information requires the use of a unique patient identifier.”

“It is therefore imperative to develop and implement unique patient identifiers to improve both longitudinal and geographical patient information linkage,” the researchers documented — as did the authors of the February 2010 Global Health Action paper, First Experiences in the Implementation of Biometric Technology to Link Data from Health and Demographic Surveillance Systems with Health Facility Data. “Integrating both data sources through reliable record linkage could provide both numerator and denominator populations to estimate disease prevalence and incidence rates in the population and enable determination of accurate health service coverage,” they conveyed.

And that is where the need for accurate, reliable biometrics comes into play. As the authors remarked, “(i)n sub-Saharan Africa as of 2013, use of biometrics for identity authentication was largely in elections, followed by social/cash transfers, and thirdly in health. Iris scanning … has great potential for integration with health information systems,” and if “a large-scale iris identification system” was deployed – if not mandated — especially if launched in combination with a patient registry and electronic medical record system, [it] would allow for subjects to move more naturally through the health system, be recognized at any facility, and receive the care they need then rather than only at their ‘home’ facility.”

Thus, they resolved, “(g)iven the global burden and the stigma associated with HIV, understanding the uptake and performance of biometrics in this setting is important in assessing the utility of such technology.” This motivated the feasibility and acceptability study.

The researchers’ findings agreed with UNAIDS position on unique identifiers enabling better HIV-specific services through improved information flows. “Our findings demonstrate potential for iris scanning to be scaled up as a unique patient identifier that can be effectively linked to electronic medical records and enhance individual tracking within the HIV care continuum, even in resource-limited settings,” they conclude

As the Global Health Action paper’s author explained, the lack of standardized forms of identification like social security numbers, lack of street addresses in rural areas, high migration rates and other challenges make techniques for records linkage used in much of the developed world inapplicable.

“Biometric technologies have been proposed as a possible technological solution for these issues due to its ability to provide a mechanism for unique verification of an individual’s identity,” but the general problem seems to be that “there are a few reports of fingerprint biometrics use in the health field,” the authors reported, noting that “the SonLa Study Group used fingerprint recognition technology for the identification of clinical trial participants among teachers and students at a nursing college in Vietnam,” and “found the system simple to use and recommended that fingerprint recognition should become the standard technology for identification of participants in field trials,” according to the group’s paper, Using a Fingerprint Recognition System in a Vaccine Trial to Avoid Misclassification, published in the January 2007, Bulletin of the World Health Organization.

In their paper, Demographic and Health Surveillance of Mobile Pastoralists in Chad: Integration of Biometric Fingerprint Identification Into a Geographical Information System, published in Geospatial Health in 2008, the authors conveyed that the use of fingerprint biometrics to identify mobile pastoralists in Chad resulted in a fingerprint enrolment rate of 89.9 percent among adult women.”

The April 23, 2005, Lancet paper, Fingerprint Identification of AIDS Patients on ART, reported the use of fingerprint biometrics in ART patients, but gave no details on enrolment rates. The authors further broached that, “(t)o fight AIDS in resource-limited countries … financial resources may not be the immediate constraint, but [rather] the lack of personnel may be a serious obstacle for implementing the national ARV scale-up plan,” a problem reported by other researchers. Still, “(f)rom our experience, fingerprint identification system[s] can be beneficial in reducing manpower requirements in ART clinics” in rural Third-World and other underdeveloped areas of the world.”

In conclusion, there are literally scores of research reports, studies, and academic papers on this issue too numerous to mention. But, suffice it to say, they all overlap. They also are in conflict. Clearly, most conclude, nevertheless, biometrics works to ID and track the nation’s HIV positive population, and presents a mostly statistically relevant model for employing biometrics to track populations exposed to all manners of infectious diseases, such as the next global influenza pandemic hopefully when it’s only at an epidemic level.

Related Posts

Article Topics

 |   |   |   |   |   |   | 

Comments

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Most Read This Week

Featured Company

Biometrics Research

Biometrics White Papers

Biometrics Events

Explaining Biometrics